Merge tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie: "Highlights: - Core DRM had a lot of refactoring around managed drm resources to make drivers simpler. - Intel Tigerlake support is on by default - amdgpu now support p2p PCI buffer sharing and encrypted GPU memory Details: core: - uapi: error out EBUSY when existing master - uapi: rework SET/DROP MASTER permission handling - remove drm_pci.h - drm_pci* are now legacy - introduced managed DRM resources - subclassing support for drm_framebuffer - simple encoder helper - edid improvements - vblank + writeback documentation improved - drm/mm - optimise tree searches - port drivers to use devm_drm_dev_alloc dma-buf: - add flag for p2p buffer support mst: - ACT timeout improvements - remove drm_dp_mst_has_audio - don't use 2nd TX slot - spec recommends against it bridge: - dw-hdmi various improvements - chrontel ch7033 support - fix stack issues with old gcc hdmi: - add unpack function for drm infoframe fbdev: - misc fbdev driver fixes i915: - uapi: global sseu pinning - uapi: OA buffer polling - uapi: remove generated perf code - uapi: per-engine default property values in sysfs - Tigerlake GEN12 enabled. - Lots of gem refactoring - Tigerlake enablement patches - move to drm_device logging - Icelake gamma HW readout - push MST link retrain to hotplug work - bandwidth atomic helpers - ICL fixes - RPS/GT refactoring - Cherryview full-ppgtt support - i915 locking guidelines documented - require linear fb stride to be 512 multiple on gen9 - Tigerlake SAGV support amdgpu: - uapi: encrypted GPU memory handling - uapi: add MEM_SYNC IB flag - p2p dma-buf support - export VRAM dma-bufs - FRU chip access support - RAS/SR-IOV updates - Powerplay locking fixes - VCN DPG (powergating) enablement - GFX10 clockgating fixes - DC fixes - GPU reset fixes - navi SDMA fix - expose FP16 for modesetting - DP 1.4 compliance fixes - gfx10 soft recovery - Improved Critical Thermal Faults handling - resizable BAR on gmc10 amdkfd: - uapi: GWS resource management - track GPU memory per process - report PCI domain in topology radeon: - safe reg list generator fixes nouveau: - HD audio fixes on recent systems - vGPU detection (fail probe if we're on one, for now) - Interlaced mode fixes (mostly avoidance on Turing, which doesn't support it) - SVM improvements/fixes - NVIDIA format modifier support - Misc other fixes. adv7511: - HDMI SPDIF support ast: - allocate crtc state size - fix double assignment - fix suspend bochs: - drop connector register cirrus: - move to tiny drivers. exynos: - fix imported dma-buf mapping - enable runtime PM - fixes and cleanups mediatek: - DPI pin mode swap - config mipi_tx current/impedance lima: - devfreq + cooling device support - task handling improvements - runtime PM support pl111: - vexpress init improvements - fix module auto-load rcar-du: - DT bindings conversion to YAML - Planes zpos sanity check and fix - MAINTAINERS entry for LVDS panel driver mcde: - fix return value mgag200: - use managed config init stm: - read endpoints from DT vboxvideo: - use PCI managed functions - drop WC mtrr vkms: - enable cursor by default rockchip: - afbc support virtio: - various cleanups qxl: - fix cursor notify port hisilicon: - 128-byte stride alignment fix sun4i: - improved format handling" * tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm: (1401 commits) drm/amd/display: Fix potential integer wraparound resulting in a hang drm/amd/display: drop cursor position check in atomic test drm/amdgpu: fix device attribute node create failed with multi gpu drm/nouveau: use correct conflicting framebuffer API drm/vblank: Fix -Wformat compile warnings on some arches drm/amdgpu: Sync with VM root BO when switching VM to CPU update mode drm/amd/display: Handle GPU reset for DC block drm/amdgpu: add apu flags (v2) drm/amd/powerpay: Disable gfxoff when setting manual mode on picasso and raven drm/amdgpu: fix pm sysfs node handling (v2) drm/amdgpu: move gpu_info parsing after common early init drm/amdgpu: move discovery gfx config fetching drm/nouveau/dispnv50: fix runtime pm imbalance on error drm/nouveau: fix runtime pm imbalance on error drm/nouveau: fix runtime pm imbalance on error drm/nouveau/debugfs: fix runtime pm imbalance on error drm/nouveau/nouveau/hmm: fix migrate zero page to GPU drm/nouveau/nouveau/hmm: fix nouveau_dmem_chunk allocations drm/nouveau/kms/nv50-: Share DP SST mode_valid() handling with MST drm/nouveau/kms/nv50-: Move 8BPC limit for MST into nv50_mstc_get_modes() ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2020-06-03 00:04:15 +0200
committer: Linus Torvalds <torvalds@linux-foundation.org> 2020-06-03 00:04:15 +0200
commit: faa392181a0bd42c5478175cef601adeecdc91b6 (patch)
tree: e020e1142e34786676d0cd40f539bccdbb66099e /drivers/gpu/drm/i915
parent: Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rd... (diff)
parent: Merge tag 'amd-drm-next-5.8-2020-05-27' of git://people.freedesktop.org/~agd5... (diff)
download: linux-faa392181a0bd42c5478175cef601adeecdc91b6.tar.xz
linux-faa392181a0bd42c5478175cef601adeecdc91b6.zip
258 files changed, 13479 insertions, 7308 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index 0bfd276c19fe..35bbe2b80596 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -1,3 +1,15 @@
+config DRM_I915_FENCE_TIMEOUT
+	int "Timeout for unsignaled foreign fences (ms, jiffy granularity)"
+	default 10000 # milliseconds
+	help
+	  When listening to a foreign fence, we install a supplementary timer
+	  to ensure that we are always signaled and our userspace is able to
+	  make forward progress. This value specifies the timeout used for an
+	  unsignaled foreign fence.
+
+	  May be 0 to disable the timeout, and rely on the foreign fence being
+	  eventually signaled.
+
 config DRM_I915_USERFAULT_AUTOSUSPEND
 	int "Runtime autosuspend delay for userspace GGTT mmaps (ms)"
 	default 250 # milliseconds
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 6cd1f6253814..b0da6ea6e3f1 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -22,6 +22,7 @@ subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
 subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized)
 subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides)
 subdir-ccflags-y += $(call cc-disable-warning, uninitialized)
+subdir-ccflags-y += $(call cc-disable-warning, frame-address)
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
 
 # Fine grained warnings disable
@@ -34,6 +35,7 @@ subdir-ccflags-y += -I$(srctree)/$(src)
 
 # core driver code
 i915-y += i915_drv.o \
+	  i915_config.o \
 	  i915_irq.o \
 	  i915_getparam.o \
 	  i915_params.o \
@@ -86,10 +88,12 @@ gt-y += \
 	gt/intel_engine_cs.o \
 	gt/intel_engine_heartbeat.o \
 	gt/intel_engine_pm.o \
-	gt/intel_engine_pool.o \
 	gt/intel_engine_user.o \
 	gt/intel_ggtt.o \
+	gt/intel_ggtt_fencing.o \
 	gt/intel_gt.o \
+	gt/intel_gt_buffer_pool.o \
+	gt/intel_gt_clock_utils.o \
 	gt/intel_gt_irq.o \
 	gt/intel_gt_pm.o \
 	gt/intel_gt_pm_irq.o \
@@ -108,6 +112,7 @@ gt-y += \
 	gt/intel_sseu.o \
 	gt/intel_timeline.o \
 	gt/intel_workarounds.o \
+	gt/shmem_utils.o \
 	gt/sysfs_engines.o
 # autogenerated null render state
 gt-y += \
@@ -150,7 +155,6 @@ i915-y += \
 	  i915_buddy.o \
 	  i915_cmd_parser.o \
 	  i915_gem_evict.o \
-	  i915_gem_fence_reg.o \
 	  i915_gem_gtt.o \
 	  i915_gem.o \
 	  i915_globals.o \
@@ -164,14 +168,18 @@ i915-y += \
 
 # general-purpose microcontroller (GuC) support
 i915-y += gt/uc/intel_uc.o \
+	  gt/uc/intel_uc_debugfs.o \
 	  gt/uc/intel_uc_fw.o \
 	  gt/uc/intel_guc.o \
 	  gt/uc/intel_guc_ads.o \
 	  gt/uc/intel_guc_ct.o \
+	  gt/uc/intel_guc_debugfs.o \
 	  gt/uc/intel_guc_fw.o \
 	  gt/uc/intel_guc_log.o \
+	  gt/uc/intel_guc_log_debugfs.o \
 	  gt/uc/intel_guc_submission.o \
 	  gt/uc/intel_huc.o \
+	  gt/uc/intel_huc_debugfs.o \
 	  gt/uc/intel_huc_fw.o
 
 # modesetting core code
@@ -240,23 +248,6 @@ i915-y += \
 	display/vlv_dsi.o \
 	display/vlv_dsi_pll.o
 
-# perf code
-i915-y += \
-	oa/i915_oa_hsw.o \
-	oa/i915_oa_bdw.o \
-	oa/i915_oa_chv.o \
-	oa/i915_oa_sklgt2.o \
-	oa/i915_oa_sklgt3.o \
-	oa/i915_oa_sklgt4.o \
-	oa/i915_oa_bxt.o \
-	oa/i915_oa_kblgt2.o \
-	oa/i915_oa_kblgt3.o \
-	oa/i915_oa_glk.o \
-	oa/i915_oa_cflgt2.o \
-	oa/i915_oa_cflgt3.o \
-	oa/i915_oa_cnl.o \
-	oa/i915_oa_icl.o \
-	oa/i915_oa_tgl.o
 i915-y += i915_perf.o
 
 # Post-mortem debug and GPU hang state capture
@@ -270,7 +261,8 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	selftests/igt_live_test.o \
 	selftests/igt_mmap.o \
 	selftests/igt_reset.o \
-	selftests/igt_spinner.o
+	selftests/igt_spinner.o \
+	selftests/librapl.o
 
 # virtual gpu code
 i915-y += i915_vgpu.o
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 17cee6f80d8b..4fec5bd64920 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -36,15 +36,15 @@
 #include "intel_panel.h"
 #include "intel_vdsc.h"
 
-static inline int header_credits_available(struct drm_i915_private *dev_priv,
-					   enum transcoder dsi_trans)
+static int header_credits_available(struct drm_i915_private *dev_priv,
+				    enum transcoder dsi_trans)
 {
 	return (intel_de_read(dev_priv, DSI_CMD_TXCTL(dsi_trans)) & FREE_HEADER_CREDIT_MASK)
 		>> FREE_HEADER_CREDIT_SHIFT;
 }
 
-static inline int payload_credits_available(struct drm_i915_private *dev_priv,
-					    enum transcoder dsi_trans)
+static int payload_credits_available(struct drm_i915_private *dev_priv,
+				     enum transcoder dsi_trans)
 {
 	return (intel_de_read(dev_priv, DSI_CMD_TXCTL(dsi_trans)) & FREE_PLOAD_CREDIT_MASK)
 		>> FREE_PLOAD_CREDIT_SHIFT;
@@ -186,16 +186,19 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host,
 static int dsi_send_pkt_payld(struct intel_dsi_host *host,
 			      struct mipi_dsi_packet pkt)
 {
+	struct intel_dsi *intel_dsi = host->intel_dsi;
+	struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev);
+
 	/* payload queue can accept *256 bytes*, check limit */
 	if (pkt.payload_length > MAX_PLOAD_CREDIT * 4) {
-		DRM_ERROR("payload size exceeds max queue limit\n");
+		drm_err(&i915->drm, "payload size exceeds max queue limit\n");
 		return -1;
 	}
 
 	/* load data into command payload queue */
 	if (!add_payld_to_queue(host, pkt.payload,
 				pkt.payload_length)) {
-		DRM_ERROR("adding payload to queue failed\n");
+		drm_err(&i915->drm, "adding payload to queue failed\n");
 		return -1;
 	}
 
@@ -744,6 +747,18 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 				tmp |= VIDEO_MODE_SYNC_PULSE;
 				break;
 			}
+		} else {
+			/*
+			 * FIXME: Retrieve this info from VBT.
+			 * As per the spec when dsi transcoder is operating
+			 * in TE GATE mode, TE comes from GPIO
+			 * which is UTIL PIN for DSI 0.
+			 * Also this GPIO would not be used for other
+			 * purposes is an assumption.
+			 */
+			tmp &= ~OP_MODE_MASK;
+			tmp |= CMD_MODE_TE_GATE;
+			tmp |= TE_SOURCE_GPIO;
 		}
 
 		intel_de_write(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans), tmp);
@@ -837,14 +852,33 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	}
 
 	hactive = adjusted_mode->crtc_hdisplay;
-	htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+
+	if (is_vid_mode(intel_dsi))
+		htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+	else
+		htotal = DIV_ROUND_UP((hactive + 160) * mul, div);
+
 	hsync_start = DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div);
 	hsync_end = DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div);
 	hsync_size  = hsync_end - hsync_start;
 	hback_porch = (adjusted_mode->crtc_htotal -
 		       adjusted_mode->crtc_hsync_end);
 	vactive = adjusted_mode->crtc_vdisplay;
-	vtotal = adjusted_mode->crtc_vtotal;
+
+	if (is_vid_mode(intel_dsi)) {
+		vtotal = adjusted_mode->crtc_vtotal;
+	} else {
+		int bpp, line_time_us, byte_clk_period_ns;
+
+		if (crtc_state->dsc.compression_enable)
+			bpp = crtc_state->dsc.compressed_bpp;
+		else
+			bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+
+		byte_clk_period_ns = 1000000 / afe_clk(encoder, crtc_state);
+		line_time_us = (htotal * (bpp / 8) * byte_clk_period_ns) / (1000 * intel_dsi->lane_count);
+		vtotal = vactive + DIV_ROUND_UP(400, line_time_us);
+	}
 	vsync_start = adjusted_mode->crtc_vsync_start;
 	vsync_end = adjusted_mode->crtc_vsync_end;
 	vsync_shift = hsync_start - htotal / 2;
@@ -873,7 +907,7 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	}
 
 	/* TRANS_HSYNC register to be programmed only for video mode */
-	if (intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE) {
+	if (is_vid_mode(intel_dsi)) {
 		if (intel_dsi->video_mode_format ==
 		    VIDEO_MODE_NON_BURST_WITH_SYNC_PULSE) {
 			/* BSPEC: hsync size should be atleast 16 pixels */
@@ -916,22 +950,27 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	if (vsync_start < vactive)
 		drm_err(&dev_priv->drm, "vsync_start less than vactive\n");
 
-	/* program TRANS_VSYNC register */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		dsi_trans = dsi_port_to_transcoder(port);
-		intel_de_write(dev_priv, VSYNC(dsi_trans),
-			       (vsync_start - 1) | ((vsync_end - 1) << 16));
+	/* program TRANS_VSYNC register for video mode only */
+	if (is_vid_mode(intel_dsi)) {
+		for_each_dsi_port(port, intel_dsi->ports) {
+			dsi_trans = dsi_port_to_transcoder(port);
+			intel_de_write(dev_priv, VSYNC(dsi_trans),
+				       (vsync_start - 1) | ((vsync_end - 1) << 16));
+		}
 	}
 
 	/*
-	 * FIXME: It has to be programmed only for interlaced
+	 * FIXME: It has to be programmed only for video modes and interlaced
 	 * modes. Put the check condition here once interlaced
 	 * info available as described above.
 	 * program TRANS_VSYNCSHIFT register
 	 */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		dsi_trans = dsi_port_to_transcoder(port);
-		intel_de_write(dev_priv, VSYNCSHIFT(dsi_trans), vsync_shift);
+	if (is_vid_mode(intel_dsi)) {
+		for_each_dsi_port(port, intel_dsi->ports) {
+			dsi_trans = dsi_port_to_transcoder(port);
+			intel_de_write(dev_priv, VSYNCSHIFT(dsi_trans),
+				       vsync_shift);
+		}
 	}
 
 	/* program TRANS_VBLANK register, should be same as vtotal programmed */
@@ -1016,6 +1055,32 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
 	}
 }
 
+static void gen11_dsi_config_util_pin(struct intel_encoder *encoder,
+				      bool enable)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	u32 tmp;
+
+	/*
+	 * used as TE i/p for DSI0,
+	 * for dual link/DSI1 TE is from slave DSI1
+	 * through GPIO.
+	 */
+	if (is_vid_mode(intel_dsi) || (intel_dsi->ports & BIT(PORT_B)))
+		return;
+
+	tmp = intel_de_read(dev_priv, UTIL_PIN_CTL);
+
+	if (enable) {
+		tmp |= UTIL_PIN_DIRECTION_INPUT;
+		tmp |= UTIL_PIN_ENABLE;
+	} else {
+		tmp &= ~UTIL_PIN_ENABLE;
+	}
+	intel_de_write(dev_priv, UTIL_PIN_CTL, tmp);
+}
+
 static void
 gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state)
@@ -1037,6 +1102,9 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 	/* setup D-PHY timings */
 	gen11_dsi_setup_dphy_timings(encoder, crtc_state);
 
+	/* Since transcoder is configured to take events from GPIO */
+	gen11_dsi_config_util_pin(encoder, true);
+
 	/* step 4h: setup DSI protocol timeouts */
 	gen11_dsi_setup_timeouts(encoder, crtc_state);
 
@@ -1088,7 +1156,8 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 	wait_for_cmds_dispatched_to_panel(encoder);
 }
 
-static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder,
+static void gen11_dsi_pre_pll_enable(struct intel_atomic_state *state,
+				     struct intel_encoder *encoder,
 				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
@@ -1099,7 +1168,8 @@ static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder,
 	gen11_dsi_program_esc_clk_div(encoder, crtc_state);
 }
 
-static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
+static void gen11_dsi_pre_enable(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
@@ -1118,13 +1188,14 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 	gen11_dsi_set_transcoder_timings(encoder, pipe_config);
 }
 
-static void gen11_dsi_enable(struct intel_encoder *encoder,
+static void gen11_dsi_enable(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct drm_connector_state *conn_state)
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
-	WARN_ON(crtc_state->has_pch_encoder);
+	drm_WARN_ON(state->base.dev, crtc_state->has_pch_encoder);
 
 	/* step6d: enable dsi transcoder */
 	gen11_dsi_enable_transcoder(encoder);
@@ -1180,6 +1251,15 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 	enum transcoder dsi_trans;
 	u32 tmp;
 
+	/* disable periodic update mode */
+	if (is_cmd_mode(intel_dsi)) {
+		for_each_dsi_port(port, intel_dsi->ports) {
+			tmp = intel_de_read(dev_priv, DSI_CMD_FRMCTL(port));
+			tmp &= ~DSI_PERIODIC_FRAME_UPDATE_ENABLE;
+			intel_de_write(dev_priv, DSI_CMD_FRMCTL(port), tmp);
+		}
+	}
+
 	/* put dsi link in ULPS */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
@@ -1264,7 +1344,8 @@ static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 	}
 }
 
-static void gen11_dsi_disable(struct intel_encoder *encoder,
+static void gen11_dsi_disable(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
@@ -1286,11 +1367,14 @@ static void gen11_dsi_disable(struct intel_encoder *encoder,
 	/* step3: disable port */
 	gen11_dsi_disable_port(encoder);
 
+	gen11_dsi_config_util_pin(encoder, false);
+
 	/* step4: disable IO power */
 	gen11_dsi_disable_io_power(encoder);
 }
 
-static void gen11_dsi_post_disable(struct intel_encoder *encoder,
+static void gen11_dsi_post_disable(struct intel_atomic_state *state,
+				   struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
@@ -1347,6 +1431,22 @@ static void gen11_dsi_get_timings(struct intel_encoder *encoder,
 	adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vtotal;
 }
 
+static bool gen11_dsi_is_periodic_cmd_mode(struct intel_dsi *intel_dsi)
+{
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum transcoder dsi_trans;
+	u32 val;
+
+	if (intel_dsi->ports == BIT(PORT_B))
+		dsi_trans = TRANSCODER_DSI_1;
+	else
+		dsi_trans = TRANSCODER_DSI_0;
+
+	val = intel_de_read(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans));
+	return (val & DSI_PERIODIC_FRAME_UPDATE_ENABLE);
+}
+
 static void gen11_dsi_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
@@ -1367,6 +1467,10 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder,
 	gen11_dsi_get_timings(encoder, pipe_config);
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 	pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
+
+	if (gen11_dsi_is_periodic_cmd_mode(intel_dsi))
+		pipe_config->hw.adjusted_mode.private_flags |=
+					I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE;
 }
 
 static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
@@ -1417,18 +1521,22 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode =
-					intel_connector->panel.fixed_mode;
+		intel_connector->panel.fixed_mode;
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->hw.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
+	int ret;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
 	intel_fixed_panel_mode(fixed_mode, adjusted_mode);
-	intel_pch_panel_fitting(crtc, pipe_config, conn_state->scaling_mode);
+
+	ret = intel_pch_panel_fitting(pipe_config, conn_state);
+	if (ret)
+		return ret;
 
 	adjusted_mode->flags = 0;
 
@@ -1446,10 +1554,32 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	pipe_config->clock_set = true;
 
 	if (gen11_dsi_dsc_compute_config(encoder, pipe_config))
-		DRM_DEBUG_KMS("Attempting to use DSC failed\n");
+		drm_dbg_kms(&i915->drm, "Attempting to use DSC failed\n");
 
 	pipe_config->port_clock = afe_clk(encoder, pipe_config) / 5;
 
+	/* We would not operate in periodic command mode */
+	pipe_config->hw.adjusted_mode.private_flags &=
+					~I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE;
+
+	/*
+	 * In case of TE GATE cmd mode, we
+	 * receive TE from the slave if
+	 * dual link is enabled
+	 */
+	if (is_cmd_mode(intel_dsi)) {
+		if (intel_dsi->ports == (BIT(PORT_B) | BIT(PORT_A)))
+			pipe_config->hw.adjusted_mode.private_flags |=
+						I915_MODE_FLAG_DSI_USE_TE1 |
+						I915_MODE_FLAG_DSI_USE_TE0;
+		else if (intel_dsi->ports == BIT(PORT_B))
+			pipe_config->hw.adjusted_mode.private_flags |=
+						I915_MODE_FLAG_DSI_USE_TE1;
+		else
+			pipe_config->hw.adjusted_mode.private_flags |=
+						I915_MODE_FLAG_DSI_USE_TE0;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 457b258683d3..79032701873a 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -125,7 +125,7 @@ intel_plane_destroy_state(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
 	struct intel_plane_state *plane_state = to_intel_plane_state(state);
-	WARN_ON(plane_state->vma);
+	drm_WARN_ON(plane->dev, plane_state->vma);
 
 	__drm_atomic_helper_plane_destroy_state(&plane_state->uapi);
 	if (plane_state->hw.fb)
@@ -264,6 +264,20 @@ void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
 	plane_state->hw.color_range = from_plane_state->uapi.color_range;
 }
 
+void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
+			       struct intel_plane_state *plane_state)
+{
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+
+	crtc_state->active_planes &= ~BIT(plane->id);
+	crtc_state->nv12_planes &= ~BIT(plane->id);
+	crtc_state->c8_planes &= ~BIT(plane->id);
+	crtc_state->data_rate[plane->id] = 0;
+	crtc_state->min_cdclk[plane->id] = 0;
+
+	plane_state->uapi.visible = false;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
@@ -273,12 +287,7 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	const struct drm_framebuffer *fb = new_plane_state->hw.fb;
 	int ret;
 
-	new_crtc_state->active_planes &= ~BIT(plane->id);
-	new_crtc_state->nv12_planes &= ~BIT(plane->id);
-	new_crtc_state->c8_planes &= ~BIT(plane->id);
-	new_crtc_state->data_rate[plane->id] = 0;
-	new_crtc_state->min_cdclk[plane->id] = 0;
-	new_plane_state->uapi.visible = false;
+	intel_plane_set_invisible(new_crtc_state, new_plane_state);
 
 	if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc)
 		return 0;
@@ -387,7 +396,7 @@ skl_next_plane_to_commit(struct intel_atomic_state *state,
 	}
 
 	/* should never happen */
-	WARN_ON(1);
+	drm_WARN_ON(state->base.dev, 1);
 
 	return NULL;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index a6bbf42bae1f..59dd1fbb02ea 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -52,5 +52,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 int intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 			       struct intel_plane *plane,
 			       bool *need_cdclk_calc);
+void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
+			       struct intel_plane_state *plane_state);
 
 #endif /* __INTEL_ATOMIC_PLANE_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 62f234f641de..ad4aa66fd676 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -252,14 +252,16 @@ static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_sta
 		i = ARRAY_SIZE(hdmi_audio_clock);
 
 	if (i == ARRAY_SIZE(hdmi_audio_clock)) {
-		DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n",
-			      adjusted_mode->crtc_clock);
+		drm_dbg_kms(&dev_priv->drm,
+			    "HDMI audio pixel clock setting for %d not found, falling back to defaults\n",
+			    adjusted_mode->crtc_clock);
 		i = 1;
 	}
 
-	DRM_DEBUG_KMS("Configuring HDMI audio for pixel clock %d (0x%08x)\n",
-		      hdmi_audio_clock[i].clock,
-		      hdmi_audio_clock[i].config);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Configuring HDMI audio for pixel clock %d (0x%08x)\n",
+		    hdmi_audio_clock[i].clock,
+		    hdmi_audio_clock[i].config);
 
 	return hdmi_audio_clock[i].config;
 }
@@ -512,6 +514,124 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder,
 	mutex_unlock(&dev_priv->av_mutex);
 }
 
+static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder,
+					   const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	unsigned int link_clks_available, link_clks_required;
+	unsigned int tu_data, tu_line, link_clks_active;
+	unsigned int h_active, h_total, hblank_delta, pixel_clk;
+	unsigned int fec_coeff, cdclk, vdsc_bpp;
+	unsigned int link_clk, lanes;
+	unsigned int hblank_rise;
+
+	h_active = crtc_state->hw.adjusted_mode.crtc_hdisplay;
+	h_total = crtc_state->hw.adjusted_mode.crtc_htotal;
+	pixel_clk = crtc_state->hw.adjusted_mode.crtc_clock;
+	vdsc_bpp = crtc_state->dsc.compressed_bpp;
+	cdclk = i915->cdclk.hw.cdclk;
+	/* fec= 0.972261, using rounding multiplier of 1000000 */
+	fec_coeff = 972261;
+	link_clk = crtc_state->port_clock;
+	lanes = crtc_state->lane_count;
+
+	drm_dbg_kms(&i915->drm, "h_active = %u link_clk = %u :"
+		    "lanes = %u vdsc_bpp = %u cdclk = %u\n",
+		    h_active, link_clk, lanes, vdsc_bpp, cdclk);
+
+	if (WARN_ON(!link_clk || !pixel_clk || !lanes || !vdsc_bpp || !cdclk))
+		return 0;
+
+	link_clks_available = (h_total - h_active) * link_clk / pixel_clk - 28;
+	link_clks_required = DIV_ROUND_UP(192000 * h_total, 1000 * pixel_clk) * (48 / lanes + 2);
+
+	if (link_clks_available > link_clks_required)
+		hblank_delta = 32;
+	else
+		hblank_delta = DIV64_U64_ROUND_UP(mul_u32_u32(5 * (link_clk + cdclk), pixel_clk),
+						  mul_u32_u32(link_clk, cdclk));
+
+	tu_data = div64_u64(mul_u32_u32(pixel_clk * vdsc_bpp * 8, 1000000),
+			    mul_u32_u32(link_clk * lanes, fec_coeff));
+	tu_line = div64_u64(h_active * mul_u32_u32(link_clk, fec_coeff),
+			    mul_u32_u32(64 * pixel_clk, 1000000));
+	link_clks_active  = (tu_line - 1) * 64 + tu_data;
+
+	hblank_rise = (link_clks_active + 6 * DIV_ROUND_UP(link_clks_active, 250) + 4) * pixel_clk / link_clk;
+
+	return h_active - hblank_rise + hblank_delta;
+}
+
+static unsigned int calc_samples_room(const struct intel_crtc_state *crtc_state)
+{
+	unsigned int h_active, h_total, pixel_clk;
+	unsigned int link_clk, lanes;
+
+	h_active = crtc_state->hw.adjusted_mode.hdisplay;
+	h_total = crtc_state->hw.adjusted_mode.htotal;
+	pixel_clk = crtc_state->hw.adjusted_mode.clock;
+	link_clk = crtc_state->port_clock;
+	lanes = crtc_state->lane_count;
+
+	return ((h_total - h_active) * link_clk - 12 * pixel_clk) /
+		(pixel_clk * (48 / lanes + 2));
+}
+
+static void enable_audio_dsc_wa(struct intel_encoder *encoder,
+				const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	enum pipe pipe = crtc->pipe;
+	unsigned int hblank_early_prog, samples_room;
+	unsigned int val;
+
+	if (INTEL_GEN(i915) < 11)
+		return;
+
+	val = intel_de_read(i915, AUD_CONFIG_BE);
+
+	if (INTEL_GEN(i915) == 11)
+		val |= HBLANK_EARLY_ENABLE_ICL(pipe);
+	else if (INTEL_GEN(i915) >= 12)
+		val |= HBLANK_EARLY_ENABLE_TGL(pipe);
+
+	if (crtc_state->dsc.compression_enable &&
+	    (crtc_state->hw.adjusted_mode.hdisplay >= 3840 &&
+	    crtc_state->hw.adjusted_mode.vdisplay >= 2160)) {
+		/* Get hblank early enable value required */
+		hblank_early_prog = calc_hblank_early_prog(encoder, crtc_state);
+		if (hblank_early_prog < 32) {
+			val &= ~HBLANK_START_COUNT_MASK(pipe);
+			val |= HBLANK_START_COUNT(pipe, HBLANK_START_COUNT_32);
+		} else if (hblank_early_prog < 64) {
+			val &= ~HBLANK_START_COUNT_MASK(pipe);
+			val |= HBLANK_START_COUNT(pipe, HBLANK_START_COUNT_64);
+		} else if (hblank_early_prog < 96) {
+			val &= ~HBLANK_START_COUNT_MASK(pipe);
+			val |= HBLANK_START_COUNT(pipe, HBLANK_START_COUNT_96);
+		} else {
+			val &= ~HBLANK_START_COUNT_MASK(pipe);
+			val |= HBLANK_START_COUNT(pipe, HBLANK_START_COUNT_128);
+		}
+
+		/* Get samples room value required */
+		samples_room = calc_samples_room(crtc_state);
+		if (samples_room < 3) {
+			val &= ~NUMBER_SAMPLES_PER_LINE_MASK(pipe);
+			val |= NUMBER_SAMPLES_PER_LINE(pipe, samples_room);
+		} else {
+			/* Program 0 i.e "All Samples available in buffer" */
+			val &= ~NUMBER_SAMPLES_PER_LINE_MASK(pipe);
+			val |= NUMBER_SAMPLES_PER_LINE(pipe, 0x0);
+		}
+	}
+
+	intel_de_write(i915, AUD_CONFIG_BE, val);
+}
+
+#undef ROUNDING_FACTOR
+
 static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state)
@@ -529,6 +649,10 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 
 	mutex_lock(&dev_priv->av_mutex);
 
+	/* Enable Audio WA for 4k DSC usecases */
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP))
+		enable_audio_dsc_wa(encoder, crtc_state);
+
 	/* Enable audio presence detect, invalidate ELD */
 	tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD);
 	tmp |= AUDIO_OUTPUT_ENABLE(cpu_transcoder);
@@ -891,7 +1015,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 	ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
 
 	if (dev_priv->audio_power_refcount++ == 0) {
-		if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) {
+		if (INTEL_GEN(dev_priv) >= 9) {
 			intel_de_write(dev_priv, AUD_FREQ_CNTRL,
 				       dev_priv->audio_freq_cntrl);
 			drm_dbg_kms(&dev_priv->drm,
@@ -931,7 +1055,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev,
 	unsigned long cookie;
 	u32 tmp;
 
-	if (!IS_GEN(dev_priv, 9))
+	if (INTEL_GEN(dev_priv) < 9)
 		return;
 
 	cookie = i915_audio_component_get_power(kdev);
@@ -1136,6 +1260,10 @@ static void i915_audio_component_unbind(struct device *i915_kdev,
 	drm_modeset_unlock_all(&dev_priv->drm);
 
 	device_link_remove(hda_kdev, i915_kdev);
+
+	if (dev_priv->audio_power_refcount)
+		drm_err(&dev_priv->drm, "audio power refcount %d after unbind\n",
+			dev_priv->audio_power_refcount);
 }
 
 static const struct component_ops i915_audio_component_bind_ops = {
@@ -1173,7 +1301,7 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv)
 		return;
 	}
 
-	if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		dev_priv->audio_freq_cntrl = intel_de_read(dev_priv,
 							   AUD_FREQ_CNTRL);
 		drm_dbg_kms(&dev_priv->drm,
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 58b264bc318d..fef04e2d954e 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -8,6 +8,9 @@
 #include "intel_bw.h"
 #include "intel_display_types.h"
 #include "intel_sideband.h"
+#include "intel_atomic.h"
+#include "intel_pm.h"
+
 
 /* Parameters for Qclk Geyserville (QGV) */
 struct intel_qgv_point {
@@ -113,6 +116,26 @@ static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv,
+				  u32 points_mask)
+{
+	int ret;
+
+	/* bspec says to keep retrying for at least 1 ms */
+	ret = skl_pcode_request(dev_priv, ICL_PCODE_SAGV_DE_MEM_SS_CONFIG,
+				points_mask,
+				ICL_PCODE_POINTS_RESTRICTED_MASK,
+				ICL_PCODE_POINTS_RESTRICTED,
+				1);
+
+	if (ret < 0) {
+		drm_err(&dev_priv->drm, "Failed to disable qgv points (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
 			      struct intel_qgv_info *qi)
 {
@@ -240,6 +263,16 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 			break;
 	}
 
+	/*
+	 * In case if SAGV is disabled in BIOS, we always get 1
+	 * SAGV point, but we can't send PCode commands to restrict it
+	 * as it will fail and pointless anyway.
+	 */
+	if (qi.num_points == 1)
+		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
+	else
+		dev_priv->sagv_status = I915_SAGV_ENABLED;
+
 	return 0;
 }
 
@@ -248,6 +281,11 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 {
 	int i;
 
+	/*
+	 * Let's return max bw for 0 planes
+	 */
+	num_planes = max(1, num_planes);
+
 	for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) {
 		const struct intel_bw_info *bi =
 			&dev_priv->max_bw[i];
@@ -277,34 +315,6 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 		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 (INTEL_GEN(dev_priv) >= 11) {
-		/*
-		 * Any bw group has same amount of QGV points
-		 */
-		const struct intel_bw_info *bi =
-			&dev_priv->max_bw[0];
-		unsigned int min_bw = UINT_MAX;
-		int i;
-
-		/*
-		 * FIXME with SAGV disabled maybe we can assume
-		 * point 1 will always be used? Seems to match
-		 * the behaviour observed in the wild.
-		 */
-		for (i = 0; i < bi->num_qgv_points; i++) {
-			unsigned int bw = icl_max_bw(dev_priv, num_planes, i);
-
-			min_bw = min(bw, min_bw);
-		}
-		return min_bw;
-	} else {
-		return UINT_MAX;
-	}
-}
-
 static unsigned int intel_bw_crtc_num_active_planes(const struct intel_crtc_state *crtc_state)
 {
 	/*
@@ -338,16 +348,17 @@ void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
 
 	bw_state->data_rate[crtc->pipe] =
 		intel_bw_crtc_data_rate(crtc_state);
 	bw_state->num_active_planes[crtc->pipe] =
 		intel_bw_crtc_num_active_planes(crtc_state);
 
-	DRM_DEBUG_KMS("pipe %c data rate %u num active planes %u\n",
-		      pipe_name(crtc->pipe),
-		      bw_state->data_rate[crtc->pipe],
-		      bw_state->num_active_planes[crtc->pipe]);
+	drm_dbg_kms(&i915->drm, "pipe %c data rate %u num active planes %u\n",
+		    pipe_name(crtc->pipe),
+		    bw_state->data_rate[crtc->pipe],
+		    bw_state->num_active_planes[crtc->pipe]);
 }
 
 static unsigned int intel_bw_num_active_planes(struct drm_i915_private *dev_priv,
@@ -374,7 +385,29 @@ static unsigned int intel_bw_data_rate(struct drm_i915_private *dev_priv,
 	return data_rate;
 }
 
-static struct intel_bw_state *
+struct intel_bw_state *
+intel_atomic_get_old_bw_state(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_global_state *bw_state;
+
+	bw_state = intel_atomic_get_old_global_obj_state(state, &dev_priv->bw_obj);
+
+	return to_intel_bw_state(bw_state);
+}
+
+struct intel_bw_state *
+intel_atomic_get_new_bw_state(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_global_state *bw_state;
+
+	bw_state = intel_atomic_get_new_global_obj_state(state, &dev_priv->bw_obj);
+
+	return to_intel_bw_state(bw_state);
+}
+
+struct intel_bw_state *
 intel_atomic_get_bw_state(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
@@ -391,11 +424,16 @@ int intel_bw_atomic_check(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc_state *new_crtc_state, *old_crtc_state;
-	struct intel_bw_state *bw_state = NULL;
-	unsigned int data_rate, max_data_rate;
+	struct intel_bw_state *new_bw_state = NULL;
+	const struct intel_bw_state *old_bw_state = NULL;
+	unsigned int data_rate;
 	unsigned int num_active_planes;
 	struct intel_crtc *crtc;
 	int i, ret;
+	u32 allowed_points = 0;
+	unsigned int max_bw_point = 0, max_bw = 0;
+	unsigned int num_qgv_points = dev_priv->max_bw[0].num_qgv_points;
+	u32 mask = (1 << num_qgv_points) - 1;
 
 	/* FIXME earlier gens need some checks too */
 	if (INTEL_GEN(dev_priv) < 11)
@@ -420,41 +458,93 @@ int intel_bw_atomic_check(struct intel_atomic_state *state)
 		    old_active_planes == new_active_planes)
 			continue;
 
-		bw_state  = intel_atomic_get_bw_state(state);
-		if (IS_ERR(bw_state))
-			return PTR_ERR(bw_state);
+		new_bw_state = intel_atomic_get_bw_state(state);
+		if (IS_ERR(new_bw_state))
+			return PTR_ERR(new_bw_state);
 
-		bw_state->data_rate[crtc->pipe] = new_data_rate;
-		bw_state->num_active_planes[crtc->pipe] = new_active_planes;
+		new_bw_state->data_rate[crtc->pipe] = new_data_rate;
+		new_bw_state->num_active_planes[crtc->pipe] = new_active_planes;
 
 		drm_dbg_kms(&dev_priv->drm,
 			    "pipe %c data rate %u num active planes %u\n",
 			    pipe_name(crtc->pipe),
-			    bw_state->data_rate[crtc->pipe],
-			    bw_state->num_active_planes[crtc->pipe]);
+			    new_bw_state->data_rate[crtc->pipe],
+			    new_bw_state->num_active_planes[crtc->pipe]);
 	}
 
-	if (!bw_state)
+	if (!new_bw_state)
 		return 0;
 
-	ret = intel_atomic_lock_global_state(&bw_state->base);
+	ret = intel_atomic_lock_global_state(&new_bw_state->base);
 	if (ret)
 		return ret;
 
-	data_rate = intel_bw_data_rate(dev_priv, bw_state);
-	num_active_planes = intel_bw_num_active_planes(dev_priv, bw_state);
+	data_rate = intel_bw_data_rate(dev_priv, new_bw_state);
+	data_rate = DIV_ROUND_UP(data_rate, 1000);
 
-	max_data_rate = intel_max_data_rate(dev_priv, num_active_planes);
+	num_active_planes = intel_bw_num_active_planes(dev_priv, new_bw_state);
 
-	data_rate = DIV_ROUND_UP(data_rate, 1000);
+	for (i = 0; i < num_qgv_points; i++) {
+		unsigned int max_data_rate;
 
-	if (data_rate > max_data_rate) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "Bandwidth %u MB/s exceeds max available %d MB/s (%d active planes)\n",
-			    data_rate, max_data_rate, num_active_planes);
+		max_data_rate = icl_max_bw(dev_priv, num_active_planes, i);
+		/*
+		 * We need to know which qgv point gives us
+		 * maximum bandwidth in order to disable SAGV
+		 * if we find that we exceed SAGV block time
+		 * with watermarks. By that moment we already
+		 * have those, as it is calculated earlier in
+		 * intel_atomic_check,
+		 */
+		if (max_data_rate > max_bw) {
+			max_bw_point = i;
+			max_bw = max_data_rate;
+		}
+		if (max_data_rate >= data_rate)
+			allowed_points |= BIT(i);
+		drm_dbg_kms(&dev_priv->drm, "QGV point %d: max bw %d required %d\n",
+			    i, max_data_rate, data_rate);
+	}
+
+	/*
+	 * BSpec states that we always should have at least one allowed point
+	 * left, so if we couldn't - simply reject the configuration for obvious
+	 * reasons.
+	 */
+	if (allowed_points == 0) {
+		drm_dbg_kms(&dev_priv->drm, "No QGV points provide sufficient memory"
+			    " bandwidth %d for display configuration(%d active planes).\n",
+			    data_rate, num_active_planes);
 		return -EINVAL;
 	}
 
+	/*
+	 * Leave only single point with highest bandwidth, if
+	 * we can't enable SAGV due to the increased memory latency it may
+	 * cause.
+	 */
+	if (!intel_can_enable_sagv(dev_priv, new_bw_state)) {
+		allowed_points = BIT(max_bw_point);
+		drm_dbg_kms(&dev_priv->drm, "No SAGV, using single QGV point %d\n",
+			    max_bw_point);
+	}
+	/*
+	 * We store the ones which need to be masked as that is what PCode
+	 * actually accepts as a parameter.
+	 */
+	new_bw_state->qgv_points_mask = ~allowed_points & mask;
+
+	old_bw_state = intel_atomic_get_old_bw_state(state);
+	/*
+	 * If the actual mask had changed we need to make sure that
+	 * the commits are serialized(in case this is a nomodeset, nonblocking)
+	 */
+	if (new_bw_state->qgv_points_mask != old_bw_state->qgv_points_mask) {
+		ret = intel_atomic_serialize_global_state(&new_bw_state->base);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h
index a8aa7624c5aa..bbcaaa73ec1b 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_bw.h
@@ -18,16 +18,43 @@ struct intel_crtc_state;
 struct intel_bw_state {
 	struct intel_global_state base;
 
+	/*
+	 * Contains a bit mask, used to determine, whether correspondent
+	 * pipe allows SAGV or not.
+	 */
+	u8 pipe_sagv_reject;
+
+	/*
+	 * Current QGV points mask, which restricts
+	 * some particular SAGV states, not to confuse
+	 * with pipe_sagv_mask.
+	 */
+	u8 qgv_points_mask;
+
 	unsigned int data_rate[I915_MAX_PIPES];
 	u8 num_active_planes[I915_MAX_PIPES];
+
+	/* bitmask of active pipes */
+	u8 active_pipes;
 };
 
 #define to_intel_bw_state(x) container_of((x), struct intel_bw_state, base)
 
+struct intel_bw_state *
+intel_atomic_get_old_bw_state(struct intel_atomic_state *state);
+
+struct intel_bw_state *
+intel_atomic_get_new_bw_state(struct intel_atomic_state *state);
+
+struct intel_bw_state *
+intel_atomic_get_bw_state(struct intel_atomic_state *state);
+
 void intel_bw_init_hw(struct drm_i915_private *dev_priv);
 int intel_bw_init(struct drm_i915_private *dev_priv);
 int intel_bw_atomic_check(struct intel_atomic_state *state);
 void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state);
+int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv,
+				  u32 points_mask);
 
 #endif /* __INTEL_BW_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index c1cce93a1c25..98ece9cd7cdd 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -460,6 +460,16 @@ static void ilk_lut_10_pack(struct drm_color_lut *entry, u32 val)
 	entry->blue = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_BLUE_MASK, val), 10);
 }
 
+static void icl_lut_multi_seg_pack(struct drm_color_lut *entry, u32 ldw, u32 udw)
+{
+	entry->red = REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_UDW_MASK, udw) << 6 |
+				   REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_LDW_MASK, ldw);
+	entry->green = REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_UDW_MASK, udw) << 6 |
+				     REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_LDW_MASK, ldw);
+	entry->blue = REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_UDW_MASK, udw) << 6 |
+				    REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_LDW_MASK, ldw);
+}
+
 static void i9xx_color_commit(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
@@ -893,7 +903,7 @@ icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 	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 */
+	/* FIXME LUT entries are 16 bit only, so we can prog 0xFFFF max */
 	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);
@@ -1630,6 +1640,24 @@ 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->uapi.crtc);
@@ -1641,7 +1669,9 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat
 		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);
@@ -1658,9 +1688,9 @@ static bool err_check(struct drm_color_lut *lut1,
 		((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)
+static bool intel_color_lut_entries_equal(struct drm_color_lut *lut1,
+					  struct drm_color_lut *lut2,
+					  int lut_size, u32 err)
 {
 	int i;
 
@@ -1690,16 +1720,8 @@ 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;
@@ -1707,11 +1729,16 @@ 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))
+		if (!intel_color_lut_entries_equal(lut1, lut2,
+						   lut_size2, err))
+			return false;
+		break;
+	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
+		if (!intel_color_lut_entries_equal(lut1, lut2,
+						   9, err))
 			return false;
 		break;
 	default:
@@ -1946,6 +1973,63 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 		crtc_state->hw.gamma_lut = glk_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
 }
 
+static struct drm_property_blob *
+icl_read_lut_multi_segment(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	int i, lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *lut;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	lut = blob->data;
+
+	intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe),
+		       PAL_PREC_AUTO_INCREMENT);
+
+	for (i = 0; i < 9; i++) {
+		u32 ldw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe));
+		u32 udw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe));
+
+		icl_lut_multi_seg_pack(&lut[i], ldw, udw);
+	}
+
+	intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), 0);
+
+	/*
+	 * 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)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+
+	if ((crtc_state->gamma_mode & POST_CSC_GAMMA_ENABLE) == 0)
+		return;
+
+	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
+	case GAMMA_MODE_MODE_8BIT:
+		crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc);
+		break;
+	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
+		crtc_state->hw.gamma_lut = icl_read_lut_multi_segment(crtc);
+		break;
+	default:
+		crtc_state->hw.gamma_lut = glk_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0));
+	}
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1989,6 +2073,7 @@ 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/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c
index 903e49659f56..406e96785c76 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.c
+++ b/drivers/gpu/drm/i915/display/intel_connector.c
@@ -33,6 +33,7 @@
 
 #include "i915_drv.h"
 #include "intel_connector.h"
+#include "intel_display_debugfs.h"
 #include "intel_display_types.h"
 #include "intel_hdcp.h"
 
@@ -123,6 +124,8 @@ int intel_connector_register(struct drm_connector *connector)
 		goto err_backlight;
 	}
 
+	intel_connector_debugfs_add(connector);
+
 	return 0;
 
 err_backlight:
@@ -290,7 +293,7 @@ intel_attach_colorspace_property(struct drm_connector *connector)
 			return;
 		break;
 	default:
-		DRM_DEBUG_KMS("Colorspace property not supported\n");
+		MISSING_CASE(connector->connector_type);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 78f9b6cde810..2f5b9a4baafd 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -203,27 +203,31 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder,
 	intel_de_write(dev_priv, crt->adpa_reg, adpa);
 }
 
-static void intel_disable_crt(struct intel_encoder *encoder,
+static void intel_disable_crt(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
 	intel_crt_set_dpms(encoder, old_crtc_state, DRM_MODE_DPMS_OFF);
 }
 
-static void pch_disable_crt(struct intel_encoder *encoder,
+static void pch_disable_crt(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *old_crtc_state,
 			    const struct drm_connector_state *old_conn_state)
 {
 }
 
-static void pch_post_disable_crt(struct intel_encoder *encoder,
+static void pch_post_disable_crt(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_crt(encoder, old_crtc_state, old_conn_state);
+	intel_disable_crt(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void hsw_disable_crt(struct intel_encoder *encoder,
+static void hsw_disable_crt(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *old_crtc_state,
 			    const struct drm_connector_state *old_conn_state)
 {
@@ -234,7 +238,8 @@ static void hsw_disable_crt(struct intel_encoder *encoder,
 	intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 }
 
-static void hsw_post_disable_crt(struct intel_encoder *encoder,
+static void hsw_post_disable_crt(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
@@ -250,19 +255,20 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder,
 
 	intel_ddi_disable_pipe_clock(old_crtc_state);
 
-	pch_post_disable_crt(encoder, old_crtc_state, old_conn_state);
+	pch_post_disable_crt(state, encoder, old_crtc_state, old_conn_state);
 
 	lpt_disable_pch_transcoder(dev_priv);
 	lpt_disable_iclkip(dev_priv);
 
-	intel_ddi_fdi_post_disable(encoder, old_crtc_state, old_conn_state);
+	intel_ddi_fdi_post_disable(state, encoder, old_crtc_state, old_conn_state);
 
 	drm_WARN_ON(&dev_priv->drm, !old_crtc_state->has_pch_encoder);
 
 	intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 }
 
-static void hsw_pre_pll_enable_crt(struct intel_encoder *encoder,
+static void hsw_pre_pll_enable_crt(struct intel_atomic_state *state,
+				   struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state)
 {
@@ -273,7 +279,8 @@ static void hsw_pre_pll_enable_crt(struct intel_encoder *encoder,
 	intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 }
 
-static void hsw_pre_enable_crt(struct intel_encoder *encoder,
+static void hsw_pre_enable_crt(struct intel_atomic_state *state,
+			       struct intel_encoder *encoder,
 			       const struct intel_crtc_state *crtc_state,
 			       const struct drm_connector_state *conn_state)
 {
@@ -287,10 +294,11 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder,
 
 	hsw_fdi_link_train(encoder, crtc_state);
 
-	intel_ddi_enable_pipe_clock(crtc_state);
+	intel_ddi_enable_pipe_clock(encoder, crtc_state);
 }
 
-static void hsw_enable_crt(struct intel_encoder *encoder,
+static void hsw_enable_crt(struct intel_atomic_state *state,
+			   struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state,
 			   const struct drm_connector_state *conn_state)
 {
@@ -300,6 +308,8 @@ static void hsw_enable_crt(struct intel_encoder *encoder,
 
 	drm_WARN_ON(&dev_priv->drm, !crtc_state->has_pch_encoder);
 
+	intel_ddi_enable_transcoder_func(encoder, crtc_state);
+
 	intel_enable_pipe(crtc_state);
 
 	lpt_pch_enable(crtc_state);
@@ -314,7 +324,8 @@ static void hsw_enable_crt(struct intel_encoder *encoder,
 	intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 }
 
-static void intel_enable_crt(struct intel_encoder *encoder,
+static void intel_enable_crt(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct drm_connector_state *conn_state)
 {
@@ -594,7 +605,8 @@ static struct edid *intel_crt_get_edid(struct drm_connector *connector,
 	edid = drm_get_edid(connector, i2c);
 
 	if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
-		DRM_DEBUG_KMS("CRT GMBUS EDID read failed, retry using GPIO bit-banging\n");
+		drm_dbg_kms(connector->dev,
+			    "CRT GMBUS EDID read failed, retry using GPIO bit-banging\n");
 		intel_gmbus_force_bit(i2c, true);
 		edid = drm_get_edid(connector, i2c);
 		intel_gmbus_force_bit(i2c, false);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 52db7852827b..aa22465bb56e 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -568,7 +568,7 @@ static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = {
 	{ 0x6, 0x7F, 0x35, 0x00, 0x0A },	/* 600   850      3.0   */
 };
 
-static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_hbr2_hbr3[] = {
+static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_dp[] = {
 						/* NT mV Trans mV db    */
 	{ 0xA, 0x33, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
 	{ 0xA, 0x47, 0x36, 0x00, 0x09 },	/* 350   500      3.1   */
@@ -583,23 +583,51 @@ static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_hbr2_hbr3[]
 };
 
 struct icl_mg_phy_ddi_buf_trans {
-	u32 cri_txdeemph_override_5_0;
 	u32 cri_txdeemph_override_11_6;
+	u32 cri_txdeemph_override_5_0;
 	u32 cri_txdeemph_override_17_12;
 };
 
-static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations[] = {
+static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_rbr_hbr[] = {
+				/* Voltage swing  pre-emphasis */
+	{ 0x18, 0x00, 0x00 },	/* 0              0   */
+	{ 0x1D, 0x00, 0x05 },	/* 0              1   */
+	{ 0x24, 0x00, 0x0C },	/* 0              2   */
+	{ 0x2B, 0x00, 0x14 },	/* 0              3   */
+	{ 0x21, 0x00, 0x00 },	/* 1              0   */
+	{ 0x2B, 0x00, 0x08 },	/* 1              1   */
+	{ 0x30, 0x00, 0x0F },	/* 1              2   */
+	{ 0x31, 0x00, 0x03 },	/* 2              0   */
+	{ 0x34, 0x00, 0x0B },	/* 2              1   */
+	{ 0x3F, 0x00, 0x00 },	/* 3              0   */
+};
+
+static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hbr2_hbr3[] = {
 				/* Voltage swing  pre-emphasis */
-	{ 0x0, 0x1B, 0x00 },	/* 0              0   */
-	{ 0x0, 0x23, 0x08 },	/* 0              1   */
-	{ 0x0, 0x2D, 0x12 },	/* 0              2   */
-	{ 0x0, 0x00, 0x00 },	/* 0              3   */
-	{ 0x0, 0x23, 0x00 },	/* 1              0   */
-	{ 0x0, 0x2B, 0x09 },	/* 1              1   */
-	{ 0x0, 0x2E, 0x11 },	/* 1              2   */
-	{ 0x0, 0x2F, 0x00 },	/* 2              0   */
-	{ 0x0, 0x33, 0x0C },	/* 2              1   */
-	{ 0x0, 0x00, 0x00 },	/* 3              0   */
+	{ 0x18, 0x00, 0x00 },	/* 0              0   */
+	{ 0x1D, 0x00, 0x05 },	/* 0              1   */
+	{ 0x24, 0x00, 0x0C },	/* 0              2   */
+	{ 0x2B, 0x00, 0x14 },	/* 0              3   */
+	{ 0x26, 0x00, 0x00 },	/* 1              0   */
+	{ 0x2C, 0x00, 0x07 },	/* 1              1   */
+	{ 0x33, 0x00, 0x0C },	/* 1              2   */
+	{ 0x2E, 0x00, 0x00 },	/* 2              0   */
+	{ 0x36, 0x00, 0x09 },	/* 2              1   */
+	{ 0x3F, 0x00, 0x00 },	/* 3              0   */
+};
+
+static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hdmi[] = {
+				/* HDMI Preset	VS	Pre-emph */
+	{ 0x1A, 0x0, 0x0 },	/* 1		400mV	0dB */
+	{ 0x20, 0x0, 0x0 },	/* 2		500mV	0dB */
+	{ 0x29, 0x0, 0x0 },	/* 3		650mV	0dB */
+	{ 0x32, 0x0, 0x0 },	/* 4		800mV	0dB */
+	{ 0x3F, 0x0, 0x0 },	/* 5		1000mV	0dB */
+	{ 0x3A, 0x0, 0x5 },	/* 6		Full	-1.5 dB */
+	{ 0x39, 0x0, 0x6 },	/* 7		Full	-1.8 dB */
+	{ 0x38, 0x0, 0x7 },	/* 8		Full	-2 dB */
+	{ 0x37, 0x0, 0x8 },	/* 9		Full	-2.5 dB */
+	{ 0x36, 0x0, 0x9 },	/* 10		Full	-3 dB */
 };
 
 struct tgl_dkl_phy_ddi_buf_trans {
@@ -943,14 +971,29 @@ icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate,
 	return icl_combo_phy_ddi_translations_dp_hbr2;
 }
 
+static const struct icl_mg_phy_ddi_buf_trans *
+icl_get_mg_buf_trans(struct drm_i915_private *dev_priv, int type, int rate,
+		     int *n_entries)
+{
+	if (type == INTEL_OUTPUT_HDMI) {
+		*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hdmi);
+		return icl_mg_phy_ddi_translations_hdmi;
+	} else if (rate > 270000) {
+		*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hbr2_hbr3);
+		return icl_mg_phy_ddi_translations_hbr2_hbr3;
+	}
+
+	*n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_rbr_hbr);
+	return icl_mg_phy_ddi_translations_rbr_hbr;
+}
+
 static const struct cnl_ddi_buf_trans *
 ehl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate,
 			int *n_entries)
 {
-	if (type != INTEL_OUTPUT_HDMI && type != INTEL_OUTPUT_EDP &&
-	    rate > 270000) {
-		*n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_hbr2_hbr3);
-		return ehl_combo_phy_ddi_translations_hbr2_hbr3;
+	if (type != INTEL_OUTPUT_HDMI && type != INTEL_OUTPUT_EDP) {
+		*n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_dp);
+		return ehl_combo_phy_ddi_translations_dp;
 	}
 
 	return icl_get_combo_buf_trans(dev_priv, type, rate, n_entries);
@@ -989,7 +1032,8 @@ static int intel_ddi_hdmi_level(struct intel_encoder *encoder)
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
 						0, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
+			icl_get_mg_buf_trans(dev_priv, INTEL_OUTPUT_HDMI, 0,
+					     &n_entries);
 		default_entry = n_entries - 1;
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		cnl_get_buf_trans_hdmi(dev_priv, &n_entries);
@@ -1103,7 +1147,8 @@ static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 		if (intel_de_read(dev_priv, reg) & DDI_BUF_IS_IDLE)
 			return;
 	}
-	DRM_ERROR("Timeout waiting for DDI BUF %c idle bit\n", port_name(port));
+	drm_err(&dev_priv->drm, "Timeout waiting for DDI BUF %c idle bit\n",
+		port_name(port));
 }
 
 static u32 hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll)
@@ -1216,7 +1261,10 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 	for (i = 0; i < ARRAY_SIZE(hsw_ddi_translations_fdi) * 2; i++) {
 		/* Configure DP_TP_CTL with auto-training */
 		intel_de_write(dev_priv, DP_TP_CTL(PORT_E),
-			       DP_TP_CTL_FDI_AUTOTRAIN | DP_TP_CTL_ENHANCED_FRAME_ENABLE | DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_ENABLE);
+			       DP_TP_CTL_FDI_AUTOTRAIN |
+			       DP_TP_CTL_ENHANCED_FRAME_ENABLE |
+			       DP_TP_CTL_LINK_TRAIN_PAT1 |
+			       DP_TP_CTL_ENABLE);
 
 		/* Configure and enable DDI_BUF_CTL for DDI E with next voltage.
 		 * DDI E does not support port reversal, the functionality is
@@ -1250,7 +1298,8 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 
 		temp = intel_de_read(dev_priv, DP_TP_STATUS(PORT_E));
 		if (temp & DP_TP_STATUS_AUTOTRAIN_DONE) {
-			DRM_DEBUG_KMS("FDI link training done on step %d\n", i);
+			drm_dbg_kms(&dev_priv->drm,
+				    "FDI link training done on step %d\n", i);
 			break;
 		}
 
@@ -1259,7 +1308,7 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 		 * Results in less fireworks from the state checker.
 		 */
 		if (i == ARRAY_SIZE(hsw_ddi_translations_fdi) * 2 - 1) {
-			DRM_ERROR("FDI link training failed!\n");
+			drm_err(&dev_priv->drm, "FDI link training failed!\n");
 			break;
 		}
 
@@ -1291,7 +1340,10 @@ void hsw_fdi_link_train(struct intel_encoder *encoder,
 
 	/* Enable normal pixel sending for FDI */
 	intel_de_write(dev_priv, DP_TP_CTL(PORT_E),
-		       DP_TP_CTL_FDI_AUTOTRAIN | DP_TP_CTL_LINK_TRAIN_NORMAL | DP_TP_CTL_ENHANCED_FRAME_ENABLE | DP_TP_CTL_ENABLE);
+		       DP_TP_CTL_FDI_AUTOTRAIN |
+		       DP_TP_CTL_LINK_TRAIN_NORMAL |
+		       DP_TP_CTL_ENHANCED_FRAME_ENABLE |
+		       DP_TP_CTL_ENABLE);
 }
 
 static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder)
@@ -1305,27 +1357,6 @@ static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder)
 	intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
 }
 
-static struct intel_encoder *
-intel_ddi_get_crtc_encoder(struct intel_crtc *crtc)
-{
-	struct drm_device *dev = crtc->base.dev;
-	struct intel_encoder *encoder, *ret = NULL;
-	int num_encoders = 0;
-
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
-		ret = encoder;
-		num_encoders++;
-	}
-
-	if (num_encoders != 1)
-		drm_WARN(dev, 1, "%d encoders on crtc for pipe %c\n",
-			 num_encoders,
-			 pipe_name(crtc->pipe));
-
-	BUG_ON(ret == NULL);
-	return ret;
-}
-
 static int icl_calc_tbt_pll_link(struct drm_i915_private *dev_priv,
 				 enum port port)
 {
@@ -1451,6 +1482,14 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	intel_de_write(dev_priv, TRANS_MSA_MISC(cpu_transcoder), temp);
 }
 
+static u32 bdw_trans_port_sync_master_select(enum transcoder master_transcoder)
+{
+	if (master_transcoder == TRANSCODER_EDP)
+		return 0;
+	else
+		return master_transcoder + 1;
+}
+
 /*
  * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state.
  *
@@ -1458,10 +1497,10 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
  * intel_ddi_config_transcoder_func().
  */
 static u32
-intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
+intel_ddi_transcoder_func_reg_val_get(struct intel_encoder *encoder,
+				      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
@@ -1551,20 +1590,46 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
 	}
 
+	if (IS_GEN_RANGE(dev_priv, 8, 10) &&
+	    crtc_state->master_transcoder != INVALID_TRANSCODER) {
+		u8 master_select =
+			bdw_trans_port_sync_master_select(crtc_state->master_transcoder);
+
+		temp |= TRANS_DDI_PORT_SYNC_ENABLE |
+			TRANS_DDI_PORT_SYNC_MASTER_SELECT(master_select);
+	}
+
 	return temp;
 }
 
-void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
+void intel_ddi_enable_transcoder_func(struct intel_encoder *encoder,
+				      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 temp;
+	u32 ctl;
+
+	if (INTEL_GEN(dev_priv) >= 11) {
+		enum transcoder master_transcoder = crtc_state->master_transcoder;
+		u32 ctl2 = 0;
+
+		if (master_transcoder != INVALID_TRANSCODER) {
+			u8 master_select =
+				bdw_trans_port_sync_master_select(master_transcoder);
+
+			ctl2 |= PORT_SYNC_MODE_ENABLE |
+				PORT_SYNC_MODE_MASTER_SELECT(master_select);
+		}
 
-	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
+		intel_de_write(dev_priv,
+			       TRANS_DDI_FUNC_CTL2(cpu_transcoder), ctl2);
+	}
+
+	ctl = intel_ddi_transcoder_func_reg_val_get(encoder, crtc_state);
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
-		temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
+		ctl |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
+	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl);
 }
 
 /*
@@ -1572,16 +1637,17 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
  * bit.
  */
 static void
-intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
+intel_ddi_config_transcoder_func(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 temp;
+	u32 ctl;
 
-	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
-	temp &= ~TRANS_DDI_FUNC_ENABLE;
-	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
+	ctl = intel_ddi_transcoder_func_reg_val_get(encoder, crtc_state);
+	ctl &= ~TRANS_DDI_FUNC_ENABLE;
+	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl);
 }
 
 void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
@@ -1589,24 +1655,35 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 val;
+	u32 ctl;
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		intel_de_write(dev_priv,
+			       TRANS_DDI_FUNC_CTL2(cpu_transcoder), 0);
 
-	val = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder));
-	val &= ~TRANS_DDI_FUNC_ENABLE;
+	ctl = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder));
+
+	ctl &= ~TRANS_DDI_FUNC_ENABLE;
+
+	if (IS_GEN_RANGE(dev_priv, 8, 10))
+		ctl &= ~(TRANS_DDI_PORT_SYNC_ENABLE |
+			 TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
 		if (!intel_dp_mst_is_master_trans(crtc_state)) {
-			val &= ~(TGL_TRANS_DDI_PORT_MASK |
+			ctl &= ~(TGL_TRANS_DDI_PORT_MASK |
 				 TRANS_DDI_MODE_SELECT_MASK);
 		}
 	} else {
-		val &= ~(TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK);
+		ctl &= ~(TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK);
 	}
-	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), val);
+
+	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl);
 
 	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
 	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
-		DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Quirk Increase DDI disabled time\n");
 		/* Quirk time at 100ms for reliable operation */
 		msleep(100);
 	}
@@ -1667,7 +1744,7 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 		goto out;
 	}
 
-	if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A)
+	if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A)
 		cpu_transcoder = TRANSCODER_EDP;
 	else
 		cpu_transcoder = (enum transcoder) pipe;
@@ -1729,7 +1806,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 	if (!(tmp & DDI_BUF_CTL_ENABLE))
 		goto out;
 
-	if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A) {
+	if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A) {
 		tmp = intel_de_read(dev_priv,
 				    TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
 
@@ -1787,20 +1864,23 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 	}
 
 	if (!*pipe_mask)
-		DRM_DEBUG_KMS("No pipe for [ENCODER:%d:%s] found\n",
-			      encoder->base.base.id, encoder->base.name);
+		drm_dbg_kms(&dev_priv->drm,
+			    "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 [ENCODER:%d:%s] (pipe_mask %02x)\n",
-			      encoder->base.base.id, encoder->base.name,
-			      *pipe_mask);
+		drm_dbg_kms(&dev_priv->drm,
+			    "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 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);
+		drm_dbg_kms(&dev_priv->drm,
+			    "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;
 
@@ -1810,9 +1890,9 @@ out:
 		if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED)
-			DRM_ERROR("[ENCODER:%d:%s] enabled but PHY powered down? "
-				  "(PHY_CTL %08x)\n", encoder->base.base.id,
-				  encoder->base.name, tmp);
+			drm_err(&dev_priv->drm,
+				"[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);
@@ -1834,7 +1914,7 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
-static inline enum intel_display_power_domain
+static enum intel_display_power_domain
 intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port)
 {
 	/* CNL+ HW requires corresponding AUX IOs to be powered up for PSR with
@@ -1893,11 +1973,11 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 					intel_dsc_power_domain(crtc_state));
 }
 
-void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
+void intel_ddi_enable_pipe_clock(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum port port = encoder->port;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
@@ -1978,7 +2058,7 @@ static void skl_ddi_set_iboost(struct intel_encoder *encoder,
 
 	/* Make sure that the requested I_boost is valid */
 	if (iboost && iboost != 0x1 && iboost != 0x3 && iboost != 0x7) {
-		DRM_ERROR("Invalid I_boost value %u\n", iboost);
+		drm_err(&dev_priv->drm, "Invalid I_boost value %u\n", iboost);
 		return;
 	}
 
@@ -2037,7 +2117,8 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
 						intel_dp->link_rate, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
+			icl_get_mg_buf_trans(dev_priv, encoder->type,
+					     intel_dp->link_rate, &n_entries);
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		if (encoder->type == INTEL_OUTPUT_EDP)
 			cnl_get_buf_trans_edp(dev_priv, &n_entries);
@@ -2237,7 +2318,9 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv,
 		return;
 
 	if (level >= n_entries) {
-		DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.", level, n_entries - 1);
+		drm_dbg_kms(&dev_priv->drm,
+			    "DDI translation not found for level %d. Using %d instead.",
+			    level, n_entries - 1);
 		level = n_entries - 1;
 	}
 
@@ -2350,21 +2433,28 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 }
 
 static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
-					   int link_clock,
-					   u32 level)
+					   int link_clock, u32 level,
+					   enum intel_output_type type)
 {
 	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 icl_mg_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val;
-	int ln;
+	int ln, rate = 0;
+
+	if (type != INTEL_OUTPUT_HDMI) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+		rate = intel_dp->link_rate;
+	}
 
-	n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
-	ddi_translations = icl_mg_phy_ddi_translations;
+	ddi_translations = icl_get_mg_buf_trans(dev_priv, type, rate,
+						&n_entries);
 	/* The table does not have values for level 3 and level 9. */
 	if (level >= n_entries || level == 3 || level == 9) {
-		DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.",
-			      level, n_entries - 2);
+		drm_dbg_kms(&dev_priv->drm,
+			    "DDI translation not found for level %d. Using %d instead.",
+			    level, n_entries - 2);
 		level = n_entries - 2;
 	}
 
@@ -2483,7 +2573,8 @@ static void icl_ddi_vswing_sequence(struct intel_encoder *encoder,
 	if (intel_phy_is_combo(dev_priv, phy))
 		icl_combo_phy_ddi_vswing_sequence(encoder, level, type);
 	else
-		icl_mg_phy_ddi_vswing_sequence(encoder, link_clock, level);
+		icl_mg_phy_ddi_vswing_sequence(encoder, link_clock, level,
+					       type);
 }
 
 static void
@@ -2550,8 +2641,9 @@ static void tgl_ddi_vswing_sequence(struct intel_encoder *encoder,
 		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level);
 }
 
-static u32 translate_signal_level(int signal_levels)
+static u32 translate_signal_level(struct intel_dp *intel_dp, int signal_levels)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(index_to_dp_signal_levels); i++) {
@@ -2559,8 +2651,9 @@ static u32 translate_signal_level(int signal_levels)
 			return i;
 	}
 
-	WARN(1, "Unsupported voltage swing/pre-emphasis level: 0x%x\n",
-	     signal_levels);
+	drm_WARN(&i915->drm, 1,
+		 "Unsupported voltage swing/pre-emphasis level: 0x%x\n",
+		 signal_levels);
 
 	return 0;
 }
@@ -2571,46 +2664,73 @@ static u32 intel_ddi_dp_level(struct intel_dp *intel_dp)
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
 
-	return translate_signal_level(signal_levels);
+	return translate_signal_level(intel_dp, signal_levels);
 }
 
-u32 bxt_signal_levels(struct intel_dp *intel_dp)
+static void
+tgl_set_signal_levels(struct intel_dp *intel_dp)
 {
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
-	struct intel_encoder *encoder = &dport->base;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	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))
-		cnl_ddi_vswing_sequence(encoder, level, encoder->type);
-	else
-		bxt_ddi_vswing_sequence(encoder, level, encoder->type);
+	tgl_ddi_vswing_sequence(encoder, intel_dp->link_rate,
+				level, encoder->type);
+}
 
-	return 0;
+static void
+icl_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	int level = intel_ddi_dp_level(intel_dp);
+
+	icl_ddi_vswing_sequence(encoder, intel_dp->link_rate,
+				level, encoder->type);
 }
 
-u32 ddi_signal_levels(struct intel_dp *intel_dp)
+static void
+cnl_set_signal_levels(struct intel_dp *intel_dp)
 {
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
-	struct intel_encoder *encoder = &dport->base;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
+	cnl_ddi_vswing_sequence(encoder, level, encoder->type);
+}
+
+static void
+bxt_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	int level = intel_ddi_dp_level(intel_dp);
+
+	bxt_ddi_vswing_sequence(encoder, level, encoder->type);
+}
+
+static void
+hsw_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	int level = intel_ddi_dp_level(intel_dp);
+	enum port port = encoder->port;
+	u32 signal_levels;
+
+	signal_levels = DDI_BUF_TRANS_SELECT(level);
+
+	drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n",
+		    signal_levels);
+
+	intel_dp->DP &= ~DDI_BUF_EMP_MASK;
+	intel_dp->DP |= signal_levels;
+
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, encoder->type);
 
-	return DDI_BUF_TRANS_SELECT(level);
+	intel_de_write(dev_priv, DDI_BUF_CTL(port), intel_dp->DP);
+	intel_de_posting_read(dev_priv, DDI_BUF_CTL(port));
 }
 
-static inline
-u32 icl_dpclka_cfgcr0_clk_off(struct drm_i915_private *dev_priv,
-			      enum phy phy)
+static u32 icl_dpclka_cfgcr0_clk_off(struct drm_i915_private *dev_priv,
+				     enum phy phy)
 {
 	if (intel_phy_is_combo(dev_priv, phy)) {
 		return ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
@@ -2698,8 +2818,9 @@ static void icl_sanitize_port_clk_off(struct drm_i915_private *dev_priv,
 		if (drm_WARN_ON(&dev_priv->drm, ddi_clk_needed))
 			continue;
 
-		DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
-			 phy_name(phy));
+		drm_notice(&dev_priv->drm,
+			   "PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
+			   phy_name(phy));
 		val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy);
 		intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
 	}
@@ -2936,11 +3057,14 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 static void intel_dp_sink_set_fec_ready(struct intel_dp *intel_dp,
 					const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
 	if (!crtc_state->fec_enable)
 		return;
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_FEC_CONFIGURATION, DP_FEC_READY) <= 0)
-		DRM_DEBUG_KMS("Failed to set FEC_READY in the sink\n");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to set FEC_READY in the sink\n");
 }
 
 static void intel_ddi_enable_fec(struct intel_encoder *encoder,
@@ -2960,7 +3084,8 @@ static void intel_ddi_enable_fec(struct intel_encoder *encoder,
 
 	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");
+		drm_err(&dev_priv->drm,
+			"Timed out waiting for FEC Enable Status\n");
 }
 
 static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
@@ -2980,7 +3105,8 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	intel_de_posting_read(dev_priv, intel_dp->regs.dp_tp_ctl);
 }
 
-static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
+static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
@@ -3048,13 +3174,13 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	 * 7.a Configure Transcoder Clock Select to direct the Port clock to the
 	 * Transcoder.
 	 */
-	intel_ddi_enable_pipe_clock(crtc_state);
+	intel_ddi_enable_pipe_clock(encoder, crtc_state);
 
 	/*
 	 * 7.b Configure TRANS_DDI_FUNC_CTL DDI Select, DDI Mode Select & MST
 	 * Transport Select
 	 */
-	intel_ddi_config_transcoder_func(crtc_state);
+	intel_ddi_config_transcoder_func(encoder, crtc_state);
 
 	/*
 	 * 7.c Configure & enable DP_TP_CTL with link training pattern 1
@@ -3120,7 +3246,8 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dsc_enable(encoder, crtc_state);
 }
 
-static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
+static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
@@ -3185,21 +3312,22 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_ddi_enable_fec(encoder, crtc_state);
 
 	if (!is_mst)
-		intel_ddi_enable_pipe_clock(crtc_state);
+		intel_ddi_enable_pipe_clock(encoder, crtc_state);
 
 	intel_dsc_enable(encoder, crtc_state);
 }
 
-static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
+static void intel_ddi_pre_enable_dp(struct intel_atomic_state *state,
+				    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);
+		tgl_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state);
 	else
-		hsw_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
+		hsw_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state);
 
 	/* MST will call a setting of MSA after an allocating of Virtual Channel
 	 * from MST encoder pre_enable callback.
@@ -3211,7 +3339,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	}
 }
 
-static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
+static void intel_ddi_pre_enable_hdmi(struct intel_atomic_state *state,
+				      struct intel_encoder *encoder,
 				      const struct intel_crtc_state *crtc_state,
 				      const struct drm_connector_state *conn_state)
 {
@@ -3244,14 +3373,15 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
 
-	intel_ddi_enable_pipe_clock(crtc_state);
+	intel_ddi_enable_pipe_clock(encoder, crtc_state);
 
 	intel_dig_port->set_infoframes(encoder,
 				       crtc_state->has_infoframe,
 				       crtc_state, conn_state);
 }
 
-static void intel_ddi_pre_enable(struct intel_encoder *encoder,
+static void intel_ddi_pre_enable(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state,
 				 const struct drm_connector_state *conn_state)
 {
@@ -3280,12 +3410,14 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
-		intel_ddi_pre_enable_hdmi(encoder, crtc_state, conn_state);
+		intel_ddi_pre_enable_hdmi(state, encoder, crtc_state,
+					  conn_state);
 	} else {
 		struct intel_lspcon *lspcon =
 				enc_to_intel_lspcon(encoder);
 
-		intel_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
+		intel_ddi_pre_enable_dp(state, encoder, crtc_state,
+					conn_state);
 		if (lspcon->active) {
 			struct intel_digital_port *dig_port =
 					enc_to_dig_port(encoder);
@@ -3328,7 +3460,8 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder,
 		intel_wait_ddi_buf_idle(dev_priv, port);
 }
 
-static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
+static void intel_ddi_post_disable_dp(struct intel_atomic_state *state,
+				      struct intel_encoder *encoder,
 				      const struct intel_crtc_state *old_crtc_state,
 				      const struct drm_connector_state *old_conn_state)
 {
@@ -3339,6 +3472,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 					  INTEL_OUTPUT_DP_MST);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
+	intel_dp_set_infoframes(encoder, false, old_crtc_state, old_conn_state);
+
 	/*
 	 * Power down sink before disabling the port, otherwise we end
 	 * up getting interrupts from the sink on detecting link loss.
@@ -3384,7 +3519,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	intel_ddi_clk_disable(encoder);
 }
 
-static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
+static void intel_ddi_post_disable_hdmi(struct intel_atomic_state *state,
+					struct intel_encoder *encoder,
 					const struct intel_crtc_state *old_crtc_state,
 					const struct drm_connector_state *old_conn_state)
 {
@@ -3407,22 +3543,8 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
 }
 
-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->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	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));
-
-	intel_de_write(dev_priv,
-		       TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
-}
-
-static void intel_ddi_post_disable(struct intel_encoder *encoder,
+static void intel_ddi_post_disable(struct intel_atomic_state *state,
+				   struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
@@ -3436,9 +3558,6 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder,
 
 		intel_disable_pipe(old_crtc_state);
 
-		if (INTEL_GEN(dev_priv) >= 11)
-			icl_disable_transcoder_port_sync(old_crtc_state);
-
 		intel_ddi_disable_transcoder_func(old_crtc_state);
 
 		intel_dsc_disable(old_crtc_state);
@@ -3463,11 +3582,11 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder,
 	 */
 
 	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI))
-		intel_ddi_post_disable_hdmi(encoder,
-					    old_crtc_state, old_conn_state);
+		intel_ddi_post_disable_hdmi(state, encoder, old_crtc_state,
+					    old_conn_state);
 	else
-		intel_ddi_post_disable_dp(encoder,
-					  old_crtc_state, old_conn_state);
+		intel_ddi_post_disable_dp(state, encoder, old_crtc_state,
+					  old_conn_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_unmap_plls_to_ports(encoder);
@@ -3480,7 +3599,8 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder,
 		intel_tc_port_put_link(dig_port);
 }
 
-void intel_ddi_fdi_post_disable(struct intel_encoder *encoder,
+void intel_ddi_fdi_post_disable(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
@@ -3514,7 +3634,43 @@ void intel_ddi_fdi_post_disable(struct intel_encoder *encoder,
 	intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val);
 }
 
-static void intel_enable_ddi_dp(struct intel_encoder *encoder,
+static void trans_port_sync_stop_link_train(struct intel_atomic_state *state,
+					    struct intel_encoder *encoder,
+					    const struct intel_crtc_state *crtc_state)
+{
+	const struct drm_connector_state *conn_state;
+	struct drm_connector *conn;
+	int i;
+
+	if (!crtc_state->sync_mode_slaves_mask)
+		return;
+
+	for_each_new_connector_in_state(&state->base, conn, conn_state, i) {
+		struct intel_encoder *slave_encoder =
+			to_intel_encoder(conn_state->best_encoder);
+		struct intel_crtc *slave_crtc = to_intel_crtc(conn_state->crtc);
+		const struct intel_crtc_state *slave_crtc_state;
+
+		if (!slave_crtc)
+			continue;
+
+		slave_crtc_state =
+			intel_atomic_get_new_crtc_state(state, slave_crtc);
+
+		if (slave_crtc_state->master_transcoder !=
+		    crtc_state->cpu_transcoder)
+			continue;
+
+		intel_dp_stop_link_train(enc_to_intel_dp(slave_encoder));
+	}
+
+	usleep_range(200, 400);
+
+	intel_dp_stop_link_train(enc_to_intel_dp(encoder));
+}
+
+static void intel_enable_ddi_dp(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state,
 				const struct drm_connector_state *conn_state)
 {
@@ -3526,13 +3682,14 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder,
 		intel_dp_stop_link_train(intel_dp);
 
 	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_psr_enable(intel_dp, crtc_state, conn_state);
+	intel_dp_set_infoframes(encoder, true, crtc_state, conn_state);
 	intel_edp_drrs_enable(intel_dp, crtc_state);
 
 	if (crtc_state->has_audio)
 		intel_audio_codec_enable(encoder, crtc_state, conn_state);
+
+	trans_port_sync_stop_link_train(state, encoder, crtc_state);
 }
 
 static i915_reg_t
@@ -3555,7 +3712,8 @@ gen9_chicken_trans_reg_by_port(struct drm_i915_private *dev_priv,
 	return CHICKEN_TRANS(trans[port]);
 }
 
-static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
+static void intel_enable_ddi_hdmi(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
@@ -3567,9 +3725,9 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 	if (!intel_hdmi_handle_sink_scrambling(encoder, connector,
 					       crtc_state->hdmi_high_tmds_clock_ratio,
 					       crtc_state->hdmi_scrambling))
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Failed to configure sink "
-			      "scrambling/TMDS bit clock ratio\n",
-			       connector->base.id, connector->name);
+		drm_dbg_kms(&dev_priv->drm,
+			    "[CONNECTOR:%d:%s] Failed to configure sink scrambling/TMDS bit clock ratio\n",
+			    connector->base.id, connector->name);
 
 	/* Display WA #1143: skl,kbl,cfl */
 	if (IS_GEN9_BC(dev_priv)) {
@@ -3617,20 +3775,23 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 		intel_audio_codec_enable(encoder, crtc_state, conn_state);
 }
 
-static void intel_enable_ddi(struct intel_encoder *encoder,
+static void intel_enable_ddi(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct drm_connector_state *conn_state)
 {
-	WARN_ON(crtc_state->has_pch_encoder);
+	drm_WARN_ON(state->base.dev, crtc_state->has_pch_encoder);
+
+	intel_ddi_enable_transcoder_func(encoder, crtc_state);
 
 	intel_enable_pipe(crtc_state);
 
 	intel_crtc_vblank_on(crtc_state);
 
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		intel_enable_ddi_hdmi(encoder, crtc_state, conn_state);
+		intel_enable_ddi_hdmi(state, encoder, crtc_state, conn_state);
 	else
-		intel_enable_ddi_dp(encoder, crtc_state, conn_state);
+		intel_enable_ddi_dp(state, encoder, crtc_state, conn_state);
 
 	/* Enable hdcp if it's desired */
 	if (conn_state->content_protection ==
@@ -3640,7 +3801,8 @@ static void intel_enable_ddi(struct intel_encoder *encoder,
 				  (u8)conn_state->hdcp_content_type);
 }
 
-static void intel_disable_ddi_dp(struct intel_encoder *encoder,
+static void intel_disable_ddi_dp(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
@@ -3660,10 +3822,12 @@ static void intel_disable_ddi_dp(struct intel_encoder *encoder,
 					      false);
 }
 
-static void intel_disable_ddi_hdmi(struct intel_encoder *encoder,
+static void intel_disable_ddi_hdmi(struct intel_atomic_state *state,
+				   struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct drm_connector *connector = old_conn_state->connector;
 
 	if (old_crtc_state->has_audio)
@@ -3672,23 +3836,28 @@ static void intel_disable_ddi_hdmi(struct intel_encoder *encoder,
 
 	if (!intel_hdmi_handle_sink_scrambling(encoder, connector,
 					       false, false))
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Failed to reset sink scrambling/TMDS bit clock ratio\n",
-			      connector->base.id, connector->name);
+		drm_dbg_kms(&i915->drm,
+			    "[CONNECTOR:%d:%s] Failed to reset sink scrambling/TMDS bit clock ratio\n",
+			    connector->base.id, connector->name);
 }
 
-static void intel_disable_ddi(struct intel_encoder *encoder,
+static void intel_disable_ddi(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
 	intel_hdcp_disable(to_intel_connector(old_conn_state->connector));
 
 	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI))
-		intel_disable_ddi_hdmi(encoder, old_crtc_state, old_conn_state);
+		intel_disable_ddi_hdmi(state, encoder, old_crtc_state,
+				       old_conn_state);
 	else
-		intel_disable_ddi_dp(encoder, old_crtc_state, old_conn_state);
+		intel_disable_ddi_dp(state, encoder, old_crtc_state,
+				     old_conn_state);
 }
 
-static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder,
+static void intel_ddi_update_pipe_dp(struct intel_atomic_state *state,
+				     struct intel_encoder *encoder,
 				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
@@ -3696,21 +3865,24 @@ static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder,
 
 	intel_ddi_set_dp_msa(crtc_state, conn_state);
 
-	intel_psr_update(intel_dp, crtc_state);
+	intel_psr_update(intel_dp, crtc_state, conn_state);
+	intel_dp_set_infoframes(encoder, true, crtc_state, conn_state);
 	intel_edp_drrs_enable(intel_dp, crtc_state);
 
-	intel_panel_update_backlight(encoder, crtc_state, conn_state);
+	intel_panel_update_backlight(state, encoder, crtc_state, conn_state);
 }
 
-static void intel_ddi_update_pipe(struct intel_encoder *encoder,
+static void intel_ddi_update_pipe(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
 
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
-		intel_ddi_update_pipe_dp(encoder, crtc_state, conn_state);
+		intel_ddi_update_pipe_dp(state, encoder, crtc_state,
+					 conn_state);
 
-	intel_hdcp_update_pipe(encoder, crtc_state, conn_state);
+	intel_hdcp_update_pipe(state, encoder, crtc_state, conn_state);
 }
 
 static void
@@ -3722,7 +3894,7 @@ intel_ddi_update_prepare(struct intel_atomic_state *state,
 		crtc ? intel_atomic_get_new_crtc_state(state, crtc) : NULL;
 	int required_lanes = crtc_state ? crtc_state->lane_count : 1;
 
-	WARN_ON(crtc && crtc->active);
+	drm_WARN_ON(state->base.dev, crtc && crtc->active);
 
 	intel_tc_port_get_link(enc_to_dig_port(encoder),
 		               required_lanes);
@@ -3739,7 +3911,8 @@ intel_ddi_update_complete(struct intel_atomic_state *state,
 }
 
 static void
-intel_ddi_pre_pll_enable(struct intel_encoder *encoder,
+intel_ddi_pre_pll_enable(struct intel_atomic_state *state,
+			 struct intel_encoder *encoder,
 			 const struct intel_crtc_state *crtc_state,
 			 const struct drm_connector_state *conn_state)
 {
@@ -3813,6 +3986,74 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 	udelay(600);
 }
 
+static void intel_ddi_set_link_train(struct intel_dp *intel_dp,
+				     u8 dp_train_pat)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
+	enum port port = dp_to_dig_port(intel_dp)->base.port;
+	u32 temp;
+
+	temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
+
+	if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
+		temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
+	else
+		temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
+
+	temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
+	switch (dp_train_pat & train_pat_mask) {
+	case DP_TRAINING_PATTERN_DISABLE:
+		temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
+		break;
+	case DP_TRAINING_PATTERN_1:
+		temp |= DP_TP_CTL_LINK_TRAIN_PAT1;
+		break;
+	case DP_TRAINING_PATTERN_2:
+		temp |= DP_TP_CTL_LINK_TRAIN_PAT2;
+		break;
+	case DP_TRAINING_PATTERN_3:
+		temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
+		break;
+	case DP_TRAINING_PATTERN_4:
+		temp |= DP_TP_CTL_LINK_TRAIN_PAT4;
+		break;
+	}
+
+	intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, temp);
+
+	intel_de_write(dev_priv, DDI_BUF_CTL(port), intel_dp->DP);
+	intel_de_posting_read(dev_priv, DDI_BUF_CTL(port));
+}
+
+static void intel_ddi_set_idle_link_train(struct intel_dp *intel_dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum port port = encoder->port;
+	u32 val;
+
+	val = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
+	val &= ~DP_TP_CTL_LINK_TRAIN_MASK;
+	val |= DP_TP_CTL_LINK_TRAIN_IDLE;
+	intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, val);
+
+	/*
+	 * 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 && INTEL_GEN(dev_priv) < 12)
+		return;
+
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
+				  DP_TP_STATUS_IDLE_DONE, 1))
+		drm_err(&dev_priv->drm,
+			"Timed out waiting for DP idle patterns\n");
+}
+
 static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
 				       enum transcoder cpu_transcoder)
 {
@@ -3839,6 +4080,66 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 		crtc_state->min_voltage_level = 2;
 }
 
+static enum transcoder bdw_transcoder_master_readout(struct drm_i915_private *dev_priv,
+						     enum transcoder cpu_transcoder)
+{
+	u32 master_select;
+
+	if (INTEL_GEN(dev_priv) >= 11) {
+		u32 ctl2 = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL2(cpu_transcoder));
+
+		if ((ctl2 & PORT_SYNC_MODE_ENABLE) == 0)
+			return INVALID_TRANSCODER;
+
+		master_select = REG_FIELD_GET(PORT_SYNC_MODE_MASTER_SELECT_MASK, ctl2);
+	} else {
+		u32 ctl = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder));
+
+		if ((ctl & TRANS_DDI_PORT_SYNC_ENABLE) == 0)
+			return INVALID_TRANSCODER;
+
+		master_select = REG_FIELD_GET(TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK, ctl);
+	}
+
+	if (master_select == 0)
+		return TRANSCODER_EDP;
+	else
+		return master_select - 1;
+}
+
+static void bdw_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	u32 transcoders = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_D);
+	enum transcoder cpu_transcoder;
+
+	crtc_state->master_transcoder =
+		bdw_transcoder_master_readout(dev_priv, crtc_state->cpu_transcoder);
+
+	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 (bdw_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);
+	}
+
+	drm_WARN_ON(&dev_priv->drm,
+		    crtc_state->master_transcoder != INVALID_TRANSCODER &&
+		    crtc_state->sync_mode_slaves_mask);
+}
+
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config)
 {
@@ -3930,11 +4231,15 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 			pipe_config->fec_enable =
 				intel_de_read(dev_priv, 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);
+			drm_dbg_kms(&dev_priv->drm,
+				    "[ENCODER:%d:%s] Fec status: %u\n",
+				    encoder->base.base.id, encoder->base.name,
+				    pipe_config->fec_enable);
 		}
 
+		pipe_config->infoframes.enable |=
+			intel_hdmi_infoframes_enabled(encoder, pipe_config);
+
 		break;
 	case TRANS_DDI_MODE_SELECT_DP_MST:
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_DP_MST);
@@ -3946,6 +4251,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 					REG_FIELD_GET(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, temp);
 
 		intel_dp_get_m_n(intel_crtc, pipe_config);
+
+		pipe_config->infoframes.enable |=
+			intel_hdmi_infoframes_enabled(encoder, pipe_config);
 		break;
 	default:
 		break;
@@ -3969,8 +4277,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		 * up by the BIOS, and thus we can't get the mode at module
 		 * load.
 		 */
-		DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n",
-			      pipe_config->pipe_bpp, dev_priv->vbt.edp.bpp);
+		drm_dbg_kms(&dev_priv->drm,
+			    "pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n",
+			    pipe_config->pipe_bpp, dev_priv->vbt.edp.bpp);
 		dev_priv->vbt.edp.bpp = pipe_config->pipe_bpp;
 	}
 
@@ -3996,6 +4305,12 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	intel_read_infoframe(encoder, pipe_config,
 			     HDMI_INFOFRAME_TYPE_DRM,
 			     &pipe_config->infoframes.drm);
+
+	if (INTEL_GEN(dev_priv) >= 8)
+		bdw_get_trans_port_sync_config(pipe_config);
+
+	intel_read_dp_sdp(encoder, pipe_config, HDMI_PACKET_TYPE_GAMUT_METADATA);
+	intel_read_dp_sdp(encoder, pipe_config, DP_SDP_VSC);
 }
 
 static enum intel_output_type
@@ -4025,7 +4340,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 	enum port port = encoder->port;
 	int ret;
 
-	if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A)
+	if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A)
 		pipe_config->cpu_transcoder = TRANSCODER_EDP;
 
 	if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI)) {
@@ -4097,7 +4412,11 @@ intel_ddi_port_sync_transcoders(const struct intel_crtc_state *ref_crtc_state,
 	u8 transcoders = 0;
 	int i;
 
-	if (INTEL_GEN(dev_priv) < 11)
+	/*
+	 * We don't enable port sync on BDW due to missing w/as and
+	 * due to not having adjusted the modeset sequence appropriately.
+	 */
+	if (INTEL_GEN(dev_priv) < 9)
 		return 0;
 
 	if (!intel_crtc_has_type(ref_crtc_state, INTEL_OUTPUT_DP))
@@ -4129,12 +4448,13 @@ static int intel_ddi_compute_config_late(struct intel_encoder *encoder,
 					 struct intel_crtc_state *crtc_state,
 					 struct drm_connector_state *conn_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct drm_connector *connector = conn_state->connector;
 	u8 port_sync_transcoders = 0;
 
-	DRM_DEBUG_KMS("[ENCODER:%d:%s] [CRTC:%d:%s]",
-		      encoder->base.base.id, encoder->base.name,
-		      crtc_state->uapi.crtc->base.id, crtc_state->uapi.crtc->name);
+	drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] [CRTC:%d:%s]",
+		    encoder->base.base.id, encoder->base.name,
+		    crtc_state->uapi.crtc->base.id, crtc_state->uapi.crtc->name);
 
 	if (connector->has_tile)
 		port_sync_transcoders = intel_ddi_port_sync_transcoders(crtc_state,
@@ -4187,6 +4507,20 @@ intel_ddi_init_dp_connector(struct intel_digital_port *intel_dig_port)
 	intel_dig_port->dp.output_reg = DDI_BUF_CTL(port);
 	intel_dig_port->dp.prepare_link_retrain =
 		intel_ddi_prepare_link_retrain;
+	intel_dig_port->dp.set_link_train = intel_ddi_set_link_train;
+	intel_dig_port->dp.set_idle_link_train = intel_ddi_set_idle_link_train;
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		intel_dig_port->dp.set_signal_levels = tgl_set_signal_levels;
+	else if (INTEL_GEN(dev_priv) >= 11)
+		intel_dig_port->dp.set_signal_levels = icl_set_signal_levels;
+	else if (IS_CANNONLAKE(dev_priv))
+		intel_dig_port->dp.set_signal_levels = cnl_set_signal_levels;
+	else if (IS_GEN9_LP(dev_priv))
+		intel_dig_port->dp.set_signal_levels = bxt_set_signal_levels;
+	else
+		intel_dig_port->dp.set_signal_levels = hsw_set_signal_levels;
+
 	if (INTEL_GEN(dev_priv) < 12) {
 		intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port);
 		intel_dig_port->dp.regs.dp_tp_status = DP_TP_STATUS(port);
@@ -4278,7 +4612,8 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 
 	ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config);
 	if (ret < 0) {
-		DRM_ERROR("Failed to read TMDS config: %d\n", ret);
+		drm_err(&dev_priv->drm, "Failed to read TMDS config: %d\n",
+			ret);
 		return 0;
 	}
 
@@ -4302,15 +4637,17 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 
 static enum intel_hotplug_state
 intel_ddi_hotplug(struct intel_encoder *encoder,
-		  struct intel_connector *connector,
-		  bool irq_received)
+		  struct intel_connector *connector)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+	bool is_tc = intel_phy_is_tc(i915, phy);
 	struct drm_modeset_acquire_ctx ctx;
 	enum intel_hotplug_state state;
 	int ret;
 
-	state = intel_encoder_hotplug(encoder, connector, irq_received);
+	state = intel_encoder_hotplug(encoder, connector);
 
 	drm_modeset_acquire_init(&ctx, 0);
 
@@ -4348,14 +4685,45 @@ intel_ddi_hotplug(struct intel_encoder *encoder,
 	 * valid EDID. To solve this schedule another detection cycle if this
 	 * time around we didn't detect any change in the sink's connection
 	 * status.
+	 *
+	 * Type-c connectors which get their HPD signal deasserted then
+	 * reasserted, without unplugging/replugging the sink from the
+	 * connector, introduce a delay until the AUX channel communication
+	 * becomes functional. Retry the detection for 5 seconds on type-c
+	 * connectors to account for this delay.
 	 */
-	if (state == INTEL_HOTPLUG_UNCHANGED && irq_received &&
+	if (state == INTEL_HOTPLUG_UNCHANGED &&
+	    connector->hotplug_retries < (is_tc ? 5 : 1) &&
 	    !dig_port->dp.is_mst)
 		state = INTEL_HOTPLUG_RETRY;
 
 	return state;
 }
 
+static bool lpt_digital_port_connected(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 bit = dev_priv->hotplug.pch_hpd[encoder->hpd_pin];
+
+	return intel_de_read(dev_priv, SDEISR) & bit;
+}
+
+static bool hsw_digital_port_connected(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin];
+
+	return intel_de_read(dev_priv, DEISR) & bit;
+}
+
+static bool bdw_digital_port_connected(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin];
+
+	return intel_de_read(dev_priv, GEN8_DE_PORT_ISR) & bit;
+}
+
 static struct intel_connector *
 intel_ddi_init_hdmi_connector(struct intel_digital_port *intel_dig_port)
 {
@@ -4424,7 +4792,8 @@ intel_ddi_max_lanes(struct intel_digital_port *intel_dport)
 	 * so we use the proper lane count for our calculations.
 	 */
 	if (intel_ddi_a_force_4_lanes(intel_dport)) {
-		DRM_DEBUG_KMS("Forcing DDI_A_4_LANES for port A\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Forcing DDI_A_4_LANES for port A\n");
 		intel_dport->saved_port_bits |= DDI_A_4_LANES;
 		max_lanes = 4;
 	}
@@ -4452,12 +4821,14 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 		init_dp = true;
 		init_lspcon = true;
 		init_hdmi = false;
-		DRM_DEBUG_KMS("VBT says port %c has lspcon\n", port_name(port));
+		drm_dbg_kms(&dev_priv->drm, "VBT says port %c has lspcon\n",
+			    port_name(port));
 	}
 
 	if (!init_dp && !init_hdmi) {
-		DRM_DEBUG_KMS("VBT says port %c is not DVI/HDMI/DP compatible, respect it\n",
-			      port_name(port));
+		drm_dbg_kms(&dev_priv->drm,
+			    "VBT says port %c is not DVI/HDMI/DP compatible, respect it\n",
+			    port_name(port));
 		return;
 	}
 
@@ -4536,17 +4907,36 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	if (init_lspcon) {
 		if (lspcon_init(intel_dig_port))
 			/* TODO: handle hdmi info frame part */
-			DRM_DEBUG_KMS("LSPCON init success on port %c\n",
-				port_name(port));
+			drm_dbg_kms(&dev_priv->drm,
+				    "LSPCON init success on port %c\n",
+				    port_name(port));
 		else
 			/*
 			 * LSPCON init faied, but DP init was success, so
 			 * lets try to drive as DP++ port.
 			 */
-			DRM_ERROR("LSPCON init failed on port %c\n",
+			drm_err(&dev_priv->drm,
+				"LSPCON init failed on port %c\n",
 				port_name(port));
 	}
 
+	if (INTEL_GEN(dev_priv) >= 11) {
+		if (intel_phy_is_tc(dev_priv, phy))
+			intel_dig_port->connected = intel_tc_port_connected;
+		else
+			intel_dig_port->connected = lpt_digital_port_connected;
+	} else if (INTEL_GEN(dev_priv) >= 8) {
+		if (port == PORT_A || IS_GEN9_LP(dev_priv))
+			intel_dig_port->connected = bdw_digital_port_connected;
+		else
+			intel_dig_port->connected = lpt_digital_port_connected;
+	} else {
+		if (port == PORT_A)
+			intel_dig_port->connected = hsw_digital_port_connected;
+		else
+			intel_dig_port->connected = lpt_digital_port_connected;
+	}
+
 	intel_infoframe_init(intel_dig_port);
 
 	return;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h
index 55fd72b901fe..fbdf8ddde486 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi.h
@@ -17,16 +17,19 @@ struct intel_dp;
 struct intel_dpll_hw_state;
 struct intel_encoder;
 
-void intel_ddi_fdi_post_disable(struct intel_encoder *intel_encoder,
+void intel_ddi_fdi_post_disable(struct intel_atomic_state *state,
+				struct intel_encoder *intel_encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state);
 void hsw_fdi_link_train(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state);
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
-void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state);
+void intel_ddi_enable_transcoder_func(struct intel_encoder *encoder,
+				      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_enable_pipe_clock(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(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);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 346846609f45..9ea1a397d1b5 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -238,9 +238,9 @@ static void intel_update_czclk(struct drm_i915_private *dev_priv)
 		dev_priv->czclk_freq);
 }
 
-static inline u32 /* units of 100MHz */
-intel_fdi_link_freq(struct drm_i915_private *dev_priv,
-		    const struct intel_crtc_state *pipe_config)
+/* units of 100MHz */
+static u32 intel_fdi_link_freq(struct drm_i915_private *dev_priv,
+			       const struct intel_crtc_state *pipe_config)
 {
 	if (HAS_DDI(dev_priv))
 		return pipe_config->port_clock; /* SPLL */
@@ -525,7 +525,7 @@ skl_wa_827(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable)
 		               intel_de_read(dev_priv, CLKGATE_DIS_PSL(pipe)) & ~(DUPS1_GATING_DIS | DUPS2_GATING_DIS));
 }
 
-/* Wa_2006604312:icl */
+/* Wa_2006604312:icl,ehl */
 static void
 icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe,
 		       bool enable)
@@ -544,17 +544,23 @@ needs_modeset(const struct intel_crtc_state *state)
 	return drm_atomic_crtc_needs_modeset(&state->uapi);
 }
 
-bool
-is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
+static bool
+is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state)
 {
-	return (crtc_state->master_transcoder != INVALID_TRANSCODER ||
-		crtc_state->sync_mode_slaves_mask);
+	return crtc_state->master_transcoder != INVALID_TRANSCODER;
 }
 
 static bool
-is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state)
+is_trans_port_sync_master(const struct intel_crtc_state *crtc_state)
 {
-	return crtc_state->master_transcoder != INVALID_TRANSCODER;
+	return crtc_state->sync_mode_slaves_mask != 0;
+}
+
+bool
+is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
+{
+	return is_trans_port_sync_master(crtc_state) ||
+		is_trans_port_sync_slave(crtc_state);
 }
 
 /*
@@ -620,45 +626,43 @@ int chv_calc_dpll_params(int refclk, struct dpll *clock)
 	return clock->dot / 5;
 }
 
-#define INTELPllInvalid(s)   do { /* DRM_DEBUG(s); */ return false; } while (0)
-
 /*
  * Returns whether the given set of divisors are valid for a given refclk with
  * the given connectors.
  */
-static bool intel_PLL_is_valid(struct drm_i915_private *dev_priv,
+static bool intel_pll_is_valid(struct drm_i915_private *dev_priv,
 			       const struct intel_limit *limit,
 			       const struct dpll *clock)
 {
-	if (clock->n   < limit->n.min   || limit->n.max   < clock->n)
-		INTELPllInvalid("n out of range\n");
-	if (clock->p1  < limit->p1.min  || limit->p1.max  < clock->p1)
-		INTELPllInvalid("p1 out of range\n");
-	if (clock->m2  < limit->m2.min  || limit->m2.max  < clock->m2)
-		INTELPllInvalid("m2 out of range\n");
-	if (clock->m1  < limit->m1.min  || limit->m1.max  < clock->m1)
-		INTELPllInvalid("m1 out of range\n");
+	if (clock->n < limit->n.min || limit->n.max < clock->n)
+		return false;
+	if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1)
+		return false;
+	if (clock->m2 < limit->m2.min || limit->m2.max < clock->m2)
+		return false;
+	if (clock->m1 < limit->m1.min || limit->m1.max < clock->m1)
+		return false;
 
 	if (!IS_PINEVIEW(dev_priv) && !IS_VALLEYVIEW(dev_priv) &&
 	    !IS_CHERRYVIEW(dev_priv) && !IS_GEN9_LP(dev_priv))
 		if (clock->m1 <= clock->m2)
-			INTELPllInvalid("m1 <= m2\n");
+			return false;
 
 	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv) &&
 	    !IS_GEN9_LP(dev_priv)) {
 		if (clock->p < limit->p.min || limit->p.max < clock->p)
-			INTELPllInvalid("p out of range\n");
+			return false;
 		if (clock->m < limit->m.min || limit->m.max < clock->m)
-			INTELPllInvalid("m out of range\n");
+			return false;
 	}
 
 	if (clock->vco < limit->vco.min || limit->vco.max < clock->vco)
-		INTELPllInvalid("vco out of range\n");
+		return false;
 	/* XXX: We may need to be checking "Dot clock" depending on the multiplier,
 	 * connector, etc., rather than just a single range.
 	 */
 	if (clock->dot < limit->dot.min || limit->dot.max < clock->dot)
-		INTELPllInvalid("dot out of range\n");
+		return false;
 
 	return true;
 }
@@ -725,7 +729,7 @@ i9xx_find_best_dpll(const struct intel_limit *limit,
 					int this_err;
 
 					i9xx_calc_dpll_params(refclk, &clock);
-					if (!intel_PLL_is_valid(to_i915(dev),
+					if (!intel_pll_is_valid(to_i915(dev),
 								limit,
 								&clock))
 						continue;
@@ -781,7 +785,7 @@ pnv_find_best_dpll(const struct intel_limit *limit,
 					int this_err;
 
 					pnv_calc_dpll_params(refclk, &clock);
-					if (!intel_PLL_is_valid(to_i915(dev),
+					if (!intel_pll_is_valid(to_i915(dev),
 								limit,
 								&clock))
 						continue;
@@ -842,7 +846,7 @@ g4x_find_best_dpll(const struct intel_limit *limit,
 					int this_err;
 
 					i9xx_calc_dpll_params(refclk, &clock);
-					if (!intel_PLL_is_valid(to_i915(dev),
+					if (!intel_pll_is_valid(to_i915(dev),
 								limit,
 								&clock))
 						continue;
@@ -939,7 +943,7 @@ vlv_find_best_dpll(const struct intel_limit *limit,
 
 					vlv_calc_dpll_params(refclk, &clock);
 
-					if (!intel_PLL_is_valid(to_i915(dev),
+					if (!intel_pll_is_valid(to_i915(dev),
 								limit,
 								&clock))
 						continue;
@@ -1008,7 +1012,7 @@ chv_find_best_dpll(const struct intel_limit *limit,
 
 			chv_calc_dpll_params(refclk, &clock);
 
-			if (!intel_PLL_is_valid(to_i915(dev), limit, &clock))
+			if (!intel_pll_is_valid(to_i915(dev), limit, &clock))
 				continue;
 
 			if (!vlv_PLL_is_optimal(dev, target, &clock, best_clock,
@@ -1969,16 +1973,16 @@ static bool is_aux_plane(const struct drm_framebuffer *fb, int plane)
 
 static int main_to_ccs_plane(const struct drm_framebuffer *fb, int main_plane)
 {
-	WARN_ON(!is_ccs_modifier(fb->modifier) ||
-		(main_plane && main_plane >= fb->format->num_planes / 2));
+	drm_WARN_ON(fb->dev, !is_ccs_modifier(fb->modifier) ||
+		    (main_plane && main_plane >= fb->format->num_planes / 2));
 
 	return fb->format->num_planes / 2 + main_plane;
 }
 
 static int ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane)
 {
-	WARN_ON(!is_ccs_modifier(fb->modifier) ||
-		ccs_plane < fb->format->num_planes / 2);
+	drm_WARN_ON(fb->dev, !is_ccs_modifier(fb->modifier) ||
+		    ccs_plane < fb->format->num_planes / 2);
 
 	return ccs_plane - fb->format->num_planes / 2;
 }
@@ -2910,6 +2914,7 @@ intel_fb_plane_get_subsampling(int *hsub, int *vsub,
 static int
 intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y)
 {
+	struct drm_i915_private *i915 = to_i915(fb->dev);
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	int main_plane;
 	int hsub, vsub;
@@ -2938,7 +2943,8 @@ intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y)
 	 * x/y offsets must match between CCS and the main surface.
 	 */
 	if (main_x != ccs_x || main_y != ccs_y) {
-		DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
+		drm_dbg_kms(&i915->drm,
+			      "Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
 			      main_x, main_y,
 			      ccs_x, ccs_y,
 			      intel_fb->normal[main_plane].x,
@@ -2986,7 +2992,7 @@ setup_fb_rotation(int plane, const struct intel_remapped_plane_info *plane_info,
 	    fb->modifier != I915_FORMAT_MOD_Yf_TILED)
 		return 0;
 
-	if (WARN_ON(plane >= ARRAY_SIZE(rot_info->plane)))
+	if (drm_WARN_ON(fb->dev, plane >= ARRAY_SIZE(rot_info->plane)))
 		return 0;
 
 	rot_info->plane[plane] = *plane_info;
@@ -3336,6 +3342,8 @@ int skl_format_to_fourcc(int format, bool rgb_order, bool alpha)
 		return DRM_FORMAT_RGB565;
 	case PLANE_CTL_FORMAT_NV12:
 		return DRM_FORMAT_NV12;
+	case PLANE_CTL_FORMAT_XYUV:
+		return DRM_FORMAT_XYUV8888;
 	case PLANE_CTL_FORMAT_P010:
 		return DRM_FORMAT_P010;
 	case PLANE_CTL_FORMAT_P012:
@@ -4580,6 +4588,8 @@ static u32 skl_plane_ctl_format(u32 pixel_format)
 	case DRM_FORMAT_XRGB16161616F:
 	case DRM_FORMAT_ARGB16161616F:
 		return PLANE_CTL_FORMAT_XRGB_16161616F;
+	case DRM_FORMAT_XYUV8888:
+		return PLANE_CTL_FORMAT_XYUV;
 	case DRM_FORMAT_YUYV:
 		return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_YUYV;
 	case DRM_FORMAT_YVYU:
@@ -4998,37 +5008,6 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 	intel_de_write(dev_priv, 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->uapi.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;
-
-	intel_de_write(dev_priv,
-		       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;
@@ -6110,30 +6089,26 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	return 0;
 }
 
-/**
- * skl_update_scaler_crtc - Stages update to scaler state for a given crtc.
- *
- * @state: crtc's scaler state
- *
- * Return
- *     0 - scaler_usage updated successfully
- *    error - requested scaling cannot be supported or other error condition
- */
-int skl_update_scaler_crtc(struct intel_crtc_state *state)
+static int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state)
 {
-	const struct drm_display_mode *adjusted_mode = &state->hw.adjusted_mode;
-	bool need_scaler = false;
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->hw.adjusted_mode;
+	int width, height;
 
-	if (state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 ||
-	    state->pch_pfit.enabled)
-		need_scaler = true;
+	if (crtc_state->pch_pfit.enabled) {
+		width = drm_rect_width(&crtc_state->pch_pfit.dst);
+		height = drm_rect_height(&crtc_state->pch_pfit.dst);
+	} else {
+		width = adjusted_mode->crtc_hdisplay;
+		height = adjusted_mode->crtc_vdisplay;
+	}
 
-	return skl_update_scaler(state, !state->hw.active, SKL_CRTC_INDEX,
-				 &state->scaler_state.scaler_id,
-				 state->pipe_src_w, state->pipe_src_h,
-				 adjusted_mode->crtc_hdisplay,
-				 adjusted_mode->crtc_vdisplay, NULL, 0,
-				 need_scaler);
+	return skl_update_scaler(crtc_state, !crtc_state->hw.active,
+				 SKL_CRTC_INDEX,
+				 &crtc_state->scaler_state.scaler_id,
+				 crtc_state->pipe_src_w, crtc_state->pipe_src_h,
+				 width, height, NULL, 0,
+				 crtc_state->pch_pfit.enabled);
 }
 
 /**
@@ -6200,6 +6175,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
 	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_XYUV8888:
 	case DRM_FORMAT_P010:
 	case DRM_FORMAT_P012:
 	case DRM_FORMAT_P016:
@@ -6241,70 +6217,80 @@ static void skl_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum pipe pipe = crtc->pipe;
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
+	struct drm_rect src = {
+		.x2 = crtc_state->pipe_src_w << 16,
+		.y2 = crtc_state->pipe_src_h << 16,
+	};
+	const struct drm_rect *dst = &crtc_state->pch_pfit.dst;
+	u16 uv_rgb_hphase, uv_rgb_vphase;
+	enum pipe pipe = crtc->pipe;
+	int width = drm_rect_width(dst);
+	int height = drm_rect_height(dst);
+	int x = dst->x1;
+	int y = dst->y1;
+	int hscale, vscale;
+	unsigned long irqflags;
+	int id;
 
-	if (crtc_state->pch_pfit.enabled) {
-		u16 uv_rgb_hphase, uv_rgb_vphase;
-		int pfit_w, pfit_h, hscale, vscale;
-		unsigned long irqflags;
-		int id;
-
-		if (drm_WARN_ON(&dev_priv->drm,
-				crtc_state->scaler_state.scaler_id < 0))
-			return;
+	if (!crtc_state->pch_pfit.enabled)
+		return;
 
-		pfit_w = (crtc_state->pch_pfit.size >> 16) & 0xFFFF;
-		pfit_h = crtc_state->pch_pfit.size & 0xFFFF;
+	if (drm_WARN_ON(&dev_priv->drm,
+			crtc_state->scaler_state.scaler_id < 0))
+		return;
 
-		hscale = (crtc_state->pipe_src_w << 16) / pfit_w;
-		vscale = (crtc_state->pipe_src_h << 16) / pfit_h;
+	hscale = drm_rect_calc_hscale(&src, dst, 0, INT_MAX);
+	vscale = drm_rect_calc_vscale(&src, dst, 0, INT_MAX);
 
-		uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false);
-		uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false);
+	uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false);
+	uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false);
 
-		id = scaler_state->scaler_id;
+	id = scaler_state->scaler_id;
 
-		spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
-		intel_de_write_fw(dev_priv, SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
-				  PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
-		intel_de_write_fw(dev_priv, SKL_PS_VPHASE(pipe, id),
-				  PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase));
-		intel_de_write_fw(dev_priv, SKL_PS_HPHASE(pipe, id),
-				  PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase));
-		intel_de_write_fw(dev_priv, SKL_PS_WIN_POS(pipe, id),
-				  crtc_state->pch_pfit.pos);
-		intel_de_write_fw(dev_priv, SKL_PS_WIN_SZ(pipe, id),
-				  crtc_state->pch_pfit.size);
+	intel_de_write_fw(dev_priv, SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
+			  PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
+	intel_de_write_fw(dev_priv, SKL_PS_VPHASE(pipe, id),
+			  PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+	intel_de_write_fw(dev_priv, SKL_PS_HPHASE(pipe, id),
+			  PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase));
+	intel_de_write_fw(dev_priv, SKL_PS_WIN_POS(pipe, id),
+			  x << 16 | y);
+	intel_de_write_fw(dev_priv, SKL_PS_WIN_SZ(pipe, id),
+			  width << 16 | height);
 
-		spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
-	}
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
 static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_rect *dst = &crtc_state->pch_pfit.dst;
 	enum pipe pipe = crtc->pipe;
+	int width = drm_rect_width(dst);
+	int height = drm_rect_height(dst);
+	int x = dst->x1;
+	int y = dst->y1;
 
-	if (crtc_state->pch_pfit.enabled) {
-		/* Force use of hard-coded filter coefficients
-		 * as some pre-programmed values are broken,
-		 * e.g. x201.
-		 */
-		if (IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv))
-			intel_de_write(dev_priv, PF_CTL(pipe),
-				       PF_ENABLE | PF_FILTER_MED_3x3 | PF_PIPE_SEL_IVB(pipe));
-		else
-			intel_de_write(dev_priv, PF_CTL(pipe),
-				       PF_ENABLE | PF_FILTER_MED_3x3);
-		intel_de_write(dev_priv, PF_WIN_POS(pipe),
-			       crtc_state->pch_pfit.pos);
-		intel_de_write(dev_priv, PF_WIN_SZ(pipe),
-			       crtc_state->pch_pfit.size);
-	}
+	if (!crtc_state->pch_pfit.enabled)
+		return;
+
+	/* Force use of hard-coded filter coefficients
+	 * as some pre-programmed values are broken,
+	 * e.g. x201.
+	 */
+	if (IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv))
+		intel_de_write(dev_priv, PF_CTL(pipe), PF_ENABLE |
+			       PF_FILTER_MED_3x3 | PF_PIPE_SEL_IVB(pipe));
+	else
+		intel_de_write(dev_priv, PF_CTL(pipe), PF_ENABLE |
+			       PF_FILTER_MED_3x3);
+	intel_de_write(dev_priv, PF_WIN_POS(pipe), x << 16 | y);
+	intel_de_write(dev_priv, PF_WIN_SZ(pipe), width << 16 | height);
 }
 
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
@@ -6463,8 +6449,8 @@ static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
-	/* Wa_2006604312:icl */
-	if (crtc_state->scaler_state.scaler_users > 0 && IS_ICELAKE(dev_priv))
+	/* Wa_2006604312:icl,ehl */
+	if (crtc_state->scaler_state.scaler_users > 0 && IS_GEN(dev_priv, 11))
 		return true;
 
 	return false;
@@ -6534,7 +6520,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state,
 	    needs_nv12_wa(new_crtc_state))
 		skl_wa_827(dev_priv, pipe, true);
 
-	/* Wa_2006604312:icl */
+	/* Wa_2006604312:icl,ehl */
 	if (!needs_scalerclk_wa(old_crtc_state) &&
 	    needs_scalerclk_wa(new_crtc_state))
 		icl_wa_scalerclkgating(dev_priv, pipe, true);
@@ -6646,7 +6632,7 @@ intel_connector_primary_encoder(struct intel_connector *connector)
 		return &dp_to_dig_port(connector->mst_port)->base;
 
 	encoder = intel_attached_encoder(connector);
-	WARN_ON(!encoder);
+	drm_WARN_ON(connector->base.dev, !encoder);
 
 	return encoder;
 }
@@ -6720,7 +6706,8 @@ static void intel_encoders_pre_pll_enable(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->pre_pll_enable)
-			encoder->pre_pll_enable(encoder, crtc_state, conn_state);
+			encoder->pre_pll_enable(state, encoder,
+						crtc_state, conn_state);
 	}
 }
 
@@ -6741,7 +6728,8 @@ static void intel_encoders_pre_enable(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->pre_enable)
-			encoder->pre_enable(encoder, crtc_state, conn_state);
+			encoder->pre_enable(state, encoder,
+					    crtc_state, conn_state);
 	}
 }
 
@@ -6762,7 +6750,8 @@ static void intel_encoders_enable(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->enable)
-			encoder->enable(encoder, crtc_state, conn_state);
+			encoder->enable(state, encoder,
+					crtc_state, conn_state);
 		intel_opregion_notify_encoder(encoder, true);
 	}
 }
@@ -6785,7 +6774,8 @@ static void intel_encoders_disable(struct intel_atomic_state *state,
 
 		intel_opregion_notify_encoder(encoder, false);
 		if (encoder->disable)
-			encoder->disable(encoder, old_crtc_state, old_conn_state);
+			encoder->disable(state, encoder,
+					 old_crtc_state, old_conn_state);
 	}
 }
 
@@ -6806,7 +6796,8 @@ static void intel_encoders_post_disable(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->post_disable)
-			encoder->post_disable(encoder, old_crtc_state, old_conn_state);
+			encoder->post_disable(state, encoder,
+					      old_crtc_state, old_conn_state);
 	}
 }
 
@@ -6827,7 +6818,8 @@ static void intel_encoders_post_pll_disable(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->post_pll_disable)
-			encoder->post_pll_disable(encoder, old_crtc_state, old_conn_state);
+			encoder->post_pll_disable(state, encoder,
+						  old_crtc_state, old_conn_state);
 	}
 }
 
@@ -6848,7 +6840,8 @@ static void intel_encoders_update_pipe(struct intel_atomic_state *state,
 			continue;
 
 		if (encoder->update_pipe)
-			encoder->update_pipe(encoder, crtc_state, conn_state);
+			encoder->update_pipe(state, encoder,
+					     crtc_state, conn_state);
 	}
 }
 
@@ -7037,9 +7030,6 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_set_pipe_timings(new_crtc_state);
 
-	if (INTEL_GEN(dev_priv) >= 11)
-		icl_enable_trans_port_sync(new_crtc_state);
-
 	intel_set_pipe_src_size(new_crtc_state);
 
 	if (cpu_transcoder != TRANSCODER_EDP &&
@@ -7087,9 +7077,6 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_set_pipe_chicken(crtc);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_transcoder_func(new_crtc_state);
-
 	if (dev_priv->display.initial_watermarks)
 		dev_priv->display.initial_watermarks(state, crtc);
 
@@ -7120,11 +7107,12 @@ void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 
 	/* To avoid upsetting the power well on haswell only disable the pfit if
 	 * it's in use. The hw state code will make sure we get this right. */
-	if (old_crtc_state->pch_pfit.enabled) {
-		intel_de_write(dev_priv, PF_CTL(pipe), 0);
-		intel_de_write(dev_priv, PF_WIN_POS(pipe), 0);
-		intel_de_write(dev_priv, PF_WIN_SZ(pipe), 0);
-	}
+	if (!old_crtc_state->pch_pfit.enabled)
+		return;
+
+	intel_de_write(dev_priv, PF_CTL(pipe), 0);
+	intel_de_write(dev_priv, PF_WIN_POS(pipe), 0);
+	intel_de_write(dev_priv, PF_WIN_SZ(pipe), 0);
 }
 
 static void ilk_crtc_disable(struct intel_atomic_state *state,
@@ -7312,7 +7300,17 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 		}
 	}
 
-	switch (dig_port->aux_ch) {
+	return intel_legacy_aux_to_power_domain(dig_port->aux_ch);
+}
+
+/*
+ * Converts aux_ch to power_domain without caring about TBT ports for that use
+ * intel_aux_power_domain()
+ */
+enum intel_display_power_domain
+intel_legacy_aux_to_power_domain(enum aux_ch aux_ch)
+{
+	switch (aux_ch) {
 	case AUX_CH_A:
 		return POWER_DOMAIN_AUX_A;
 	case AUX_CH_B:
@@ -7328,7 +7326,7 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 	case AUX_CH_G:
 		return POWER_DOMAIN_AUX_G;
 	default:
-		MISSING_CASE(dig_port->aux_ch);
+		MISSING_CASE(aux_ch);
 		return POWER_DOMAIN_AUX_A;
 	}
 }
@@ -7942,39 +7940,36 @@ static bool intel_crtc_supports_double_wide(const struct intel_crtc *crtc)
 		(crtc->pipe == PIPE_A || IS_I915G(dev_priv));
 }
 
-static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
+static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *crtc_state)
 {
-	u32 pixel_rate;
-
-	pixel_rate = pipe_config->hw.adjusted_mode.crtc_clock;
+	u32 pixel_rate = crtc_state->hw.adjusted_mode.crtc_clock;
+	unsigned int pipe_w, pipe_h, pfit_w, pfit_h;
 
 	/*
 	 * We only use IF-ID interlacing. If we ever use
 	 * PF-ID we'll need to adjust the pixel_rate here.
 	 */
 
-	if (pipe_config->pch_pfit.enabled) {
-		u64 pipe_w, pipe_h, pfit_w, pfit_h;
-		u32 pfit_size = pipe_config->pch_pfit.size;
+	if (!crtc_state->pch_pfit.enabled)
+		return pixel_rate;
 
-		pipe_w = pipe_config->pipe_src_w;
-		pipe_h = pipe_config->pipe_src_h;
+	pipe_w = crtc_state->pipe_src_w;
+	pipe_h = crtc_state->pipe_src_h;
 
-		pfit_w = (pfit_size >> 16) & 0xFFFF;
-		pfit_h = pfit_size & 0xFFFF;
-		if (pipe_w < pfit_w)
-			pipe_w = pfit_w;
-		if (pipe_h < pfit_h)
-			pipe_h = pfit_h;
+	pfit_w = drm_rect_width(&crtc_state->pch_pfit.dst);
+	pfit_h = drm_rect_height(&crtc_state->pch_pfit.dst);
 
-		if (WARN_ON(!pfit_w || !pfit_h))
-			return pixel_rate;
+	if (pipe_w < pfit_w)
+		pipe_w = pfit_w;
+	if (pipe_h < pfit_h)
+		pipe_h = pfit_h;
 
-		pixel_rate = div_u64(mul_u32_u32(pixel_rate, pipe_w * pipe_h),
-				     pfit_w * pfit_h);
-	}
+	if (drm_WARN_ON(crtc_state->uapi.crtc->dev,
+			!pfit_w || !pfit_h))
+		return pixel_rate;
 
-	return pixel_rate;
+	return div_u64(mul_u32_u32(pixel_rate, pipe_w * pipe_h),
+		       pfit_w * pfit_h);
 }
 
 static void intel_crtc_compute_pixel_rate(struct intel_crtc_state *crtc_state)
@@ -8143,7 +8138,7 @@ static void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv)
 	}
 }
 
-static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
+static bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
 {
 	if (i915_modparams.panel_use_ssc >= 0)
 		return i915_modparams.panel_use_ssc != 0;
@@ -8891,7 +8886,6 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 
 	mode->clock = pipe_config->hw.adjusted_mode.crtc_clock;
 
-	mode->hsync = drm_mode_hsync(mode);
 	mode->vrefresh = drm_mode_vrefresh(mode);
 	drm_mode_set_name(mode);
 }
@@ -9168,9 +9162,9 @@ static bool i9xx_has_pfit(struct drm_i915_private *dev_priv)
 		IS_PINEVIEW(dev_priv) || IS_MOBILE(dev_priv);
 }
 
-static void i9xx_get_pfit_config(struct intel_crtc *crtc,
-				 struct intel_crtc_state *pipe_config)
+static void i9xx_get_pfit_config(struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 tmp;
 
@@ -9190,9 +9184,9 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc,
 			return;
 	}
 
-	pipe_config->gmch_pfit.control = tmp;
-	pipe_config->gmch_pfit.pgm_ratios = intel_de_read(dev_priv,
-							  PFIT_PGM_RATIOS);
+	crtc_state->gmch_pfit.control = tmp;
+	crtc_state->gmch_pfit.pgm_ratios =
+		intel_de_read(dev_priv, PFIT_PGM_RATIOS);
 }
 
 static void vlv_crtc_clock_get(struct intel_crtc *crtc,
@@ -9398,7 +9392,6 @@ 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;
 
@@ -9443,7 +9436,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	intel_get_pipe_timings(crtc, pipe_config);
 	intel_get_pipe_src_size(crtc, pipe_config);
 
-	i9xx_get_pfit_config(crtc, pipe_config);
+	i9xx_get_pfit_config(pipe_config);
 
 	if (INTEL_GEN(dev_priv) >= 4) {
 		/* No way to read it out on pipes B and C */
@@ -10413,37 +10406,47 @@ static void ilk_get_fdi_m_n_config(struct intel_crtc *crtc,
 				     &pipe_config->fdi_m_n, NULL);
 }
 
-static void skl_get_pfit_config(struct intel_crtc *crtc,
-				struct intel_crtc_state *pipe_config)
+static void ilk_get_pfit_pos_size(struct intel_crtc_state *crtc_state,
+				  u32 pos, u32 size)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_scaler_state *scaler_state = &pipe_config->scaler_state;
-	u32 ps_ctrl = 0;
+	drm_rect_init(&crtc_state->pch_pfit.dst,
+		      pos >> 16, pos & 0xffff,
+		      size >> 16, size & 0xffff);
+}
+
+static void skl_get_pfit_config(struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state;
 	int id = -1;
 	int i;
 
 	/* find scaler attached to this pipe */
 	for (i = 0; i < crtc->num_scalers; i++) {
-		ps_ctrl = intel_de_read(dev_priv, SKL_PS_CTRL(crtc->pipe, i));
-		if (ps_ctrl & PS_SCALER_EN && !(ps_ctrl & PS_PLANE_SEL_MASK)) {
-			id = i;
-			pipe_config->pch_pfit.enabled = true;
-			pipe_config->pch_pfit.pos = intel_de_read(dev_priv,
-								  SKL_PS_WIN_POS(crtc->pipe, i));
-			pipe_config->pch_pfit.size = intel_de_read(dev_priv,
-								   SKL_PS_WIN_SZ(crtc->pipe, i));
-			scaler_state->scalers[i].in_use = true;
-			break;
-		}
+		u32 ctl, pos, size;
+
+		ctl = intel_de_read(dev_priv, SKL_PS_CTRL(crtc->pipe, i));
+		if ((ctl & (PS_SCALER_EN | PS_PLANE_SEL_MASK)) != PS_SCALER_EN)
+			continue;
+
+		id = i;
+		crtc_state->pch_pfit.enabled = true;
+
+		pos = intel_de_read(dev_priv, SKL_PS_WIN_POS(crtc->pipe, i));
+		size = intel_de_read(dev_priv, SKL_PS_WIN_SZ(crtc->pipe, i));
+
+		ilk_get_pfit_pos_size(crtc_state, pos, size);
+
+		scaler_state->scalers[i].in_use = true;
+		break;
 	}
 
 	scaler_state->scaler_id = id;
-	if (id >= 0) {
+	if (id >= 0)
 		scaler_state->scaler_users |= (1 << SKL_CRTC_INDEX);
-	} else {
+	else
 		scaler_state->scaler_users &= ~(1 << SKL_CRTC_INDEX);
-	}
 }
 
 static void
@@ -10579,30 +10582,30 @@ error:
 	kfree(intel_fb);
 }
 
-static void ilk_get_pfit_config(struct intel_crtc *crtc,
-				struct intel_crtc_state *pipe_config)
+static void ilk_get_pfit_config(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	u32 tmp;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 ctl, pos, size;
 
-	tmp = intel_de_read(dev_priv, PF_CTL(crtc->pipe));
-
-	if (tmp & PF_ENABLE) {
-		pipe_config->pch_pfit.enabled = true;
-		pipe_config->pch_pfit.pos = intel_de_read(dev_priv,
-							  PF_WIN_POS(crtc->pipe));
-		pipe_config->pch_pfit.size = intel_de_read(dev_priv,
-							   PF_WIN_SZ(crtc->pipe));
-
-		/* We currently do not free assignements of panel fitters on
-		 * ivb/hsw (since we don't use the higher upscaling modes which
-		 * differentiates them) so just WARN about this case for now. */
-		if (IS_GEN(dev_priv, 7)) {
-			drm_WARN_ON(dev, (tmp & PF_PIPE_SEL_MASK_IVB) !=
-				    PF_PIPE_SEL_IVB(crtc->pipe));
-		}
-	}
+	ctl = intel_de_read(dev_priv, PF_CTL(crtc->pipe));
+	if ((ctl & PF_ENABLE) == 0)
+		return;
+
+	crtc_state->pch_pfit.enabled = true;
+
+	pos = intel_de_read(dev_priv, PF_WIN_POS(crtc->pipe));
+	size = intel_de_read(dev_priv, PF_WIN_SZ(crtc->pipe));
+
+	ilk_get_pfit_pos_size(crtc_state, pos, size);
+
+	/*
+	 * We currently do not free assignements of panel fitters on
+	 * ivb/hsw (since we don't use the higher upscaling modes which
+	 * differentiates them) so just WARN about this case for now.
+	 */
+	drm_WARN_ON(&dev_priv->drm, IS_GEN(dev_priv, 7) &&
+		    (ctl & PF_PIPE_SEL_MASK_IVB) != PF_PIPE_SEL_IVB(crtc->pipe));
 }
 
 static bool ilk_get_pipe_config(struct intel_crtc *crtc,
@@ -10622,7 +10625,6 @@ static bool ilk_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 = intel_de_read(dev_priv, PIPECONF(crtc->pipe));
@@ -10714,7 +10716,7 @@ static bool ilk_get_pipe_config(struct intel_crtc *crtc,
 	intel_get_pipe_timings(crtc, pipe_config);
 	intel_get_pipe_src_size(crtc, pipe_config);
 
-	ilk_get_pfit_config(crtc, pipe_config);
+	ilk_get_pfit_config(pipe_config);
 
 	ret = true;
 
@@ -10891,7 +10893,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		panel_transcoder_mask |=
 			BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1);
 
-	if (HAS_TRANSCODER_EDP(dev_priv))
+	if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP))
 		panel_transcoder_mask |= BIT(TRANSCODER_EDP);
 
 	/*
@@ -11085,61 +11087,6 @@ static void hsw_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 = intel_de_read(dev_priv,
-				        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 icl_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.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);
-	}
-
-	drm_WARN_ON(&dev_priv->drm,
-		    crtc_state->master_transcoder != INVALID_TRANSCODER &&
-		    crtc_state->sync_mode_slaves_mask);
-}
-
 static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config)
 {
@@ -11243,9 +11190,9 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 		power_domain_mask |= BIT_ULL(power_domain);
 
 		if (INTEL_GEN(dev_priv) >= 9)
-			skl_get_pfit_config(crtc, pipe_config);
+			skl_get_pfit_config(pipe_config);
 		else
-			ilk_get_pfit_config(crtc, pipe_config);
+			ilk_get_pfit_config(pipe_config);
 	}
 
 	if (hsw_crtc_supports_ips(crtc)) {
@@ -11271,10 +11218,6 @@ static bool hsw_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))
-		icl_get_trans_port_sync_config(pipe_config);
-
 out:
 	for_each_power_domain(power_domain, power_domain_mask)
 		intel_display_power_put(dev_priv,
@@ -12377,10 +12320,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 	 * only combine the results from all planes in the current place?
 	 */
 	if (!is_crtc_enabled) {
-		plane_state->uapi.visible = visible = false;
-		crtc_state->active_planes &= ~BIT(plane->id);
-		crtc_state->data_rate[plane->id] = 0;
-		crtc_state->min_cdclk[plane->id] = 0;
+		intel_plane_set_invisible(crtc_state, plane_state);
+		visible = false;
 	}
 
 	if (!was_visible && !visible)
@@ -12510,8 +12451,10 @@ 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->planar_linked_plane != plane);
-		WARN_ON(linked_plane_state->planar_slave == plane_state->planar_slave);
+		drm_WARN_ON(state->base.dev,
+			    linked_plane_state->planar_linked_plane != plane);
+		drm_WARN_ON(state->base.dev,
+			    linked_plane_state->planar_slave == plane_state->planar_slave);
 	}
 
 	return 0;
@@ -12886,19 +12829,20 @@ compute_baseline_pipe_bpp(struct intel_crtc *crtc,
 	return 0;
 }
 
-static void intel_dump_crtc_timings(const struct drm_display_mode *mode)
+static void intel_dump_crtc_timings(struct drm_i915_private *i915,
+				    const struct drm_display_mode *mode)
 {
-	DRM_DEBUG_KMS("crtc timings: %d %d %d %d %d %d %d %d %d, "
-		      "type: 0x%x flags: 0x%x\n",
-		      mode->crtc_clock,
-		      mode->crtc_hdisplay, mode->crtc_hsync_start,
-		      mode->crtc_hsync_end, mode->crtc_htotal,
-		      mode->crtc_vdisplay, mode->crtc_vsync_start,
-		      mode->crtc_vsync_end, mode->crtc_vtotal,
-		      mode->type, mode->flags);
+	drm_dbg_kms(&i915->drm, "crtc timings: %d %d %d %d %d %d %d %d %d, "
+		    "type: 0x%x flags: 0x%x\n",
+		    mode->crtc_clock,
+		    mode->crtc_hdisplay, mode->crtc_hsync_start,
+		    mode->crtc_hsync_end, mode->crtc_htotal,
+		    mode->crtc_vdisplay, mode->crtc_vsync_start,
+		    mode->crtc_vsync_end, mode->crtc_vtotal,
+		    mode->type, mode->flags);
 }
 
-static inline void
+static void
 intel_dump_m_n_config(const struct intel_crtc_state *pipe_config,
 		      const char *id, unsigned int lane_count,
 		      const struct intel_link_m_n *m_n)
@@ -12922,6 +12866,16 @@ intel_dump_infoframe(struct drm_i915_private *dev_priv,
 	hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, frame);
 }
 
+static void
+intel_dump_dp_vsc_sdp(struct drm_i915_private *dev_priv,
+		      const struct drm_dp_vsc_sdp *vsc)
+{
+	if (!drm_debug_enabled(DRM_UT_KMS))
+		return;
+
+	drm_dp_vsc_sdp_log(KERN_DEBUG, dev_priv->drm.dev, vsc);
+}
+
 #define OUTPUT_TYPE(x) [INTEL_OUTPUT_ ## x] = #x
 
 static const char * const output_type_str[] = {
@@ -13042,6 +12996,11 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 		    transcoder_name(pipe_config->cpu_transcoder),
 		    pipe_config->pipe_bpp, pipe_config->dither);
 
+	drm_dbg_kms(&dev_priv->drm,
+		    "port sync: master transcoder: %s, slave transcoder bitmask = 0x%x\n",
+		    transcoder_name(pipe_config->master_transcoder),
+		    pipe_config->sync_mode_slaves_mask);
+
 	if (pipe_config->has_pch_encoder)
 		intel_dump_m_n_config(pipe_config, "fdi",
 				      pipe_config->fdi_lanes,
@@ -13074,12 +13033,21 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 	if (pipe_config->infoframes.enable &
 	    intel_hdmi_infoframe_enable(HDMI_INFOFRAME_TYPE_VENDOR))
 		intel_dump_infoframe(dev_priv, &pipe_config->infoframes.hdmi);
+	if (pipe_config->infoframes.enable &
+	    intel_hdmi_infoframe_enable(HDMI_INFOFRAME_TYPE_DRM))
+		intel_dump_infoframe(dev_priv, &pipe_config->infoframes.drm);
+	if (pipe_config->infoframes.enable &
+	    intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA))
+		intel_dump_infoframe(dev_priv, &pipe_config->infoframes.drm);
+	if (pipe_config->infoframes.enable &
+	    intel_hdmi_infoframe_enable(DP_SDP_VSC))
+		intel_dump_dp_vsc_sdp(dev_priv, &pipe_config->infoframes.vsc);
 
 	drm_dbg_kms(&dev_priv->drm, "requested mode:\n");
 	drm_mode_debug_printmodeline(&pipe_config->hw.mode);
 	drm_dbg_kms(&dev_priv->drm, "adjusted mode:\n");
 	drm_mode_debug_printmodeline(&pipe_config->hw.adjusted_mode);
-	intel_dump_crtc_timings(&pipe_config->hw.adjusted_mode);
+	intel_dump_crtc_timings(dev_priv, &pipe_config->hw.adjusted_mode);
 	drm_dbg_kms(&dev_priv->drm,
 		    "port clock: %d, pipe src size: %dx%d, pixel rate %d\n",
 		    pipe_config->port_clock,
@@ -13104,9 +13072,8 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 			    pipe_config->gmch_pfit.lvds_border_bits);
 	else
 		drm_dbg_kms(&dev_priv->drm,
-			    "pch pfit: pos: 0x%08x, size: 0x%08x, %s, force thru: %s\n",
-			    pipe_config->pch_pfit.pos,
-			    pipe_config->pch_pfit.size,
+			    "pch pfit: " DRM_RECT_FMT ", %s, force thru: %s\n",
+			    DRM_RECT_ARG(&pipe_config->pch_pfit.dst),
 			    enableddisabled(pipe_config->pch_pfit.enabled),
 			    yesno(pipe_config->pch_pfit.force_thru));
 
@@ -13228,7 +13195,8 @@ static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state
 {
 	crtc_state->uapi.enable = crtc_state->hw.enable;
 	crtc_state->uapi.active = crtc_state->hw.active;
-	WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->uapi, &crtc_state->hw.mode) < 0);
+	drm_WARN_ON(crtc_state->uapi.crtc->dev,
+		    drm_atomic_set_mode_for_crtc(&crtc_state->uapi, &crtc_state->hw.mode) < 0);
 
 	crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode;
 
@@ -13521,6 +13489,13 @@ intel_compare_infoframe(const union hdmi_infoframe *a,
 	return memcmp(a, b, sizeof(*a)) == 0;
 }
 
+static bool
+intel_compare_dp_vsc_sdp(const struct drm_dp_vsc_sdp *a,
+			 const struct drm_dp_vsc_sdp *b)
+{
+	return memcmp(a, b, sizeof(*a)) == 0;
+}
+
 static void
 pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 			       bool fastset, const char *name,
@@ -13546,6 +13521,31 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 	}
 }
 
+static void
+pipe_config_dp_vsc_sdp_mismatch(struct drm_i915_private *dev_priv,
+				bool fastset, const char *name,
+				const struct drm_dp_vsc_sdp *a,
+				const struct drm_dp_vsc_sdp *b)
+{
+	if (fastset) {
+		if (!drm_debug_enabled(DRM_UT_KMS))
+			return;
+
+		drm_dbg_kms(&dev_priv->drm,
+			    "fastset mismatch in %s dp sdp\n", name);
+		drm_dbg_kms(&dev_priv->drm, "expected:\n");
+		drm_dp_vsc_sdp_log(KERN_DEBUG, dev_priv->drm.dev, a);
+		drm_dbg_kms(&dev_priv->drm, "found:\n");
+		drm_dp_vsc_sdp_log(KERN_DEBUG, dev_priv->drm.dev, b);
+	} else {
+		drm_err(&dev_priv->drm, "mismatch in %s dp sdp\n", name);
+		drm_err(&dev_priv->drm, "expected:\n");
+		drm_dp_vsc_sdp_log(KERN_ERR, dev_priv->drm.dev, a);
+		drm_err(&dev_priv->drm, "found:\n");
+		drm_dp_vsc_sdp_log(KERN_ERR, dev_priv->drm.dev, b);
+	}
+}
+
 static void __printf(4, 5)
 pipe_config_mismatch(bool fastset, const struct intel_crtc *crtc,
 		     const char *name, const char *format, ...)
@@ -13747,6 +13747,17 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	} \
 } while (0)
 
+#define PIPE_CONF_CHECK_DP_VSC_SDP(name) do { \
+	if (!current_config->has_psr && !pipe_config->has_psr && \
+	    !intel_compare_dp_vsc_sdp(&current_config->infoframes.name, \
+				      &pipe_config->infoframes.name)) { \
+		pipe_config_dp_vsc_sdp_mismatch(dev_priv, fastset, __stringify(name), \
+						&current_config->infoframes.name, \
+						&pipe_config->infoframes.name); \
+		ret = false; \
+	} \
+} while (0)
+
 #define PIPE_CONF_CHECK_COLOR_LUT(name1, name2, bit_precision) do { \
 	if (current_config->name1 != pipe_config->name1) { \
 		pipe_config_mismatch(fastset, crtc, __stringify(name1), \
@@ -13847,8 +13858,10 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 		PIPE_CONF_CHECK_BOOL(pch_pfit.enabled);
 		if (current_config->pch_pfit.enabled) {
-			PIPE_CONF_CHECK_X(pch_pfit.pos);
-			PIPE_CONF_CHECK_X(pch_pfit.size);
+			PIPE_CONF_CHECK_I(pch_pfit.dst.x1);
+			PIPE_CONF_CHECK_I(pch_pfit.dst.y1);
+			PIPE_CONF_CHECK_I(pch_pfit.dst.x2);
+			PIPE_CONF_CHECK_I(pch_pfit.dst.y2);
 		}
 
 		PIPE_CONF_CHECK_I(scaler_state.scaler_id);
@@ -13922,6 +13935,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_INFOFRAME(spd);
 	PIPE_CONF_CHECK_INFOFRAME(hdmi);
 	PIPE_CONF_CHECK_INFOFRAME(drm);
+	PIPE_CONF_CHECK_DP_VSC_SDP(vsc);
 
 	PIPE_CONF_CHECK_X(sync_mode_slaves_mask);
 	PIPE_CONF_CHECK_I(master_transcoder);
@@ -14010,7 +14024,9 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		/* Watermarks */
 		for (level = 0; level <= max_level; level++) {
 			if (skl_wm_level_equals(&hw_plane_wm->wm[level],
-						&sw_plane_wm->wm[level]))
+						&sw_plane_wm->wm[level]) ||
+			    (level == 0 && skl_wm_level_equals(&hw_plane_wm->wm[level],
+							       &sw_plane_wm->sagv_wm0)))
 				continue;
 
 			drm_err(&dev_priv->drm,
@@ -14065,7 +14081,9 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		/* Watermarks */
 		for (level = 0; level <= max_level; level++) {
 			if (skl_wm_level_equals(&hw_plane_wm->wm[level],
-						&sw_plane_wm->wm[level]))
+						&sw_plane_wm->wm[level]) ||
+			    (level == 0 && skl_wm_level_equals(&hw_plane_wm->wm[level],
+							       &sw_plane_wm->sagv_wm0)))
 				continue;
 
 			drm_err(&dev_priv->drm,
@@ -14999,11 +15017,13 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 }
 
 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 intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	bool modeset = needs_modeset(new_crtc_state);
 
 	/*
@@ -15029,22 +15049,35 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 		dev_priv->display.atomic_update_watermarks(state, crtc);
 }
 
-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)
+static void intel_enable_crtc(struct intel_atomic_state *state,
+			      struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	bool modeset = needs_modeset(new_crtc_state);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
-	if (modeset) {
-		intel_crtc_update_active_timings(new_crtc_state);
+	if (!needs_modeset(new_crtc_state))
+		return;
 
-		dev_priv->display.crtc_enable(state, crtc);
+	intel_crtc_update_active_timings(new_crtc_state);
 
-		/* vblanks work again, re-enable pipe CRC. */
-		intel_crtc_enable_pipe_crc(crtc);
-	} else {
+	dev_priv->display.crtc_enable(state, crtc);
+
+	/* vblanks work again, re-enable pipe CRC. */
+	intel_crtc_enable_pipe_crc(crtc);
+}
+
+static void intel_update_crtc(struct intel_atomic_state *state,
+			      struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	const 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);
+
+	if (!modeset) {
 		if (new_crtc_state->preload_luts &&
 		    (new_crtc_state->uapi.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
@@ -15064,7 +15097,7 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	/* Perform vblank evasion around commit operation */
 	intel_pipe_update_start(new_crtc_state);
 
-	commit_pipe_config(state, old_crtc_state, new_crtc_state);
+	commit_pipe_config(state, crtc);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skl_update_planes_on_crtc(state, crtc);
@@ -15084,18 +15117,6 @@ 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->uapi.crtc->dev);
-	enum transcoder slave_transcoder;
-
-	drm_WARN_ON(&dev_priv->drm,
-		    !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,
@@ -15171,129 +15192,19 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 
 static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 {
+	struct intel_crtc_state *new_crtc_state;
 	struct intel_crtc *crtc;
-	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
 	int i;
 
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		if (!new_crtc_state->hw.active)
 			continue;
 
-		intel_update_crtc(crtc, state, old_crtc_state,
-				  new_crtc_state);
+		intel_enable_crtc(state, crtc);
+		intel_update_crtc(state, crtc);
 	}
 }
 
-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(state, crtc);
-	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 *uninitialized_var(conn);
-	struct drm_connector_state *conn_state;
-	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 = intel_attached_dp(to_intel_connector(conn));
-	intel_dp_stop_link_train(intel_dp);
-}
-
-/*
- * TODO: This is only called from port sync and it is identical to what will be
- * executed again in intel_update_crtc() over port sync pipes
- */
-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);
-	bool modeset = needs_modeset(new_crtc_state);
-
-	if (new_crtc_state->update_pipe && !new_crtc_state->enable_fbc)
-		intel_fbc_disable(crtc);
-	else
-		intel_fbc_enable(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);
-	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->hw.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 drm_i915_private *i915 = to_i915(crtc->base.dev);
-	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);
-
-	drm_WARN_ON(&i915->drm, !slave_crtc || !new_slave_crtc_state ||
-		    !old_slave_crtc_state);
-
-	drm_dbg_kms(&i915->drm,
-		    "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 icl_dbuf_slice_pre_update(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
@@ -15365,8 +15276,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 			entries[pipe] = new_crtc_state->wm.skl.ddb;
 			update_pipes &= ~BIT(pipe);
 
-			intel_update_crtc(crtc, state, old_crtc_state,
-					  new_crtc_state);
+			intel_update_crtc(state, crtc);
 
 			/*
 			 * If this is an already active pipe, it's DDB changed,
@@ -15381,67 +15291,62 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 		}
 	}
 
+	update_pipes = modeset_pipes;
+
 	/*
 	 * Enable all pipes that needs a modeset and do not depends on other
 	 * pipes
 	 */
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
-					    new_crtc_state, i) {
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		enum pipe pipe = crtc->pipe;
 
 		if ((modeset_pipes & BIT(pipe)) == 0)
 			continue;
 
 		if (intel_dp_mst_is_slave_trans(new_crtc_state) ||
-		    is_trans_port_sync_slave(new_crtc_state))
+		    is_trans_port_sync_master(new_crtc_state))
 			continue;
 
-		drm_WARN_ON(&dev_priv->drm, skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
-									entries, I915_MAX_PIPES, pipe));
-
-		entries[pipe] = new_crtc_state->wm.skl.ddb;
 		modeset_pipes &= ~BIT(pipe);
 
-		if (is_trans_port_sync_mode(new_crtc_state)) {
-			struct intel_crtc *slave_crtc;
+		intel_enable_crtc(state, crtc);
+	}
 
-			intel_update_trans_port_sync_crtcs(crtc, state,
-							   old_crtc_state,
-							   new_crtc_state);
+	/*
+	 * Then we enable all remaining pipes that depend on other
+	 * pipes: MST slaves and port sync masters.
+	 */
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		enum pipe pipe = crtc->pipe;
 
-			slave_crtc = intel_get_slave_crtc(new_crtc_state);
-			/* TODO: update entries[] of slave */
-			modeset_pipes &= ~BIT(slave_crtc->pipe);
+		if ((modeset_pipes & BIT(pipe)) == 0)
+			continue;
 
-		} else {
-			intel_update_crtc(crtc, state, old_crtc_state,
-					  new_crtc_state);
-		}
+		modeset_pipes &= ~BIT(pipe);
+
+		intel_enable_crtc(state, crtc);
 	}
 
 	/*
-	 * Finally enable all pipes that needs a modeset and depends on
-	 * other pipes, right now it is only MST slaves as both port sync slave
-	 * and master are enabled together
+	 * Finally we do the plane updates/etc. for all pipes that got enabled.
 	 */
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
-					    new_crtc_state, i) {
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		enum pipe pipe = crtc->pipe;
 
-		if ((modeset_pipes & BIT(pipe)) == 0)
+		if ((update_pipes & BIT(pipe)) == 0)
 			continue;
 
 		drm_WARN_ON(&dev_priv->drm, skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
 									entries, I915_MAX_PIPES, pipe));
 
 		entries[pipe] = new_crtc_state->wm.skl.ddb;
-		modeset_pipes &= ~BIT(pipe);
+		update_pipes &= ~BIT(pipe);
 
-		intel_update_crtc(crtc, state, old_crtc_state, new_crtc_state);
+		intel_update_crtc(state, crtc);
 	}
 
 	drm_WARN_ON(&dev_priv->drm, modeset_pipes);
-
+	drm_WARN_ON(&dev_priv->drm, update_pipes);
 }
 
 static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv)
@@ -15540,16 +15445,11 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 
 		intel_set_cdclk_pre_plane_update(state);
 
-		/*
-		 * SKL workaround: bspec recommends we disable the SAGV when we
-		 * have more then one pipe enabled
-		 */
-		if (!intel_can_enable_sagv(state))
-			intel_disable_sagv(dev_priv);
-
 		intel_modeset_verify_disabled(dev_priv, state);
 	}
 
+	intel_sagv_pre_plane_update(state);
+
 	/* Complete the events for pipes that have now been disabled */
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		bool modeset = needs_modeset(new_crtc_state);
@@ -15645,8 +15545,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	if (state->modeset)
 		intel_verify_planes(state);
 
-	if (state->modeset && intel_can_enable_sagv(state))
-		intel_enable_sagv(dev_priv);
+	intel_sagv_post_plane_update(state);
 
 	drm_atomic_helper_commit_hw_done(&state->base);
 
@@ -15982,7 +15881,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 	if (new_plane_state->uapi.fence) { /* explicit fencing */
 		ret = i915_sw_fence_await_dma_fence(&state->commit_ready,
 						    new_plane_state->uapi.fence,
-						    I915_FENCE_TIMEOUT,
+						    i915_fence_timeout(dev_priv),
 						    GFP_KERNEL);
 		if (ret < 0)
 			return ret;
@@ -16009,7 +15908,8 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 
 		ret = i915_sw_fence_await_reservation(&state->commit_ready,
 						      obj->base.resv, NULL,
-						      false, I915_FENCE_TIMEOUT,
+						      false,
+						      i915_fence_timeout(dev_priv),
 						      GFP_KERNEL);
 		if (ret < 0)
 			goto unpin_fb;
@@ -18261,11 +18161,12 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 			best_encoder = connector->base.state->best_encoder;
 			connector->base.state->best_encoder = &encoder->base;
 
+			/* FIXME NULL atomic state passed! */
 			if (encoder->disable)
-				encoder->disable(encoder, crtc_state,
+				encoder->disable(NULL, encoder, crtc_state,
 						 connector->base.state);
 			if (encoder->post_disable)
-				encoder->post_disable(encoder, crtc_state,
+				encoder->post_disable(NULL, encoder, crtc_state,
 						      connector->base.state);
 
 			connector->base.state->best_encoder = best_encoder;
@@ -18802,15 +18703,6 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915)
 
 #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 
-static bool
-has_transcoder(struct drm_i915_private *dev_priv, enum transcoder cpu_transcoder)
-{
-	if (cpu_transcoder == TRANSCODER_EDP)
-		return HAS_TRANSCODER_EDP(dev_priv);
-	else
-		return INTEL_INFO(dev_priv)->pipe_mask & BIT(cpu_transcoder);
-}
-
 struct intel_display_error_state {
 
 	u32 power_well_driver;
@@ -18919,7 +18811,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv)
 	for (i = 0; i < ARRAY_SIZE(error->transcoder); i++) {
 		enum transcoder cpu_transcoder = transcoders[i];
 
-		if (!has_transcoder(dev_priv, cpu_transcoder))
+		if (!HAS_TRANSCODER(dev_priv, cpu_transcoder))
 			continue;
 
 		error->transcoder[i].available = true;
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index adb1225a3480..efb4da205ea2 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -320,9 +320,13 @@ enum phy_fia {
 	for_each_pipe(__dev_priv, __p) \
 		for_each_if((__mask) & BIT(__p))
 
-#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \
+#define for_each_cpu_transcoder(__dev_priv, __t) \
 	for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++)	\
-		for_each_if ((__mask) & (1 << (__t)))
+		for_each_if (INTEL_INFO(__dev_priv)->cpu_transcoder_mask & BIT(__t))
+
+#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \
+	for_each_cpu_transcoder(__dev_priv, __t) \
+		for_each_if ((__mask) & BIT(__t))
 
 #define for_each_universal_plane(__dev_priv, __pipe, __p)		\
 	for ((__p) = 0;							\
@@ -579,13 +583,14 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain intel_port_to_power_domain(enum port port);
 enum intel_display_power_domain
 intel_aux_power_domain(struct intel_digital_port *dig_port);
+enum intel_display_power_domain
+intel_legacy_aux_to_power_domain(enum aux_ch aux_ch);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config);
 void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
 
 u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
-int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state);
 void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state);
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 1e6eb7f2f72d..70525623bcdf 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -9,6 +9,7 @@
 #include "i915_debugfs.h"
 #include "intel_csr.h"
 #include "intel_display_debugfs.h"
+#include "intel_display_power.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
 #include "intel_fbc.h"
@@ -631,15 +632,9 @@ static void intel_dp_info(struct seq_file *m,
 }
 
 static void intel_dp_mst_info(struct seq_file *m,
-			  struct intel_connector *intel_connector)
+			      struct intel_connector *intel_connector)
 {
-	struct intel_encoder *intel_encoder = intel_attached_encoder(intel_connector);
-	struct intel_dp_mst_encoder *intel_mst =
-		enc_to_mst(intel_encoder);
-	struct intel_digital_port *intel_dig_port = intel_mst->primary;
-	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	bool has_audio = drm_dp_mst_port_has_audio(&intel_dp->mst_mgr,
-					intel_connector->port);
+	bool has_audio = intel_connector->port->has_audio;
 
 	seq_printf(m, "\taudio support: %s\n", yesno(has_audio));
 }
@@ -1149,6 +1144,51 @@ static int i915_drrs_status(struct seq_file *m, void *unused)
 	return 0;
 }
 
+#define LPSP_STATUS(COND) (COND ? seq_puts(m, "LPSP: enabled\n") : \
+				seq_puts(m, "LPSP: disabled\n"))
+
+static bool
+intel_lpsp_power_well_enabled(struct drm_i915_private *i915,
+			      enum i915_power_well_id power_well_id)
+{
+	intel_wakeref_t wakeref;
+	bool is_enabled;
+
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	is_enabled = intel_display_power_well_is_enabled(i915,
+							 power_well_id);
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+
+	return is_enabled;
+}
+
+static int i915_lpsp_status(struct seq_file *m, void *unused)
+{
+	struct drm_i915_private *i915 = node_to_i915(m->private);
+
+	switch (INTEL_GEN(i915)) {
+	case 12:
+	case 11:
+		LPSP_STATUS(!intel_lpsp_power_well_enabled(i915, ICL_DISP_PW_3));
+		break;
+	case 10:
+	case 9:
+		LPSP_STATUS(!intel_lpsp_power_well_enabled(i915, SKL_DISP_PW_2));
+		break;
+	default:
+		/*
+		 * Apart from HASWELL/BROADWELL other legacy platform doesn't
+		 * support lpsp.
+		 */
+		if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+			LPSP_STATUS(!intel_lpsp_power_well_enabled(i915, HSW_DISP_PW_GLOBAL));
+		else
+			seq_puts(m, "LPSP: not supported\n");
+	}
+
+	return 0;
+}
+
 static int i915_dp_mst_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -1326,6 +1366,16 @@ static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 					   intel_dp->compliance.test_data.vdisplay);
 				seq_printf(m, "bpc: %u\n",
 					   intel_dp->compliance.test_data.bpc);
+			} else if (intel_dp->compliance.test_type ==
+				   DP_TEST_LINK_PHY_TEST_PATTERN) {
+				seq_printf(m, "pattern: %d\n",
+					   intel_dp->compliance.test_data.phytest.phy_pattern);
+				seq_printf(m, "Number of lanes: %d\n",
+					   intel_dp->compliance.test_data.phytest.num_lanes);
+				seq_printf(m, "Link Rate: %d\n",
+					   intel_dp->compliance.test_data.phytest.link_rate);
+				seq_printf(m, "level: %02x\n",
+					   intel_dp->train_set[0]);
 			}
 		} else
 			seq_puts(m, "0");
@@ -1358,7 +1408,7 @@ static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 
 		if (encoder && connector->status == connector_status_connected) {
 			intel_dp = enc_to_intel_dp(encoder);
-			seq_printf(m, "%02lx", intel_dp->compliance.test_type);
+			seq_printf(m, "%02lx\n", intel_dp->compliance.test_type);
 		} else
 			seq_puts(m, "0");
 	}
@@ -1906,6 +1956,7 @@ static const struct drm_info_list intel_display_debugfs_list[] = {
 	{"i915_dp_mst_info", i915_dp_mst_info, 0},
 	{"i915_ddb_info", i915_ddb_info, 0},
 	{"i915_drrs_status", i915_drrs_status, 0},
+	{"i915_lpsp_status", i915_lpsp_status, 0},
 };
 
 static const struct {
@@ -1927,7 +1978,7 @@ static const struct {
 	{"i915_edp_psr_debug", &i915_edp_psr_debug_fops},
 };
 
-int intel_display_debugfs_register(struct drm_i915_private *i915)
+void intel_display_debugfs_register(struct drm_i915_private *i915)
 {
 	struct drm_minor *minor = i915->drm.primary;
 	int i;
@@ -1940,9 +1991,9 @@ int intel_display_debugfs_register(struct drm_i915_private *i915)
 				    intel_display_debugfs_files[i].fops);
 	}
 
-	return drm_debugfs_create_files(intel_display_debugfs_list,
-					ARRAY_SIZE(intel_display_debugfs_list),
-					minor->debugfs_root, minor);
+	drm_debugfs_create_files(intel_display_debugfs_list,
+				 ARRAY_SIZE(intel_display_debugfs_list),
+				 minor->debugfs_root, minor);
 }
 
 static int i915_panel_show(struct seq_file *m, void *data)
@@ -1987,6 +2038,48 @@ static int i915_hdcp_sink_capability_show(struct seq_file *m, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability);
 
+#define LPSP_CAPABLE(COND) (COND ? seq_puts(m, "LPSP: capable\n") : \
+				seq_puts(m, "LPSP: incapable\n"))
+
+static int i915_lpsp_capability_show(struct seq_file *m, void *data)
+{
+	struct drm_connector *connector = m->private;
+	struct intel_encoder *encoder =
+			intel_attached_encoder(to_intel_connector(connector));
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+
+	if (connector->status != connector_status_connected)
+		return -ENODEV;
+
+	switch (INTEL_GEN(i915)) {
+	case 12:
+		/*
+		 * Actually TGL can drive LPSP on port till DDI_C
+		 * but there is no physical connected DDI_C on TGL sku's,
+		 * even driver is not initilizing DDI_C port for gen12.
+		 */
+		LPSP_CAPABLE(encoder->port <= PORT_B);
+		break;
+	case 11:
+		LPSP_CAPABLE(connector->connector_type == DRM_MODE_CONNECTOR_DSI ||
+			     connector->connector_type == DRM_MODE_CONNECTOR_eDP);
+		break;
+	case 10:
+	case 9:
+		LPSP_CAPABLE(encoder->port == PORT_A &&
+			     (connector->connector_type == DRM_MODE_CONNECTOR_DSI ||
+			     connector->connector_type == DRM_MODE_CONNECTOR_eDP  ||
+			     connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort));
+		break;
+	default:
+		if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+			LPSP_CAPABLE(connector->connector_type == DRM_MODE_CONNECTOR_eDP);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(i915_lpsp_capability);
+
 static int i915_dsc_fec_support_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
@@ -2130,5 +2223,16 @@ int intel_connector_debugfs_add(struct drm_connector *connector)
 		debugfs_create_file("i915_dsc_fec_support", S_IRUGO, root,
 				    connector, &i915_dsc_fec_support_fops);
 
+	/* Legacy panels doesn't lpsp on any platform */
+	if ((INTEL_GEN(dev_priv) >= 9 || IS_HASWELL(dev_priv) ||
+	     IS_BROADWELL(dev_priv)) &&
+	     (connector->connector_type == DRM_MODE_CONNECTOR_DSI ||
+	     connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
+	     connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+	     connector->connector_type == DRM_MODE_CONNECTOR_HDMIA ||
+	     connector->connector_type == DRM_MODE_CONNECTOR_HDMIB))
+		debugfs_create_file("i915_lpsp_capability", 0444, root,
+				    connector, &i915_lpsp_capability_fops);
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.h b/drivers/gpu/drm/i915/display/intel_display_debugfs.h
index a3bea1ce04c2..c922c1745bfe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.h
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.h
@@ -10,10 +10,10 @@ struct drm_connector;
 struct drm_i915_private;
 
 #ifdef CONFIG_DEBUG_FS
-int intel_display_debugfs_register(struct drm_i915_private *i915);
+void intel_display_debugfs_register(struct drm_i915_private *i915);
 int intel_connector_debugfs_add(struct drm_connector *connector);
 #else
-static inline int intel_display_debugfs_register(struct drm_i915_private *i915) { return 0; }
+static inline void intel_display_debugfs_register(struct drm_i915_private *i915) {}
 static inline int intel_connector_debugfs_add(struct drm_connector *connector) { return 0; }
 #endif
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 84ecf8e58523..49998906cc61 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -151,6 +151,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "GT_IRQ";
 	case POWER_DOMAIN_DPLL_DC_OFF:
 		return "DPLL_DC_OFF";
+	case POWER_DOMAIN_TC_COLD_OFF:
+		return "TC_COLD_OFF";
 	default:
 		MISSING_CASE(domain);
 		return "?";
@@ -282,8 +284,51 @@ static void hsw_power_well_pre_disable(struct drm_i915_private *dev_priv,
 		gen8_irq_power_well_pre_disable(dev_priv, irq_pipe_mask);
 }
 
+#define ICL_AUX_PW_TO_CH(pw_idx)	\
+	((pw_idx) - ICL_PW_CTL_IDX_AUX_A + AUX_CH_A)
+
+#define ICL_TBT_AUX_PW_TO_CH(pw_idx)	\
+	((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C)
+
+static enum aux_ch icl_tc_phy_aux_ch(struct drm_i915_private *dev_priv,
+				     struct i915_power_well *power_well)
+{
+	int pw_idx = power_well->desc->hsw.idx;
+
+	return power_well->desc->hsw.is_tc_tbt ? ICL_TBT_AUX_PW_TO_CH(pw_idx) :
+						 ICL_AUX_PW_TO_CH(pw_idx);
+}
+
+static struct intel_digital_port *
+aux_ch_to_digital_port(struct drm_i915_private *dev_priv,
+		       enum aux_ch aux_ch)
+{
+	struct intel_digital_port *dig_port = NULL;
+	struct intel_encoder *encoder;
+
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		/* We'll check the MST primary port */
+		if (encoder->type == INTEL_OUTPUT_DP_MST)
+			continue;
+
+		dig_port = enc_to_dig_port(encoder);
+		if (!dig_port)
+			continue;
+
+		if (dig_port->aux_ch != aux_ch) {
+			dig_port = NULL;
+			continue;
+		}
+
+		break;
+	}
+
+	return dig_port;
+}
+
 static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
-					   struct i915_power_well *power_well)
+					   struct i915_power_well *power_well,
+					   bool timeout_expected)
 {
 	const struct i915_power_well_regs *regs = power_well->desc->hsw.regs;
 	int pw_idx = power_well->desc->hsw.idx;
@@ -294,8 +339,8 @@ static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
 		drm_dbg_kms(&dev_priv->drm, "%s power well enable timeout\n",
 			    power_well->desc->name);
 
-		/* An AUX timeout is expected if the TBT DP tunnel is down. */
-		drm_WARN_ON(&dev_priv->drm, !power_well->desc->hsw.is_tc_tbt);
+		drm_WARN_ON(&dev_priv->drm, !timeout_expected);
+
 	}
 }
 
@@ -358,11 +403,11 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 {
 	const struct i915_power_well_regs *regs = power_well->desc->hsw.regs;
 	int pw_idx = power_well->desc->hsw.idx;
-	bool wait_fuses = power_well->desc->hsw.has_fuses;
-	enum skl_power_gate uninitialized_var(pg);
 	u32 val;
 
-	if (wait_fuses) {
+	if (power_well->desc->hsw.has_fuses) {
+		enum skl_power_gate pg;
+
 		pg = INTEL_GEN(dev_priv) >= 11 ? ICL_PW_CTL_IDX_TO_PG(pw_idx) :
 						 SKL_PW_CTL_IDX_TO_PG(pw_idx);
 		/*
@@ -379,19 +424,27 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 	val = intel_de_read(dev_priv, regs->driver);
 	intel_de_write(dev_priv, regs->driver,
 		       val | HSW_PWR_WELL_CTL_REQ(pw_idx));
-	hsw_wait_for_power_well_enable(dev_priv, power_well);
+
+	hsw_wait_for_power_well_enable(dev_priv, power_well, false);
 
 	/* Display WA #1178: cnl */
 	if (IS_CANNONLAKE(dev_priv) &&
 	    pw_idx >= GLK_PW_CTL_IDX_AUX_B &&
 	    pw_idx <= CNL_PW_CTL_IDX_AUX_F) {
+		u32 val;
+
 		val = intel_de_read(dev_priv, CNL_AUX_ANAOVRD1(pw_idx));
 		val |= CNL_AUX_ANAOVRD1_ENABLE | CNL_AUX_ANAOVRD1_LDO_BYPASS;
 		intel_de_write(dev_priv, CNL_AUX_ANAOVRD1(pw_idx), val);
 	}
 
-	if (wait_fuses)
+	if (power_well->desc->hsw.has_fuses) {
+		enum skl_power_gate pg;
+
+		pg = INTEL_GEN(dev_priv) >= 11 ? ICL_PW_CTL_IDX_TO_PG(pw_idx) :
+						 SKL_PW_CTL_IDX_TO_PG(pw_idx);
 		gen9_wait_for_power_well_fuses(dev_priv, pg);
+	}
 
 	hsw_power_well_post_enable(dev_priv,
 				   power_well->desc->hsw.irq_pipe_mask,
@@ -437,7 +490,7 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 			       val | ICL_LANE_ENABLE_AUX);
 	}
 
-	hsw_wait_for_power_well_enable(dev_priv, power_well);
+	hsw_wait_for_power_well_enable(dev_priv, power_well, false);
 
 	/* Display WA #1178: icl */
 	if (pw_idx >= ICL_PW_CTL_IDX_AUX_A && pw_idx <= ICL_PW_CTL_IDX_AUX_B &&
@@ -470,21 +523,6 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 	hsw_wait_for_power_well_disable(dev_priv, power_well);
 }
 
-#define ICL_AUX_PW_TO_CH(pw_idx)	\
-	((pw_idx) - ICL_PW_CTL_IDX_AUX_A + AUX_CH_A)
-
-#define ICL_TBT_AUX_PW_TO_CH(pw_idx)	\
-	((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C)
-
-static enum aux_ch icl_tc_phy_aux_ch(struct drm_i915_private *dev_priv,
-				     struct i915_power_well *power_well)
-{
-	int pw_idx = power_well->desc->hsw.idx;
-
-	return power_well->desc->hsw.is_tc_tbt ? ICL_TBT_AUX_PW_TO_CH(pw_idx) :
-						 ICL_AUX_PW_TO_CH(pw_idx);
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 
 static u64 async_put_domains_mask(struct i915_power_domains *power_domains);
@@ -501,51 +539,28 @@ static int power_well_async_ref_count(struct drm_i915_private *dev_priv,
 }
 
 static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
-					struct i915_power_well *power_well)
+					struct i915_power_well *power_well,
+					struct intel_digital_port *dig_port)
 {
-	enum aux_ch aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well);
-	struct intel_digital_port *dig_port = NULL;
-	struct intel_encoder *encoder;
-
 	/* Bypass the check if all references are released asynchronously */
 	if (power_well_async_ref_count(dev_priv, power_well) ==
 	    power_well->count)
 		return;
 
-	aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well);
-
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-
-		if (!intel_phy_is_tc(dev_priv, phy))
-			continue;
-
-		/* We'll check the MST primary port */
-		if (encoder->type == INTEL_OUTPUT_DP_MST)
-			continue;
-
-		dig_port = enc_to_dig_port(encoder);
-		if (drm_WARN_ON(&dev_priv->drm, !dig_port))
-			continue;
-
-		if (dig_port->aux_ch != aux_ch) {
-			dig_port = NULL;
-			continue;
-		}
-
-		break;
-	}
-
 	if (drm_WARN_ON(&dev_priv->drm, !dig_port))
 		return;
 
+	if (INTEL_GEN(dev_priv) == 11 && dig_port->tc_legacy_port)
+		return;
+
 	drm_WARN_ON(&dev_priv->drm, !intel_tc_port_ref_held(dig_port));
 }
 
 #else
 
 static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
-					struct i915_power_well *power_well)
+					struct i915_power_well *power_well,
+					struct intel_digital_port *dig_port)
 {
 }
 
@@ -553,24 +568,65 @@ static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
 
 #define TGL_AUX_PW_TO_TC_PORT(pw_idx)	((pw_idx) - TGL_PW_CTL_IDX_AUX_TC1)
 
+static void icl_tc_cold_exit(struct drm_i915_private *i915)
+{
+	int ret, tries = 0;
+
+	while (1) {
+		ret = sandybridge_pcode_write_timeout(i915,
+						      ICL_PCODE_EXIT_TCCOLD,
+						      0, 250, 1);
+		if (ret != -EAGAIN || ++tries == 3)
+			break;
+		msleep(1);
+	}
+
+	/* Spec states that TC cold exit can take up to 1ms to complete */
+	if (!ret)
+		msleep(1);
+
+	/* TODO: turn failure into a error as soon i915 CI updates ICL IFWI */
+	drm_dbg_kms(&i915->drm, "TC cold block %s\n", ret ? "failed" :
+		    "succeeded");
+}
+
 static void
 icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 				 struct i915_power_well *power_well)
 {
 	enum aux_ch aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well);
+	struct intel_digital_port *dig_port = aux_ch_to_digital_port(dev_priv, aux_ch);
+	const struct i915_power_well_regs *regs = power_well->desc->hsw.regs;
+	bool is_tbt = power_well->desc->hsw.is_tc_tbt;
+	bool timeout_expected;
 	u32 val;
 
-	icl_tc_port_assert_ref_held(dev_priv, power_well);
+	icl_tc_port_assert_ref_held(dev_priv, power_well, dig_port);
 
 	val = intel_de_read(dev_priv, DP_AUX_CH_CTL(aux_ch));
 	val &= ~DP_AUX_CH_CTL_TBT_IO;
-	if (power_well->desc->hsw.is_tc_tbt)
+	if (is_tbt)
 		val |= DP_AUX_CH_CTL_TBT_IO;
 	intel_de_write(dev_priv, DP_AUX_CH_CTL(aux_ch), val);
 
-	hsw_power_well_enable(dev_priv, power_well);
+	val = intel_de_read(dev_priv, regs->driver);
+	intel_de_write(dev_priv, regs->driver,
+		       val | HSW_PWR_WELL_CTL_REQ(power_well->desc->hsw.idx));
+
+	/*
+	 * An AUX timeout is expected if the TBT DP tunnel is down,
+	 * or need to enable AUX on a legacy TypeC port as part of the TC-cold
+	 * exit sequence.
+	 */
+	timeout_expected = is_tbt;
+	if (INTEL_GEN(dev_priv) == 11 && dig_port->tc_legacy_port) {
+		icl_tc_cold_exit(dev_priv);
+		timeout_expected = true;
+	}
+
+	hsw_wait_for_power_well_enable(dev_priv, power_well, timeout_expected);
 
-	if (INTEL_GEN(dev_priv) >= 12 && !power_well->desc->hsw.is_tc_tbt) {
+	if (INTEL_GEN(dev_priv) >= 12 && !is_tbt) {
 		enum tc_port tc_port;
 
 		tc_port = TGL_AUX_PW_TO_TC_PORT(power_well->desc->hsw.idx);
@@ -588,11 +644,48 @@ static void
 icl_tc_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 				  struct i915_power_well *power_well)
 {
-	icl_tc_port_assert_ref_held(dev_priv, power_well);
+	enum aux_ch aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well);
+	struct intel_digital_port *dig_port = aux_ch_to_digital_port(dev_priv, aux_ch);
+
+	icl_tc_port_assert_ref_held(dev_priv, power_well, dig_port);
 
 	hsw_power_well_disable(dev_priv, power_well);
 }
 
+static void
+icl_aux_power_well_enable(struct drm_i915_private *dev_priv,
+			  struct i915_power_well *power_well)
+{
+	int pw_idx = power_well->desc->hsw.idx;
+	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);  /* non-TBT only */
+	bool is_tbt = power_well->desc->hsw.is_tc_tbt;
+
+	if (is_tbt || intel_phy_is_tc(dev_priv, phy))
+		return icl_tc_phy_aux_power_well_enable(dev_priv, power_well);
+	else if (IS_ICELAKE(dev_priv))
+		return icl_combo_phy_aux_power_well_enable(dev_priv,
+							   power_well);
+	else
+		return hsw_power_well_enable(dev_priv, power_well);
+}
+
+static void
+icl_aux_power_well_disable(struct drm_i915_private *dev_priv,
+			   struct i915_power_well *power_well)
+{
+	int pw_idx = power_well->desc->hsw.idx;
+	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);  /* non-TBT only */
+	bool is_tbt = power_well->desc->hsw.is_tc_tbt;
+
+	if (is_tbt || intel_phy_is_tc(dev_priv, phy))
+		return icl_tc_phy_aux_power_well_disable(dev_priv, power_well);
+	else if (IS_ICELAKE(dev_priv))
+		return icl_combo_phy_aux_power_well_disable(dev_priv,
+							    power_well);
+	else
+		return hsw_power_well_disable(dev_priv, power_well);
+}
+
 /*
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
@@ -943,7 +1036,7 @@ static void assert_can_enable_dc5(struct drm_i915_private *dev_priv)
 
 	/* Power wells at this level and above must be disabled for DC5 entry */
 	if (INTEL_GEN(dev_priv) >= 12)
-		high_pg = TGL_DISP_PW_3;
+		high_pg = ICL_DISP_PW_3;
 	else
 		high_pg = SKL_DISP_PW_2;
 
@@ -1873,20 +1966,27 @@ __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));
+	drm_dbg(&i915->drm, "%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(domain),
-				 power_domains->domain_use_count[domain]);
+		drm_dbg(&i915->drm, "%s use_count %d\n",
+			intel_display_power_domain_str(domain),
+			power_domains->domain_use_count[domain]);
 }
 
 static void
 print_async_put_domains_state(struct i915_power_domains *power_domains)
 {
-	DRM_DEBUG_DRIVER("async_put_wakeref %u\n",
-			 power_domains->async_put_wakeref);
+	struct drm_i915_private *i915 = container_of(power_domains,
+						     struct drm_i915_private,
+						     power_domains);
+
+	drm_dbg(&i915->drm, "async_put_wakeref %u\n",
+		power_domains->async_put_wakeref);
 
 	print_power_domains(power_domains, "async_put_domains[0]",
 			    power_domains->async_put_domains[0]);
@@ -2798,6 +2898,21 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 #define TGL_AUX_I_TBT6_IO_POWER_DOMAINS (	\
 	BIT_ULL(POWER_DOMAIN_AUX_I_TBT))
 
+#define TGL_TC_COLD_OFF_POWER_DOMAINS (		\
+	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_TC_COLD_OFF))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_power_well_sync_hw_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -3496,17 +3611,10 @@ static const struct i915_power_well_desc cnl_power_wells[] = {
 	},
 };
 
-static const struct i915_power_well_ops icl_combo_phy_aux_power_well_ops = {
-	.sync_hw = hsw_power_well_sync_hw,
-	.enable = icl_combo_phy_aux_power_well_enable,
-	.disable = icl_combo_phy_aux_power_well_disable,
-	.is_enabled = hsw_power_well_enabled,
-};
-
-static const struct i915_power_well_ops icl_tc_phy_aux_power_well_ops = {
+static const struct i915_power_well_ops icl_aux_power_well_ops = {
 	.sync_hw = hsw_power_well_sync_hw,
-	.enable = icl_tc_phy_aux_power_well_enable,
-	.disable = icl_tc_phy_aux_power_well_disable,
+	.enable = icl_aux_power_well_enable,
+	.disable = icl_aux_power_well_disable,
 	.is_enabled = hsw_power_well_enabled,
 };
 
@@ -3564,7 +3672,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		.name = "power well 3",
 		.domains = ICL_PW_3_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = ICL_DISP_PW_3,
 		{
 			.hsw.regs = &hsw_power_well_regs,
 			.hsw.idx = ICL_PW_CTL_IDX_PW_3,
@@ -3636,7 +3744,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX A",
 		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
-		.ops = &icl_combo_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3646,7 +3754,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX B",
 		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
-		.ops = &icl_combo_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3656,7 +3764,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX C TC1",
 		.domains = ICL_AUX_C_TC1_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3667,7 +3775,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX D TC2",
 		.domains = ICL_AUX_D_TC2_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3678,7 +3786,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX E TC3",
 		.domains = ICL_AUX_E_TC3_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3689,7 +3797,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX F TC4",
 		.domains = ICL_AUX_F_TC4_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3700,7 +3808,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX C TBT1",
 		.domains = ICL_AUX_C_TBT1_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3711,7 +3819,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX D TBT2",
 		.domains = ICL_AUX_D_TBT2_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3722,7 +3830,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX E TBT3",
 		.domains = ICL_AUX_E_TBT3_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3733,7 +3841,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	{
 		.name = "AUX F TBT4",
 		.domains = ICL_AUX_F_TBT4_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -3755,149 +3863,89 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 	},
 };
 
-static const struct i915_power_well_desc ehl_power_wells[] = {
-	{
-		.name = "always-on",
-		.always_on = true,
-		.domains = POWER_DOMAIN_MASK,
-		.ops = &i9xx_always_on_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-	},
-	{
-		.name = "power well 1",
-		/* Handled by the DMC firmware */
-		.always_on = true,
-		.domains = 0,
-		.ops = &hsw_power_well_ops,
-		.id = SKL_DISP_PW_1,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_PW_1,
-			.hsw.has_fuses = true,
-		},
-	},
-	{
-		.name = "DC off",
-		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
-		.ops = &gen9_dc_off_power_well_ops,
-		.id = SKL_DISP_DC_OFF,
-	},
-	{
-		.name = "power well 2",
-		.domains = ICL_PW_2_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = SKL_DISP_PW_2,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_PW_2,
-			.hsw.has_fuses = true,
-		},
-	},
-	{
-		.name = "power well 3",
-		.domains = ICL_PW_3_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_PW_3,
-			.hsw.irq_pipe_mask = BIT(PIPE_B),
-			.hsw.has_vga = true,
-			.hsw.has_fuses = true,
-		},
-	},
-	{
-		.name = "DDI A IO",
-		.domains = ICL_DDI_IO_A_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_ddi_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_DDI_A,
-		},
-	},
-	{
-		.name = "DDI B IO",
-		.domains = ICL_DDI_IO_B_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_ddi_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_DDI_B,
-		},
-	},
-	{
-		.name = "DDI C IO",
-		.domains = ICL_DDI_IO_C_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_ddi_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_DDI_C,
-		},
-	},
-	{
-		.name = "DDI D IO",
-		.domains = ICL_DDI_IO_D_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_ddi_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_DDI_D,
-		},
-	},
-	{
-		.name = "AUX A",
-		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_aux_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_AUX_A,
-		},
-	},
-	{
-		.name = "AUX B",
-		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_aux_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_AUX_B,
-		},
-	},
-	{
-		.name = "AUX C",
-		.domains = ICL_AUX_C_TC1_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_aux_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_AUX_C,
-		},
-	},
-	{
-		.name = "AUX D",
-		.domains = ICL_AUX_D_TC2_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &icl_aux_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_AUX_D,
-		},
-	},
-	{
-		.name = "power well 4",
-		.domains = ICL_PW_4_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-		{
-			.hsw.regs = &hsw_power_well_regs,
-			.hsw.idx = ICL_PW_CTL_IDX_PW_4,
-			.hsw.has_fuses = true,
-			.hsw.irq_pipe_mask = BIT(PIPE_C),
-		},
-	},
+static void
+tgl_tc_cold_request(struct drm_i915_private *i915, bool block)
+{
+	u8 tries = 0;
+	int ret;
+
+	while (1) {
+		u32 low_val = 0, high_val;
+
+		if (block)
+			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ;
+		else
+			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ;
+
+		/*
+		 * Spec states that we should timeout the request after 200us
+		 * but the function below will timeout after 500us
+		 */
+		ret = sandybridge_pcode_read(i915, TGL_PCODE_TCCOLD, &low_val,
+					     &high_val);
+		if (ret == 0) {
+			if (block &&
+			    (low_val & TGL_PCODE_EXIT_TCCOLD_DATA_L_EXIT_FAILED))
+				ret = -EIO;
+			else
+				break;
+		}
+
+		if (++tries == 3)
+			break;
+
+		if (ret == -EAGAIN)
+			msleep(1);
+	}
+
+	if (ret)
+		drm_err(&i915->drm, "TC cold %sblock failed\n",
+			block ? "" : "un");
+	else
+		drm_dbg_kms(&i915->drm, "TC cold %sblock succeeded\n",
+			    block ? "" : "un");
+}
+
+static void
+tgl_tc_cold_off_power_well_enable(struct drm_i915_private *i915,
+				  struct i915_power_well *power_well)
+{
+	tgl_tc_cold_request(i915, true);
+}
+
+static void
+tgl_tc_cold_off_power_well_disable(struct drm_i915_private *i915,
+				   struct i915_power_well *power_well)
+{
+	tgl_tc_cold_request(i915, false);
+}
+
+static void
+tgl_tc_cold_off_power_well_sync_hw(struct drm_i915_private *i915,
+				   struct i915_power_well *power_well)
+{
+	if (power_well->count > 0)
+		tgl_tc_cold_off_power_well_enable(i915, power_well);
+	else
+		tgl_tc_cold_off_power_well_disable(i915, power_well);
+}
+
+static bool
+tgl_tc_cold_off_power_well_is_enabled(struct drm_i915_private *dev_priv,
+				      struct i915_power_well *power_well)
+{
+	/*
+	 * Not the correctly implementation but there is no way to just read it
+	 * from PCODE, so returning count to avoid state mismatch errors
+	 */
+	return power_well->count;
+}
+
+static const struct i915_power_well_ops tgl_tc_cold_off_ops = {
+	.sync_hw = tgl_tc_cold_off_power_well_sync_hw,
+	.enable = tgl_tc_cold_off_power_well_enable,
+	.disable = tgl_tc_cold_off_power_well_disable,
+	.is_enabled = tgl_tc_cold_off_power_well_is_enabled,
 };
 
 static const struct i915_power_well_desc tgl_power_wells[] = {
@@ -3942,7 +3990,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		.name = "power well 3",
 		.domains = TGL_PW_3_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
-		.id = TGL_DISP_PW_3,
+		.id = ICL_DISP_PW_3,
 		{
 			.hsw.regs = &hsw_power_well_regs,
 			.hsw.idx = ICL_PW_CTL_IDX_PW_3,
@@ -4044,7 +4092,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX A",
 		.domains = TGL_AUX_A_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4054,7 +4102,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX B",
 		.domains = TGL_AUX_B_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4064,7 +4112,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX C",
 		.domains = TGL_AUX_C_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4074,7 +4122,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX D TC1",
 		.domains = TGL_AUX_D_TC1_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4085,7 +4133,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX E TC2",
 		.domains = TGL_AUX_E_TC2_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4096,7 +4144,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX F TC3",
 		.domains = TGL_AUX_F_TC3_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4107,7 +4155,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX G TC4",
 		.domains = TGL_AUX_G_TC4_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4118,7 +4166,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX H TC5",
 		.domains = TGL_AUX_H_TC5_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4129,7 +4177,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX I TC6",
 		.domains = TGL_AUX_I_TC6_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4140,7 +4188,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX D TBT1",
 		.domains = TGL_AUX_D_TBT1_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4151,7 +4199,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX E TBT2",
 		.domains = TGL_AUX_E_TBT2_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4162,7 +4210,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX F TBT3",
 		.domains = TGL_AUX_F_TBT3_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4173,7 +4221,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX G TBT4",
 		.domains = TGL_AUX_G_TBT4_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4184,7 +4232,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX H TBT5",
 		.domains = TGL_AUX_H_TBT5_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4195,7 +4243,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX I TBT6",
 		.domains = TGL_AUX_I_TBT6_IO_POWER_DOMAINS,
-		.ops = &icl_tc_phy_aux_power_well_ops,
+		.ops = &icl_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4227,6 +4275,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 			.hsw.irq_pipe_mask = BIT(PIPE_D),
 		},
 	},
+	{
+		.name = "TC cold off",
+		.domains = TGL_TC_COLD_OFF_POWER_DOMAINS,
+		.ops = &tgl_tc_cold_off_ops,
+		.id = DISP_PW_ID_NONE,
+	},
 };
 
 static int
@@ -4376,8 +4430,6 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_GEN(dev_priv, 12)) {
 		err = set_power_wells(power_domains, tgl_power_wells);
-	} else if (IS_ELKHARTLAKE(dev_priv)) {
-		err = set_power_wells(power_domains, ehl_power_wells);
 	} else if (IS_GEN(dev_priv, 11)) {
 		err = set_power_wells(power_domains, icl_power_wells);
 	} else if (IS_CANNONLAKE(dev_priv)) {
@@ -4439,9 +4491,8 @@ static void intel_power_domains_sync_hw(struct drm_i915_private *dev_priv)
 	mutex_unlock(&power_domains->lock);
 }
 
-static inline
-bool intel_dbuf_slice_set(struct drm_i915_private *dev_priv,
-			  i915_reg_t reg, bool enable)
+static bool intel_dbuf_slice_set(struct drm_i915_private *dev_priv,
+				 i915_reg_t reg, bool enable)
 {
 	u32 val, status;
 
@@ -4480,7 +4531,8 @@ void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 	drm_WARN(&dev_priv->drm, hweight8(req_slices) > max_slices,
 		 "Invalid number of dbuf slices requested\n");
 
-	DRM_DEBUG_KMS("Updating dbuf slices to 0x%x\n", req_slices);
+	drm_dbg_kms(&dev_priv->drm, "Updating dbuf slices to 0x%x\n",
+		    req_slices);
 
 	/*
 	 * Might be running this in parallel to gen9_dc_off_power_well_enable
@@ -5016,7 +5068,7 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
 	const struct buddy_page_mask *table;
 	int i;
 
-	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0))
+	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B0))
 		/* Wa_1409767108: tgl */
 		table = wa_1409767108_buddy_page_masks;
 	else
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index da64a5edae7a..6c917699293b 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -76,6 +76,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
 	POWER_DOMAIN_DPLL_DC_OFF,
+	POWER_DOMAIN_TC_COLD_OFF,
 	POWER_DOMAIN_INIT,
 
 	POWER_DOMAIN_NUM,
@@ -100,7 +101,7 @@ enum i915_power_well_id {
 	SKL_DISP_PW_MISC_IO,
 	SKL_DISP_PW_1,
 	SKL_DISP_PW_2,
-	TGL_DISP_PW_3,
+	ICL_DISP_PW_3,
 	SKL_DISP_DC_OFF,
 };
 
@@ -266,6 +267,8 @@ 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);
+bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
+					 enum i915_power_well_id power_well_id);
 bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				      enum intel_display_power_domain domain);
 intel_wakeref_t intel_display_power_get(struct drm_i915_private *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 5e00e611f077..2bf3d4cb4ea9 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -132,8 +132,7 @@ struct intel_encoder {
 	u16 cloneable;
 	u8 pipe_mask;
 	enum intel_hotplug_state (*hotplug)(struct intel_encoder *encoder,
-					    struct intel_connector *connector,
-					    bool irq_received);
+					    struct intel_connector *connector);
 	enum intel_output_type (*compute_output_type)(struct intel_encoder *,
 						      struct intel_crtc_state *,
 						      struct drm_connector_state *);
@@ -146,28 +145,35 @@ struct intel_encoder {
 	void (*update_prepare)(struct intel_atomic_state *,
 			       struct intel_encoder *,
 			       struct intel_crtc *);
-	void (*pre_pll_enable)(struct intel_encoder *,
+	void (*pre_pll_enable)(struct intel_atomic_state *,
+			       struct intel_encoder *,
 			       const struct intel_crtc_state *,
 			       const struct drm_connector_state *);
-	void (*pre_enable)(struct intel_encoder *,
+	void (*pre_enable)(struct intel_atomic_state *,
+			   struct intel_encoder *,
 			   const struct intel_crtc_state *,
 			   const struct drm_connector_state *);
-	void (*enable)(struct intel_encoder *,
+	void (*enable)(struct intel_atomic_state *,
+		       struct intel_encoder *,
 		       const struct intel_crtc_state *,
 		       const struct drm_connector_state *);
 	void (*update_complete)(struct intel_atomic_state *,
 				struct intel_encoder *,
 				struct intel_crtc *);
-	void (*disable)(struct intel_encoder *,
+	void (*disable)(struct intel_atomic_state *,
+			struct intel_encoder *,
 			const struct intel_crtc_state *,
 			const struct drm_connector_state *);
-	void (*post_disable)(struct intel_encoder *,
+	void (*post_disable)(struct intel_atomic_state *,
+			     struct intel_encoder *,
 			     const struct intel_crtc_state *,
 			     const struct drm_connector_state *);
-	void (*post_pll_disable)(struct intel_encoder *,
+	void (*post_pll_disable)(struct intel_atomic_state *,
+				 struct intel_encoder *,
 				 const struct intel_crtc_state *,
 				 const struct drm_connector_state *);
-	void (*update_pipe)(struct intel_encoder *,
+	void (*update_pipe)(struct intel_atomic_state *,
+			    struct intel_encoder *,
 			    const struct intel_crtc_state *,
 			    const struct drm_connector_state *);
 	/* Read out the current hw state of this connector, returning true if
@@ -425,11 +431,14 @@ struct intel_connector {
 	struct edid *edid;
 	struct edid *detect_edid;
 
+	/* Number of times hotplug detection was tried after an HPD interrupt */
+	int hotplug_retries;
+
 	/* since POLL and HPD connectors may use the same HPD line keep the native
 	   state of connector->polled in case hotplug storm detection changes it */
 	u8 polled;
 
-	void *port; /* store this opaque as its illegal to dereference it */
+	struct drm_dp_mst_port *port;
 
 	struct intel_dp *mst_port;
 
@@ -640,6 +649,16 @@ struct intel_crtc_scaler_state {
 #define I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP (1<<1)
 /* Flag to use the scanline counter instead of the pixel counter */
 #define I915_MODE_FLAG_USE_SCANLINE_COUNTER (1<<2)
+/*
+ * TE0 or TE1 flag is set if the crtc has a DSI encoder which
+ * is operating in command mode.
+ * Flag to use TE from DSI0 instead of VBI in command mode
+ */
+#define I915_MODE_FLAG_DSI_USE_TE0 (1<<3)
+/* Flag to use TE from DSI1 instead of VBI in command mode */
+#define I915_MODE_FLAG_DSI_USE_TE1 (1<<4)
+/* Flag to indicate mipi dsi periodic command mode where we do not get TE */
+#define I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE (1<<5)
 
 struct intel_wm_level {
 	bool enable;
@@ -669,11 +688,13 @@ struct skl_plane_wm {
 	struct skl_wm_level wm[8];
 	struct skl_wm_level uv_wm[8];
 	struct skl_wm_level trans_wm;
+	struct skl_wm_level sagv_wm0;
 	bool is_planar;
 };
 
 struct skl_pipe_wm {
 	struct skl_plane_wm planes[I915_MAX_PLANES];
+	bool use_sagv_wm;
 };
 
 enum vlv_wm_level {
@@ -955,8 +976,7 @@ struct intel_crtc_state {
 
 	/* Panel fitter placement and size for Ironlake+ */
 	struct {
-		u32 pos;
-		u32 size;
+		struct drm_rect dst;
 		bool enabled;
 		bool force_thru;
 	} pch_pfit;
@@ -1015,6 +1035,7 @@ struct intel_crtc_state {
 		union hdmi_infoframe spd;
 		union hdmi_infoframe hdmi;
 		union hdmi_infoframe drm;
+		struct drm_dp_vsc_sdp vsc;
 	} infoframes;
 
 	/* HDMI scrambling status */
@@ -1238,6 +1259,7 @@ struct intel_dp_compliance_data {
 	u8 video_pattern;
 	u16 hdisplay, vdisplay;
 	u8 bpc;
+	struct drm_dp_phy_test_params phytest;
 };
 
 struct intel_dp_compliance {
@@ -1347,6 +1369,9 @@ struct intel_dp {
 
 	/* This is called before a link training is starterd */
 	void (*prepare_link_retrain)(struct intel_dp *intel_dp);
+	void (*set_link_train)(struct intel_dp *intel_dp, u8 dp_train_pat);
+	void (*set_idle_link_train)(struct intel_dp *intel_dp);
+	void (*set_signal_levels)(struct intel_dp *intel_dp);
 
 	/* Displayport compliance testing */
 	struct intel_dp_compliance compliance;
@@ -1401,6 +1426,7 @@ struct intel_digital_port {
 			       const struct drm_connector_state *conn_state);
 	u32 (*infoframes_enabled)(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config);
+	bool (*connected)(struct intel_encoder *encoder);
 };
 
 struct intel_dp_mst_encoder {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index a2fafd4499f2..40d42dcff0b7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -48,7 +48,6 @@
 #include "intel_audio.h"
 #include "intel_connector.h"
 #include "intel_ddi.h"
-#include "intel_display_debugfs.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
 #include "intel_dp_link_training.h"
@@ -164,6 +163,17 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp)
 	};
 	int i, max_rate;
 
+	if (drm_dp_has_quirk(&intel_dp->desc, 0,
+			     DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS)) {
+		/* Needed, e.g., for Apple MBP 2017, 15 inch eDP Retina panel */
+		static const int quirk_rates[] = { 162000, 270000, 324000 };
+
+		memcpy(intel_dp->sink_rates, quirk_rates, sizeof(quirk_rates));
+		intel_dp->num_sink_rates = ARRAY_SIZE(quirk_rates);
+
+		return;
+	}
+
 	max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
 
 	for (i = 0; i < ARRAY_SIZE(dp_rates); i++) {
@@ -452,6 +462,7 @@ static bool intel_dp_can_link_train_fallback_for_edp(struct intel_dp *intel_dp,
 int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 					    int link_rate, u8 lane_count)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	int index;
 
 	index = intel_dp_rate_index(intel_dp->common_rates,
@@ -462,7 +473,8 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 		    !intel_dp_can_link_train_fallback_for_edp(intel_dp,
 							      intel_dp->common_rates[index - 1],
 							      lane_count)) {
-			DRM_DEBUG_KMS("Retrying Link training for eDP with same parameters\n");
+			drm_dbg_kms(&i915->drm,
+				    "Retrying Link training for eDP with same parameters\n");
 			return 0;
 		}
 		intel_dp->max_link_rate = intel_dp->common_rates[index - 1];
@@ -472,13 +484,14 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 		    !intel_dp_can_link_train_fallback_for_edp(intel_dp,
 							      intel_dp_max_common_rate(intel_dp),
 							      lane_count >> 1)) {
-			DRM_DEBUG_KMS("Retrying Link training for eDP with same parameters\n");
+			drm_dbg_kms(&i915->drm,
+				    "Retrying Link training for eDP with same parameters\n");
 			return 0;
 		}
 		intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp);
 		intel_dp->max_link_lane_count = lane_count >> 1;
 	} else {
-		DRM_ERROR("Link Training Unsuccessful\n");
+		drm_err(&i915->drm, "Link Training Unsuccessful\n");
 		return -1;
 	}
 
@@ -553,6 +566,7 @@ static u16 intel_dp_dsc_get_output_bpp(struct drm_i915_private *i915,
 static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
 				       int mode_clock, int mode_hdisplay)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 min_slice_count, i;
 	int max_slice_width;
 
@@ -565,8 +579,9 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
 
 	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);
+		drm_dbg_kms(&i915->drm,
+			    "Unsupported slice width %d by DP DSC Sink device\n",
+			    max_slice_width);
 		return 0;
 	}
 	/* Also take into account max slice width */
@@ -584,7 +599,8 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
 			return valid_dsc_slicecount[i];
 	}
 
-	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+	drm_dbg_kms(&i915->drm, "Unsupported Slice Count %d\n",
+		    min_slice_count);
 	return 0;
 }
 
@@ -1343,8 +1359,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	bool is_tc_port = intel_phy_is_tc(i915, phy);
 	i915_reg_t ch_ctl, ch_data[5];
 	u32 aux_clock_divider;
-	enum intel_display_power_domain aux_domain =
-		intel_aux_power_domain(intel_dig_port);
+	enum intel_display_power_domain aux_domain;
 	intel_wakeref_t aux_wakeref;
 	intel_wakeref_t pps_wakeref;
 	int i, ret, recv_bytes;
@@ -1359,6 +1374,8 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	if (is_tc_port)
 		intel_tc_port_lock(intel_dig_port);
 
+	aux_domain = intel_aux_power_domain(intel_dig_port);
+
 	aux_wakeref = intel_display_power_get(i915, aux_domain);
 	pps_wakeref = pps_lock(intel_dp);
 
@@ -1832,6 +1849,7 @@ static void snprintf_int_array(char *str, size_t len,
 
 static void intel_dp_print_rates(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	char str[128]; /* FIXME: too big for stack? */
 
 	if (!drm_debug_enabled(DRM_UT_KMS))
@@ -1839,15 +1857,15 @@ static void intel_dp_print_rates(struct intel_dp *intel_dp)
 
 	snprintf_int_array(str, sizeof(str),
 			   intel_dp->source_rates, intel_dp->num_source_rates);
-	DRM_DEBUG_KMS("source rates: %s\n", str);
+	drm_dbg_kms(&i915->drm, "source rates: %s\n", str);
 
 	snprintf_int_array(str, sizeof(str),
 			   intel_dp->sink_rates, intel_dp->num_sink_rates);
-	DRM_DEBUG_KMS("sink rates: %s\n", str);
+	drm_dbg_kms(&i915->drm, "sink rates: %s\n", str);
 
 	snprintf_int_array(str, sizeof(str),
 			   intel_dp->common_rates, intel_dp->num_common_rates);
-	DRM_DEBUG_KMS("common rates: %s\n", str);
+	drm_dbg_kms(&i915->drm, "common rates: %s\n", str);
 }
 
 int
@@ -1954,6 +1972,8 @@ intel_dp_adjust_compliance_config(struct intel_dp *intel_dp,
 				  struct intel_crtc_state *pipe_config,
 				  struct link_config_limits *limits)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
 	/* For DP Compliance we override the computed bpp for the pipe */
 	if (intel_dp->compliance.test_data.bpc != 0) {
 		int bpp = 3 * intel_dp->compliance.test_data.bpc;
@@ -1961,7 +1981,7 @@ intel_dp_adjust_compliance_config(struct intel_dp *intel_dp,
 		limits->min_bpp = limits->max_bpp = bpp;
 		pipe_config->dither_force_disable = bpp == 6 * 3;
 
-		DRM_DEBUG_KMS("Setting pipe_bpp to %d\n", bpp);
+		drm_dbg_kms(&i915->drm, "Setting pipe_bpp to %d\n", bpp);
 	}
 
 	/* Use values requested by Compliance Test Request */
@@ -2055,6 +2075,7 @@ static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
 static int intel_dp_dsc_compute_params(struct intel_encoder *encoder,
 				       struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	u8 line_buf_depth;
@@ -2089,7 +2110,8 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder,
 
 	line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd);
 	if (!line_buf_depth) {
-		DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n");
+		drm_dbg_kms(&i915->drm,
+			    "DSC Sink Line Buffer Depth invalid\n");
 		return -EINVAL;
 	}
 
@@ -2114,7 +2136,8 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode =
+		&pipe_config->hw.adjusted_mode;
 	u8 dsc_max_bpc;
 	int pipe_bpp;
 	int ret;
@@ -2229,7 +2252,9 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	const struct drm_display_mode *adjusted_mode =
+		&pipe_config->hw.adjusted_mode;
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct link_config_limits limits;
 	int common_len;
@@ -2264,11 +2289,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 
 	intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits);
 
-	DRM_DEBUG_KMS("DP link computation with max lane count %i "
-		      "max rate %d max bpp %d pixel clock %iKHz\n",
-		      limits.max_lane_count,
-		      intel_dp->common_rates[limits.max_clock],
-		      limits.max_bpp, adjusted_mode->crtc_clock);
+	drm_dbg_kms(&i915->drm, "DP link computation with max lane count %i "
+		    "max rate %d max bpp %d pixel clock %iKHz\n",
+		    limits.max_lane_count,
+		    intel_dp->common_rates[limits.max_clock],
+		    limits.max_bpp, adjusted_mode->crtc_clock);
 
 	/*
 	 * Optimize for slow and wide. This is the place to add alternative
@@ -2277,7 +2302,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits);
 
 	/* enable compression if the mode doesn't fit available BW */
-	DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en);
+	drm_dbg_kms(&i915->drm, "Force DSC en = %d\n", intel_dp->force_dsc_en);
 	if (ret || intel_dp->force_dsc_en) {
 		ret = intel_dp_dsc_compute_config(intel_dp, pipe_config,
 						  conn_state, &limits);
@@ -2286,40 +2311,42 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	}
 
 	if (pipe_config->dsc.compression_enable) {
-		DRM_DEBUG_KMS("DP lane count %d clock %d Input bpp %d Compressed bpp %d\n",
-			      pipe_config->lane_count, pipe_config->port_clock,
-			      pipe_config->pipe_bpp,
-			      pipe_config->dsc.compressed_bpp);
-
-		DRM_DEBUG_KMS("DP link rate required %i available %i\n",
-			      intel_dp_link_required(adjusted_mode->crtc_clock,
-						     pipe_config->dsc.compressed_bpp),
-			      intel_dp_max_data_rate(pipe_config->port_clock,
-						     pipe_config->lane_count));
+		drm_dbg_kms(&i915->drm,
+			    "DP lane count %d clock %d Input bpp %d Compressed bpp %d\n",
+			    pipe_config->lane_count, pipe_config->port_clock,
+			    pipe_config->pipe_bpp,
+			    pipe_config->dsc.compressed_bpp);
+
+		drm_dbg_kms(&i915->drm,
+			    "DP link rate required %i available %i\n",
+			    intel_dp_link_required(adjusted_mode->crtc_clock,
+						   pipe_config->dsc.compressed_bpp),
+			    intel_dp_max_data_rate(pipe_config->port_clock,
+						   pipe_config->lane_count));
 	} else {
-		DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n",
-			      pipe_config->lane_count, pipe_config->port_clock,
-			      pipe_config->pipe_bpp);
+		drm_dbg_kms(&i915->drm, "DP lane count %d clock %d bpp %d\n",
+			    pipe_config->lane_count, pipe_config->port_clock,
+			    pipe_config->pipe_bpp);
 
-		DRM_DEBUG_KMS("DP link rate required %i available %i\n",
-			      intel_dp_link_required(adjusted_mode->crtc_clock,
-						     pipe_config->pipe_bpp),
-			      intel_dp_max_data_rate(pipe_config->port_clock,
-						     pipe_config->lane_count));
+		drm_dbg_kms(&i915->drm,
+			    "DP link rate required %i available %i\n",
+			    intel_dp_link_required(adjusted_mode->crtc_clock,
+						   pipe_config->pipe_bpp),
+			    intel_dp_max_data_rate(pipe_config->port_clock,
+						   pipe_config->lane_count));
 	}
 	return 0;
 }
 
 static int
 intel_dp_ycbcr420_config(struct intel_dp *intel_dp,
-			 struct drm_connector *connector,
-			 struct intel_crtc_state *crtc_state)
+			 struct intel_crtc_state *crtc_state,
+			 const struct drm_connector_state *conn_state)
 {
+	struct drm_connector *connector = conn_state->connector;
 	const struct drm_display_info *info = &connector->display_info;
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	int ret;
 
 	if (!drm_mode_is_420_only(info, adjusted_mode) ||
 	    !intel_dp_get_colorimetry_status(intel_dp) ||
@@ -2328,16 +2355,7 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp,
 
 	crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR420;
 
-	/* YCBCR 420 output conversion needs a scaler */
-	ret = skl_update_scaler_crtc(crtc_state);
-	if (ret) {
-		DRM_DEBUG_KMS("Scaler allocation for output failed\n");
-		return ret;
-	}
-
-	intel_pch_panel_fitting(crtc, crtc_state, DRM_MODE_SCALE_FULLSCREEN);
-
-	return 0;
+	return intel_pch_panel_fitting(crtc_state, conn_state);
 }
 
 bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
@@ -2384,6 +2402,164 @@ static bool intel_dp_port_has_audio(struct drm_i915_private *dev_priv,
 	return true;
 }
 
+static void intel_dp_compute_vsc_colorimetry(const struct intel_crtc_state *crtc_state,
+					     const struct drm_connector_state *conn_state,
+					     struct drm_dp_vsc_sdp *vsc)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	/*
+	 * Prepare VSC Header for SU as per DP 1.4 spec, Table 2-118
+	 * VSC SDP supporting 3D stereo, PSR2, and Pixel Encoding/
+	 * Colorimetry Format indication.
+	 */
+	vsc->revision = 0x5;
+	vsc->length = 0x13;
+
+	/* DP 1.4a spec, Table 2-120 */
+	switch (crtc_state->output_format) {
+	case INTEL_OUTPUT_FORMAT_YCBCR444:
+		vsc->pixelformat = DP_PIXELFORMAT_YUV444;
+		break;
+	case INTEL_OUTPUT_FORMAT_YCBCR420:
+		vsc->pixelformat = DP_PIXELFORMAT_YUV420;
+		break;
+	case INTEL_OUTPUT_FORMAT_RGB:
+	default:
+		vsc->pixelformat = DP_PIXELFORMAT_RGB;
+	}
+
+	switch (conn_state->colorspace) {
+	case DRM_MODE_COLORIMETRY_BT709_YCC:
+		vsc->colorimetry = DP_COLORIMETRY_BT709_YCC;
+		break;
+	case DRM_MODE_COLORIMETRY_XVYCC_601:
+		vsc->colorimetry = DP_COLORIMETRY_XVYCC_601;
+		break;
+	case DRM_MODE_COLORIMETRY_XVYCC_709:
+		vsc->colorimetry = DP_COLORIMETRY_XVYCC_709;
+		break;
+	case DRM_MODE_COLORIMETRY_SYCC_601:
+		vsc->colorimetry = DP_COLORIMETRY_SYCC_601;
+		break;
+	case DRM_MODE_COLORIMETRY_OPYCC_601:
+		vsc->colorimetry = DP_COLORIMETRY_OPYCC_601;
+		break;
+	case DRM_MODE_COLORIMETRY_BT2020_CYCC:
+		vsc->colorimetry = DP_COLORIMETRY_BT2020_CYCC;
+		break;
+	case DRM_MODE_COLORIMETRY_BT2020_RGB:
+		vsc->colorimetry = DP_COLORIMETRY_BT2020_RGB;
+		break;
+	case DRM_MODE_COLORIMETRY_BT2020_YCC:
+		vsc->colorimetry = DP_COLORIMETRY_BT2020_YCC;
+		break;
+	case DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65:
+	case DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER:
+		vsc->colorimetry = DP_COLORIMETRY_DCI_P3_RGB;
+		break;
+	default:
+		/*
+		 * RGB->YCBCR color conversion uses the BT.709
+		 * color space.
+		 */
+		if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
+			vsc->colorimetry = DP_COLORIMETRY_BT709_YCC;
+		else
+			vsc->colorimetry = DP_COLORIMETRY_DEFAULT;
+		break;
+	}
+
+	vsc->bpc = crtc_state->pipe_bpp / 3;
+
+	/* only RGB pixelformat supports 6 bpc */
+	drm_WARN_ON(&dev_priv->drm,
+		    vsc->bpc == 6 && vsc->pixelformat != DP_PIXELFORMAT_RGB);
+
+	/* all YCbCr are always limited range */
+	vsc->dynamic_range = DP_DYNAMIC_RANGE_CTA;
+	vsc->content_type = DP_CONTENT_TYPE_NOT_DEFINED;
+}
+
+static void intel_dp_compute_vsc_sdp(struct intel_dp *intel_dp,
+				     struct intel_crtc_state *crtc_state,
+				     const struct drm_connector_state *conn_state)
+{
+	struct drm_dp_vsc_sdp *vsc = &crtc_state->infoframes.vsc;
+
+	/* When a crtc state has PSR, VSC SDP will be handled by PSR routine */
+	if (crtc_state->has_psr)
+		return;
+
+	if (!intel_dp_needs_vsc_sdp(crtc_state, conn_state))
+		return;
+
+	crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_VSC);
+	vsc->sdp_type = DP_SDP_VSC;
+	intel_dp_compute_vsc_colorimetry(crtc_state, conn_state,
+					 &crtc_state->infoframes.vsc);
+}
+
+void intel_dp_compute_psr_vsc_sdp(struct intel_dp *intel_dp,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state,
+				  struct drm_dp_vsc_sdp *vsc)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+
+	vsc->sdp_type = DP_SDP_VSC;
+
+	if (dev_priv->psr.psr2_enabled) {
+		if (dev_priv->psr.colorimetry_support &&
+		    intel_dp_needs_vsc_sdp(crtc_state, conn_state)) {
+			/* [PSR2, +Colorimetry] */
+			intel_dp_compute_vsc_colorimetry(crtc_state, conn_state,
+							 vsc);
+		} else {
+			/*
+			 * [PSR2, -Colorimetry]
+			 * Prepare VSC Header for SU as per eDP 1.4 spec, Table 6-11
+			 * 3D stereo + PSR/PSR2 + Y-coordinate.
+			 */
+			vsc->revision = 0x4;
+			vsc->length = 0xe;
+		}
+	} else {
+		/*
+		 * [PSR1]
+		 * Prepare VSC Header for SU as per DP 1.4 spec, Table 2-118
+		 * VSC SDP supporting 3D stereo + PSR (applies to eDP v1.3 or
+		 * higher).
+		 */
+		vsc->revision = 0x2;
+		vsc->length = 0x8;
+	}
+}
+
+static void
+intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
+					    struct intel_crtc_state *crtc_state,
+					    const struct drm_connector_state *conn_state)
+{
+	int ret;
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct hdmi_drm_infoframe *drm_infoframe = &crtc_state->infoframes.drm.drm;
+
+	if (!conn_state->hdr_output_metadata)
+		return;
+
+	ret = drm_hdmi_infoframe_set_hdr_metadata(drm_infoframe, conn_state);
+
+	if (ret) {
+		drm_dbg_kms(&dev_priv->drm, "couldn't set HDR metadata in infoframe\n");
+		return;
+	}
+
+	crtc_state->infoframes.enable |=
+		intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA);
+}
+
 int
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config,
@@ -2394,7 +2570,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder);
 	enum port port = encoder->port;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
@@ -2410,9 +2585,8 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (lspcon->active)
 		lspcon_ycbcr420_config(&intel_connector->base, pipe_config);
 	else
-		ret = intel_dp_ycbcr420_config(intel_dp, &intel_connector->base,
-					       pipe_config);
-
+		ret = intel_dp_ycbcr420_config(intel_dp, pipe_config,
+					       conn_state);
 	if (ret)
 		return ret;
 
@@ -2428,18 +2602,12 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
 				       adjusted_mode);
 
-		if (INTEL_GEN(dev_priv) >= 9) {
-			ret = skl_update_scaler_crtc(pipe_config);
-			if (ret)
-				return ret;
-		}
-
 		if (HAS_GMCH(dev_priv))
-			intel_gmch_panel_fitting(intel_crtc, pipe_config,
-						 conn_state->scaling_mode);
+			ret = intel_gmch_panel_fitting(pipe_config, conn_state);
 		else
-			intel_pch_panel_fitting(intel_crtc, pipe_config,
-						conn_state->scaling_mode);
+			ret = intel_pch_panel_fitting(pipe_config, conn_state);
+		if (ret)
+			return ret;
 	}
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
@@ -2489,6 +2657,8 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		intel_dp_set_clock(encoder, pipe_config);
 
 	intel_psr_compute_config(intel_dp, pipe_config);
+	intel_dp_compute_vsc_sdp(intel_dp, pipe_config, conn_state);
+	intel_dp_compute_hdr_metadata_infoframe_sdp(intel_dp, pipe_config, conn_state);
 
 	return 0;
 }
@@ -2630,22 +2800,27 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 
 static void wait_panel_on(struct intel_dp *intel_dp)
 {
-	DRM_DEBUG_KMS("Wait for panel power on\n");
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	drm_dbg_kms(&i915->drm, "Wait for panel power on\n");
 	wait_panel_status(intel_dp, IDLE_ON_MASK, IDLE_ON_VALUE);
 }
 
 static void wait_panel_off(struct intel_dp *intel_dp)
 {
-	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	drm_dbg_kms(&i915->drm, "Wait for panel power off time\n");
 	wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE);
 }
 
 static void wait_panel_power_cycle(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	ktime_t panel_power_on_time;
 	s64 panel_power_off_duration;
 
-	DRM_DEBUG_KMS("Wait for panel power cycle\n");
+	drm_dbg_kms(&i915->drm, "Wait for panel power cycle\n");
 
 	/* take the difference of currrent time and panel power off time
 	 * and then make panel wait for t11_t12 if needed. */
@@ -3009,11 +3184,12 @@ void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(conn_state->best_encoder));
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(&i915->drm, "\n");
 
 	intel_panel_enable_backlight(crtc_state, conn_state);
 	_intel_edp_backlight_on(intel_dp);
@@ -3047,11 +3223,12 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder));
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(&i915->drm, "\n");
 
 	_intel_edp_backlight_off(intel_dp);
 	intel_panel_disable_backlight(old_conn_state);
@@ -3064,6 +3241,7 @@ void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 static void intel_edp_backlight_power(struct intel_connector *connector,
 				      bool enable)
 {
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	intel_wakeref_t wakeref;
 	bool is_enabled;
@@ -3074,8 +3252,8 @@ static void intel_edp_backlight_power(struct intel_connector *connector,
 	if (is_enabled == enable)
 		return;
 
-	DRM_DEBUG_KMS("panel power control backlight %s\n",
-		      enable ? "enable" : "disable");
+	drm_dbg_kms(&i915->drm, "panel power control backlight %s\n",
+		    enable ? "enable" : "disable");
 
 	if (enable)
 		_intel_edp_backlight_on(intel_dp);
@@ -3185,6 +3363,7 @@ void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp,
 					   const struct intel_crtc_state *crtc_state,
 					   bool enable)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	int ret;
 
 	if (!crtc_state->dsc.compression_enable)
@@ -3193,13 +3372,15 @@ void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp,
 	ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_DSC_ENABLE,
 				 enable ? DP_DECOMPRESSION_EN : 0);
 	if (ret < 0)
-		DRM_DEBUG_KMS("Failed to %s sink decompression state\n",
-			      enable ? "enable" : "disable");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to %s sink decompression state\n",
+			    enable ? "enable" : "disable");
 }
 
 /* If the sink supports it, try to set the power state appropriately */
 void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	int ret, i;
 
 	/* Should have a valid DPCD by this point */
@@ -3232,8 +3413,8 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 	}
 
 	if (ret != 1)
-		DRM_DEBUG_KMS("failed to %s sink power state\n",
-			      mode == DRM_MODE_DPMS_ON ? "enable" : "disable");
+		drm_dbg_kms(&i915->drm, "failed to %s sink power state\n",
+			    mode == DRM_MODE_DPMS_ON ? "enable" : "disable");
 }
 
 static bool cpt_dp_port_selected(struct drm_i915_private *dev_priv,
@@ -3390,7 +3571,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	}
 }
 
-static void intel_disable_dp(struct intel_encoder *encoder,
+static void intel_disable_dp(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
@@ -3410,21 +3592,24 @@ static void intel_disable_dp(struct intel_encoder *encoder,
 	intel_edp_panel_off(intel_dp);
 }
 
-static void g4x_disable_dp(struct intel_encoder *encoder,
+static void g4x_disable_dp(struct intel_atomic_state *state,
+			   struct intel_encoder *encoder,
 			   const struct intel_crtc_state *old_crtc_state,
 			   const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
+	intel_disable_dp(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void vlv_disable_dp(struct intel_encoder *encoder,
+static void vlv_disable_dp(struct intel_atomic_state *state,
+			   struct intel_encoder *encoder,
 			   const struct intel_crtc_state *old_crtc_state,
 			   const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
+	intel_disable_dp(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void g4x_post_disable_dp(struct intel_encoder *encoder,
+static void g4x_post_disable_dp(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
@@ -3444,14 +3629,16 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder,
 		ilk_edp_pll_off(intel_dp, old_crtc_state);
 }
 
-static void vlv_post_disable_dp(struct intel_encoder *encoder,
+static void vlv_post_disable_dp(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
 	intel_dp_link_down(encoder, old_crtc_state);
 }
 
-static void chv_post_disable_dp(struct intel_encoder *encoder,
+static void chv_post_disable_dp(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
@@ -3468,90 +3655,63 @@ static void chv_post_disable_dp(struct intel_encoder *encoder,
 }
 
 static void
-_intel_dp_set_link_train(struct intel_dp *intel_dp,
-			 u32 *DP,
-			 u8 dp_train_pat)
+cpt_set_link_train(struct intel_dp *intel_dp,
+		   u8 dp_train_pat)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	enum port port = intel_dig_port->base.port;
-	u8 train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
-
-	if (dp_train_pat & train_pat_mask)
-		drm_dbg_kms(&dev_priv->drm,
-			    "Using DP training pattern TPS%d\n",
-			    dp_train_pat & train_pat_mask);
-
-	if (HAS_DDI(dev_priv)) {
-		u32 temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
+	u32 *DP = &intel_dp->DP;
 
-		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
-			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
-		else
-			temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
-
-		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-		switch (dp_train_pat & train_pat_mask) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
+	*DP &= ~DP_LINK_TRAIN_MASK_CPT;
 
-			break;
-		case DP_TRAINING_PATTERN_1:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT1;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT2;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
-			break;
-		case DP_TRAINING_PATTERN_4:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT4;
-			break;
-		}
-		intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, temp);
+	switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+	case DP_TRAINING_PATTERN_DISABLE:
+		*DP |= DP_LINK_TRAIN_OFF_CPT;
+		break;
+	case DP_TRAINING_PATTERN_1:
+		*DP |= DP_LINK_TRAIN_PAT_1_CPT;
+		break;
+	case DP_TRAINING_PATTERN_2:
+		*DP |= DP_LINK_TRAIN_PAT_2_CPT;
+		break;
+	case DP_TRAINING_PATTERN_3:
+		drm_dbg_kms(&dev_priv->drm,
+			    "TPS3 not supported, using TPS2 instead\n");
+		*DP |= DP_LINK_TRAIN_PAT_2_CPT;
+		break;
+	}
 
-	} else if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
-		   (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
-		*DP &= ~DP_LINK_TRAIN_MASK_CPT;
+	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+}
 
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			*DP |= DP_LINK_TRAIN_OFF_CPT;
-			break;
-		case DP_TRAINING_PATTERN_1:
-			*DP |= DP_LINK_TRAIN_PAT_1_CPT;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			drm_dbg_kms(&dev_priv->drm,
-				    "TPS3 not supported, using TPS2 instead\n");
-			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
-			break;
-		}
+static void
+g4x_set_link_train(struct intel_dp *intel_dp,
+		   u8 dp_train_pat)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u32 *DP = &intel_dp->DP;
 
-	} else {
-		*DP &= ~DP_LINK_TRAIN_MASK;
+	*DP &= ~DP_LINK_TRAIN_MASK;
 
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			*DP |= DP_LINK_TRAIN_OFF;
-			break;
-		case DP_TRAINING_PATTERN_1:
-			*DP |= DP_LINK_TRAIN_PAT_1;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			*DP |= DP_LINK_TRAIN_PAT_2;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			drm_dbg_kms(&dev_priv->drm,
-				    "TPS3 not supported, using TPS2 instead\n");
-			*DP |= DP_LINK_TRAIN_PAT_2;
-			break;
-		}
+	switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+	case DP_TRAINING_PATTERN_DISABLE:
+		*DP |= DP_LINK_TRAIN_OFF;
+		break;
+	case DP_TRAINING_PATTERN_1:
+		*DP |= DP_LINK_TRAIN_PAT_1;
+		break;
+	case DP_TRAINING_PATTERN_2:
+		*DP |= DP_LINK_TRAIN_PAT_2;
+		break;
+	case DP_TRAINING_PATTERN_3:
+		drm_dbg_kms(&dev_priv->drm,
+			    "TPS3 not supported, using TPS2 instead\n");
+		*DP |= DP_LINK_TRAIN_PAT_2;
+		break;
 	}
+
+	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(dev_priv, intel_dp->output_reg);
 }
 
 static void intel_dp_enable_port(struct intel_dp *intel_dp,
@@ -3577,7 +3737,8 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp,
 	intel_de_posting_read(dev_priv, intel_dp->output_reg);
 }
 
-static void intel_enable_dp(struct intel_encoder *encoder,
+static void intel_enable_dp(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_connector_state *conn_state)
 {
@@ -3623,22 +3784,25 @@ static void intel_enable_dp(struct intel_encoder *encoder,
 	}
 }
 
-static void g4x_enable_dp(struct intel_encoder *encoder,
+static void g4x_enable_dp(struct intel_atomic_state *state,
+			  struct intel_encoder *encoder,
 			  const struct intel_crtc_state *pipe_config,
 			  const struct drm_connector_state *conn_state)
 {
-	intel_enable_dp(encoder, pipe_config, conn_state);
+	intel_enable_dp(state, encoder, pipe_config, conn_state);
 	intel_edp_backlight_on(pipe_config, conn_state);
 }
 
-static void vlv_enable_dp(struct intel_encoder *encoder,
+static void vlv_enable_dp(struct intel_atomic_state *state,
+			  struct intel_encoder *encoder,
 			  const struct intel_crtc_state *pipe_config,
 			  const struct drm_connector_state *conn_state)
 {
 	intel_edp_backlight_on(pipe_config, conn_state);
 }
 
-static void g4x_pre_enable_dp(struct intel_encoder *encoder,
+static void g4x_pre_enable_dp(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
@@ -3758,16 +3922,18 @@ static void vlv_init_panel_power_sequencer(struct intel_encoder *encoder,
 	intel_dp_init_panel_power_sequencer_registers(intel_dp, true);
 }
 
-static void vlv_pre_enable_dp(struct intel_encoder *encoder,
+static void vlv_pre_enable_dp(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
 	vlv_phy_pre_encoder_enable(encoder, pipe_config);
 
-	intel_enable_dp(encoder, pipe_config, conn_state);
+	intel_enable_dp(state, encoder, pipe_config, conn_state);
 }
 
-static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder,
+static void vlv_dp_pre_pll_enable(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config,
 				  const struct drm_connector_state *conn_state)
 {
@@ -3776,19 +3942,21 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder,
 	vlv_phy_pre_pll_enable(encoder, pipe_config);
 }
 
-static void chv_pre_enable_dp(struct intel_encoder *encoder,
+static void chv_pre_enable_dp(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
 	chv_phy_pre_encoder_enable(encoder, pipe_config);
 
-	intel_enable_dp(encoder, pipe_config, conn_state);
+	intel_enable_dp(state, encoder, pipe_config, conn_state);
 
 	/* Second common lane will stay alive on its own now */
 	chv_phy_release_cl2_override(encoder);
 }
 
-static void chv_dp_pre_pll_enable(struct intel_encoder *encoder,
+static void chv_dp_pre_pll_enable(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config,
 				  const struct drm_connector_state *conn_state)
 {
@@ -3797,7 +3965,8 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder,
 	chv_phy_pre_pll_enable(encoder, pipe_config);
 }
 
-static void chv_dp_post_pll_disable(struct intel_encoder *encoder,
+static void chv_dp_post_pll_disable(struct intel_atomic_state *state,
+				    struct intel_encoder *encoder,
 				    const struct intel_crtc_state *old_crtc_state,
 				    const struct drm_connector_state *old_conn_state)
 {
@@ -3881,7 +4050,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, u8 voltage_swing)
 	}
 }
 
-static u32 vlv_signal_levels(struct intel_dp *intel_dp)
+static void vlv_set_signal_levels(struct intel_dp *intel_dp)
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	unsigned long demph_reg_value, preemph_reg_value,
@@ -3909,7 +4078,7 @@ static u32 vlv_signal_levels(struct intel_dp *intel_dp)
 			uniqtranscale_reg_value = 0x5598DA3A;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_1:
@@ -3928,7 +4097,7 @@ static u32 vlv_signal_levels(struct intel_dp *intel_dp)
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_2:
@@ -3943,7 +4112,7 @@ static u32 vlv_signal_levels(struct intel_dp *intel_dp)
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_3:
@@ -3954,20 +4123,18 @@ static u32 vlv_signal_levels(struct intel_dp *intel_dp)
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	default:
-		return 0;
+		return;
 	}
 
 	vlv_set_phy_signal_level(encoder, demph_reg_value, preemph_reg_value,
 				 uniqtranscale_reg_value, 0);
-
-	return 0;
 }
 
-static u32 chv_signal_levels(struct intel_dp *intel_dp)
+static void chv_set_signal_levels(struct intel_dp *intel_dp)
 {
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	u32 deemph_reg_value, margin_reg_value;
@@ -3995,7 +4162,7 @@ static u32 chv_signal_levels(struct intel_dp *intel_dp)
 			uniq_trans_scale = true;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_1:
@@ -4013,7 +4180,7 @@ static u32 chv_signal_levels(struct intel_dp *intel_dp)
 			margin_reg_value = 154;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_2:
@@ -4027,7 +4194,7 @@ static u32 chv_signal_levels(struct intel_dp *intel_dp)
 			margin_reg_value = 154;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	case DP_TRAIN_PRE_EMPH_LEVEL_3:
@@ -4037,21 +4204,18 @@ static u32 chv_signal_levels(struct intel_dp *intel_dp)
 			margin_reg_value = 154;
 			break;
 		default:
-			return 0;
+			return;
 		}
 		break;
 	default:
-		return 0;
+		return;
 	}
 
 	chv_set_phy_signal_level(encoder, deemph_reg_value,
 				 margin_reg_value, uniq_trans_scale);
-
-	return 0;
 }
 
-static u32
-g4x_signal_levels(u8 train_set)
+static u32 g4x_signal_levels(u8 train_set)
 {
 	u32 signal_levels = 0;
 
@@ -4088,12 +4252,31 @@ g4x_signal_levels(u8 train_set)
 	return signal_levels;
 }
 
+static void
+g4x_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_set = intel_dp->train_set[0];
+	u32 signal_levels;
+
+	signal_levels = g4x_signal_levels(train_set);
+
+	drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n",
+		    signal_levels);
+
+	intel_dp->DP &= ~(DP_VOLTAGE_MASK | DP_PRE_EMPHASIS_MASK);
+	intel_dp->DP |= signal_levels;
+
+	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+}
+
 /* SNB CPU eDP voltage swing and pre-emphasis control */
-static u32
-snb_cpu_edp_signal_levels(u8 train_set)
+static u32 snb_cpu_edp_signal_levels(u8 train_set)
 {
-	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
-					 DP_TRAIN_PRE_EMPHASIS_MASK);
+	u8 signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
+					DP_TRAIN_PRE_EMPHASIS_MASK);
+
 	switch (signal_levels) {
 	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
@@ -4116,12 +4299,31 @@ snb_cpu_edp_signal_levels(u8 train_set)
 	}
 }
 
+static void
+snb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_set = intel_dp->train_set[0];
+	u32 signal_levels;
+
+	signal_levels = snb_cpu_edp_signal_levels(train_set);
+
+	drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n",
+		    signal_levels);
+
+	intel_dp->DP &= ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
+	intel_dp->DP |= signal_levels;
+
+	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+}
+
 /* IVB CPU eDP voltage swing and pre-emphasis control */
-static u32
-ivb_cpu_edp_signal_levels(u8 train_set)
+static u32 ivb_cpu_edp_signal_levels(u8 train_set)
 {
-	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
-					 DP_TRAIN_PRE_EMPHASIS_MASK);
+	u8 signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
+					DP_TRAIN_PRE_EMPHASIS_MASK);
+
 	switch (signal_levels) {
 	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_400MV_0DB_IVB;
@@ -4147,38 +4349,29 @@ ivb_cpu_edp_signal_levels(u8 train_set)
 	}
 }
 
-void
-intel_dp_set_signal_levels(struct intel_dp *intel_dp)
+static void
+ivb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	enum port port = intel_dig_port->base.port;
-	u32 signal_levels, mask = 0;
 	u8 train_set = intel_dp->train_set[0];
+	u32 signal_levels;
 
-	if (IS_GEN9_LP(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
-		signal_levels = bxt_signal_levels(intel_dp);
-	} else if (HAS_DDI(dev_priv)) {
-		signal_levels = ddi_signal_levels(intel_dp);
-		mask = DDI_BUF_EMP_MASK;
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		signal_levels = chv_signal_levels(intel_dp);
-	} else if (IS_VALLEYVIEW(dev_priv)) {
-		signal_levels = vlv_signal_levels(intel_dp);
-	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
-		signal_levels = ivb_cpu_edp_signal_levels(train_set);
-		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
-	} else if (IS_GEN(dev_priv, 6) && port == PORT_A) {
-		signal_levels = snb_cpu_edp_signal_levels(train_set);
-		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
-	} else {
-		signal_levels = g4x_signal_levels(train_set);
-		mask = DP_VOLTAGE_MASK | DP_PRE_EMPHASIS_MASK;
-	}
+	signal_levels = ivb_cpu_edp_signal_levels(train_set);
+
+	drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n",
+		    signal_levels);
+
+	intel_dp->DP &= ~EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
+	intel_dp->DP |= signal_levels;
 
-	if (mask)
-		drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n",
-			    signal_levels);
+	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+}
+
+void intel_dp_set_signal_levels(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_set = intel_dp->train_set[0];
 
 	drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s\n",
 		    train_set & DP_TRAIN_VOLTAGE_SWING_MASK,
@@ -4189,55 +4382,28 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp)
 		    train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ?
 		    " (max)" : "");
 
-	intel_dp->DP = (intel_dp->DP & ~mask) | signal_levels;
-
-	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
-	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+	intel_dp->set_signal_levels(intel_dp);
 }
 
 void
 intel_dp_program_link_training_pattern(struct intel_dp *intel_dp,
 				       u8 dp_train_pat)
 {
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv =
-		to_i915(intel_dig_port->base.base.dev);
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
 
-	_intel_dp_set_link_train(intel_dp, &intel_dp->DP, dp_train_pat);
+	if (dp_train_pat & train_pat_mask)
+		drm_dbg_kms(&dev_priv->drm,
+			    "Using DP training pattern TPS%d\n",
+			    dp_train_pat & train_pat_mask);
 
-	intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP);
-	intel_de_posting_read(dev_priv, intel_dp->output_reg);
+	intel_dp->set_link_train(intel_dp, dp_train_pat);
 }
 
 void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	enum port port = intel_dig_port->base.port;
-	u32 val;
-
-	if (!HAS_DDI(dev_priv))
-		return;
-
-	val = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
-	val &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-	val |= DP_TP_CTL_LINK_TRAIN_IDLE;
-	intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, val);
-
-	/*
-	 * 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 && INTEL_GEN(dev_priv) < 12)
-		return;
-
-	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
-				  DP_TP_STATUS_IDLE_DONE, 1))
-		drm_err(&dev_priv->drm,
-			"Timed out waiting for DP idle patterns\n");
+	if (intel_dp->set_idle_link_train)
+		intel_dp->set_idle_link_train(intel_dp);
 }
 
 static void
@@ -4316,6 +4482,7 @@ intel_dp_link_down(struct intel_encoder *encoder,
 static void
 intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 dpcd_ext[6];
 
 	/*
@@ -4331,20 +4498,22 @@ intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp)
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_DP13_DPCD_REV,
 			     &dpcd_ext, sizeof(dpcd_ext)) != sizeof(dpcd_ext)) {
-		DRM_ERROR("DPCD failed read at extended capabilities\n");
+		drm_err(&i915->drm,
+			"DPCD failed read at extended capabilities\n");
 		return;
 	}
 
 	if (intel_dp->dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
-		DRM_DEBUG_KMS("DPCD extended DPCD rev less than base DPCD rev\n");
+		drm_dbg_kms(&i915->drm,
+			    "DPCD extended DPCD rev less than base DPCD rev\n");
 		return;
 	}
 
 	if (!memcmp(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext)))
 		return;
 
-	DRM_DEBUG_KMS("Base DPCD: %*ph\n",
-		      (int)sizeof(intel_dp->dpcd), intel_dp->dpcd);
+	drm_dbg_kms(&i915->drm, "Base DPCD: %*ph\n",
+		    (int)sizeof(intel_dp->dpcd), intel_dp->dpcd);
 
 	memcpy(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext));
 }
@@ -4352,13 +4521,16 @@ intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp)
 bool
 intel_dp_read_dpcd(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
 	if (drm_dp_dpcd_read(&intel_dp->aux, 0x000, intel_dp->dpcd,
 			     sizeof(intel_dp->dpcd)) < 0)
 		return false; /* aux transfer failed */
 
 	intel_dp_extended_receiver_capabilities(intel_dp);
 
-	DRM_DEBUG_KMS("DPCD: %*ph\n", (int) sizeof(intel_dp->dpcd), intel_dp->dpcd);
+	drm_dbg_kms(&i915->drm, "DPCD: %*ph\n", (int)sizeof(intel_dp->dpcd),
+		    intel_dp->dpcd);
 
 	return intel_dp->dpcd[DP_DPCD_REV] != 0;
 }
@@ -4375,6 +4547,8 @@ bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 
 static void intel_dp_get_dsc_sink_cap(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
 	/*
 	 * Clear the cached register set to avoid using stale values
 	 * for the sinks that do not support DSC.
@@ -4390,20 +4564,23 @@ static void intel_dp_get_dsc_sink_cap(struct intel_dp *intel_dp)
 		if (drm_dp_dpcd_read(&intel_dp->aux, DP_DSC_SUPPORT,
 				     intel_dp->dsc_dpcd,
 				     sizeof(intel_dp->dsc_dpcd)) < 0)
-			DRM_ERROR("Failed to read DPCD register 0x%x\n",
-				  DP_DSC_SUPPORT);
+			drm_err(&i915->drm,
+				"Failed to read DPCD register 0x%x\n",
+				DP_DSC_SUPPORT);
 
-		DRM_DEBUG_KMS("DSC DPCD: %*ph\n",
-			      (int)sizeof(intel_dp->dsc_dpcd),
-			      intel_dp->dsc_dpcd);
+		drm_dbg_kms(&i915->drm, "DSC DPCD: %*ph\n",
+			    (int)sizeof(intel_dp->dsc_dpcd),
+			    intel_dp->dsc_dpcd);
 
 		/* FEC is supported only on DP 1.4 */
 		if (!intel_dp_is_edp(intel_dp) &&
 		    drm_dp_dpcd_readb(&intel_dp->aux, DP_FEC_CAPABILITY,
 				      &intel_dp->fec_capable) < 0)
-			DRM_ERROR("Failed to read FEC DPCD register\n");
+			drm_err(&i915->drm,
+				"Failed to read FEC DPCD register\n");
 
-		DRM_DEBUG_KMS("FEC CAPABILITY: %x\n", intel_dp->fec_capable);
+		drm_dbg_kms(&i915->drm, "FEC CAPABILITY: %x\n",
+			    intel_dp->fec_capable);
 	}
 }
 
@@ -4577,14 +4754,16 @@ intel_dp_can_mst(struct intel_dp *intel_dp)
 static void
 intel_dp_configure_mst(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_encoder *encoder =
 		&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",
-		      encoder->base.base.id, encoder->base.name,
-		      yesno(intel_dp->can_mst), yesno(sink_can_mst),
-		      yesno(i915_modparams.enable_dp_mst));
+	drm_dbg_kms(&i915->drm,
+		    "[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;
@@ -4630,158 +4809,92 @@ intel_dp_needs_vsc_sdp(const struct intel_crtc_state *crtc_state,
 	return false;
 }
 
-static void
-intel_dp_setup_vsc_sdp(struct intel_dp *intel_dp,
-		       const struct intel_crtc_state *crtc_state,
-		       const struct drm_connector_state *conn_state)
+static ssize_t intel_dp_vsc_sdp_pack(const struct drm_dp_vsc_sdp *vsc,
+				     struct dp_sdp *sdp, size_t size)
 {
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct dp_sdp vsc_sdp = {};
+	size_t length = sizeof(struct dp_sdp);
 
-	/* Prepare VSC Header for SU as per DP 1.4a spec, Table 2-119 */
-	vsc_sdp.sdp_header.HB0 = 0;
-	vsc_sdp.sdp_header.HB1 = 0x7;
+	if (size < length)
+		return -ENOSPC;
+
+	memset(sdp, 0, size);
 
 	/*
-	 * VSC SDP supporting 3D stereo, PSR2, and Pixel Encoding/
-	 * Colorimetry Format indication.
+	 * Prepare VSC Header for SU as per DP 1.4a spec, Table 2-119
+	 * VSC SDP Header Bytes
 	 */
-	vsc_sdp.sdp_header.HB2 = 0x5;
+	sdp->sdp_header.HB0 = 0; /* Secondary-Data Packet ID = 0 */
+	sdp->sdp_header.HB1 = vsc->sdp_type; /* Secondary-data Packet Type */
+	sdp->sdp_header.HB2 = vsc->revision; /* Revision Number */
+	sdp->sdp_header.HB3 = vsc->length; /* Number of Valid Data Bytes */
 
 	/*
-	 * VSC SDP supporting 3D stereo, + PSR2, + Pixel Encoding/
-	 * Colorimetry Format indication (HB2 = 05h).
+	 * Only revision 0x5 supports Pixel Encoding/Colorimetry Format as
+	 * per DP 1.4a spec.
 	 */
-	vsc_sdp.sdp_header.HB3 = 0x13;
-
-	/* 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;
-	}
+	if (vsc->revision != 0x5)
+		goto out;
 
-	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 */
+	/* VSC SDP Payload for DB16 through DB18 */
+	/* Pixel Encoding and Colorimetry Formats  */
+	sdp->db[16] = (vsc->pixelformat & 0xf) << 4; /* DB16[7:4] */
+	sdp->db[16] |= vsc->colorimetry & 0xf; /* DB16[3:0] */
 
-		/* 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 */
+	switch (vsc->bpc) {
+	case 6:
+		/* 6bpc: 0x0 */
 		break;
-	}
-
-	/*
-	 * For pixel encoding formats YCbCr444, YCbCr422, YCbCr420, and Y Only,
-	 * the following Component Bit Depth values are defined:
-	 * 001b = 8bpc.
-	 * 010b = 10bpc.
-	 * 011b = 12bpc.
-	 * 100b = 16bpc.
-	 */
-	switch (crtc_state->pipe_bpp) {
-	case 24: /* 8bpc */
-		vsc_sdp.db[17] = 0x1;
+	case 8:
+		sdp->db[17] = 0x1; /* DB17[3:0] */
 		break;
-	case 30: /* 10bpc */
-		vsc_sdp.db[17] = 0x2;
+	case 10:
+		sdp->db[17] = 0x2;
 		break;
-	case 36: /* 12bpc */
-		vsc_sdp.db[17] = 0x3;
+	case 12:
+		sdp->db[17] = 0x3;
 		break;
-	case 48: /* 16bpc */
-		vsc_sdp.db[17] = 0x4;
+	case 16:
+		sdp->db[17] = 0x4;
 		break;
 	default:
-		MISSING_CASE(crtc_state->pipe_bpp);
+		MISSING_CASE(vsc->bpc);
 		break;
 	}
+	/* Dynamic Range and Component Bit Depth */
+	if (vsc->dynamic_range == DP_DYNAMIC_RANGE_CTA)
+		sdp->db[17] |= 0x80;  /* DB17[7] */
 
-	/*
-	 * Dynamic Range (Bit 7)
-	 * 0 = VESA range, 1 = CTA range.
-	 * all YCbCr are always limited range
-	 */
-	vsc_sdp.db[17] |= 0x80;
-
-	/*
-	 * Content Type (Bits 2:0)
-	 * 000b = Not defined.
-	 * 001b = Graphics.
-	 * 010b = Photo.
-	 * 011b = Video.
-	 * 100b = Game
-	 * All other values are RESERVED.
-	 * Note: See CTA-861-G for the definition and expected
-	 * processing by a stream sink for the above contect types.
-	 */
-	vsc_sdp.db[18] = 0;
+	/* Content Type */
+	sdp->db[18] = vsc->content_type & 0x7;
 
-	intel_dig_port->write_infoframe(&intel_dig_port->base,
-			crtc_state, DP_SDP_VSC, &vsc_sdp, sizeof(vsc_sdp));
+out:
+	return length;
 }
 
-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)
+static ssize_t
+intel_dp_hdr_metadata_infoframe_sdp_pack(const struct hdmi_drm_infoframe *drm_infoframe,
+					 struct dp_sdp *sdp,
+					 size_t size)
 {
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct dp_sdp infoframe_sdp = {};
-	struct hdmi_drm_infoframe drm_infoframe = {};
+	size_t length = sizeof(struct dp_sdp);
 	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;
-	}
+	if (size < length)
+		return -ENOSPC;
+
+	memset(sdp, 0, size);
 
-	len = hdmi_drm_infoframe_pack_only(&drm_infoframe, buf, sizeof(buf));
+	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;
+		return -ENOSPC;
 	}
 
 	if (len != infoframe_size) {
 		DRM_DEBUG_KMS("wrong static hdr metadata size\n");
-		return;
+		return -ENOSPC;
 	}
 
 	/*
@@ -4790,34 +4903,37 @@ intel_dp_setup_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
 	 * Table 2-100 and Table 2-101
 	 */
 
-	/* Packet ID, 00h for non-Audio INFOFRAME */
-	infoframe_sdp.sdp_header.HB0 = 0;
+	/* Secondary-Data Packet ID, 00h for non-Audio INFOFRAME */
+	sdp->sdp_header.HB0 = 0;
 	/*
 	 * Packet Type 80h + Non-audio INFOFRAME Type value
-	 * HDMI_INFOFRAME_TYPE_DRM: 0x87,
+	 * HDMI_INFOFRAME_TYPE_DRM: 0x87
+	 * - 80h + Non-audio INFOFRAME Type value
+	 * - InfoFrame Type: 0x07
+	 *    [CTA-861-G Table-42 Dynamic Range and Mastering InfoFrame]
 	 */
-	infoframe_sdp.sdp_header.HB1 = drm_infoframe.type;
+	sdp->sdp_header.HB1 = drm_infoframe->type;
 	/*
 	 * Least Significant Eight Bits of (Data Byte Count – 1)
-	 * infoframe_size - 1,
+	 * infoframe_size - 1
 	 */
-	infoframe_sdp.sdp_header.HB2 = 0x1D;
+	sdp->sdp_header.HB2 = 0x1D;
 	/* INFOFRAME SDP Version Number */
-	infoframe_sdp.sdp_header.HB3 = (0x13 << 2);
+	sdp->sdp_header.HB3 = (0x13 << 2);
 	/* CTA Header Byte 2 (INFOFRAME Version Number) */
-	infoframe_sdp.db[0] = drm_infoframe.version;
+	sdp->db[0] = drm_infoframe->version;
 	/* CTA Header Byte 3 (Length of INFOFRAME): HDMI_DRM_INFOFRAME_SIZE */
-	infoframe_sdp.db[1] = drm_infoframe.length;
+	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],
+	BUILD_BUG_ON(sizeof(sdp->db) < HDMI_DRM_INFOFRAME_SIZE + 2);
+	memcpy(&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
+	 * Size of DP infoframe sdp packet for HDR static metadata consists of
 	 * - DP SDP Header(struct dp_sdp_header): 4 bytes
 	 * - Two Data Blocks: 2 bytes
 	 *    CTA Header Byte2 (INFOFRAME Version Number)
@@ -4828,36 +4944,286 @@ intel_dp_setup_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
 	 * 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);
+	return 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)
+static void intel_write_dp_sdp(struct intel_encoder *encoder,
+			       const struct intel_crtc_state *crtc_state,
+			       unsigned int type)
 {
-	if (!intel_dp_needs_vsc_sdp(crtc_state, conn_state))
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct dp_sdp sdp = {};
+	ssize_t len;
+
+	if ((crtc_state->infoframes.enable &
+	     intel_hdmi_infoframe_enable(type)) == 0)
 		return;
 
-	intel_dp_setup_vsc_sdp(intel_dp, crtc_state, conn_state);
+	switch (type) {
+	case DP_SDP_VSC:
+		len = intel_dp_vsc_sdp_pack(&crtc_state->infoframes.vsc, &sdp,
+					    sizeof(sdp));
+		break;
+	case HDMI_PACKET_TYPE_GAMUT_METADATA:
+		len = intel_dp_hdr_metadata_infoframe_sdp_pack(&crtc_state->infoframes.drm.drm,
+							       &sdp, sizeof(sdp));
+		break;
+	default:
+		MISSING_CASE(type);
+		return;
+	}
+
+	if (drm_WARN_ON(&dev_priv->drm, len < 0))
+		return;
+
+	intel_dig_port->write_infoframe(encoder, crtc_state, type, &sdp, len);
 }
 
-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)
+void intel_write_dp_vsc_sdp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    struct drm_dp_vsc_sdp *vsc)
 {
-	if (!conn_state->hdr_output_metadata)
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct dp_sdp sdp = {};
+	ssize_t len;
+
+	len = intel_dp_vsc_sdp_pack(vsc, &sdp, sizeof(sdp));
+
+	if (drm_WARN_ON(&dev_priv->drm, len < 0))
+		return;
+
+	intel_dig_port->write_infoframe(encoder, crtc_state, DP_SDP_VSC,
+					&sdp, len);
+}
+
+void intel_dp_set_infoframes(struct intel_encoder *encoder,
+			     bool enable,
+			     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);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	i915_reg_t reg = HSW_TVIDEO_DIP_CTL(crtc_state->cpu_transcoder);
+	u32 dip_enable = VIDEO_DIP_ENABLE_AVI_HSW | VIDEO_DIP_ENABLE_GCP_HSW |
+			 VIDEO_DIP_ENABLE_VS_HSW | VIDEO_DIP_ENABLE_GMP_HSW |
+			 VIDEO_DIP_ENABLE_SPD_HSW | VIDEO_DIP_ENABLE_DRM_GLK;
+	u32 val = intel_de_read(dev_priv, reg);
+
+	/* TODO: Add DSC case (DIP_ENABLE_PPS) */
+	/* When PSR is enabled, this routine doesn't disable VSC DIP */
+	if (intel_psr_enabled(intel_dp))
+		val &= ~dip_enable;
+	else
+		val &= ~(dip_enable | VIDEO_DIP_ENABLE_VSC_HSW);
+
+	if (!enable) {
+		intel_de_write(dev_priv, reg, val);
+		intel_de_posting_read(dev_priv, reg);
+		return;
+	}
+
+	intel_de_write(dev_priv, reg, val);
+	intel_de_posting_read(dev_priv, reg);
+
+	/* When PSR is enabled, VSC SDP is handled by PSR routine */
+	if (!intel_psr_enabled(intel_dp))
+		intel_write_dp_sdp(encoder, crtc_state, DP_SDP_VSC);
+
+	intel_write_dp_sdp(encoder, crtc_state, HDMI_PACKET_TYPE_GAMUT_METADATA);
+}
+
+static int intel_dp_vsc_sdp_unpack(struct drm_dp_vsc_sdp *vsc,
+				   const void *buffer, size_t size)
+{
+	const struct dp_sdp *sdp = buffer;
+
+	if (size < sizeof(struct dp_sdp))
+		return -EINVAL;
+
+	memset(vsc, 0, size);
+
+	if (sdp->sdp_header.HB0 != 0)
+		return -EINVAL;
+
+	if (sdp->sdp_header.HB1 != DP_SDP_VSC)
+		return -EINVAL;
+
+	vsc->sdp_type = sdp->sdp_header.HB1;
+	vsc->revision = sdp->sdp_header.HB2;
+	vsc->length = sdp->sdp_header.HB3;
+
+	if ((sdp->sdp_header.HB2 == 0x2 && sdp->sdp_header.HB3 == 0x8) ||
+	    (sdp->sdp_header.HB2 == 0x4 && sdp->sdp_header.HB3 == 0xe)) {
+		/*
+		 * - HB2 = 0x2, HB3 = 0x8
+		 *   VSC SDP supporting 3D stereo + PSR
+		 * - HB2 = 0x4, HB3 = 0xe
+		 *   VSC SDP supporting 3D stereo + PSR2 with Y-coordinate of
+		 *   first scan line of the SU region (applies to eDP v1.4b
+		 *   and higher).
+		 */
+		return 0;
+	} else if (sdp->sdp_header.HB2 == 0x5 && sdp->sdp_header.HB3 == 0x13) {
+		/*
+		 * - HB2 = 0x5, HB3 = 0x13
+		 *   VSC SDP supporting 3D stereo + PSR2 + Pixel Encoding/Colorimetry
+		 *   Format.
+		 */
+		vsc->pixelformat = (sdp->db[16] >> 4) & 0xf;
+		vsc->colorimetry = sdp->db[16] & 0xf;
+		vsc->dynamic_range = (sdp->db[17] >> 7) & 0x1;
+
+		switch (sdp->db[17] & 0x7) {
+		case 0x0:
+			vsc->bpc = 6;
+			break;
+		case 0x1:
+			vsc->bpc = 8;
+			break;
+		case 0x2:
+			vsc->bpc = 10;
+			break;
+		case 0x3:
+			vsc->bpc = 12;
+			break;
+		case 0x4:
+			vsc->bpc = 16;
+			break;
+		default:
+			MISSING_CASE(sdp->db[17] & 0x7);
+			return -EINVAL;
+		}
+
+		vsc->content_type = sdp->db[18] & 0x7;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+intel_dp_hdr_metadata_infoframe_sdp_unpack(struct hdmi_drm_infoframe *drm_infoframe,
+					   const void *buffer, size_t size)
+{
+	int ret;
+
+	const struct dp_sdp *sdp = buffer;
+
+	if (size < sizeof(struct dp_sdp))
+		return -EINVAL;
+
+	if (sdp->sdp_header.HB0 != 0)
+		return -EINVAL;
+
+	if (sdp->sdp_header.HB1 != HDMI_INFOFRAME_TYPE_DRM)
+		return -EINVAL;
+
+	/*
+	 * Least Significant Eight Bits of (Data Byte Count – 1)
+	 * 1Dh (i.e., Data Byte Count = 30 bytes).
+	 */
+	if (sdp->sdp_header.HB2 != 0x1D)
+		return -EINVAL;
+
+	/* Most Significant Two Bits of (Data Byte Count – 1), Clear to 00b. */
+	if ((sdp->sdp_header.HB3 & 0x3) != 0)
+		return -EINVAL;
+
+	/* INFOFRAME SDP Version Number */
+	if (((sdp->sdp_header.HB3 >> 2) & 0x3f) != 0x13)
+		return -EINVAL;
+
+	/* CTA Header Byte 2 (INFOFRAME Version Number) */
+	if (sdp->db[0] != 1)
+		return -EINVAL;
+
+	/* CTA Header Byte 3 (Length of INFOFRAME): HDMI_DRM_INFOFRAME_SIZE */
+	if (sdp->db[1] != HDMI_DRM_INFOFRAME_SIZE)
+		return -EINVAL;
+
+	ret = hdmi_drm_infoframe_unpack_only(drm_infoframe, &sdp->db[2],
+					     HDMI_DRM_INFOFRAME_SIZE);
+
+	return ret;
+}
+
+static void intel_read_dp_vsc_sdp(struct intel_encoder *encoder,
+				  struct intel_crtc_state *crtc_state,
+				  struct drm_dp_vsc_sdp *vsc)
+{
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	unsigned int type = DP_SDP_VSC;
+	struct dp_sdp sdp = {};
+	int ret;
+
+	/* When PSR is enabled, VSC SDP is handled by PSR routine */
+	if (intel_psr_enabled(intel_dp))
+		return;
+
+	if ((crtc_state->infoframes.enable &
+	     intel_hdmi_infoframe_enable(type)) == 0)
+		return;
+
+	intel_dig_port->read_infoframe(encoder, crtc_state, type, &sdp, sizeof(sdp));
+
+	ret = intel_dp_vsc_sdp_unpack(vsc, &sdp, sizeof(sdp));
+
+	if (ret)
+		drm_dbg_kms(&dev_priv->drm, "Failed to unpack DP VSC SDP\n");
+}
+
+static void intel_read_dp_hdr_metadata_infoframe_sdp(struct intel_encoder *encoder,
+						     struct intel_crtc_state *crtc_state,
+						     struct hdmi_drm_infoframe *drm_infoframe)
+{
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	unsigned int type = HDMI_PACKET_TYPE_GAMUT_METADATA;
+	struct dp_sdp sdp = {};
+	int ret;
+
+	if ((crtc_state->infoframes.enable &
+	    intel_hdmi_infoframe_enable(type)) == 0)
 		return;
 
-	intel_dp_setup_hdr_metadata_infoframe_sdp(intel_dp,
-						  crtc_state,
-						  conn_state);
+	intel_dig_port->read_infoframe(encoder, crtc_state, type, &sdp,
+				       sizeof(sdp));
+
+	ret = intel_dp_hdr_metadata_infoframe_sdp_unpack(drm_infoframe, &sdp,
+							 sizeof(sdp));
+
+	if (ret)
+		drm_dbg_kms(&dev_priv->drm,
+			    "Failed to unpack DP HDR Metadata Infoframe SDP\n");
+}
+
+void intel_read_dp_sdp(struct intel_encoder *encoder,
+		       struct intel_crtc_state *crtc_state,
+		       unsigned int type)
+{
+	switch (type) {
+	case DP_SDP_VSC:
+		intel_read_dp_vsc_sdp(encoder, crtc_state,
+				      &crtc_state->infoframes.vsc);
+		break;
+	case HDMI_PACKET_TYPE_GAMUT_METADATA:
+		intel_read_dp_hdr_metadata_infoframe_sdp(encoder, crtc_state,
+							 &crtc_state->infoframes.drm.drm);
+		break;
+	default:
+		MISSING_CASE(type);
+		break;
+	}
 }
 
 static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	int status = 0;
 	int test_link_rate;
 	u8 test_lane_count, test_link_bw;
@@ -4869,7 +5235,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
 				   &test_lane_count);
 
 	if (status <= 0) {
-		DRM_DEBUG_KMS("Lane count read failed\n");
+		drm_dbg_kms(&i915->drm, "Lane count read failed\n");
 		return DP_TEST_NAK;
 	}
 	test_lane_count &= DP_MAX_LANE_COUNT_MASK;
@@ -4877,7 +5243,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
 	status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_LINK_RATE,
 				   &test_link_bw);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("Link Rate read failed\n");
+		drm_dbg_kms(&i915->drm, "Link Rate read failed\n");
 		return DP_TEST_NAK;
 	}
 	test_link_rate = drm_dp_bw_code_to_link_rate(test_link_bw);
@@ -4895,6 +5261,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
 
 static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 test_pattern;
 	u8 test_misc;
 	__be16 h_width, v_height;
@@ -4904,7 +5271,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 	status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_PATTERN,
 				   &test_pattern);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("Test pattern read failed\n");
+		drm_dbg_kms(&i915->drm, "Test pattern read failed\n");
 		return DP_TEST_NAK;
 	}
 	if (test_pattern != DP_COLOR_RAMP)
@@ -4913,21 +5280,21 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 	status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_H_WIDTH_HI,
 				  &h_width, 2);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("H Width read failed\n");
+		drm_dbg_kms(&i915->drm, "H Width read failed\n");
 		return DP_TEST_NAK;
 	}
 
 	status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_V_HEIGHT_HI,
 				  &v_height, 2);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("V Height read failed\n");
+		drm_dbg_kms(&i915->drm, "V Height read failed\n");
 		return DP_TEST_NAK;
 	}
 
 	status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_MISC0,
 				   &test_misc);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("TEST MISC read failed\n");
+		drm_dbg_kms(&i915->drm, "TEST MISC read failed\n");
 		return DP_TEST_NAK;
 	}
 	if ((test_misc & DP_TEST_COLOR_FORMAT_MASK) != DP_COLOR_FORMAT_RGB)
@@ -4956,6 +5323,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 
 static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 test_result = DP_TEST_ACK;
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	struct drm_connector *connector = &intel_connector->base;
@@ -4972,9 +5340,10 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 		 */
 		if (intel_dp->aux.i2c_nack_count > 0 ||
 			intel_dp->aux.i2c_defer_count > 0)
-			DRM_DEBUG_KMS("EDID read had %d NACKs, %d DEFERs\n",
-				      intel_dp->aux.i2c_nack_count,
-				      intel_dp->aux.i2c_defer_count);
+			drm_dbg_kms(&i915->drm,
+				    "EDID read had %d NACKs, %d DEFERs\n",
+				    intel_dp->aux.i2c_nack_count,
+				    intel_dp->aux.i2c_defer_count);
 		intel_dp->compliance.test_data.edid = INTEL_DP_RESOLUTION_FAILSAFE;
 	} else {
 		struct edid *block = intel_connector->detect_edid;
@@ -4986,7 +5355,8 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 
 		if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_EDID_CHECKSUM,
 				       block->checksum) <= 0)
-			DRM_DEBUG_KMS("Failed to write EDID checksum\n");
+			drm_dbg_kms(&i915->drm,
+				    "Failed to write EDID checksum\n");
 
 		test_result = DP_TEST_ACK | DP_TEST_EDID_CHECKSUM_WRITE;
 		intel_dp->compliance.test_data.edid = INTEL_DP_RESOLUTION_PREFERRED;
@@ -4998,43 +5368,217 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 	return test_result;
 }
 
+static u8 intel_dp_prepare_phytest(struct intel_dp *intel_dp)
+{
+	struct drm_dp_phy_test_params *data =
+		&intel_dp->compliance.test_data.phytest;
+
+	if (drm_dp_get_phy_test_pattern(&intel_dp->aux, data)) {
+		DRM_DEBUG_KMS("DP Phy Test pattern AUX read failure\n");
+		return DP_TEST_NAK;
+	}
+
+	/*
+	 * link_mst is set to false to avoid executing mst related code
+	 * during compliance testing.
+	 */
+	intel_dp->link_mst = false;
+
+	return DP_TEST_ACK;
+}
+
+static void intel_dp_phy_pattern_update(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv =
+			to_i915(dp_to_dig_port(intel_dp)->base.base.dev);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_dp_phy_test_params *data =
+			&intel_dp->compliance.test_data.phytest;
+	struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
+	enum pipe pipe = crtc->pipe;
+	u32 pattern_val;
+
+	switch (data->phy_pattern) {
+	case DP_PHY_TEST_PATTERN_NONE:
+		DRM_DEBUG_KMS("Disable Phy Test Pattern\n");
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), 0x0);
+		break;
+	case DP_PHY_TEST_PATTERN_D10_2:
+		DRM_DEBUG_KMS("Set D10.2 Phy Test Pattern\n");
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe),
+			       DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_D10_2);
+		break;
+	case DP_PHY_TEST_PATTERN_ERROR_COUNT:
+		DRM_DEBUG_KMS("Set Error Count Phy Test Pattern\n");
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe),
+			       DDI_DP_COMP_CTL_ENABLE |
+			       DDI_DP_COMP_CTL_SCRAMBLED_0);
+		break;
+	case DP_PHY_TEST_PATTERN_PRBS7:
+		DRM_DEBUG_KMS("Set PRBS7 Phy Test Pattern\n");
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe),
+			       DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_PRBS7);
+		break;
+	case DP_PHY_TEST_PATTERN_80BIT_CUSTOM:
+		/*
+		 * FIXME: Ideally pattern should come from DPCD 0x250. As
+		 * current firmware of DPR-100 could not set it, so hardcoding
+		 * now for complaince test.
+		 */
+		DRM_DEBUG_KMS("Set 80Bit Custom Phy Test Pattern 0x3e0f83e0 0x0f83e0f8 0x0000f83e\n");
+		pattern_val = 0x3e0f83e0;
+		intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 0), pattern_val);
+		pattern_val = 0x0f83e0f8;
+		intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 1), pattern_val);
+		pattern_val = 0x0000f83e;
+		intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 2), pattern_val);
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe),
+			       DDI_DP_COMP_CTL_ENABLE |
+			       DDI_DP_COMP_CTL_CUSTOM80);
+		break;
+	case DP_PHY_TEST_PATTERN_CP2520:
+		/*
+		 * FIXME: Ideally pattern should come from DPCD 0x24A. As
+		 * current firmware of DPR-100 could not set it, so hardcoding
+		 * now for complaince test.
+		 */
+		DRM_DEBUG_KMS("Set HBR2 compliance Phy Test Pattern\n");
+		pattern_val = 0xFB;
+		intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe),
+			       DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_HBR2 |
+			       pattern_val);
+		break;
+	default:
+		WARN(1, "Invalid Phy Test Pattern\n");
+	}
+}
+
+static void
+intel_dp_autotest_phy_ddi_disable(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
+	enum pipe pipe = crtc->pipe;
+	u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value;
+
+	trans_ddi_func_ctl_value = intel_de_read(dev_priv,
+						 TRANS_DDI_FUNC_CTL(pipe));
+	trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe));
+	dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe));
+
+	trans_ddi_func_ctl_value &= ~(TRANS_DDI_FUNC_ENABLE |
+				      TGL_TRANS_DDI_PORT_MASK);
+	trans_conf_value &= ~PIPECONF_ENABLE;
+	dp_tp_ctl_value &= ~DP_TP_CTL_ENABLE;
+
+	intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value);
+	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe),
+		       trans_ddi_func_ctl_value);
+	intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value);
+}
+
+static void
+intel_dp_autotest_phy_ddi_enable(struct intel_dp *intel_dp, uint8_t lane_cnt)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum port port = intel_dig_port->base.port;
+	struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
+	enum pipe pipe = crtc->pipe;
+	u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value;
+
+	trans_ddi_func_ctl_value = intel_de_read(dev_priv,
+						 TRANS_DDI_FUNC_CTL(pipe));
+	trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe));
+	dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe));
+
+	trans_ddi_func_ctl_value |= TRANS_DDI_FUNC_ENABLE |
+				    TGL_TRANS_DDI_SELECT_PORT(port);
+	trans_conf_value |= PIPECONF_ENABLE;
+	dp_tp_ctl_value |= DP_TP_CTL_ENABLE;
+
+	intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value);
+	intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value);
+	intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe),
+		       trans_ddi_func_ctl_value);
+}
+
+void intel_dp_process_phy_request(struct intel_dp *intel_dp)
+{
+	struct drm_dp_phy_test_params *data =
+		&intel_dp->compliance.test_data.phytest;
+	u8 link_status[DP_LINK_STATUS_SIZE];
+
+	if (!intel_dp_get_link_status(intel_dp, link_status)) {
+		DRM_DEBUG_KMS("failed to get link status\n");
+		return;
+	}
+
+	/* retrieve vswing & pre-emphasis setting */
+	intel_dp_get_adjust_train(intel_dp, link_status);
+
+	intel_dp_autotest_phy_ddi_disable(intel_dp);
+
+	intel_dp_set_signal_levels(intel_dp);
+
+	intel_dp_phy_pattern_update(intel_dp);
+
+	intel_dp_autotest_phy_ddi_enable(intel_dp, data->num_lanes);
+
+	drm_dp_set_phy_test_pattern(&intel_dp->aux, data,
+				    link_status[DP_DPCD_REV]);
+}
+
 static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp)
 {
-	u8 test_result = DP_TEST_NAK;
+	u8 test_result;
+
+	test_result = intel_dp_prepare_phytest(intel_dp);
+	if (test_result != DP_TEST_ACK)
+		DRM_ERROR("Phy test preparation failed\n");
+
+	intel_dp_process_phy_request(intel_dp);
+
 	return test_result;
 }
 
 static void intel_dp_handle_test_request(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 response = DP_TEST_NAK;
 	u8 request = 0;
 	int status;
 
 	status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_REQUEST, &request);
 	if (status <= 0) {
-		DRM_DEBUG_KMS("Could not read test request from sink\n");
+		drm_dbg_kms(&i915->drm,
+			    "Could not read test request from sink\n");
 		goto update_status;
 	}
 
 	switch (request) {
 	case DP_TEST_LINK_TRAINING:
-		DRM_DEBUG_KMS("LINK_TRAINING test requested\n");
+		drm_dbg_kms(&i915->drm, "LINK_TRAINING test requested\n");
 		response = intel_dp_autotest_link_training(intel_dp);
 		break;
 	case DP_TEST_LINK_VIDEO_PATTERN:
-		DRM_DEBUG_KMS("TEST_PATTERN test requested\n");
+		drm_dbg_kms(&i915->drm, "TEST_PATTERN test requested\n");
 		response = intel_dp_autotest_video_pattern(intel_dp);
 		break;
 	case DP_TEST_LINK_EDID_READ:
-		DRM_DEBUG_KMS("EDID test requested\n");
+		drm_dbg_kms(&i915->drm, "EDID test requested\n");
 		response = intel_dp_autotest_edid(intel_dp);
 		break;
 	case DP_TEST_LINK_PHY_TEST_PATTERN:
-		DRM_DEBUG_KMS("PHY_PATTERN test requested\n");
+		drm_dbg_kms(&i915->drm, "PHY_PATTERN test requested\n");
 		response = intel_dp_autotest_phy_pattern(intel_dp);
 		break;
 	default:
-		DRM_DEBUG_KMS("Invalid test request '%02x'\n", request);
+		drm_dbg_kms(&i915->drm, "Invalid test request '%02x'\n",
+			    request);
 		break;
 	}
 
@@ -5044,64 +5588,59 @@ static void intel_dp_handle_test_request(struct intel_dp *intel_dp)
 update_status:
 	status = drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_RESPONSE, response);
 	if (status <= 0)
-		DRM_DEBUG_KMS("Could not write test response to sink\n");
+		drm_dbg_kms(&i915->drm,
+			    "Could not write test response to sink\n");
 }
 
 static int
 intel_dp_check_mst_status(struct intel_dp *intel_dp)
 {
-	bool bret;
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	bool need_retrain = false;
 
-	if (intel_dp->is_mst) {
-		u8 esi[DP_DPRX_ESI_LEN] = { 0 };
-		int ret = 0;
+	if (!intel_dp->is_mst)
+		return -EINVAL;
+
+	WARN_ON_ONCE(intel_dp->active_mst_links < 0);
+
+	for (;;) {
+		u8 esi[DP_DPRX_ESI_LEN] = {};
+		bool bret, handled;
 		int retry;
-		bool handled;
 
-		WARN_ON_ONCE(intel_dp->active_mst_links < 0);
 		bret = intel_dp_get_sink_irq_esi(intel_dp, esi);
-go_again:
-		if (bret == true) {
-
-			/* check link status - esi[10] = 0x200c */
-			if (intel_dp->active_mst_links > 0 &&
-			    !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) {
-				DRM_DEBUG_KMS("channel EQ not ok, retraining\n");
-				intel_dp_start_link_train(intel_dp);
-				intel_dp_stop_link_train(intel_dp);
-			}
+		if (!bret) {
+			drm_dbg_kms(&i915->drm,
+				    "failed to get ESI - device may have failed\n");
+			return -EINVAL;
+		}
 
-			DRM_DEBUG_KMS("got esi %3ph\n", esi);
-			ret = drm_dp_mst_hpd_irq(&intel_dp->mst_mgr, esi, &handled);
-
-			if (handled) {
-				for (retry = 0; retry < 3; retry++) {
-					int wret;
-					wret = drm_dp_dpcd_write(&intel_dp->aux,
-								 DP_SINK_COUNT_ESI+1,
-								 &esi[1], 3);
-					if (wret == 3) {
-						break;
-					}
-				}
+		/* check link status - esi[10] = 0x200c */
+		if (intel_dp->active_mst_links > 0 && !need_retrain &&
+		    !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) {
+			drm_dbg_kms(&i915->drm,
+				    "channel EQ not ok, retraining\n");
+			need_retrain = true;
+		}
 
-				bret = intel_dp_get_sink_irq_esi(intel_dp, esi);
-				if (bret == true) {
-					DRM_DEBUG_KMS("got esi2 %3ph\n", esi);
-					goto go_again;
-				}
-			} else
-				ret = 0;
+		drm_dbg_kms(&i915->drm, "got esi %3ph\n", esi);
 
-			return ret;
-		} else {
-			DRM_DEBUG_KMS("failed to get ESI - device may have failed\n");
-			intel_dp->is_mst = false;
-			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr,
-							intel_dp->is_mst);
+		drm_dp_mst_hpd_irq(&intel_dp->mst_mgr, esi, &handled);
+		if (!handled)
+			break;
+
+		for (retry = 0; retry < 3; retry++) {
+			int wret;
+
+			wret = drm_dp_dpcd_write(&intel_dp->aux,
+						 DP_SINK_COUNT_ESI+1,
+						 &esi[1], 3);
+			if (wret == 3)
+				break;
 		}
 	}
-	return -EINVAL;
+
+	return need_retrain;
 }
 
 static bool
@@ -5138,20 +5677,102 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp)
 	return !drm_dp_channel_eq_ok(link_status, intel_dp->lane_count);
 }
 
+static bool intel_dp_has_connector(struct intel_dp *intel_dp,
+				   const struct drm_connector_state *conn_state)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct intel_encoder *encoder;
+	enum pipe pipe;
+
+	if (!conn_state->best_encoder)
+		return false;
+
+	/* SST */
+	encoder = &dp_to_dig_port(intel_dp)->base;
+	if (conn_state->best_encoder == &encoder->base)
+		return true;
+
+	/* MST */
+	for_each_pipe(i915, pipe) {
+		encoder = &intel_dp->mst_encoders[pipe]->base;
+		if (conn_state->best_encoder == &encoder->base)
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_dp_prep_link_retrain(struct intel_dp *intel_dp,
+				      struct drm_modeset_acquire_ctx *ctx,
+				      u32 *crtc_mask)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct drm_connector_list_iter conn_iter;
+	struct intel_connector *connector;
+	int ret = 0;
+
+	*crtc_mask = 0;
+
+	if (!intel_dp_needs_link_retrain(intel_dp))
+		return 0;
+
+	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
+	for_each_intel_connector_iter(connector, &conn_iter) {
+		struct drm_connector_state *conn_state =
+			connector->base.state;
+		struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+
+		if (!intel_dp_has_connector(intel_dp, conn_state))
+			continue;
+
+		crtc = to_intel_crtc(conn_state->crtc);
+		if (!crtc)
+			continue;
+
+		ret = drm_modeset_lock(&crtc->base.mutex, ctx);
+		if (ret)
+			break;
+
+		crtc_state = to_intel_crtc_state(crtc->base.state);
+
+		drm_WARN_ON(&i915->drm, !intel_crtc_has_dp_encoder(crtc_state));
+
+		if (!crtc_state->hw.active)
+			continue;
+
+		if (conn_state->commit &&
+		    !try_wait_for_completion(&conn_state->commit->hw_done))
+			continue;
+
+		*crtc_mask |= drm_crtc_mask(&crtc->base);
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	if (!intel_dp_needs_link_retrain(intel_dp))
+		*crtc_mask = 0;
+
+	return ret;
+}
+
+static bool intel_dp_is_connected(struct intel_dp *intel_dp)
+{
+	struct intel_connector *connector = intel_dp->attached_connector;
+
+	return connector->base.status == connector_status_connected ||
+		intel_dp->is_mst;
+}
+
 int intel_dp_retrain_link(struct intel_encoder *encoder,
 			  struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
-	struct intel_connector *connector = intel_dp->attached_connector;
-	struct drm_connector_state *conn_state;
-	struct intel_crtc_state *crtc_state;
 	struct intel_crtc *crtc;
+	u32 crtc_mask;
 	int ret;
 
-	/* FIXME handle the MST connectors as well */
-
-	if (!connector || connector->base.status != connector_status_connected)
+	if (!intel_dp_is_connected(intel_dp))
 		return 0;
 
 	ret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex,
@@ -5159,46 +5780,42 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
-	conn_state = connector->base.state;
-
-	crtc = to_intel_crtc(conn_state->crtc);
-	if (!crtc)
-		return 0;
-
-	ret = drm_modeset_lock(&crtc->base.mutex, ctx);
+	ret = intel_dp_prep_link_retrain(intel_dp, ctx, &crtc_mask);
 	if (ret)
 		return ret;
 
-	crtc_state = to_intel_crtc_state(crtc->base.state);
-
-	drm_WARN_ON(&dev_priv->drm, !intel_crtc_has_dp_encoder(crtc_state));
-
-	if (!crtc_state->hw.active)
+	if (crtc_mask == 0)
 		return 0;
 
-	if (conn_state->commit &&
-	    !try_wait_for_completion(&conn_state->commit->hw_done))
-		return 0;
+	drm_dbg_kms(&dev_priv->drm, "[ENCODER:%d:%s] retraining link\n",
+		    encoder->base.base.id, encoder->base.name);
 
-	if (!intel_dp_needs_link_retrain(intel_dp))
-		return 0;
+	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+		const struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 
-	/* Suppress underruns caused by re-training */
-	intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
-	if (crtc_state->has_pch_encoder)
-		intel_set_pch_fifo_underrun_reporting(dev_priv,
-						      intel_crtc_pch_transcoder(crtc), false);
+		/* Suppress underruns caused by re-training */
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
+		if (crtc_state->has_pch_encoder)
+			intel_set_pch_fifo_underrun_reporting(dev_priv,
+							      intel_crtc_pch_transcoder(crtc), false);
+	}
 
 	intel_dp_start_link_train(intel_dp);
 	intel_dp_stop_link_train(intel_dp);
 
-	/* Keep underrun reporting disabled until things are stable */
-	intel_wait_for_vblank(dev_priv, crtc->pipe);
+	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+		const struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 
-	intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
-	if (crtc_state->has_pch_encoder)
-		intel_set_pch_fifo_underrun_reporting(dev_priv,
-						      intel_crtc_pch_transcoder(crtc), true);
+		/* Keep underrun reporting disabled until things are stable */
+		intel_wait_for_vblank(dev_priv, crtc->pipe);
+
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
+		if (crtc_state->has_pch_encoder)
+			intel_set_pch_fifo_underrun_reporting(dev_priv,
+							      intel_crtc_pch_transcoder(crtc), true);
+	}
 
 	return 0;
 }
@@ -5217,14 +5834,13 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
  */
 static enum intel_hotplug_state
 intel_dp_hotplug(struct intel_encoder *encoder,
-		 struct intel_connector *connector,
-		 bool irq_received)
+		 struct intel_connector *connector)
 {
 	struct drm_modeset_acquire_ctx ctx;
 	enum intel_hotplug_state state;
 	int ret;
 
-	state = intel_encoder_hotplug(encoder, connector, irq_received);
+	state = intel_encoder_hotplug(encoder, connector);
 
 	drm_modeset_acquire_init(&ctx, 0);
 
@@ -5248,7 +5864,7 @@ intel_dp_hotplug(struct intel_encoder *encoder,
 	 * Keeping it consistent with intel_ddi_hotplug() and
 	 * intel_hdmi_hotplug().
 	 */
-	if (state == INTEL_HOTPLUG_UNCHANGED && irq_received)
+	if (state == INTEL_HOTPLUG_UNCHANGED && !connector->hotplug_retries)
 		state = INTEL_HOTPLUG_RETRY;
 
 	return state;
@@ -5256,6 +5872,7 @@ intel_dp_hotplug(struct intel_encoder *encoder,
 
 static void intel_dp_check_service_irq(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 val;
 
 	if (intel_dp->dpcd[DP_DPCD_REV] < 0x11)
@@ -5274,7 +5891,7 @@ static void intel_dp_check_service_irq(struct intel_dp *intel_dp)
 		intel_hdcp_handle_cp_irq(intel_dp->attached_connector);
 
 	if (val & DP_SINK_SPECIFIC_IRQ)
-		DRM_DEBUG_DRIVER("Sink specific irq unhandled\n");
+		drm_dbg_kms(&i915->drm, "Sink specific irq unhandled\n");
 }
 
 /*
@@ -5341,6 +5958,7 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 static enum drm_connector_status
 intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_lspcon *lspcon = dp_to_lspcon(intel_dp);
 	u8 *dpcd = intel_dp->dpcd;
 	u8 type;
@@ -5388,7 +6006,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 	}
 
 	/* Anything else is out of spec, warn and ignore */
-	DRM_DEBUG_KMS("Broken DP branch device, ignoring\n");
+	drm_dbg_kms(&i915->drm, "Broken DP branch device, ignoring\n");
 	return connector_status_disconnected;
 }
 
@@ -5401,64 +6019,7 @@ edp_detect(struct intel_dp *intel_dp)
 static bool ibx_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 bit;
-
-	switch (encoder->hpd_pin) {
-	case HPD_PORT_B:
-		bit = SDE_PORTB_HOTPLUG;
-		break;
-	case HPD_PORT_C:
-		bit = SDE_PORTC_HOTPLUG;
-		break;
-	case HPD_PORT_D:
-		bit = SDE_PORTD_HOTPLUG;
-		break;
-	default:
-		MISSING_CASE(encoder->hpd_pin);
-		return false;
-	}
-
-	return intel_de_read(dev_priv, SDEISR) & bit;
-}
-
-static bool cpt_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 bit;
-
-	switch (encoder->hpd_pin) {
-	case HPD_PORT_B:
-		bit = SDE_PORTB_HOTPLUG_CPT;
-		break;
-	case HPD_PORT_C:
-		bit = SDE_PORTC_HOTPLUG_CPT;
-		break;
-	case HPD_PORT_D:
-		bit = SDE_PORTD_HOTPLUG_CPT;
-		break;
-	default:
-		MISSING_CASE(encoder->hpd_pin);
-		return false;
-	}
-
-	return intel_de_read(dev_priv, SDEISR) & bit;
-}
-
-static bool spt_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 bit;
-
-	switch (encoder->hpd_pin) {
-	case HPD_PORT_A:
-		bit = SDE_PORTA_HOTPLUG_SPT;
-		break;
-	case HPD_PORT_E:
-		bit = SDE_PORTE_HOTPLUG_SPT;
-		break;
-	default:
-		return cpt_digital_port_connected(encoder);
-	}
+	u32 bit = dev_priv->hotplug.pch_hpd[encoder->hpd_pin];
 
 	return intel_de_read(dev_priv, SDEISR) & bit;
 }
@@ -5512,89 +6073,9 @@ static bool gm45_digital_port_connected(struct intel_encoder *encoder)
 static bool ilk_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin];
 
-	if (encoder->hpd_pin == HPD_PORT_A)
-		return intel_de_read(dev_priv, DEISR) & DE_DP_A_HOTPLUG;
-	else
-		return ibx_digital_port_connected(encoder);
-}
-
-static bool snb_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (encoder->hpd_pin == HPD_PORT_A)
-		return intel_de_read(dev_priv, DEISR) & DE_DP_A_HOTPLUG;
-	else
-		return cpt_digital_port_connected(encoder);
-}
-
-static bool ivb_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (encoder->hpd_pin == HPD_PORT_A)
-		return intel_de_read(dev_priv, DEISR) & DE_DP_A_HOTPLUG_IVB;
-	else
-		return cpt_digital_port_connected(encoder);
-}
-
-static bool bdw_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (encoder->hpd_pin == HPD_PORT_A)
-		return intel_de_read(dev_priv, GEN8_DE_PORT_ISR) & GEN8_PORT_DP_A_HOTPLUG;
-	else
-		return cpt_digital_port_connected(encoder);
-}
-
-static bool bxt_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 bit;
-
-	switch (encoder->hpd_pin) {
-	case HPD_PORT_A:
-		bit = BXT_DE_PORT_HP_DDIA;
-		break;
-	case HPD_PORT_B:
-		bit = BXT_DE_PORT_HP_DDIB;
-		break;
-	case HPD_PORT_C:
-		bit = BXT_DE_PORT_HP_DDIC;
-		break;
-	default:
-		MISSING_CASE(encoder->hpd_pin);
-		return false;
-	}
-
-	return intel_de_read(dev_priv, GEN8_DE_PORT_ISR) & bit;
-}
-
-static bool intel_combo_phy_connected(struct drm_i915_private *dev_priv,
-				      enum phy phy)
-{
-	if (HAS_PCH_MCC(dev_priv) && phy == PHY_C)
-		return intel_de_read(dev_priv, SDEISR) & SDE_TC_HOTPLUG_ICP(PORT_TC1);
-
-	return intel_de_read(dev_priv, SDEISR) & SDE_DDI_HOTPLUG_ICP(phy);
-}
-
-static bool icp_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
-	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-
-	if (intel_phy_is_combo(dev_priv, phy))
-		return intel_combo_phy_connected(dev_priv, phy);
-	else if (intel_phy_is_tc(dev_priv, phy))
-		return intel_tc_port_connected(dig_port);
-	else
-		MISSING_CASE(encoder->hpd_pin);
-
-	return false;
+	return intel_de_read(dev_priv, DEISR) & bit;
 }
 
 /*
@@ -5608,44 +6089,15 @@ static bool icp_digital_port_connected(struct intel_encoder *encoder)
  *
  * Return %true if port is connected, %false otherwise.
  */
-static bool __intel_digital_port_connected(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (HAS_GMCH(dev_priv)) {
-		if (IS_GM45(dev_priv))
-			return gm45_digital_port_connected(encoder);
-		else
-			return g4x_digital_port_connected(encoder);
-	}
-
-	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
-		return icp_digital_port_connected(encoder);
-	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT)
-		return spt_digital_port_connected(encoder);
-	else if (IS_GEN9_LP(dev_priv))
-		return bxt_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 8))
-		return bdw_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 7))
-		return ivb_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 6))
-		return snb_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 5))
-		return ilk_digital_port_connected(encoder);
-
-	MISSING_CASE(INTEL_GEN(dev_priv));
-	return false;
-}
-
 bool intel_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_connected = false;
 	intel_wakeref_t wakeref;
 
 	with_intel_display_power(dev_priv, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		is_connected = __intel_digital_port_connected(encoder);
+		is_connected = dig_port->connected(encoder);
 
 	return is_connected;
 }
@@ -5860,6 +6312,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	int ret;
 
@@ -5867,10 +6320,8 @@ intel_dp_connector_register(struct drm_connector *connector)
 	if (ret)
 		return ret;
 
-	intel_connector_debugfs_add(connector);
-
-	DRM_DEBUG_KMS("registering %s bus for %s\n",
-		      intel_dp->aux.name, connector->kdev->kobj.name);
+	drm_dbg_kms(&i915->drm, "registering %s bus for %s\n",
+		    intel_dp->aux.name, connector->kdev->kobj.name);
 
 	intel_dp->aux.dev = connector->kdev;
 	ret = drm_dp_aux_register(&intel_dp->aux);
@@ -5956,6 +6407,7 @@ static
 int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 				u8 *an)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(&intel_dig_port->base.base));
 	static const struct drm_dp_aux_msg msg = {
 		.request = DP_AUX_NATIVE_WRITE,
@@ -5970,8 +6422,9 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 	dpcd_ret = drm_dp_dpcd_write(&intel_dig_port->dp.aux, DP_AUX_HDCP_AN,
 				     an, DRM_HDCP_AN_LEN);
 	if (dpcd_ret != DRM_HDCP_AN_LEN) {
-		DRM_DEBUG_KMS("Failed to write An over DP/AUX (%zd)\n",
-			      dpcd_ret);
+		drm_dbg_kms(&i915->drm,
+			    "Failed to write An over DP/AUX (%zd)\n",
+			    dpcd_ret);
 		return dpcd_ret >= 0 ? -EIO : dpcd_ret;
 	}
 
@@ -5987,17 +6440,19 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 				rxbuf, sizeof(rxbuf),
 				DP_AUX_CH_CTL_AUX_AKSV_SELECT);
 	if (ret < 0) {
-		DRM_DEBUG_KMS("Write Aksv over DP/AUX failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Write Aksv over DP/AUX failed (%d)\n", ret);
 		return ret;
 	} else if (ret == 0) {
-		DRM_DEBUG_KMS("Aksv write over DP/AUX was empty\n");
+		drm_dbg_kms(&i915->drm, "Aksv write over DP/AUX was empty\n");
 		return -EIO;
 	}
 
 	reply = (rxbuf[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK;
 	if (reply != DP_AUX_NATIVE_REPLY_ACK) {
-		DRM_DEBUG_KMS("Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n",
-			      reply);
+		drm_dbg_kms(&i915->drm,
+			    "Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n",
+			    reply);
 		return -EIO;
 	}
 	return 0;
@@ -6006,11 +6461,14 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port,
 				   u8 *bksv)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
+
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BKSV, bksv,
 			       DRM_HDCP_KSV_LEN);
 	if (ret != DRM_HDCP_KSV_LEN) {
-		DRM_DEBUG_KMS("Read Bksv from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read Bksv from DP/AUX failed (%zd)\n", ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 	return 0;
@@ -6019,7 +6477,9 @@ static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port,
 static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port,
 				      u8 *bstatus)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
+
 	/*
 	 * For some reason the HDMI and DP HDCP specs call this register
 	 * definition by different names. In the HDMI spec, it's called BSTATUS,
@@ -6028,7 +6488,8 @@ static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port,
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BINFO,
 			       bstatus, DRM_HDCP_BSTATUS_LEN);
 	if (ret != DRM_HDCP_BSTATUS_LEN) {
-		DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read bstatus from DP/AUX failed (%zd)\n", ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 	return 0;
@@ -6038,12 +6499,14 @@ static
 int intel_dp_hdcp_read_bcaps(struct intel_digital_port *intel_dig_port,
 			     u8 *bcaps)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BCAPS,
 			       bcaps, 1);
 	if (ret != 1) {
-		DRM_DEBUG_KMS("Read bcaps from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read bcaps from DP/AUX failed (%zd)\n", ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 
@@ -6069,11 +6532,14 @@ static
 int intel_dp_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port,
 				u8 *ri_prime)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
+
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_RI_PRIME,
 			       ri_prime, DRM_HDCP_RI_LEN);
 	if (ret != DRM_HDCP_RI_LEN) {
-		DRM_DEBUG_KMS("Read Ri' from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read Ri' from DP/AUX failed (%zd)\n",
+			    ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 	return 0;
@@ -6083,12 +6549,15 @@ static
 int intel_dp_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port,
 				 bool *ksv_ready)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 	u8 bstatus;
+
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS,
 			       &bstatus, 1);
 	if (ret != 1) {
-		DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read bstatus from DP/AUX failed (%zd)\n", ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 	*ksv_ready = bstatus & DP_BSTATUS_READY;
@@ -6099,6 +6568,7 @@ static
 int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port,
 				int num_downstream, u8 *ksv_fifo)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 	int i;
 
@@ -6110,8 +6580,9 @@ int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port,
 				       ksv_fifo + i * DRM_HDCP_KSV_LEN,
 				       len);
 		if (ret != len) {
-			DRM_DEBUG_KMS("Read ksv[%d] from DP/AUX failed (%zd)\n",
-				      i, ret);
+			drm_dbg_kms(&i915->drm,
+				    "Read ksv[%d] from DP/AUX failed (%zd)\n",
+				    i, ret);
 			return ret >= 0 ? -EIO : ret;
 		}
 	}
@@ -6122,6 +6593,7 @@ static
 int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
 				    int i, u32 *part)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 
 	if (i >= DRM_HDCP_V_PRIME_NUM_PARTS)
@@ -6131,7 +6603,8 @@ int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
 			       DP_AUX_HDCP_V_PRIME(i), part,
 			       DRM_HDCP_V_PRIME_PART_LEN);
 	if (ret != DRM_HDCP_V_PRIME_PART_LEN) {
-		DRM_DEBUG_KMS("Read v'[%d] from DP/AUX failed (%zd)\n", i, ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read v'[%d] from DP/AUX failed (%zd)\n", i, ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 	return 0;
@@ -6148,13 +6621,15 @@ int intel_dp_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port,
 static
 bool intel_dp_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 	u8 bstatus;
 
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS,
 			       &bstatus, 1);
 	if (ret != 1) {
-		DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read bstatus from DP/AUX failed (%zd)\n", ret);
 		return false;
 	}
 
@@ -6225,17 +6700,19 @@ static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = {
 	  0, 0 },
 };
 
-static inline
-int intel_dp_hdcp2_read_rx_status(struct intel_digital_port *intel_dig_port,
-				  u8 *rx_status)
+static int
+intel_dp_hdcp2_read_rx_status(struct intel_digital_port *intel_dig_port,
+			      u8 *rx_status)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	ssize_t ret;
 
 	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux,
 			       DP_HDCP_2_2_REG_RXSTATUS_OFFSET, rx_status,
 			       HDCP_2_2_DP_RXSTATUS_LEN);
 	if (ret != HDCP_2_2_DP_RXSTATUS_LEN) {
-		DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read bstatus from DP/AUX failed (%zd)\n", ret);
 		return ret >= 0 ? -EIO : ret;
 	}
 
@@ -6279,6 +6756,7 @@ static ssize_t
 intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port,
 			    const struct hdcp2_dp_msg_data *hdcp2_msg_data)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *dp = &intel_dig_port->dp;
 	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	u8 msg_id = hdcp2_msg_data->msg_id;
@@ -6310,8 +6788,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port,
 	}
 
 	if (ret)
-		DRM_DEBUG_KMS("msg_id %d, ret %d, timeout(mSec): %d\n",
-			      hdcp2_msg_data->msg_id, ret, timeout);
+		drm_dbg_kms(&i915->drm,
+			    "msg_id %d, ret %d, timeout(mSec): %d\n",
+			    hdcp2_msg_data->msg_id, ret, timeout);
 
 	return ret;
 }
@@ -6397,6 +6876,7 @@ static
 int intel_dp_hdcp2_read_msg(struct intel_digital_port *intel_dig_port,
 			    u8 msg_id, void *buf, size_t size)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	unsigned int offset;
 	u8 *byte = buf;
 	ssize_t ret, bytes_to_recv, len;
@@ -6430,7 +6910,8 @@ int intel_dp_hdcp2_read_msg(struct intel_digital_port *intel_dig_port,
 		ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, offset,
 				       (void *)byte, len);
 		if (ret < 0) {
-			DRM_DEBUG_KMS("msg_id %d, ret %zd\n", msg_id, ret);
+			drm_dbg_kms(&i915->drm, "msg_id %d, ret %zd\n",
+				    msg_id, ret);
 			return ret;
 		}
 
@@ -6721,7 +7202,11 @@ static int intel_dp_connector_atomic_check(struct drm_connector *conn,
 	if (ret)
 		return ret;
 
-	if (INTEL_GEN(dev_priv) < 11)
+	/*
+	 * We don't enable port sync on BDW due to missing w/as and
+	 * due to not having adjusted the modeset sequence appropriately.
+	 */
+	if (INTEL_GEN(dev_priv) < 9)
 		return 0;
 
 	if (!intel_connector_needs_modeset(state, conn))
@@ -6760,28 +7245,45 @@ static const struct drm_encoder_funcs intel_dp_enc_funcs = {
 	.destroy = intel_dp_encoder_destroy,
 };
 
+static bool intel_edp_have_power(struct intel_dp *intel_dp)
+{
+	intel_wakeref_t wakeref;
+	bool have_power = false;
+
+	with_pps_lock(intel_dp, wakeref) {
+		have_power = edp_have_panel_power(intel_dp) &&
+						  edp_have_panel_vdd(intel_dp);
+	}
+
+	return have_power;
+}
+
 enum irqreturn
 intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
-	if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
+	if (intel_dig_port->base.type == INTEL_OUTPUT_EDP &&
+	    (long_hpd || !intel_edp_have_power(intel_dp))) {
 		/*
-		 * vdd off can generate a long pulse on eDP which
+		 * vdd off can generate a long/short pulse on eDP which
 		 * would require vdd on to handle it, and thus we
 		 * would end up in an endless cycle of
-		 * "vdd off -> long hpd -> vdd on -> detect -> vdd off -> ..."
+		 * "vdd off -> long/short hpd -> vdd on -> detect -> vdd off -> ..."
 		 */
-		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);
+		drm_dbg_kms(&i915->drm,
+			    "ignoring %s hpd on eDP [ENCODER:%d:%s]\n",
+			    long_hpd ? "long" : "short",
+			    intel_dig_port->base.base.base.id,
+			    intel_dig_port->base.base.name);
 		return IRQ_HANDLED;
 	}
 
-	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");
+	drm_dbg_kms(&i915->drm, "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) {
 		intel_dp->reset_link_params = true;
@@ -6789,18 +7291,25 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	}
 
 	if (intel_dp->is_mst) {
-		if (intel_dp_check_mst_status(intel_dp) == -EINVAL) {
+		switch (intel_dp_check_mst_status(intel_dp)) {
+		case -EINVAL:
 			/*
 			 * If we were in MST mode, and device is not
 			 * there, get out of MST mode
 			 */
-			DRM_DEBUG_KMS("MST device may have disappeared %d vs %d\n",
-				      intel_dp->is_mst, intel_dp->mst_mgr.mst_state);
+			drm_dbg_kms(&i915->drm,
+				    "MST device may have disappeared %d vs %d\n",
+				    intel_dp->is_mst,
+				    intel_dp->mst_mgr.mst_state);
 			intel_dp->is_mst = false;
 			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr,
 							intel_dp->is_mst);
 
 			return IRQ_NONE;
+		case 1:
+			return IRQ_NONE;
+		default:
+			break;
 		}
 	}
 
@@ -7831,6 +8340,23 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 		intel_encoder->post_disable = g4x_post_disable_dp;
 	}
 
+	if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
+	    (HAS_PCH_CPT(dev_priv) && port != PORT_A))
+		intel_dig_port->dp.set_link_train = cpt_set_link_train;
+	else
+		intel_dig_port->dp.set_link_train = g4x_set_link_train;
+
+	if (IS_CHERRYVIEW(dev_priv))
+		intel_dig_port->dp.set_signal_levels = chv_set_signal_levels;
+	else if (IS_VALLEYVIEW(dev_priv))
+		intel_dig_port->dp.set_signal_levels = vlv_set_signal_levels;
+	else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A)
+		intel_dig_port->dp.set_signal_levels = ivb_cpu_edp_set_signal_levels;
+	else if (IS_GEN(dev_priv, 6) && port == PORT_A)
+		intel_dig_port->dp.set_signal_levels = snb_cpu_edp_set_signal_levels;
+	else
+		intel_dig_port->dp.set_signal_levels = g4x_set_signal_levels;
+
 	intel_dig_port->dp.output_reg = output_reg;
 	intel_dig_port->max_lanes = 4;
 	intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port);
@@ -7851,6 +8377,18 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 
 	intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
 
+	if (HAS_GMCH(dev_priv)) {
+		if (IS_GM45(dev_priv))
+			intel_dig_port->connected = gm45_digital_port_connected;
+		else
+			intel_dig_port->connected = g4x_digital_port_connected;
+	} else {
+		if (port == PORT_A)
+			intel_dig_port->connected = ilk_digital_port_connected;
+		else
+			intel_dig_port->connected = ibx_digital_port_connected;
+	}
+
 	if (port != PORT_A)
 		intel_infoframe_init(intel_dig_port);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 0c7be8ed1423..1702959ca079 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -16,6 +16,7 @@ struct drm_connector_state;
 struct drm_encoder;
 struct drm_i915_private;
 struct drm_modeset_acquire_ctx;
+struct drm_dp_vsc_sdp;
 struct intel_connector;
 struct intel_crtc_state;
 struct intel_digital_port;
@@ -108,13 +109,21 @@ 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);
-void intel_dp_hdr_metadata_enable(struct intel_dp *intel_dp,
+void intel_dp_compute_psr_vsc_sdp(struct intel_dp *intel_dp,
 				  const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state);
+				  const struct drm_connector_state *conn_state,
+				  struct drm_dp_vsc_sdp *vsc);
+void intel_write_dp_vsc_sdp(struct intel_encoder *encoder,
+			    const struct intel_crtc_state *crtc_state,
+			    struct drm_dp_vsc_sdp *vsc);
+void intel_dp_set_infoframes(struct intel_encoder *encoder, bool enable,
+			     const struct intel_crtc_state *crtc_state,
+			     const struct drm_connector_state *conn_state);
+void intel_read_dp_sdp(struct intel_encoder *encoder,
+		       struct intel_crtc_state *crtc_state,
+		       unsigned int type);
 bool intel_digital_port_connected(struct intel_encoder *encoder);
+void intel_dp_process_phy_request(struct intel_dp *intel_dp);
 
 static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index dbfa6895795b..0722540d64ad 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -27,6 +27,7 @@
 
 static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 reg_val = 0;
 
 	/* Early return when display use other mechanism to enable backlight. */
@@ -35,8 +36,8 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
 			      &reg_val) < 0) {
-		DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n",
-			      DP_EDP_DISPLAY_CONTROL_REGISTER);
+		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
+			    DP_EDP_DISPLAY_CONTROL_REGISTER);
 		return;
 	}
 	if (enable)
@@ -46,8 +47,8 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
 			       reg_val) != 1) {
-		DRM_DEBUG_KMS("Failed to %s aux backlight\n",
-			      enable ? "enable" : "disable");
+		drm_dbg_kms(&i915->drm, "Failed to %s aux backlight\n",
+			    enable ? "enable" : "disable");
 	}
 }
 
@@ -58,6 +59,7 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 read_val[2] = { 0x0 };
 	u8 mode_reg;
 	u16 level = 0;
@@ -65,8 +67,9 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_EDP_BACKLIGHT_MODE_SET_REGISTER,
 			      &mode_reg) != 1) {
-		DRM_DEBUG_KMS("Failed to read the DPCD register 0x%x\n",
-			      DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
+		drm_dbg_kms(&i915->drm,
+			    "Failed to read the DPCD register 0x%x\n",
+			    DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
 		return 0;
 	}
 
@@ -80,8 +83,8 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
 			     &read_val, sizeof(read_val)) < 0) {
-		DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n",
-			      DP_EDP_BACKLIGHT_BRIGHTNESS_MSB);
+		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
+			    DP_EDP_BACKLIGHT_BRIGHTNESS_MSB);
 		return 0;
 	}
 	level = read_val[0];
@@ -100,6 +103,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 vals[2] = { 0x0 };
 
 	vals[0] = level;
@@ -111,7 +115,8 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 	}
 	if (drm_dp_dpcd_write(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
 			      vals, sizeof(vals)) < 0) {
-		DRM_DEBUG_KMS("Failed to write aux backlight level\n");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to write aux backlight level\n");
 		return;
 	}
 }
@@ -133,7 +138,8 @@ static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector)
 
 	freq = dev_priv->vbt.backlight.pwm_freq_hz;
 	if (!freq) {
-		DRM_DEBUG_KMS("Use panel default backlight frequency\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Use panel default backlight frequency\n");
 		return false;
 	}
 
@@ -146,13 +152,14 @@ static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector)
 	fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4);
 
 	if (fxp_min > fxp_actual || fxp_actual > fxp_max) {
-		DRM_DEBUG_KMS("Actual frequency out of range\n");
+		drm_dbg_kms(&dev_priv->drm, "Actual frequency out of range\n");
 		return false;
 	}
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux,
 			       DP_EDP_BACKLIGHT_FREQ_SET, (u8) f) < 0) {
-		DRM_DEBUG_KMS("Failed to write aux backlight freq\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Failed to write aux backlight freq\n");
 		return false;
 	}
 	return true;
@@ -163,13 +170,14 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_panel *panel = &connector->panel;
 	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) {
-		DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n",
-			      DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
+		drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n",
+			    DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
 		return;
 	}
 
@@ -186,7 +194,8 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 		if (drm_dp_dpcd_writeb(&intel_dp->aux,
 				       DP_EDP_PWMGEN_BIT_COUNT,
 				       panel->backlight.pwmgen_bit_count) < 0)
-			DRM_DEBUG_KMS("Failed to write aux pwmgen bit count\n");
+			drm_dbg_kms(&i915->drm,
+				    "Failed to write aux pwmgen bit count\n");
 
 		break;
 
@@ -203,7 +212,8 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 	if (new_dpcd_buf != dpcd_buf) {
 		if (drm_dp_dpcd_writeb(&intel_dp->aux,
 			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf) < 0) {
-			DRM_DEBUG_KMS("Failed to write aux backlight mode\n");
+			drm_dbg_kms(&i915->drm,
+				    "Failed to write aux backlight mode\n");
 		}
 	}
 
@@ -237,9 +247,11 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector)
 	 * minimum value will applied automatically. So no need to check that.
 	 */
 	freq = i915->vbt.backlight.pwm_freq_hz;
-	DRM_DEBUG_KMS("VBT defined backlight frequency %u Hz\n", freq);
+	drm_dbg_kms(&i915->drm, "VBT defined backlight frequency %u Hz\n",
+		    freq);
 	if (!freq) {
-		DRM_DEBUG_KMS("Use panel default backlight frequency\n");
+		drm_dbg_kms(&i915->drm,
+			    "Use panel default backlight frequency\n");
 		return max_backlight;
 	}
 
@@ -254,12 +266,14 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector)
 	 */
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min) != 1) {
-		DRM_DEBUG_KMS("Failed to read pwmgen bit count cap min\n");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to read pwmgen bit count cap min\n");
 		return max_backlight;
 	}
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max) != 1) {
-		DRM_DEBUG_KMS("Failed to read pwmgen bit count cap max\n");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to read pwmgen bit count cap max\n");
 		return max_backlight;
 	}
 	pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK;
@@ -268,7 +282,8 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector)
 	fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4);
 	fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4);
 	if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) {
-		DRM_DEBUG_KMS("VBT defined backlight frequency out of range\n");
+		drm_dbg_kms(&i915->drm,
+			    "VBT defined backlight frequency out of range\n");
 		return max_backlight;
 	}
 
@@ -279,10 +294,11 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector)
 			break;
 	}
 
-	DRM_DEBUG_KMS("Using eDP pwmgen bit count of %d\n", pn);
+	drm_dbg_kms(&i915->drm, "Using eDP pwmgen bit count of %d\n", pn);
 	if (drm_dp_dpcd_writeb(&intel_dp->aux,
 			       DP_EDP_PWMGEN_BIT_COUNT, pn) < 0) {
-		DRM_DEBUG_KMS("Failed to write aux pwmgen bit count\n");
+		drm_dbg_kms(&i915->drm,
+			    "Failed to write aux pwmgen bit count\n");
 		return max_backlight;
 	}
 	panel->backlight.pwmgen_bit_count = pn;
@@ -312,6 +328,7 @@ static bool
 intel_dp_aux_display_control_capable(struct intel_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
 	/* Check the eDP Display control capabilities registers to determine if
 	 * the panel can support backlight control over the aux channel
@@ -319,7 +336,7 @@ intel_dp_aux_display_control_capable(struct intel_connector *connector)
 	if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP &&
 	    (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP) &&
 	    !(intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP)) {
-		DRM_DEBUG_KMS("AUX Backlight Control Supported!\n");
+		drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n");
 		return true;
 	}
 	return false;
@@ -329,8 +346,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector)
 {
 	struct intel_panel *panel = &intel_connector->panel;
 	struct intel_dp *intel_dp = enc_to_intel_dp(intel_connector->encoder);
-	struct drm_device *dev = intel_connector->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
 	if (i915_modparams.enable_dpcd_backlight == 0 ||
 	    !intel_dp_aux_display_control_capable(intel_connector))
@@ -340,18 +356,18 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector)
 	 * There are a lot of machines that don't advertise the backlight
 	 * control interface to use properly in their VBIOS, :\
 	 */
-	if (dev_priv->vbt.backlight.type !=
+	if (i915->vbt.backlight.type !=
 	    INTEL_BACKLIGHT_VESA_EDP_AUX_INTERFACE &&
 	    i915_modparams.enable_dpcd_backlight != 1 &&
 	    !drm_dp_has_quirk(&intel_dp->desc, intel_dp->edid_quirks,
 			      DP_QUIRK_FORCE_DPCD_BACKLIGHT)) {
-		DRM_DEV_INFO(dev->dev,
-			     "Panel advertises DPCD backlight support, but "
-			     "VBT disagrees. If your backlight controls "
-			     "don't work try booting with "
-			     "i915.enable_dpcd_backlight=1. If your machine "
-			     "needs this, please file a _new_ bug report on "
-			     "drm/i915, see " FDO_BUG_URL " for details.\n");
+		drm_info(&i915->drm,
+			 "Panel advertises DPCD backlight support, but "
+			 "VBT disagrees. If your backlight controls "
+			 "don't work try booting with "
+			 "i915.enable_dpcd_backlight=1. If your machine "
+			 "needs this, please file a _new_ bug report on "
+			 "drm/i915, see " FDO_BUG_URL " for details.\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index a7defb37ab00..e4f1843170b7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -34,9 +34,8 @@ intel_dp_dump_link_status(const u8 link_status[DP_LINK_STATUS_SIZE])
 		      link_status[3], link_status[4], link_status[5]);
 }
 
-static void
-intel_get_adjust_train(struct intel_dp *intel_dp,
-		       const u8 link_status[DP_LINK_STATUS_SIZE])
+void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
+			       const u8 link_status[DP_LINK_STATUS_SIZE])
 {
 	u8 v = 0;
 	u8 p = 0;
@@ -219,7 +218,7 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 		voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK;
 
 		/* Update training set as requested by target */
-		intel_get_adjust_train(intel_dp, link_status);
+		intel_dp_get_adjust_train(intel_dp, link_status);
 		if (!intel_dp_update_link_train(intel_dp)) {
 			drm_err(&i915->drm,
 				"failed to update link training\n");
@@ -338,7 +337,7 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 		}
 
 		/* Update training set as requested by target */
-		intel_get_adjust_train(intel_dp, link_status);
+		intel_dp_get_adjust_train(intel_dp, link_status);
 		if (!intel_dp_update_link_train(intel_dp)) {
 			drm_err(&i915->drm,
 				"failed to update link training\n");
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
index 174566adcc92..01f1dabbb060 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
@@ -6,8 +6,12 @@
 #ifndef __INTEL_DP_LINK_TRAINING_H__
 #define __INTEL_DP_LINK_TRAINING_H__
 
+#include <drm/drm_dp_helper.h>
+
 struct intel_dp;
 
+void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
+			       const u8 link_status[DP_LINK_STATUS_SIZE]);
 void intel_dp_start_link_train(struct intel_dp *intel_dp);
 void intel_dp_stop_link_train(struct intel_dp *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 44f3fd251ca1..d18b406f2a7d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -47,9 +47,9 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
-	void *port = connector->port;
 	bool constant_n = drm_dp_has_quirk(&intel_dp->desc, 0,
 					   DP_DPCD_QUIRK_CONSTANT_N);
 	int bpp, slots = -EINVAL;
@@ -65,7 +65,8 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 						       false);
 
 		slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
-						      port, crtc_state->pbn, 0);
+						      connector->port,
+						      crtc_state->pbn, 0);
 		if (slots == -EDEADLK)
 			return slots;
 		if (slots >= 0)
@@ -73,7 +74,8 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	}
 
 	if (slots < 0) {
-		DRM_DEBUG_KMS("failed finding vcpi slots:%d\n", slots);
+		drm_dbg_kms(&i915->drm, "failed finding vcpi slots:%d\n",
+			    slots);
 		return slots;
 	}
 
@@ -88,56 +90,10 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-/*
- * Iterate over all connectors and return the smallest transcoder in the MST
- * stream
- */
-static enum transcoder
-intel_dp_mst_master_trans_compute(struct intel_atomic_state *state,
-				  struct intel_dp *mst_port)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct intel_digital_connector_state *conn_state;
-	struct intel_connector *connector;
-	enum pipe ret = I915_MAX_PIPES;
-	int i;
-
-	if (INTEL_GEN(dev_priv) < 12)
-		return INVALID_TRANSCODER;
-
-	for_each_new_intel_connector_in_state(state, connector, conn_state, i) {
-		struct intel_crtc_state *crtc_state;
-		struct intel_crtc *crtc;
-
-		if (connector->mst_port != mst_port || !conn_state->base.crtc)
-			continue;
-
-		crtc = to_intel_crtc(conn_state->base.crtc);
-		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
-		if (!crtc_state->uapi.active)
-			continue;
-
-		/*
-		 * Using crtc->pipe because crtc_state->cpu_transcoder is
-		 * computed, so others CRTCs could have non-computed
-		 * cpu_transcoder
-		 */
-		if (crtc->pipe < ret)
-			ret = crtc->pipe;
-	}
-
-	if (ret == I915_MAX_PIPES)
-		return INVALID_TRANSCODER;
-
-	/* Simple cast works because TGL don't have a eDP transcoder */
-	return (enum transcoder)ret;
-}
-
 static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state)
 {
-	struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
@@ -147,7 +103,6 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
 		&pipe_config->hw.adjusted_mode;
-	void *port = connector->port;
 	struct link_config_limits limits;
 	int ret;
 
@@ -158,8 +113,7 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	pipe_config->has_pch_encoder = false;
 
 	if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
-		pipe_config->has_audio =
-			drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, port);
+		pipe_config->has_audio = connector->port->has_audio;
 	else
 		pipe_config->has_audio =
 			intel_conn_state->force_audio == HDMI_AUDIO_ON;
@@ -201,7 +155,56 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 
 	intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
 
-	pipe_config->mst_master_transcoder = intel_dp_mst_master_trans_compute(state, intel_dp);
+	return 0;
+}
+
+/*
+ * Iterate over all connectors and return a mask of
+ * all CPU transcoders streaming over the same DP link.
+ */
+static unsigned int
+intel_dp_mst_transcoder_mask(struct intel_atomic_state *state,
+			     struct intel_dp *mst_port)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	const struct intel_digital_connector_state *conn_state;
+	struct intel_connector *connector;
+	u8 transcoders = 0;
+	int i;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return 0;
+
+	for_each_new_intel_connector_in_state(state, connector, conn_state, i) {
+		const struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+
+		if (connector->mst_port != mst_port || !conn_state->base.crtc)
+			continue;
+
+		crtc = to_intel_crtc(conn_state->base.crtc);
+		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+
+		if (!crtc_state->hw.active)
+			continue;
+
+		transcoders |= BIT(crtc_state->cpu_transcoder);
+	}
+
+	return transcoders;
+}
+
+static int intel_dp_mst_compute_config_late(struct intel_encoder *encoder,
+					    struct intel_crtc_state *crtc_state,
+					    struct drm_connector_state *conn_state)
+{
+	struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
+	struct intel_dp *intel_dp = &intel_mst->primary->dp;
+
+	/* lowest numbered transcoder will be designated master */
+	crtc_state->mst_master_transcoder =
+		ffs(intel_dp_mst_transcoder_mask(state, intel_dp)) - 1;
 
 	return 0;
 }
@@ -313,7 +316,8 @@ intel_dp_mst_atomic_check(struct drm_connector *connector,
 	return ret;
 }
 
-static void intel_mst_disable_dp(struct intel_encoder *encoder,
+static void intel_mst_disable_dp(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
@@ -322,22 +326,25 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_connector *connector =
 		to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	int ret;
 
-	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
+	drm_dbg_kms(&i915->drm, "active links %d\n",
+		    intel_dp->active_mst_links);
 
 	drm_dp_mst_reset_vcpi_slots(&intel_dp->mst_mgr, connector->port);
 
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 	if (ret) {
-		DRM_DEBUG_KMS("failed to update payload %d\n", ret);
+		drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret);
 	}
 	if (old_crtc_state->has_audio)
 		intel_audio_codec_disable(encoder,
 					  old_crtc_state, old_conn_state);
 }
 
-static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
+static void intel_mst_post_disable_dp(struct intel_atomic_state *state,
+				      struct intel_encoder *encoder,
 				      const struct intel_crtc_state *old_crtc_state,
 				      const struct drm_connector_state *old_conn_state)
 {
@@ -371,7 +378,8 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
 
 	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 when disabling\n");
+		drm_err(&dev_priv->drm,
+			"Timed out waiting for ACT sent when disabling\n");
 	drm_dp_check_act_status(&intel_dp->mst_mgr);
 
 	drm_dp_mst_deallocate_vcpi(&intel_dp->mst_mgr, connector->port);
@@ -402,13 +410,15 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
 
 	intel_mst->connector = NULL;
 	if (last_mst_stream)
-		intel_dig_port->base.post_disable(&intel_dig_port->base,
+		intel_dig_port->base.post_disable(state, &intel_dig_port->base,
 						  old_crtc_state, NULL);
 
-	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
+	drm_dbg_kms(&dev_priv->drm, "active links %d\n",
+		    intel_dp->active_mst_links);
 }
 
-static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
+static void intel_mst_pre_pll_enable_dp(struct intel_atomic_state *state,
+					struct intel_encoder *encoder,
 					const struct intel_crtc_state *pipe_config,
 					const struct drm_connector_state *conn_state)
 {
@@ -417,11 +427,12 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
 	if (intel_dp->active_mst_links == 0)
-		intel_dig_port->base.pre_pll_enable(&intel_dig_port->base,
+		intel_dig_port->base.pre_pll_enable(state, &intel_dig_port->base,
 						    pipe_config, NULL);
 }
 
-static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
+static void intel_mst_pre_enable_dp(struct intel_atomic_state *state,
+				    struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
@@ -445,7 +456,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 		    INTEL_GEN(dev_priv) >= 12 && first_mst_stream &&
 		    !intel_dp_mst_is_master_trans(pipe_config));
 
-	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
+	drm_dbg_kms(&dev_priv->drm, "active links %d\n",
+		    intel_dp->active_mst_links);
 
 	if (first_mst_stream)
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
@@ -453,7 +465,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true);
 
 	if (first_mst_stream)
-		intel_dig_port->base.pre_enable(&intel_dig_port->base,
+		intel_dig_port->base.pre_enable(state, &intel_dig_port->base,
 						pipe_config, NULL);
 
 	ret = drm_dp_mst_allocate_vcpi(&intel_dp->mst_mgr,
@@ -461,7 +473,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 				       pipe_config->pbn,
 				       pipe_config->dp_m_n.tu);
 	if (!ret)
-		DRM_ERROR("failed to allocate vcpi\n");
+		drm_err(&dev_priv->drm, "failed to allocate vcpi\n");
 
 	intel_dp->active_mst_links++;
 	temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_status);
@@ -477,14 +489,15 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 	 * here for the following ones.
 	 */
 	if (INTEL_GEN(dev_priv) < 12 || !first_mst_stream)
-		intel_ddi_enable_pipe_clock(pipe_config);
+		intel_ddi_enable_pipe_clock(encoder, pipe_config);
 
 	intel_ddi_set_dp_msa(pipe_config, conn_state);
 
 	intel_dp_set_m_n(pipe_config, M1_N1);
 }
 
-static void intel_mst_enable_dp(struct intel_encoder *encoder,
+static void intel_mst_enable_dp(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
@@ -495,19 +508,23 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 
 	drm_WARN_ON(&dev_priv->drm, pipe_config->has_pch_encoder);
 
-	intel_enable_pipe(pipe_config);
-
-	intel_crtc_vblank_on(pipe_config);
+	intel_ddi_enable_transcoder_func(encoder, pipe_config);
 
-	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
+	drm_dbg_kms(&dev_priv->drm, "active links %d\n",
+		    intel_dp->active_mst_links);
 
 	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");
+		drm_err(&dev_priv->drm, "Timed out waiting for ACT sent\n");
 
 	drm_dp_check_act_status(&intel_dp->mst_mgr);
 
 	drm_dp_update_payload_part2(&intel_dp->mst_mgr);
+
+	intel_enable_pipe(pipe_config);
+
+	intel_crtc_vblank_on(pipe_config);
+
 	if (pipe_config->has_audio)
 		intel_audio_codec_enable(encoder, pipe_config, conn_state);
 }
@@ -786,6 +803,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->pipe_mask = ~0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
+	intel_encoder->compute_config_late = intel_dp_mst_compute_config_late;
 	intel_encoder->disable = intel_mst_disable_dp;
 	intel_encoder->post_disable = intel_mst_post_disable_dp;
 	intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp;
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 2d47f1f756a2..b45185b80bec 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -80,7 +80,7 @@ intel_atomic_get_shared_dpll_state(struct drm_atomic_state *s)
 {
 	struct intel_atomic_state *state = to_intel_atomic_state(s);
 
-	WARN_ON(!drm_modeset_is_locked(&s->dev->mode_config.connection_mutex));
+	drm_WARN_ON(s->dev, !drm_modeset_is_locked(&s->dev->mode_config.connection_mutex));
 
 	if (!state->dpll_set) {
 		state->dpll_set = true;
@@ -979,7 +979,7 @@ hsw_ddi_spll_get_dpll(struct intel_atomic_state *state,
 	struct intel_crtc_state *crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
 
-	if (WARN_ON(crtc_state->port_clock / 2 != 135000))
+	if (drm_WARN_ON(crtc->base.dev, crtc_state->port_clock / 2 != 135000))
 		return NULL;
 
 	crtc_state->dpll_hw_state.spll = SPLL_PLL_ENABLE | SPLL_FREQ_1350MHz |
@@ -1616,7 +1616,7 @@ static int skl_ddi_wrpll_get_freq(struct drm_i915_private *i915,
 	dco_freq += ((pll_state->cfgcr1 & DPLL_CFGCR1_DCO_FRACTION_MASK) >> 9) *
 		    ref_clock / 0x8000;
 
-	if (WARN_ON(p0 == 0 || p1 == 0 || p2 == 0))
+	if (drm_WARN_ON(&i915->drm, p0 == 0 || p1 == 0 || p2 == 0))
 		return 0;
 
 	return dco_freq / (p0 * p1 * p2 * 5);
@@ -2074,7 +2074,7 @@ bxt_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state,
 
 	clk_div->p1 = best_clock.p1;
 	clk_div->p2 = best_clock.p2;
-	WARN_ON(best_clock.m1 != 2);
+	drm_WARN_ON(&i915->drm, best_clock.m1 != 2);
 	clk_div->n = best_clock.n;
 	clk_div->m2_int = best_clock.m2 >> 22;
 	clk_div->m2_frac = best_clock.m2 & ((1 << 22) - 1);
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index d7a6bf2277df..29fec6a92d17 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -34,7 +34,7 @@
 #define DSB_BYTE_EN_SHIFT		20
 #define DSB_REG_VALUE_MASK		0xfffff
 
-static inline bool is_dsb_busy(struct intel_dsb *dsb)
+static 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);
@@ -43,7 +43,7 @@ static inline bool is_dsb_busy(struct intel_dsb *dsb)
 	return DSB_STATUS & intel_de_read(dev_priv, DSB_CTRL(pipe, dsb->id));
 }
 
-static inline bool intel_dsb_enable_engine(struct intel_dsb *dsb)
+static 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);
@@ -63,7 +63,7 @@ static inline bool intel_dsb_enable_engine(struct intel_dsb *dsb)
 	return true;
 }
 
-static inline bool intel_dsb_disable_engine(struct intel_dsb *dsb)
+static 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);
diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c
index a2a937109a5a..afa4e6817e8c 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi.c
@@ -31,20 +31,21 @@ int intel_dsi_tlpx_ns(const struct intel_dsi *intel_dsi)
 
 int intel_dsi_get_modes(struct drm_connector *connector)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_display_mode *mode;
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(&i915->drm, "\n");
 
 	if (!intel_connector->panel.fixed_mode) {
-		DRM_DEBUG_KMS("no fixed mode\n");
+		drm_dbg_kms(&i915->drm, "no fixed mode\n");
 		return 0;
 	}
 
 	mode = drm_mode_duplicate(connector->dev,
 				  intel_connector->panel.fixed_mode);
 	if (!mode) {
-		DRM_DEBUG_KMS("drm_mode_duplicate failed\n");
+		drm_dbg_kms(&i915->drm, "drm_mode_duplicate failed\n");
 		return 0;
 	}
 
@@ -60,7 +61,7 @@ enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector,
 	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(&dev_priv->drm, "\n");
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index 574dcfec9577..eed037ec0b29 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -121,7 +121,7 @@ struct i2c_adapter_lookup {
 #define  ICL_GPIO_DDPA_CTRLCLK_2	8
 #define  ICL_GPIO_DDPA_CTRLDATA_2	9
 
-static inline enum port intel_dsi_seq_port_to_port(u8 port)
+static enum port intel_dsi_seq_port_to_port(u8 port)
 {
 	return port ? PORT_C : PORT_A;
 }
@@ -453,8 +453,7 @@ static inline void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi,
 
 static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 {
-	struct drm_device *drm_dev = intel_dsi->base.base.dev;
-	struct device *dev = &drm_dev->pdev->dev;
+	struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev);
 	struct i2c_adapter *adapter;
 	struct i2c_msg msg;
 	int ret;
@@ -471,7 +470,7 @@ static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 
 	adapter = i2c_get_adapter(intel_dsi->i2c_bus_num);
 	if (!adapter) {
-		DRM_DEV_ERROR(dev, "Cannot find a valid i2c bus for xfer\n");
+		drm_err(&i915->drm, "Cannot find a valid i2c bus for xfer\n");
 		goto err_bus;
 	}
 
@@ -489,9 +488,9 @@ static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 
 	ret = i2c_transfer(adapter, &msg, 1);
 	if (ret < 0)
-		DRM_DEV_ERROR(dev,
-			      "Failed to xfer payload of size (%u) to reg (%u)\n",
-			      payload_size, reg_offset);
+		drm_err(&i915->drm,
+			"Failed to xfer payload of size (%u) to reg (%u)\n",
+			payload_size, reg_offset);
 
 	kfree(payload_data);
 err_alloc:
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 341d5ce8b062..5cd09034519b 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -183,7 +183,8 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
-static void intel_disable_dvo(struct intel_encoder *encoder,
+static void intel_disable_dvo(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
@@ -197,7 +198,8 @@ static void intel_disable_dvo(struct intel_encoder *encoder,
 	intel_de_read(dev_priv, dvo_reg);
 }
 
-static void intel_enable_dvo(struct intel_encoder *encoder,
+static void intel_enable_dvo(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *pipe_config,
 			     const struct drm_connector_state *conn_state)
 {
@@ -272,7 +274,8 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void intel_dvo_pre_enable(struct intel_encoder *encoder,
+static void intel_dvo_pre_enable(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index c125ca9ab9b3..1c26673acb2d 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -104,7 +104,7 @@ static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv)
 	/* Wait for compressing bit to clear */
 	if (intel_de_wait_for_clear(dev_priv, FBC_STATUS,
 				    FBC_STAT_COMPRESSING, 10)) {
-		DRM_DEBUG_KMS("FBC idle timed out\n");
+		drm_dbg_kms(&dev_priv->drm, "FBC idle timed out\n");
 		return;
 	}
 }
@@ -485,7 +485,8 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
+		drm_info_once(&dev_priv->drm,
+			      "Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;
@@ -520,8 +521,9 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 			       dev_priv->dsm.start + compressed_llb->start);
 	}
 
-	DRM_DEBUG_KMS("reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n",
-		      fbc->compressed_fb.size, fbc->threshold);
+	drm_dbg_kms(&dev_priv->drm,
+		    "reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n",
+		    fbc->compressed_fb.size, fbc->threshold);
 
 	return 0;
 
@@ -530,7 +532,7 @@ err_fb:
 	i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
 err_llb:
 	if (drm_mm_initialized(&dev_priv->mm.stolen))
-		pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
+		drm_info_once(&dev_priv->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
 	return -ENOSPC;
 }
 
@@ -538,6 +540,9 @@ static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
+	if (WARN_ON(intel_fbc_hw_is_active(dev_priv)))
+		return;
+
 	if (!drm_mm_node_allocated(&fbc->compressed_fb))
 		return;
 
@@ -562,7 +567,7 @@ void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 }
 
 static bool stride_is_valid(struct drm_i915_private *dev_priv,
-			    unsigned int stride)
+			    u64 modifier, unsigned int stride)
 {
 	/* This should have been caught earlier. */
 	if (drm_WARN_ON_ONCE(&dev_priv->drm, (stride & (64 - 1)) != 0))
@@ -578,6 +583,11 @@ static bool stride_is_valid(struct drm_i915_private *dev_priv,
 	if (IS_GEN(dev_priv, 4) && !IS_G4X(dev_priv) && stride < 2048)
 		return false;
 
+	/* Display WA #1105: skl,bxt,kbl,cfl,glk */
+	if (IS_GEN(dev_priv, 9) &&
+	    modifier == DRM_FORMAT_MOD_LINEAR && stride & 511)
+		return false;
+
 	if (stride > 16384)
 		return false;
 
@@ -605,6 +615,19 @@ static bool pixel_format_is_valid(struct drm_i915_private *dev_priv,
 	}
 }
 
+static bool rotation_is_valid(struct drm_i915_private *dev_priv,
+			      u32 pixel_format, unsigned int rotation)
+{
+	if (INTEL_GEN(dev_priv) >= 9 && pixel_format == DRM_FORMAT_RGB565 &&
+	    drm_rotation_90_or_270(rotation))
+		return false;
+	else if (INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv) &&
+		 rotation != DRM_MODE_ROTATE_0)
+		return false;
+
+	return true;
+}
+
 /*
  * For some reason, the hardware tracking starts looking at whatever we
  * programmed as the display plane base address register. It does not look at
@@ -639,6 +662,22 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 	return effective_w <= max_w && effective_h <= max_h;
 }
 
+static bool tiling_is_valid(struct drm_i915_private *dev_priv,
+			    uint64_t modifier)
+{
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+		if (INTEL_GEN(dev_priv) >= 9)
+			return true;
+		return false;
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 					 const struct intel_crtc_state *crtc_state,
 					 const struct intel_plane_state *plane_state)
@@ -672,6 +711,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 
 	cache->fb.format = fb->format;
 	cache->fb.stride = fb->pitches[0];
+	cache->fb.modifier = fb->modifier;
 
 	drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE &&
 		    !plane_state->vma->fence);
@@ -745,30 +785,40 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 		return false;
 	}
 
-	/* The use of a CPU fence is mandatory in order to detect writes
-	 * by the CPU to the scanout and trigger updates to the FBC.
+	/* The use of a CPU fence is one of two ways to detect writes by the
+	 * CPU to the scanout and trigger updates to the FBC.
+	 *
+	 * The other method is by software tracking (see
+	 * intel_fbc_invalidate/flush()), it will manually notify FBC and nuke
+	 * the current compressed buffer and recompress it.
 	 *
 	 * Note that is possible for a tiled surface to be unmappable (and
-	 * so have no fence associated with it) due to aperture constaints
+	 * so have no fence associated with it) due to aperture constraints
 	 * at the time of pinning.
 	 *
 	 * FIXME with 90/270 degree rotation we should use the fence on
 	 * the normal GTT view (the rotated view doesn't even have a
 	 * fence). Would need changes to the FBC fence Y offset as well.
-	 * For now this will effecively disable FBC with 90/270 degree
+	 * For now this will effectively disable FBC with 90/270 degree
 	 * rotation.
 	 */
-	if (cache->fence_id < 0) {
+	if (INTEL_GEN(dev_priv) < 9 && cache->fence_id < 0) {
 		fbc->no_fbc_reason = "framebuffer not tiled or fenced";
 		return false;
 	}
-	if (INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv) &&
-	    cache->plane.rotation != DRM_MODE_ROTATE_0) {
+
+	if (!rotation_is_valid(dev_priv, cache->fb.format->format,
+			       cache->plane.rotation)) {
 		fbc->no_fbc_reason = "rotation unsupported";
 		return false;
 	}
 
-	if (!stride_is_valid(dev_priv, cache->fb.stride)) {
+	if (!tiling_is_valid(dev_priv, cache->fb.modifier)) {
+		fbc->no_fbc_reason = "tiling unsupported";
+		return false;
+	}
+
+	if (!stride_is_valid(dev_priv, cache->fb.modifier, cache->fb.stride)) {
 		fbc->no_fbc_reason = "framebuffer stride not supported";
 		return false;
 	}
@@ -947,7 +997,8 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
 	drm_WARN_ON(&dev_priv->drm, !fbc->crtc);
 	drm_WARN_ON(&dev_priv->drm, fbc->active);
 
-	DRM_DEBUG_KMS("Disabling FBC on pipe %c\n", pipe_name(crtc->pipe));
+	drm_dbg_kms(&dev_priv->drm, "Disabling FBC on pipe %c\n",
+		    pipe_name(crtc->pipe));
 
 	__intel_fbc_cleanup_cfb(dev_priv);
 
@@ -1175,7 +1226,8 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 	else
 		cache->gen9_wa_cfb_stride = 0;
 
-	DRM_DEBUG_KMS("Enabling FBC on pipe %c\n", pipe_name(crtc->pipe));
+	drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n",
+		    pipe_name(crtc->pipe));
 	fbc->no_fbc_reason = "FBC enabled but not active yet\n";
 
 	fbc->crtc = crtc;
@@ -1237,7 +1289,7 @@ static void intel_fbc_underrun_work_fn(struct work_struct *work)
 	if (fbc->underrun_detected || !fbc->crtc)
 		goto out;
 
-	DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n");
+	drm_dbg_kms(&dev_priv->drm, "Disabling FBC due to FIFO underrun.\n");
 	fbc->underrun_detected = true;
 
 	intel_fbc_deactivate(dev_priv, "FIFO underrun");
@@ -1263,7 +1315,8 @@ int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv)
 		return ret;
 
 	if (dev_priv->fbc.underrun_detected) {
-		DRM_DEBUG_KMS("Re-allowing FBC after fifo underrun\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Re-allowing FBC after fifo underrun\n");
 		dev_priv->fbc.no_fbc_reason = "FIFO underrun cleared";
 	}
 
@@ -1334,7 +1387,8 @@ static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv)
 	/* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */
 	if (intel_vtd_active() &&
 	    (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) {
-		DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n");
+		drm_info(&dev_priv->drm,
+			 "Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n");
 		return true;
 	}
 
@@ -1362,8 +1416,8 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 		mkwrite_device_info(dev_priv)->display.has_fbc = false;
 
 	i915_modparams.enable_fbc = intel_sanitize_fbc_option(dev_priv);
-	DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n",
-		      i915_modparams.enable_fbc);
+	drm_dbg_kms(&dev_priv->drm, "Sanitized enable_fbc value: %d\n",
+		    i915_modparams.enable_fbc);
 
 	if (!HAS_FBC(dev_priv)) {
 		fbc->no_fbc_reason = "unsupported by this chipset";
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 3bc804212a99..bd39eb6a21b8 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -146,7 +146,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	if (IS_ERR(obj))
 		obj = i915_gem_object_create_shmem(dev_priv, size);
 	if (IS_ERR(obj)) {
-		DRM_ERROR("failed to allocate framebuffer\n");
+		drm_err(&dev_priv->drm, "failed to allocate framebuffer\n");
 		return PTR_ERR(obj);
 	}
 
@@ -183,21 +183,23 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	if (intel_fb &&
 	    (sizes->fb_width > intel_fb->base.width ||
 	     sizes->fb_height > intel_fb->base.height)) {
-		DRM_DEBUG_KMS("BIOS fb too small (%dx%d), we require (%dx%d),"
-			      " releasing it\n",
-			      intel_fb->base.width, intel_fb->base.height,
-			      sizes->fb_width, sizes->fb_height);
+		drm_dbg_kms(&dev_priv->drm,
+			    "BIOS fb too small (%dx%d), we require (%dx%d),"
+			    " releasing it\n",
+			    intel_fb->base.width, intel_fb->base.height,
+			    sizes->fb_width, sizes->fb_height);
 		drm_framebuffer_put(&intel_fb->base);
 		intel_fb = ifbdev->fb = NULL;
 	}
 	if (!intel_fb || drm_WARN_ON(dev, !intel_fb_obj(&intel_fb->base))) {
-		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "no BIOS fb, allocating a new one\n");
 		ret = intelfb_alloc(helper, sizes);
 		if (ret)
 			return ret;
 		intel_fb = ifbdev->fb;
 	} else {
-		DRM_DEBUG_KMS("re-using BIOS fb\n");
+		drm_dbg_kms(&dev_priv->drm, "re-using BIOS fb\n");
 		prealloc = true;
 		sizes->fb_width = intel_fb->base.width;
 		sizes->fb_height = intel_fb->base.height;
@@ -220,7 +222,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	info = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(info)) {
-		DRM_ERROR("Failed to allocate fb_info\n");
+		drm_err(&dev_priv->drm, "Failed to allocate fb_info\n");
 		ret = PTR_ERR(info);
 		goto out_unpin;
 	}
@@ -240,7 +242,8 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	vaddr = i915_vma_pin_iomap(vma);
 	if (IS_ERR(vaddr)) {
-		DRM_ERROR("Failed to remap framebuffer into virtual memory\n");
+		drm_err(&dev_priv->drm,
+			"Failed to remap framebuffer into virtual memory\n");
 		ret = PTR_ERR(vaddr);
 		goto out_unpin;
 	}
@@ -258,9 +261,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x\n",
-		      ifbdev->fb->base.width, ifbdev->fb->base.height,
-		      i915_ggtt_offset(vma));
+	drm_dbg_kms(&dev_priv->drm, "allocated %dx%d fb: 0x%08x\n",
+		    ifbdev->fb->base.width, ifbdev->fb->base.height,
+		    i915_ggtt_offset(vma));
 	ifbdev->vma = vma;
 	ifbdev->vma_flags = flags;
 
@@ -309,6 +312,7 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
 static bool intel_fbdev_init_bios(struct drm_device *dev,
 				 struct intel_fbdev *ifbdev)
 {
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct intel_framebuffer *fb = NULL;
 	struct drm_crtc *crtc;
 	struct intel_crtc *intel_crtc;
@@ -321,21 +325,24 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		intel_crtc = to_intel_crtc(crtc);
 
 		if (!crtc->state->active || !obj) {
-			DRM_DEBUG_KMS("pipe %c not active or no fb, skipping\n",
-				      pipe_name(intel_crtc->pipe));
+			drm_dbg_kms(&i915->drm,
+				    "pipe %c not active or no fb, skipping\n",
+				    pipe_name(intel_crtc->pipe));
 			continue;
 		}
 
 		if (obj->base.size > max_size) {
-			DRM_DEBUG_KMS("found possible fb from plane %c\n",
-				      pipe_name(intel_crtc->pipe));
+			drm_dbg_kms(&i915->drm,
+				    "found possible fb from plane %c\n",
+				    pipe_name(intel_crtc->pipe));
 			fb = to_intel_framebuffer(crtc->primary->state->fb);
 			max_size = obj->base.size;
 		}
 	}
 
 	if (!fb) {
-		DRM_DEBUG_KMS("no active fbs found, not using BIOS config\n");
+		drm_dbg_kms(&i915->drm,
+			    "no active fbs found, not using BIOS config\n");
 		goto out;
 	}
 
@@ -346,13 +353,14 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		intel_crtc = to_intel_crtc(crtc);
 
 		if (!crtc->state->active) {
-			DRM_DEBUG_KMS("pipe %c not active, skipping\n",
-				      pipe_name(intel_crtc->pipe));
+			drm_dbg_kms(&i915->drm,
+				    "pipe %c not active, skipping\n",
+				    pipe_name(intel_crtc->pipe));
 			continue;
 		}
 
-		DRM_DEBUG_KMS("checking plane %c for BIOS fb\n",
-			      pipe_name(intel_crtc->pipe));
+		drm_dbg_kms(&i915->drm, "checking plane %c for BIOS fb\n",
+			    pipe_name(intel_crtc->pipe));
 
 		/*
 		 * See if the plane fb we found above will fit on this
@@ -362,9 +370,10 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		cur_size = crtc->state->adjusted_mode.crtc_hdisplay;
 		cur_size = cur_size * fb->base.format->cpp[0];
 		if (fb->base.pitches[0] < cur_size) {
-			DRM_DEBUG_KMS("fb not wide enough for plane %c (%d vs %d)\n",
-				      pipe_name(intel_crtc->pipe),
-				      cur_size, fb->base.pitches[0]);
+			drm_dbg_kms(&i915->drm,
+				    "fb not wide enough for plane %c (%d vs %d)\n",
+				    pipe_name(intel_crtc->pipe),
+				    cur_size, fb->base.pitches[0]);
 			fb = NULL;
 			break;
 		}
@@ -372,28 +381,32 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		cur_size = crtc->state->adjusted_mode.crtc_vdisplay;
 		cur_size = intel_fb_align_height(&fb->base, 0, cur_size);
 		cur_size *= fb->base.pitches[0];
-		DRM_DEBUG_KMS("pipe %c area: %dx%d, bpp: %d, size: %d\n",
-			      pipe_name(intel_crtc->pipe),
-			      crtc->state->adjusted_mode.crtc_hdisplay,
-			      crtc->state->adjusted_mode.crtc_vdisplay,
-			      fb->base.format->cpp[0] * 8,
-			      cur_size);
+		drm_dbg_kms(&i915->drm,
+			    "pipe %c area: %dx%d, bpp: %d, size: %d\n",
+			    pipe_name(intel_crtc->pipe),
+			    crtc->state->adjusted_mode.crtc_hdisplay,
+			    crtc->state->adjusted_mode.crtc_vdisplay,
+			    fb->base.format->cpp[0] * 8,
+			    cur_size);
 
 		if (cur_size > max_size) {
-			DRM_DEBUG_KMS("fb not big enough for plane %c (%d vs %d)\n",
-				      pipe_name(intel_crtc->pipe),
-				      cur_size, max_size);
+			drm_dbg_kms(&i915->drm,
+				    "fb not big enough for plane %c (%d vs %d)\n",
+				    pipe_name(intel_crtc->pipe),
+				    cur_size, max_size);
 			fb = NULL;
 			break;
 		}
 
-		DRM_DEBUG_KMS("fb big enough for plane %c (%d >= %d)\n",
-			      pipe_name(intel_crtc->pipe),
-			      max_size, cur_size);
+		drm_dbg_kms(&i915->drm,
+			    "fb big enough for plane %c (%d >= %d)\n",
+			    pipe_name(intel_crtc->pipe),
+			    max_size, cur_size);
 	}
 
 	if (!fb) {
-		DRM_DEBUG_KMS("BIOS fb not suitable for all pipes, not using\n");
+		drm_dbg_kms(&i915->drm,
+			    "BIOS fb not suitable for all pipes, not using\n");
 		goto out;
 	}
 
@@ -415,7 +428,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 	}
 
 
-	DRM_DEBUG_KMS("using BIOS fb for initial console\n");
+	drm_dbg_kms(&i915->drm, "using BIOS fb for initial console\n");
 	return true;
 
 out:
@@ -522,8 +535,9 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv)
  * processing, fbdev will perform a full connector reprobe if a hotplug event
  * was received while HPD was suspended.
  */
-static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state)
+static void intel_fbdev_hpd_set_suspend(struct drm_i915_private *i915, int state)
 {
+	struct intel_fbdev *ifbdev = i915->fbdev;
 	bool send_hpd = false;
 
 	mutex_lock(&ifbdev->hpd_lock);
@@ -533,7 +547,7 @@ static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state)
 	mutex_unlock(&ifbdev->hpd_lock);
 
 	if (send_hpd) {
-		DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n");
+		drm_dbg_kms(&i915->drm, "Handling delayed fbcon HPD event\n");
 		drm_fb_helper_hotplug_event(&ifbdev->helper);
 	}
 }
@@ -588,7 +602,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 	drm_fb_helper_set_suspend(&ifbdev->helper, state);
 	console_unlock();
 
-	intel_fbdev_hpd_set_suspend(ifbdev, state);
+	intel_fbdev_hpd_set_suspend(dev_priv, state);
 }
 
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 6cb02c912acc..2979ed2588eb 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -302,12 +302,14 @@ void intel_frontbuffer_track(struct intel_frontbuffer *old,
 		     BITS_PER_TYPE(atomic_t));
 
 	if (old) {
-		WARN_ON(!(atomic_read(&old->bits) & frontbuffer_bits));
+		drm_WARN_ON(old->obj->base.dev,
+			    !(atomic_read(&old->bits) & frontbuffer_bits));
 		atomic_andnot(frontbuffer_bits, &old->bits);
 	}
 
 	if (new) {
-		WARN_ON(atomic_read(&new->bits) & frontbuffer_bits);
+		drm_WARN_ON(new->obj->base.dev,
+			    atomic_read(&new->bits) & frontbuffer_bits);
 		atomic_or(frontbuffer_bits, &new->bits);
 	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c
index a0cc894c3868..212d4ee68205 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.c
+++ b/drivers/gpu/drm/i915/display/intel_global_state.c
@@ -64,13 +64,14 @@ static void assert_global_state_read_locked(struct intel_atomic_state *state)
 			return;
 	}
 
-	WARN(1, "Global state not read locked\n");
+	drm_WARN(&dev_priv->drm, 1, "Global state not read locked\n");
 }
 
 struct intel_global_state *
 intel_atomic_get_global_obj_state(struct intel_atomic_state *state,
 				  struct intel_global_obj *obj)
 {
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	int index, num_objs, i;
 	size_t size;
 	struct __intel_global_objs_state *arr;
@@ -106,8 +107,8 @@ intel_atomic_get_global_obj_state(struct intel_atomic_state *state,
 
 	state->num_global_objs = num_objs;
 
-	DRM_DEBUG_ATOMIC("Added new global object %p state %p to %p\n",
-			 obj, obj_state, state);
+	drm_dbg_atomic(&i915->drm, "Added new global object %p state %p to %p\n",
+		       obj, obj_state, state);
 
 	return obj_state;
 }
@@ -147,7 +148,7 @@ void intel_atomic_swap_global_state(struct intel_atomic_state *state)
 
 	for_each_oldnew_global_obj_in_state(state, obj, old_obj_state,
 					    new_obj_state, i) {
-		WARN_ON(obj->state != old_obj_state);
+		drm_WARN_ON(&dev_priv->drm, obj->state != old_obj_state);
 
 		/*
 		 * If the new state wasn't modified (and properly
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 1fd3a5a6296b..a8d119b6b45c 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -379,8 +379,7 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-static inline
-unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
+static unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
 {
 	return INTEL_GEN(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX :
 	       GMBUS_BYTE_COUNT_MAX;
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index ee0f27ea2810..2cbc4619b4ce 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -109,18 +109,16 @@ bool intel_hdcp2_capable(struct intel_connector *connector)
 	return capable;
 }
 
-static inline
-bool intel_hdcp_in_use(struct drm_i915_private *dev_priv,
-		       enum transcoder cpu_transcoder, enum port port)
+static bool intel_hdcp_in_use(struct drm_i915_private *dev_priv,
+			      enum transcoder cpu_transcoder, enum port port)
 {
 	return intel_de_read(dev_priv,
 	                     HDCP_STATUS(dev_priv, cpu_transcoder, port)) &
 	       HDCP_STATUS_ENC;
 }
 
-static inline
-bool intel_hdcp2_in_use(struct drm_i915_private *dev_priv,
-			enum transcoder cpu_transcoder, enum port port)
+static bool intel_hdcp2_in_use(struct drm_i915_private *dev_priv,
+			       enum transcoder cpu_transcoder, enum port port)
 {
 	return intel_de_read(dev_priv,
 	                     HDCP2_STATUS(dev_priv, cpu_transcoder, port)) &
@@ -853,8 +851,7 @@ static int _intel_hdcp_enable(struct intel_connector *connector)
 	return ret;
 }
 
-static inline
-struct intel_connector *intel_hdcp_to_connector(struct intel_hdcp *hdcp)
+static struct intel_connector *intel_hdcp_to_connector(struct intel_hdcp *hdcp)
 {
 	return container_of(hdcp, struct intel_connector, hdcp);
 }
@@ -1391,6 +1388,7 @@ static
 int hdcp2_propagate_stream_management_info(struct intel_connector *connector)
 {
 	struct intel_digital_port *intel_dig_port = intel_attached_dig_port(connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	union {
 		struct hdcp2_rep_stream_manage stream_manage;
@@ -1431,7 +1429,7 @@ int hdcp2_propagate_stream_management_info(struct intel_connector *connector)
 	hdcp->seq_num_m++;
 
 	if (hdcp->seq_num_m > HDCP_2_2_SEQ_NUM_MAX) {
-		DRM_DEBUG_KMS("seq_num_m roll over.\n");
+		drm_dbg_kms(&i915->drm, "seq_num_m roll over.\n");
 		return -1;
 	}
 
@@ -1855,8 +1853,7 @@ 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)
+static enum mei_fw_ddi intel_get_mei_fw_ddi_index(enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -1868,8 +1865,7 @@ 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)
+static enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder)
 {
 	switch (cpu_transcoder) {
 	case TRANSCODER_A ... TRANSCODER_D:
@@ -1879,8 +1875,8 @@ enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder)
 	}
 }
 
-static inline int initialize_hdcp_port_data(struct intel_connector *connector,
-					    const struct intel_hdcp_shim *shim)
+static 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;
@@ -2075,7 +2071,8 @@ int intel_hdcp_disable(struct intel_connector *connector)
 	return ret;
 }
 
-void intel_hdcp_update_pipe(struct intel_encoder *encoder,
+void intel_hdcp_update_pipe(struct intel_atomic_state *state,
+			    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_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h
index 7c12ad609b1f..86bbaec120cc 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.h
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.h
@@ -11,6 +11,7 @@
 struct drm_connector;
 struct drm_connector_state;
 struct drm_i915_private;
+struct intel_atomic_state;
 struct intel_connector;
 struct intel_crtc_state;
 struct intel_encoder;
@@ -26,7 +27,8 @@ int intel_hdcp_init(struct intel_connector *connector,
 int intel_hdcp_enable(struct intel_connector *connector,
 		      enum transcoder cpu_transcoder, u8 content_type);
 int intel_hdcp_disable(struct intel_connector *connector);
-void intel_hdcp_update_pipe(struct intel_encoder *encoder,
+void intel_hdcp_update_pipe(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state);
 bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port);
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 821411b93dac..010f37240710 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -44,7 +44,6 @@
 #include "intel_audio.h"
 #include "intel_connector.h"
 #include "intel_ddi.h"
-#include "intel_display_debugfs.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
 #include "intel_dpio_phy.h"
@@ -707,13 +706,15 @@ void intel_read_infoframe(struct intel_encoder *encoder,
 	/* see comment above for the reason for this offset */
 	ret = hdmi_infoframe_unpack(frame, buffer + 1, sizeof(buffer) - 1);
 	if (ret) {
-		DRM_DEBUG_KMS("Failed to unpack infoframe type 0x%02x\n", type);
+		drm_dbg_kms(encoder->base.dev,
+			    "Failed to unpack infoframe type 0x%02x\n", type);
 		return;
 	}
 
 	if (frame->any.type != type)
-		DRM_DEBUG_KMS("Found the wrong infoframe type 0x%x (expected 0x%02x)\n",
-			      frame->any.type, type);
+		drm_dbg_kms(encoder->base.dev,
+			    "Found the wrong infoframe type 0x%x (expected 0x%02x)\n",
+			    frame->any.type, type);
 }
 
 static bool
@@ -853,7 +854,8 @@ intel_hdmi_compute_drm_infoframe(struct intel_encoder *encoder,
 
 	ret = drm_hdmi_infoframe_set_hdr_metadata(frame, conn_state);
 	if (ret < 0) {
-		DRM_DEBUG_KMS("couldn't set HDR metadata in infoframe\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "couldn't set HDR metadata in infoframe\n");
 		return false;
 	}
 
@@ -893,8 +895,9 @@ static void g4x_set_infoframes(struct intel_encoder *encoder,
 		if (!(val & VIDEO_DIP_ENABLE))
 			return;
 		if (port != (val & VIDEO_DIP_PORT_MASK)) {
-			DRM_DEBUG_KMS("video DIP still enabled on port %c\n",
-				      (val & VIDEO_DIP_PORT_MASK) >> 29);
+			drm_dbg_kms(&dev_priv->drm,
+				    "video DIP still enabled on port %c\n",
+				    (val & VIDEO_DIP_PORT_MASK) >> 29);
 			return;
 		}
 		val &= ~(VIDEO_DIP_ENABLE | VIDEO_DIP_ENABLE_AVI |
@@ -906,8 +909,9 @@ static void g4x_set_infoframes(struct intel_encoder *encoder,
 
 	if (port != (val & VIDEO_DIP_PORT_MASK)) {
 		if (val & VIDEO_DIP_ENABLE) {
-			DRM_DEBUG_KMS("video DIP already enabled on port %c\n",
-				      (val & VIDEO_DIP_PORT_MASK) >> 29);
+			drm_dbg_kms(&dev_priv->drm,
+				    "video DIP already enabled on port %c\n",
+				    (val & VIDEO_DIP_PORT_MASK) >> 29);
 			return;
 		}
 		val &= ~VIDEO_DIP_PORT_MASK;
@@ -1264,8 +1268,8 @@ void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
 	if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI)
 		return;
 
-	DRM_DEBUG_KMS("%s DP dual mode adaptor TMDS output\n",
-		      enable ? "Enabling" : "Disabling");
+	drm_dbg_kms(&dev_priv->drm, "%s DP dual mode adaptor TMDS output\n",
+		    enable ? "Enabling" : "Disabling");
 
 	drm_dp_dual_mode_set_tmds_output(hdmi->dp_dual_mode.type,
 					 adapter, enable);
@@ -1346,13 +1350,14 @@ int intel_hdmi_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 	ret = intel_hdmi_hdcp_write(intel_dig_port, DRM_HDCP_DDC_AN, an,
 				    DRM_HDCP_AN_LEN);
 	if (ret) {
-		DRM_DEBUG_KMS("Write An over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Write An over DDC failed (%d)\n",
+			    ret);
 		return ret;
 	}
 
 	ret = intel_gmbus_output_aksv(adapter);
 	if (ret < 0) {
-		DRM_DEBUG_KMS("Failed to output aksv (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Failed to output aksv (%d)\n", ret);
 		return ret;
 	}
 	return 0;
@@ -1361,11 +1366,14 @@ int intel_hdmi_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 static int intel_hdmi_hdcp_read_bksv(struct intel_digital_port *intel_dig_port,
 				     u8 *bksv)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
+
 	int ret;
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BKSV, bksv,
 				   DRM_HDCP_KSV_LEN);
 	if (ret)
-		DRM_DEBUG_KMS("Read Bksv over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read Bksv over DDC failed (%d)\n",
+			    ret);
 	return ret;
 }
 
@@ -1373,11 +1381,14 @@ static
 int intel_hdmi_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port,
 				 u8 *bstatus)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
+
 	int ret;
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BSTATUS,
 				   bstatus, DRM_HDCP_BSTATUS_LEN);
 	if (ret)
-		DRM_DEBUG_KMS("Read bstatus over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read bstatus over DDC failed (%d)\n",
+			    ret);
 	return ret;
 }
 
@@ -1385,12 +1396,14 @@ static
 int intel_hdmi_hdcp_repeater_present(struct intel_digital_port *intel_dig_port,
 				     bool *repeater_present)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	int ret;
 	u8 val;
 
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1);
 	if (ret) {
-		DRM_DEBUG_KMS("Read bcaps over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read bcaps over DDC failed (%d)\n",
+			    ret);
 		return ret;
 	}
 	*repeater_present = val & DRM_HDCP_DDC_BCAPS_REPEATER_PRESENT;
@@ -1401,11 +1414,14 @@ static
 int intel_hdmi_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port,
 				  u8 *ri_prime)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
+
 	int ret;
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_RI_PRIME,
 				   ri_prime, DRM_HDCP_RI_LEN);
 	if (ret)
-		DRM_DEBUG_KMS("Read Ri' over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read Ri' over DDC failed (%d)\n",
+			    ret);
 	return ret;
 }
 
@@ -1413,12 +1429,14 @@ static
 int intel_hdmi_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port,
 				   bool *ksv_ready)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	int ret;
 	u8 val;
 
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1);
 	if (ret) {
-		DRM_DEBUG_KMS("Read bcaps over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm, "Read bcaps over DDC failed (%d)\n",
+			    ret);
 		return ret;
 	}
 	*ksv_ready = val & DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY;
@@ -1429,11 +1447,13 @@ static
 int intel_hdmi_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port,
 				  int num_downstream, u8 *ksv_fifo)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	int ret;
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_KSV_FIFO,
 				   ksv_fifo, num_downstream * DRM_HDCP_KSV_LEN);
 	if (ret) {
-		DRM_DEBUG_KMS("Read ksv fifo over DDC failed (%d)\n", ret);
+		drm_dbg_kms(&i915->drm,
+			    "Read ksv fifo over DDC failed (%d)\n", ret);
 		return ret;
 	}
 	return 0;
@@ -1443,6 +1463,7 @@ static
 int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
 				      int i, u32 *part)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	int ret;
 
 	if (i >= DRM_HDCP_V_PRIME_NUM_PARTS)
@@ -1451,7 +1472,8 @@ int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
 	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_V_PRIME(i),
 				   part, DRM_HDCP_V_PRIME_PART_LEN);
 	if (ret)
-		DRM_DEBUG_KMS("Read V'[%d] over DDC failed (%d)\n", i, ret);
+		drm_dbg_kms(&i915->drm, "Read V'[%d] over DDC failed (%d)\n",
+			    i, ret);
 	return ret;
 }
 
@@ -1474,12 +1496,14 @@ static int kbl_repositioning_enc_en_signal(struct intel_connector *connector)
 
 	ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, false);
 	if (ret) {
-		DRM_ERROR("Disable HDCP signalling failed (%d)\n", ret);
+		drm_err(&dev_priv->drm,
+			"Disable HDCP signalling failed (%d)\n", ret);
 		return ret;
 	}
 	ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, true);
 	if (ret) {
-		DRM_ERROR("Enable HDCP signalling failed (%d)\n", ret);
+		drm_err(&dev_priv->drm,
+			"Enable HDCP signalling failed (%d)\n", ret);
 		return ret;
 	}
 
@@ -1500,8 +1524,8 @@ int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port,
 
 	ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, enable);
 	if (ret) {
-		DRM_ERROR("%s HDCP signalling failed (%d)\n",
-			  enable ? "Enable" : "Disable", ret);
+		drm_err(&dev_priv->drm, "%s HDCP signalling failed (%d)\n",
+			enable ? "Enable" : "Disable", ret);
 		return ret;
 	}
 
@@ -1539,8 +1563,10 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 	if (wait_for((intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) &
 		      (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC)) ==
 		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
-		DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n",
-			  intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)));
+		drm_err(&i915->drm,
+			"Ri' mismatch detected, link check failed (%x)\n",
+			intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder,
+							port)));
 		return false;
 	}
 	return true;
@@ -1588,17 +1614,19 @@ static int get_hdcp2_msg_timeout(u8 msg_id, bool is_paired)
 	return -EINVAL;
 }
 
-static inline
-int hdcp2_detect_msg_availability(struct intel_digital_port *intel_digital_port,
-				  u8 msg_id, bool *msg_ready,
-				  ssize_t *msg_sz)
+static int
+hdcp2_detect_msg_availability(struct intel_digital_port *intel_dig_port,
+			      u8 msg_id, bool *msg_ready,
+			      ssize_t *msg_sz)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	u8 rx_status[HDCP_2_2_HDMI_RXSTATUS_LEN];
 	int ret;
 
-	ret = intel_hdmi_hdcp2_read_rx_status(intel_digital_port, rx_status);
+	ret = intel_hdmi_hdcp2_read_rx_status(intel_dig_port, rx_status);
 	if (ret < 0) {
-		DRM_DEBUG_KMS("rx_status read failed. Err %d\n", ret);
+		drm_dbg_kms(&i915->drm, "rx_status read failed. Err %d\n",
+			    ret);
 		return ret;
 	}
 
@@ -1618,6 +1646,7 @@ static ssize_t
 intel_hdmi_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port,
 			      u8 msg_id, bool paired)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	bool msg_ready = false;
 	int timeout, ret;
 	ssize_t msg_sz = 0;
@@ -1632,8 +1661,8 @@ intel_hdmi_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port,
 			 !ret && msg_ready && msg_sz, timeout * 1000,
 			 1000, 5 * 1000);
 	if (ret)
-		DRM_DEBUG_KMS("msg_id: %d, ret: %d, timeout: %d\n",
-			      msg_id, ret, timeout);
+		drm_dbg_kms(&i915->drm, "msg_id: %d, ret: %d, timeout: %d\n",
+			    msg_id, ret, timeout);
 
 	return ret ? ret : msg_sz;
 }
@@ -1652,6 +1681,7 @@ static
 int intel_hdmi_hdcp2_read_msg(struct intel_digital_port *intel_dig_port,
 			      u8 msg_id, void *buf, size_t size)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_hdmi *hdmi = &intel_dig_port->hdmi;
 	struct intel_hdcp *hdcp = &hdmi->attached_connector->hdcp;
 	unsigned int offset;
@@ -1667,15 +1697,17 @@ int intel_hdmi_hdcp2_read_msg(struct intel_digital_port *intel_dig_port,
 	 * available buffer.
 	 */
 	if (ret > size) {
-		DRM_DEBUG_KMS("msg_sz(%zd) is more than exp size(%zu)\n",
-			      ret, size);
+		drm_dbg_kms(&i915->drm,
+			    "msg_sz(%zd) is more than exp size(%zu)\n",
+			    ret, size);
 		return -1;
 	}
 
 	offset = HDCP_2_2_HDMI_REG_RD_MSG_OFFSET;
 	ret = intel_hdmi_hdcp_read(intel_dig_port, offset, buf, ret);
 	if (ret)
-		DRM_DEBUG_KMS("Failed to read msg_id: %d(%zd)\n", msg_id, ret);
+		drm_dbg_kms(&i915->drm, "Failed to read msg_id: %d(%zd)\n",
+			    msg_id, ret);
 
 	return ret;
 }
@@ -1718,12 +1750,6 @@ int intel_hdmi_hdcp2_capable(struct intel_digital_port *intel_dig_port,
 	return ret;
 }
 
-static inline
-enum hdcp_wired_protocol intel_hdmi_hdcp2_protocol(void)
-{
-	return HDCP_PROTOCOL_HDMI;
-}
-
 static const struct intel_hdcp_shim intel_hdmi_hdcp_shim = {
 	.write_an_aksv = intel_hdmi_hdcp_write_an_aksv,
 	.read_bksv = intel_hdmi_hdcp_read_bksv,
@@ -1871,15 +1897,17 @@ static void intel_enable_hdmi_audio(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
-	drm_WARN_ON(encoder->base.dev, !pipe_config->has_hdmi_sink);
-	DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n",
-			 pipe_name(crtc->pipe));
+	drm_WARN_ON(&i915->drm, !pipe_config->has_hdmi_sink);
+	drm_dbg_kms(&i915->drm, "Enabling HDMI audio on pipe %c\n",
+		    pipe_name(crtc->pipe));
 	intel_audio_codec_enable(encoder, pipe_config, conn_state);
 }
 
-static void g4x_enable_hdmi(struct intel_encoder *encoder,
+static void g4x_enable_hdmi(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_connector_state *conn_state)
 {
@@ -1901,7 +1929,8 @@ static void g4x_enable_hdmi(struct intel_encoder *encoder,
 		intel_enable_hdmi_audio(encoder, pipe_config, conn_state);
 }
 
-static void ibx_enable_hdmi(struct intel_encoder *encoder,
+static void ibx_enable_hdmi(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_connector_state *conn_state)
 {
@@ -1952,7 +1981,8 @@ static void ibx_enable_hdmi(struct intel_encoder *encoder,
 		intel_enable_hdmi_audio(encoder, pipe_config, conn_state);
 }
 
-static void cpt_enable_hdmi(struct intel_encoder *encoder,
+static void cpt_enable_hdmi(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_connector_state *conn_state)
 {
@@ -2005,13 +2035,15 @@ static void cpt_enable_hdmi(struct intel_encoder *encoder,
 		intel_enable_hdmi_audio(encoder, pipe_config, conn_state);
 }
 
-static void vlv_enable_hdmi(struct intel_encoder *encoder,
+static void vlv_enable_hdmi(struct intel_atomic_state *state,
+			    struct intel_encoder *encoder,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_connector_state *conn_state)
 {
 }
 
-static void intel_disable_hdmi(struct intel_encoder *encoder,
+static void intel_disable_hdmi(struct intel_atomic_state *state,
+			       struct intel_encoder *encoder,
 			       const struct intel_crtc_state *old_crtc_state,
 			       const struct drm_connector_state *old_conn_state)
 {
@@ -2069,7 +2101,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder,
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
 }
 
-static void g4x_disable_hdmi(struct intel_encoder *encoder,
+static void g4x_disable_hdmi(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
@@ -2077,10 +2110,11 @@ static void g4x_disable_hdmi(struct intel_encoder *encoder,
 		intel_audio_codec_disable(encoder,
 					  old_crtc_state, old_conn_state);
 
-	intel_disable_hdmi(encoder, old_crtc_state, old_conn_state);
+	intel_disable_hdmi(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void pch_disable_hdmi(struct intel_encoder *encoder,
+static void pch_disable_hdmi(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
@@ -2089,11 +2123,12 @@ static void pch_disable_hdmi(struct intel_encoder *encoder,
 					  old_crtc_state, old_conn_state);
 }
 
-static void pch_post_disable_hdmi(struct intel_encoder *encoder,
+static void pch_post_disable_hdmi(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *old_crtc_state,
 				  const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_hdmi(encoder, old_crtc_state, old_conn_state);
+	intel_disable_hdmi(state, encoder, old_crtc_state, old_conn_state);
 }
 
 static int intel_hdmi_source_max_tmds_clock(struct intel_encoder *encoder)
@@ -2286,29 +2321,27 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 	return true;
 }
 
-static bool
-intel_hdmi_ycbcr420_config(struct drm_connector *connector,
-			   struct intel_crtc_state *config)
+static int
+intel_hdmi_ycbcr420_config(struct intel_crtc_state *crtc_state,
+			   const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(config->uapi.crtc);
-
-	if (!connector->ycbcr_420_allowed) {
-		DRM_ERROR("Platform doesn't support YCBCR420 output\n");
-		return false;
-	}
+	struct drm_connector *connector = conn_state->connector;
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->hw.adjusted_mode;
 
-	config->output_format = INTEL_OUTPUT_FORMAT_YCBCR420;
+	if (!drm_mode_is_420_only(&connector->display_info, adjusted_mode))
+		return 0;
 
-	/* YCBCR 420 output conversion needs a scaler */
-	if (skl_update_scaler_crtc(config)) {
-		DRM_DEBUG_KMS("Scaler allocation for output failed\n");
-		return false;
+	if (!connector->ycbcr_420_allowed) {
+		drm_err(&i915->drm,
+			"Platform doesn't support YCBCR420 output\n");
+		return -EINVAL;
 	}
 
-	intel_pch_panel_fitting(intel_crtc, config,
-				DRM_MODE_SCALE_FULLSCREEN);
+	crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR420;
 
-	return true;
+	return intel_pch_panel_fitting(crtc_state, conn_state);
 }
 
 static int intel_hdmi_port_clock(int clock, int bpc)
@@ -2342,6 +2375,7 @@ static int intel_hdmi_compute_bpc(struct intel_encoder *encoder,
 static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
 				    struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
@@ -2366,13 +2400,15 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
 	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);
+	drm_dbg_kms(&i915->drm,
+		    "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, crtc_state->has_hdmi_sink) != MODE_OK) {
-		DRM_DEBUG_KMS("unsupported HDMI clock (%d kHz), rejecting mode\n",
-			      crtc_state->port_clock);
+		drm_dbg_kms(&i915->drm,
+			    "unsupported HDMI clock (%d kHz), rejecting mode\n",
+			    crtc_state->port_clock);
 		return -EINVAL;
 	}
 
@@ -2433,12 +2469,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
 
-	if (drm_mode_is_420_only(&connector->display_info, adjusted_mode)) {
-		if (!intel_hdmi_ycbcr420_config(connector, pipe_config)) {
-			DRM_ERROR("Can't support YCBCR420 output\n");
-			return -EINVAL;
-		}
-	}
+	ret = intel_hdmi_ycbcr420_config(pipe_config, conn_state);
+	if (ret)
+		return ret;
 
 	pipe_config->limited_color_range =
 		intel_hdmi_limited_color_range(pipe_config, conn_state);
@@ -2475,25 +2508,26 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 		}
 	}
 
-	intel_hdmi_compute_gcp_infoframe(encoder, pipe_config, conn_state);
+	intel_hdmi_compute_gcp_infoframe(encoder, pipe_config,
+					 conn_state);
 
 	if (!intel_hdmi_compute_avi_infoframe(encoder, pipe_config, conn_state)) {
-		DRM_DEBUG_KMS("bad AVI infoframe\n");
+		drm_dbg_kms(&dev_priv->drm, "bad AVI infoframe\n");
 		return -EINVAL;
 	}
 
 	if (!intel_hdmi_compute_spd_infoframe(encoder, pipe_config, conn_state)) {
-		DRM_DEBUG_KMS("bad SPD infoframe\n");
+		drm_dbg_kms(&dev_priv->drm, "bad SPD infoframe\n");
 		return -EINVAL;
 	}
 
 	if (!intel_hdmi_compute_hdmi_infoframe(encoder, pipe_config, conn_state)) {
-		DRM_DEBUG_KMS("bad HDMI infoframe\n");
+		drm_dbg_kms(&dev_priv->drm, "bad HDMI infoframe\n");
 		return -EINVAL;
 	}
 
 	if (!intel_hdmi_compute_drm_infoframe(encoder, pipe_config, conn_state)) {
-		DRM_DEBUG_KMS("bad DRM infoframe\n");
+		drm_dbg_kms(&dev_priv->drm, "bad DRM infoframe\n");
 		return -EINVAL;
 	}
 
@@ -2543,7 +2577,8 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
 		 */
 		if (has_edid && !connector->override_edid &&
 		    intel_bios_is_port_dp_dual_mode(dev_priv, port)) {
-			DRM_DEBUG_KMS("Assuming DP dual mode adaptor presence based on VBT\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "Assuming DP dual mode adaptor presence based on VBT\n");
 			type = DRM_DP_DUAL_MODE_TYPE1_DVI;
 		} else {
 			type = DRM_DP_DUAL_MODE_NONE;
@@ -2557,9 +2592,10 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
 	hdmi->dp_dual_mode.max_tmds_clock =
 		drm_dp_dual_mode_max_tmds_clock(type, adapter);
 
-	DRM_DEBUG_KMS("DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n",
-		      drm_dp_get_dual_mode_type_name(type),
-		      hdmi->dp_dual_mode.max_tmds_clock);
+	drm_dbg_kms(&dev_priv->drm,
+		    "DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n",
+		    drm_dp_get_dual_mode_type_name(type),
+		    hdmi->dp_dual_mode.max_tmds_clock);
 }
 
 static bool
@@ -2579,7 +2615,8 @@ intel_hdmi_set_edid(struct drm_connector *connector)
 	edid = drm_get_edid(connector, i2c);
 
 	if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
-		DRM_DEBUG_KMS("HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n");
 		intel_gmbus_force_bit(i2c, true);
 		edid = drm_get_edid(connector, i2c);
 		intel_gmbus_force_bit(i2c, false);
@@ -2611,8 +2648,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	struct intel_encoder *encoder = &hdmi_to_dig_port(intel_hdmi)->base;
 	intel_wakeref_t wakeref;
 
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
+	drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s]\n",
+		    connector->base.id, connector->name);
 
 	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
@@ -2643,8 +2680,10 @@ out:
 static void
 intel_hdmi_force(struct drm_connector *connector)
 {
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+
+	drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s]\n",
+		    connector->base.id, connector->name);
 
 	intel_hdmi_unset_edid(connector);
 
@@ -2665,7 +2704,8 @@ static int intel_hdmi_get_modes(struct drm_connector *connector)
 	return intel_connector_update_modes(connector, edid);
 }
 
-static void intel_hdmi_pre_enable(struct intel_encoder *encoder,
+static void intel_hdmi_pre_enable(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config,
 				  const struct drm_connector_state *conn_state)
 {
@@ -2679,7 +2719,8 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder,
 				       pipe_config, conn_state);
 }
 
-static void vlv_hdmi_pre_enable(struct intel_encoder *encoder,
+static void vlv_hdmi_pre_enable(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
@@ -2696,12 +2737,13 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder,
 			      pipe_config->has_infoframe,
 			      pipe_config, conn_state);
 
-	g4x_enable_hdmi(encoder, pipe_config, conn_state);
+	g4x_enable_hdmi(state, encoder, pipe_config, conn_state);
 
 	vlv_wait_port_ready(dev_priv, dport, 0x0);
 }
 
-static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder,
+static void vlv_hdmi_pre_pll_enable(struct intel_atomic_state *state,
+				    struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
@@ -2710,7 +2752,8 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder,
 	vlv_phy_pre_pll_enable(encoder, pipe_config);
 }
 
-static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder,
+static void chv_hdmi_pre_pll_enable(struct intel_atomic_state *state,
+				    struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
@@ -2719,14 +2762,16 @@ static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder,
 	chv_phy_pre_pll_enable(encoder, pipe_config);
 }
 
-static void chv_hdmi_post_pll_disable(struct intel_encoder *encoder,
+static void chv_hdmi_post_pll_disable(struct intel_atomic_state *state,
+				      struct intel_encoder *encoder,
 				      const struct intel_crtc_state *old_crtc_state,
 				      const struct drm_connector_state *old_conn_state)
 {
 	chv_phy_post_pll_disable(encoder, old_crtc_state);
 }
 
-static void vlv_hdmi_post_disable(struct intel_encoder *encoder,
+static void vlv_hdmi_post_disable(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *old_crtc_state,
 				  const struct drm_connector_state *old_conn_state)
 {
@@ -2734,7 +2779,8 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder,
 	vlv_phy_reset_lanes(encoder, old_crtc_state);
 }
 
-static void chv_hdmi_post_disable(struct intel_encoder *encoder,
+static void chv_hdmi_post_disable(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *old_crtc_state,
 				  const struct drm_connector_state *old_conn_state)
 {
@@ -2749,7 +2795,8 @@ static void chv_hdmi_post_disable(struct intel_encoder *encoder,
 	vlv_dpio_put(dev_priv);
 }
 
-static void chv_hdmi_pre_enable(struct intel_encoder *encoder,
+static void chv_hdmi_pre_enable(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
@@ -2767,7 +2814,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder,
 			      pipe_config->has_infoframe,
 			      pipe_config, conn_state);
 
-	g4x_enable_hdmi(encoder, pipe_config, conn_state);
+	g4x_enable_hdmi(state, encoder, pipe_config, conn_state);
 
 	vlv_wait_port_ready(dev_priv, dport, 0x0);
 
@@ -2786,6 +2833,7 @@ intel_hdmi_get_i2c_adapter(struct drm_connector *connector)
 
 static void intel_hdmi_create_i2c_symlink(struct drm_connector *connector)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct i2c_adapter *adapter = intel_hdmi_get_i2c_adapter(connector);
 	struct kobject *i2c_kobj = &adapter->dev.kobj;
 	struct kobject *connector_kobj = &connector->kdev->kobj;
@@ -2793,7 +2841,7 @@ static void intel_hdmi_create_i2c_symlink(struct drm_connector *connector)
 
 	ret = sysfs_create_link(connector_kobj, i2c_kobj, i2c_kobj->name);
 	if (ret)
-		DRM_ERROR("Failed to create i2c symlink (%d)\n", ret);
+		drm_err(&i915->drm, "Failed to create i2c symlink (%d)\n", ret);
 }
 
 static void intel_hdmi_remove_i2c_symlink(struct drm_connector *connector)
@@ -2814,8 +2862,6 @@ intel_hdmi_connector_register(struct drm_connector *connector)
 	if (ret)
 		return ret;
 
-	intel_connector_debugfs_add(connector);
-
 	intel_hdmi_create_i2c_symlink(connector);
 
 	return ret;
@@ -2922,9 +2968,10 @@ bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 	if (!sink_scrambling->supported)
 		return true;
 
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] scrambling=%s, TMDS bit clock ratio=1/%d\n",
-		      connector->base.id, connector->name,
-		      yesno(scrambling), high_tmds_clock_ratio ? 40 : 10);
+	drm_dbg_kms(&dev_priv->drm,
+		    "[CONNECTOR:%d:%s] scrambling=%s, TMDS bit clock ratio=1/%d\n",
+		    connector->base.id, connector->name,
+		    yesno(scrambling), high_tmds_clock_ratio ? 40 : 10);
 
 	/* Set TMDS bit clock ratio to 1/40 or 1/10, and enable/disable scrambling */
 	return drm_scdc_set_high_tmds_clock_ratio(adapter,
@@ -3066,8 +3113,9 @@ static u8 intel_hdmi_ddc_pin(struct intel_encoder *encoder)
 
 	ddc_pin = intel_bios_alternate_ddc_pin(encoder);
 	if (ddc_pin) {
-		DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (VBT)\n",
-			      ddc_pin, port_name(port));
+		drm_dbg_kms(&dev_priv->drm,
+			    "Using DDC pin 0x%x for port %c (VBT)\n",
+			    ddc_pin, port_name(port));
 		return ddc_pin;
 	}
 
@@ -3084,8 +3132,9 @@ static u8 intel_hdmi_ddc_pin(struct intel_encoder *encoder)
 	else
 		ddc_pin = g4x_port_to_ddc_pin(dev_priv, port);
 
-	DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (platform default)\n",
-		      ddc_pin, port_name(port));
+	drm_dbg_kms(&dev_priv->drm,
+		    "Using DDC pin 0x%x for port %c (platform default)\n",
+		    ddc_pin, port_name(port));
 
 	return ddc_pin;
 }
@@ -3142,8 +3191,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	enum port port = intel_encoder->port;
 	struct cec_connector_info conn_info;
 
-	DRM_DEBUG_KMS("Adding HDMI connector on [ENCODER:%d:%s]\n",
-		      intel_encoder->base.base.id, intel_encoder->base.name);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Adding HDMI connector on [ENCODER:%d:%s]\n",
+		    intel_encoder->base.base.id, intel_encoder->base.name);
 
 	if (INTEL_GEN(dev_priv) < 12 && drm_WARN_ON(dev, port == PORT_A))
 		return;
@@ -3187,7 +3237,8 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 		int ret = intel_hdcp_init(intel_connector,
 					  &intel_hdmi_hdcp_shim);
 		if (ret)
-			DRM_DEBUG_KMS("HDCP init failed, skipping.\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "HDCP init failed, skipping.\n");
 	}
 
 	/* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written
@@ -3206,16 +3257,16 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 		cec_notifier_conn_register(dev->dev, port_identifier(port),
 					   &conn_info);
 	if (!intel_hdmi->cec_notifier)
-		DRM_DEBUG_KMS("CEC notifier get failed\n");
+		drm_dbg_kms(&dev_priv->drm, "CEC notifier get failed\n");
 }
 
 static enum intel_hotplug_state
 intel_hdmi_hotplug(struct intel_encoder *encoder,
-		   struct intel_connector *connector, bool irq_received)
+		   struct intel_connector *connector)
 {
 	enum intel_hotplug_state state;
 
-	state = intel_encoder_hotplug(encoder, connector, irq_received);
+	state = intel_encoder_hotplug(encoder, connector);
 
 	/*
 	 * On many platforms the HDMI live state signal is known to be
@@ -3229,7 +3280,7 @@ intel_hdmi_hotplug(struct intel_encoder *encoder,
 	 * time around we didn't detect any change in the sink's connection
 	 * status.
 	 */
-	if (state == INTEL_HOTPLUG_UNCHANGED && irq_received)
+	if (state == INTEL_HOTPLUG_UNCHANGED && !connector->hotplug_retries)
 		state = INTEL_HOTPLUG_RETRY;
 
 	return state;
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index a091442efba4..4f6f560e093e 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -270,8 +270,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 
 enum intel_hotplug_state
 intel_encoder_hotplug(struct intel_encoder *encoder,
-		      struct intel_connector *connector,
-		      bool irq_received)
+		      struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
 	enum drm_connector_status old_status;
@@ -392,12 +391,17 @@ static void i915_hotplug_work_func(struct work_struct *work)
 			struct intel_encoder *encoder =
 				intel_attached_encoder(connector);
 
+			if (hpd_event_bits & hpd_bit)
+				connector->hotplug_retries = 0;
+			else
+				connector->hotplug_retries++;
+
 			drm_dbg_kms(&dev_priv->drm,
-				    "Connector %s (pin %i) received hotplug event.\n",
-				    connector->base.name, pin);
+				    "Connector %s (pin %i) received hotplug event. (retry %d)\n",
+				    connector->base.name, pin,
+				    connector->hotplug_retries);
 
-			switch (encoder->hotplug(encoder, connector,
-						 hpd_event_bits & hpd_bit)) {
+			switch (encoder->hotplug(encoder, connector)) {
 			case INTEL_HOTPLUG_UNCHANGED:
 				break;
 			case INTEL_HOTPLUG_CHANGED:
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.h b/drivers/gpu/drm/i915/display/intel_hotplug.h
index 1e6b4fda2900..777b0743257e 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.h
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.h
@@ -15,8 +15,7 @@ enum port;
 
 void intel_hpd_poll_init(struct drm_i915_private *dev_priv);
 enum intel_hotplug_state intel_encoder_hotplug(struct intel_encoder *encoder,
-					       struct intel_connector *connector,
-					       bool irq_received);
+					       struct intel_connector *connector);
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask);
 void intel_hpd_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index d807c5648c87..6ff7b226f0a1 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -522,7 +522,7 @@ u32 lspcon_infoframes_enabled(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config)
 {
 	/* FIXME actually read this from the hw */
-	return enc_to_intel_lspcon(encoder)->active;
+	return 0;
 }
 
 void lspcon_resume(struct intel_lspcon *lspcon)
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 9a067effcfa0..872f2a489339 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -220,7 +220,8 @@ static void intel_lvds_pps_init_hw(struct drm_i915_private *dev_priv,
 		       REG_FIELD_PREP(PP_REFERENCE_DIVIDER_MASK, pps->divider) | REG_FIELD_PREP(PANEL_POWER_CYCLE_DELAY_MASK, DIV_ROUND_UP(pps->t4, 1000) + 1));
 }
 
-static void intel_pre_enable_lvds(struct intel_encoder *encoder,
+static void intel_pre_enable_lvds(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config,
 				  const struct drm_connector_state *conn_state)
 {
@@ -301,7 +302,8 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 /*
  * Sets the power state for the panel.
  */
-static void intel_enable_lvds(struct intel_encoder *encoder,
+static void intel_enable_lvds(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
@@ -323,7 +325,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder,
 	intel_panel_enable_backlight(pipe_config, conn_state);
 }
 
-static void intel_disable_lvds(struct intel_encoder *encoder,
+static void intel_disable_lvds(struct intel_atomic_state *state,
+			       struct intel_encoder *encoder,
 			       const struct intel_crtc_state *old_crtc_state,
 			       const struct drm_connector_state *old_conn_state)
 {
@@ -341,28 +344,31 @@ static void intel_disable_lvds(struct intel_encoder *encoder,
 	intel_de_posting_read(dev_priv, lvds_encoder->reg);
 }
 
-static void gmch_disable_lvds(struct intel_encoder *encoder,
+static void gmch_disable_lvds(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 
 {
 	intel_panel_disable_backlight(old_conn_state);
 
-	intel_disable_lvds(encoder, old_crtc_state, old_conn_state);
+	intel_disable_lvds(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void pch_disable_lvds(struct intel_encoder *encoder,
+static void pch_disable_lvds(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
 	intel_panel_disable_backlight(old_conn_state);
 }
 
-static void pch_post_disable_lvds(struct intel_encoder *encoder,
+static void pch_post_disable_lvds(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *old_crtc_state,
 				  const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_lvds(encoder, old_crtc_state, old_conn_state);
+	intel_disable_lvds(state, encoder, old_crtc_state, old_conn_state);
 }
 
 static enum drm_mode_status
@@ -397,6 +403,7 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	unsigned int lvds_bpp;
+	int ret;
 
 	/* Should never happen!! */
 	if (INTEL_GEN(dev_priv) < 4 && intel_crtc->pipe == 0) {
@@ -430,16 +437,15 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
 
-	if (HAS_PCH_SPLIT(dev_priv)) {
+	if (HAS_PCH_SPLIT(dev_priv))
 		pipe_config->has_pch_encoder = true;
 
-		intel_pch_panel_fitting(intel_crtc, pipe_config,
-					conn_state->scaling_mode);
-	} else {
-		intel_gmch_panel_fitting(intel_crtc, pipe_config,
-					 conn_state->scaling_mode);
-
-	}
+	if (HAS_GMCH(dev_priv))
+		ret = intel_gmch_panel_fitting(pipe_config, conn_state);
+	else
+		ret = intel_pch_panel_fitting(pipe_config, conn_state);
+	if (ret)
+		return ret;
 
 	/*
 	 * XXX: It would be nice to support lower refresh rates on the
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 481187223101..66711e62fa71 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -281,7 +281,7 @@ static void intel_overlay_flip_prepare(struct intel_overlay *overlay,
 	enum pipe pipe = overlay->crtc->pipe;
 	struct intel_frontbuffer *from = NULL, *to = NULL;
 
-	WARN_ON(overlay->old_vma);
+	drm_WARN_ON(&overlay->i915->drm, overlay->old_vma);
 
 	if (overlay->vma)
 		from = intel_frontbuffer_get(overlay->vma->obj);
@@ -350,7 +350,7 @@ static void intel_overlay_release_old_vma(struct intel_overlay *overlay)
 	struct i915_vma *vma;
 
 	vma = fetch_and_zero(&overlay->old_vma);
-	if (WARN_ON(!vma))
+	if (drm_WARN_ON(&overlay->i915->drm, !vma))
 		return;
 
 	intel_frontbuffer_flip_complete(overlay->i915,
@@ -396,7 +396,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	struct i915_request *rq;
 	u32 *cs, flip_addr = overlay->flip_addr;
 
-	WARN_ON(!overlay->active);
+	drm_WARN_ON(&overlay->i915->drm, !overlay->active);
 
 	/* According to intel docs the overlay hw may hang (when switching
 	 * off) without loading the filter coeffs. It is however unclear whether
@@ -1342,7 +1342,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	if (!HAS_OVERLAY(dev_priv))
 		return;
 
-	engine = dev_priv->engine[RCS0];
+	engine = dev_priv->gt.engine[RCS0];
 	if (!engine || !engine->kernel_context)
 		return;
 
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index 276f43870802..3c5056dbf607 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -176,24 +176,23 @@ intel_panel_vbt_fixed_mode(struct intel_connector *connector)
 }
 
 /* adjusted_mode has been preset to be the panel's fixed mode */
-void
-intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
-			struct intel_crtc_state *pipe_config,
-			int fitting_mode)
+int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state,
+			    const struct drm_connector_state *conn_state)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
-	int x = 0, y = 0, width = 0, height = 0;
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->hw.adjusted_mode;
+	int x, y, width, height;
 
 	/* Native modes don't need fitting */
-	if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w &&
-	    adjusted_mode->crtc_vdisplay == pipe_config->pipe_src_h &&
-	    pipe_config->output_format != INTEL_OUTPUT_FORMAT_YCBCR420)
-		goto done;
+	if (adjusted_mode->crtc_hdisplay == crtc_state->pipe_src_w &&
+	    adjusted_mode->crtc_vdisplay == crtc_state->pipe_src_h &&
+	    crtc_state->output_format != INTEL_OUTPUT_FORMAT_YCBCR420)
+		return 0;
 
-	switch (fitting_mode) {
+	switch (conn_state->scaling_mode) {
 	case DRM_MODE_SCALE_CENTER:
-		width = pipe_config->pipe_src_w;
-		height = pipe_config->pipe_src_h;
+		width = crtc_state->pipe_src_w;
+		height = crtc_state->pipe_src_h;
 		x = (adjusted_mode->crtc_hdisplay - width + 1)/2;
 		y = (adjusted_mode->crtc_vdisplay - height + 1)/2;
 		break;
@@ -202,18 +201,18 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 		/* Scale but preserve the aspect ratio */
 		{
 			u32 scaled_width = adjusted_mode->crtc_hdisplay
-				* pipe_config->pipe_src_h;
-			u32 scaled_height = pipe_config->pipe_src_w
+				* crtc_state->pipe_src_h;
+			u32 scaled_height = crtc_state->pipe_src_w
 				* adjusted_mode->crtc_vdisplay;
 			if (scaled_width > scaled_height) { /* pillar */
-				width = scaled_height / pipe_config->pipe_src_h;
+				width = scaled_height / crtc_state->pipe_src_h;
 				if (width & 1)
 					width++;
 				x = (adjusted_mode->crtc_hdisplay - width + 1) / 2;
 				y = 0;
 				height = adjusted_mode->crtc_vdisplay;
 			} else if (scaled_width < scaled_height) { /* letter */
-				height = scaled_width / pipe_config->pipe_src_w;
+				height = scaled_width / crtc_state->pipe_src_w;
 				if (height & 1)
 				    height++;
 				y = (adjusted_mode->crtc_vdisplay - height + 1) / 2;
@@ -227,6 +226,10 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 		}
 		break;
 
+	case DRM_MODE_SCALE_NONE:
+		WARN_ON(adjusted_mode->crtc_hdisplay != crtc_state->pipe_src_w);
+		WARN_ON(adjusted_mode->crtc_vdisplay != crtc_state->pipe_src_h);
+		/* fall through */
 	case DRM_MODE_SCALE_FULLSCREEN:
 		x = y = 0;
 		width = adjusted_mode->crtc_hdisplay;
@@ -234,14 +237,15 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 		break;
 
 	default:
-		WARN(1, "bad panel fit mode: %d\n", fitting_mode);
-		return;
+		MISSING_CASE(conn_state->scaling_mode);
+		return -EINVAL;
 	}
 
-done:
-	pipe_config->pch_pfit.pos = (x << 16) | y;
-	pipe_config->pch_pfit.size = (width << 16) | height;
-	pipe_config->pch_pfit.enabled = pipe_config->pch_pfit.size != 0;
+	drm_rect_init(&crtc_state->pch_pfit.dst,
+		      x, y, width, height);
+	crtc_state->pch_pfit.enabled = true;
+
+	return 0;
 }
 
 static void
@@ -287,7 +291,7 @@ centre_vertically(struct drm_display_mode *adjusted_mode,
 	adjusted_mode->crtc_vsync_end = adjusted_mode->crtc_vsync_start + sync_width;
 }
 
-static inline u32 panel_fitter_scaling(u32 source, u32 target)
+static u32 panel_fitter_scaling(u32 source, u32 target)
 {
 	/*
 	 * Floating point operation is not supported. So the FACTOR
@@ -300,13 +304,14 @@ static inline u32 panel_fitter_scaling(u32 source, u32 target)
 	return (FACTOR * ratio + FACTOR/2) / FACTOR;
 }
 
-static void i965_scale_aspect(struct intel_crtc_state *pipe_config,
+static void i965_scale_aspect(struct intel_crtc_state *crtc_state,
 			      u32 *pfit_control)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
-		pipe_config->pipe_src_h;
-	u32 scaled_height = pipe_config->pipe_src_w *
+		crtc_state->pipe_src_h;
+	u32 scaled_height = crtc_state->pipe_src_w *
 		adjusted_mode->crtc_vdisplay;
 
 	/* 965+ is easy, it does everything in hw */
@@ -316,18 +321,18 @@ static void i965_scale_aspect(struct intel_crtc_state *pipe_config,
 	else if (scaled_width < scaled_height)
 		*pfit_control |= PFIT_ENABLE |
 			PFIT_SCALING_LETTER;
-	else if (adjusted_mode->crtc_hdisplay != pipe_config->pipe_src_w)
+	else if (adjusted_mode->crtc_hdisplay != crtc_state->pipe_src_w)
 		*pfit_control |= PFIT_ENABLE | PFIT_SCALING_AUTO;
 }
 
-static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
+static void i9xx_scale_aspect(struct intel_crtc_state *crtc_state,
 			      u32 *pfit_control, u32 *pfit_pgm_ratios,
 			      u32 *border)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
-		pipe_config->pipe_src_h;
-	u32 scaled_height = pipe_config->pipe_src_w *
+		crtc_state->pipe_src_h;
+	u32 scaled_height = crtc_state->pipe_src_w *
 		adjusted_mode->crtc_vdisplay;
 	u32 bits;
 
@@ -339,11 +344,11 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
 	if (scaled_width > scaled_height) { /* pillar */
 		centre_horizontally(adjusted_mode,
 				    scaled_height /
-				    pipe_config->pipe_src_h);
+				    crtc_state->pipe_src_h);
 
 		*border = LVDS_BORDER_ENABLE;
-		if (pipe_config->pipe_src_h != adjusted_mode->crtc_vdisplay) {
-			bits = panel_fitter_scaling(pipe_config->pipe_src_h,
+		if (crtc_state->pipe_src_h != adjusted_mode->crtc_vdisplay) {
+			bits = panel_fitter_scaling(crtc_state->pipe_src_h,
 						    adjusted_mode->crtc_vdisplay);
 
 			*pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT |
@@ -355,11 +360,11 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
 	} else if (scaled_width < scaled_height) { /* letter */
 		centre_vertically(adjusted_mode,
 				  scaled_width /
-				  pipe_config->pipe_src_w);
+				  crtc_state->pipe_src_w);
 
 		*border = LVDS_BORDER_ENABLE;
-		if (pipe_config->pipe_src_w != adjusted_mode->crtc_hdisplay) {
-			bits = panel_fitter_scaling(pipe_config->pipe_src_w,
+		if (crtc_state->pipe_src_w != adjusted_mode->crtc_hdisplay) {
+			bits = panel_fitter_scaling(crtc_state->pipe_src_w,
 						    adjusted_mode->crtc_hdisplay);
 
 			*pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT |
@@ -377,35 +382,35 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
 	}
 }
 
-void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
-			      struct intel_crtc_state *pipe_config,
-			      int fitting_mode)
+int intel_gmch_panel_fitting(struct intel_crtc_state *crtc_state,
+			     const struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 pfit_control = 0, pfit_pgm_ratios = 0, border = 0;
-	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 
 	/* Native modes don't need fitting */
-	if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w &&
-	    adjusted_mode->crtc_vdisplay == pipe_config->pipe_src_h)
+	if (adjusted_mode->crtc_hdisplay == crtc_state->pipe_src_w &&
+	    adjusted_mode->crtc_vdisplay == crtc_state->pipe_src_h)
 		goto out;
 
-	switch (fitting_mode) {
+	switch (conn_state->scaling_mode) {
 	case DRM_MODE_SCALE_CENTER:
 		/*
 		 * For centered modes, we have to calculate border widths &
 		 * heights and modify the values programmed into the CRTC.
 		 */
-		centre_horizontally(adjusted_mode, pipe_config->pipe_src_w);
-		centre_vertically(adjusted_mode, pipe_config->pipe_src_h);
+		centre_horizontally(adjusted_mode, crtc_state->pipe_src_w);
+		centre_vertically(adjusted_mode, crtc_state->pipe_src_h);
 		border = LVDS_BORDER_ENABLE;
 		break;
 	case DRM_MODE_SCALE_ASPECT:
 		/* Scale but preserve the aspect ratio */
 		if (INTEL_GEN(dev_priv) >= 4)
-			i965_scale_aspect(pipe_config, &pfit_control);
+			i965_scale_aspect(crtc_state, &pfit_control);
 		else
-			i9xx_scale_aspect(pipe_config, &pfit_control,
+			i9xx_scale_aspect(crtc_state, &pfit_control,
 					  &pfit_pgm_ratios, &border);
 		break;
 	case DRM_MODE_SCALE_FULLSCREEN:
@@ -413,8 +418,8 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 		 * Full scaling, even if it changes the aspect ratio.
 		 * Fortunately this is all done for us in hw.
 		 */
-		if (pipe_config->pipe_src_h != adjusted_mode->crtc_vdisplay ||
-		    pipe_config->pipe_src_w != adjusted_mode->crtc_hdisplay) {
+		if (crtc_state->pipe_src_h != adjusted_mode->crtc_vdisplay ||
+		    crtc_state->pipe_src_w != adjusted_mode->crtc_hdisplay) {
 			pfit_control |= PFIT_ENABLE;
 			if (INTEL_GEN(dev_priv) >= 4)
 				pfit_control |= PFIT_SCALING_AUTO;
@@ -426,15 +431,14 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 		}
 		break;
 	default:
-		drm_WARN(&dev_priv->drm, 1, "bad panel fit mode: %d\n",
-			 fitting_mode);
-		return;
+		MISSING_CASE(conn_state->scaling_mode);
+		return -EINVAL;
 	}
 
 	/* 965+ wants fuzzy fitting */
 	/* FIXME: handle multiple panels by failing gracefully */
 	if (INTEL_GEN(dev_priv) >= 4)
-		pfit_control |= PFIT_PIPE(intel_crtc->pipe) | PFIT_FILTER_FUZZY;
+		pfit_control |= PFIT_PIPE(crtc->pipe) | PFIT_FILTER_FUZZY;
 
 out:
 	if ((pfit_control & PFIT_ENABLE) == 0) {
@@ -443,12 +447,14 @@ out:
 	}
 
 	/* Make sure pre-965 set dither correctly for 18bpp panels. */
-	if (INTEL_GEN(dev_priv) < 4 && pipe_config->pipe_bpp == 18)
+	if (INTEL_GEN(dev_priv) < 4 && crtc_state->pipe_bpp == 18)
 		pfit_control |= PANEL_8TO6_DITHER_ENABLE;
 
-	pipe_config->gmch_pfit.control = pfit_control;
-	pipe_config->gmch_pfit.pgm_ratios = pfit_pgm_ratios;
-	pipe_config->gmch_pfit.lvds_border_bits = border;
+	crtc_state->gmch_pfit.control = pfit_control;
+	crtc_state->gmch_pfit.pgm_ratios = pfit_pgm_ratios;
+	crtc_state->gmch_pfit.lvds_border_bits = border;
+
+	return 0;
 }
 
 /**
@@ -483,20 +489,10 @@ static u32 scale(u32 source_val,
 	return target_val;
 }
 
-/* Scale user_level in range [0..user_max] to [hw_min..hw_max]. */
-static inline u32 scale_user_to_hw(struct intel_connector *connector,
-				   u32 user_level, u32 user_max)
-{
-	struct intel_panel *panel = &connector->panel;
-
-	return scale(user_level, 0, user_max,
-		     panel->backlight.min, panel->backlight.max);
-}
-
 /* Scale user_level in range [0..user_max] to [0..hw_max], clamping the result
  * to [hw_min..hw_max]. */
-static inline u32 clamp_user_to_hw(struct intel_connector *connector,
-				   u32 user_level, u32 user_max)
+static u32 clamp_user_to_hw(struct intel_connector *connector,
+			    u32 user_level, u32 user_max)
 {
 	struct intel_panel *panel = &connector->panel;
 	u32 hw_level;
@@ -508,8 +504,8 @@ static inline u32 clamp_user_to_hw(struct intel_connector *connector,
 }
 
 /* Scale hw_level in range [hw_min..hw_max] to [0..user_max]. */
-static inline u32 scale_hw_to_user(struct intel_connector *connector,
-				   u32 hw_level, u32 user_max)
+static u32 scale_hw_to_user(struct intel_connector *connector,
+			    u32 hw_level, u32 user_max)
 {
 	struct intel_panel *panel = &connector->panel;
 
@@ -684,9 +680,10 @@ static void
 intel_panel_actually_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
 
-	DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level);
+	drm_dbg_kms(&i915->drm, "set backlight PWM = %d\n", level);
 
 	level = intel_panel_compute_brightness(connector, level);
 	panel->backlight.set(conn_state, level);
@@ -867,8 +864,8 @@ void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_st
 	 * another client is not activated.
 	 */
 	if (dev_priv->drm.switch_power_state == DRM_SWITCH_POWER_CHANGING) {
-		drm_dbg(&dev_priv->drm,
-			"Skipping backlight disable on vga switch\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Skipping backlight disable on vga switch\n");
 		return;
 	}
 
@@ -1244,10 +1241,20 @@ static u32 intel_panel_get_backlight(struct intel_connector *connector)
 
 	mutex_unlock(&dev_priv->backlight_lock);
 
-	drm_dbg(&dev_priv->drm, "get backlight PWM = %d\n", val);
+	drm_dbg_kms(&dev_priv->drm, "get backlight PWM = %d\n", val);
 	return val;
 }
 
+/* Scale user_level in range [0..user_max] to [hw_min..hw_max]. */
+static u32 scale_user_to_hw(struct intel_connector *connector,
+			    u32 user_level, u32 user_max)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	return scale(user_level, 0, user_max,
+		     panel->backlight.min, panel->backlight.max);
+}
+
 /* set backlight brightness to level in range [0..max], scaling wrt hw min */
 static void intel_panel_set_backlight(const struct drm_connector_state *conn_state,
 				      u32 user_level, u32 user_max)
@@ -1335,6 +1342,7 @@ static const struct backlight_ops intel_backlight_device_ops = {
 
 int intel_backlight_device_register(struct intel_connector *connector)
 {
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
 	struct backlight_properties props;
 
@@ -1374,14 +1382,15 @@ int intel_backlight_device_register(struct intel_connector *connector)
 					  &intel_backlight_device_ops, &props);
 
 	if (IS_ERR(panel->backlight.device)) {
-		DRM_ERROR("Failed to register backlight: %ld\n",
-			  PTR_ERR(panel->backlight.device));
+		drm_err(&i915->drm, "Failed to register backlight: %ld\n",
+			PTR_ERR(panel->backlight.device));
 		panel->backlight.device = NULL;
 		return -ENODEV;
 	}
 
-	DRM_DEBUG_KMS("Connector %s backlight sysfs interface registered\n",
-		      connector->base.name);
+	drm_dbg_kms(&i915->drm,
+		    "Connector %s backlight sysfs interface registered\n",
+		    connector->base.name);
 
 	return 0;
 }
@@ -1931,7 +1940,8 @@ static int pwm_setup_backlight(struct intel_connector *connector,
 	return 0;
 }
 
-void intel_panel_update_backlight(struct intel_encoder *encoder,
+void intel_panel_update_backlight(struct intel_atomic_state *state,
+				  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_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h
index cedeea443336..968b95281cb4 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.h
+++ b/drivers/gpu/drm/i915/display/intel_panel.h
@@ -25,19 +25,18 @@ int intel_panel_init(struct intel_panel *panel,
 void intel_panel_fini(struct intel_panel *panel);
 void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
 			    struct drm_display_mode *adjusted_mode);
-void intel_pch_panel_fitting(struct intel_crtc *crtc,
-			     struct intel_crtc_state *pipe_config,
-			     int fitting_mode);
-void intel_gmch_panel_fitting(struct intel_crtc *crtc,
-			      struct intel_crtc_state *pipe_config,
-			      int fitting_mode);
+int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state,
+			    const struct drm_connector_state *conn_state);
+int intel_gmch_panel_fitting(struct intel_crtc_state *crtc_state,
+			     const struct drm_connector_state *conn_state);
 void intel_panel_set_backlight_acpi(const struct drm_connector_state *conn_state,
 				    u32 level, u32 max);
 int intel_panel_setup_backlight(struct drm_connector *connector,
 				enum pipe pipe);
 void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state);
-void intel_panel_update_backlight(struct intel_encoder *encoder,
+void intel_panel_update_backlight(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state);
 void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index fd9b146e3aba..b7a2c102648a 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -30,6 +30,7 @@
 #include "intel_display_types.h"
 #include "intel_psr.h"
 #include "intel_sprite.h"
+#include "intel_hdmi.h"
 
 /**
  * DOC: Panel Self Refresh (PSR/SRD)
@@ -137,41 +138,42 @@ static void psr_irq_control(struct drm_i915_private *dev_priv)
 	intel_de_write(dev_priv, imr_reg, val);
 }
 
-static void psr_event_print(u32 val, bool psr2_enabled)
+static void psr_event_print(struct drm_i915_private *i915,
+			    u32 val, bool psr2_enabled)
 {
-	DRM_DEBUG_KMS("PSR exit events: 0x%x\n", val);
+	drm_dbg_kms(&i915->drm, "PSR exit events: 0x%x\n", val);
 	if (val & PSR_EVENT_PSR2_WD_TIMER_EXPIRE)
-		DRM_DEBUG_KMS("\tPSR2 watchdog timer expired\n");
+		drm_dbg_kms(&i915->drm, "\tPSR2 watchdog timer expired\n");
 	if ((val & PSR_EVENT_PSR2_DISABLED) && psr2_enabled)
-		DRM_DEBUG_KMS("\tPSR2 disabled\n");
+		drm_dbg_kms(&i915->drm, "\tPSR2 disabled\n");
 	if (val & PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN)
-		DRM_DEBUG_KMS("\tSU dirty FIFO underrun\n");
+		drm_dbg_kms(&i915->drm, "\tSU dirty FIFO underrun\n");
 	if (val & PSR_EVENT_SU_CRC_FIFO_UNDERRUN)
-		DRM_DEBUG_KMS("\tSU CRC FIFO underrun\n");
+		drm_dbg_kms(&i915->drm, "\tSU CRC FIFO underrun\n");
 	if (val & PSR_EVENT_GRAPHICS_RESET)
-		DRM_DEBUG_KMS("\tGraphics reset\n");
+		drm_dbg_kms(&i915->drm, "\tGraphics reset\n");
 	if (val & PSR_EVENT_PCH_INTERRUPT)
-		DRM_DEBUG_KMS("\tPCH interrupt\n");
+		drm_dbg_kms(&i915->drm, "\tPCH interrupt\n");
 	if (val & PSR_EVENT_MEMORY_UP)
-		DRM_DEBUG_KMS("\tMemory up\n");
+		drm_dbg_kms(&i915->drm, "\tMemory up\n");
 	if (val & PSR_EVENT_FRONT_BUFFER_MODIFY)
-		DRM_DEBUG_KMS("\tFront buffer modification\n");
+		drm_dbg_kms(&i915->drm, "\tFront buffer modification\n");
 	if (val & PSR_EVENT_WD_TIMER_EXPIRE)
-		DRM_DEBUG_KMS("\tPSR watchdog timer expired\n");
+		drm_dbg_kms(&i915->drm, "\tPSR watchdog timer expired\n");
 	if (val & PSR_EVENT_PIPE_REGISTERS_UPDATE)
-		DRM_DEBUG_KMS("\tPIPE registers updated\n");
+		drm_dbg_kms(&i915->drm, "\tPIPE registers updated\n");
 	if (val & PSR_EVENT_REGISTER_UPDATE)
-		DRM_DEBUG_KMS("\tRegister updated\n");
+		drm_dbg_kms(&i915->drm, "\tRegister updated\n");
 	if (val & PSR_EVENT_HDCP_ENABLE)
-		DRM_DEBUG_KMS("\tHDCP enabled\n");
+		drm_dbg_kms(&i915->drm, "\tHDCP enabled\n");
 	if (val & PSR_EVENT_KVMR_SESSION_ENABLE)
-		DRM_DEBUG_KMS("\tKVMR session enabled\n");
+		drm_dbg_kms(&i915->drm, "\tKVMR session enabled\n");
 	if (val & PSR_EVENT_VBI_ENABLE)
-		DRM_DEBUG_KMS("\tVBI enabled\n");
+		drm_dbg_kms(&i915->drm, "\tVBI enabled\n");
 	if (val & PSR_EVENT_LPSP_MODE_EXIT)
-		DRM_DEBUG_KMS("\tLPSP mode exited\n");
+		drm_dbg_kms(&i915->drm, "\tLPSP mode exited\n");
 	if ((val & PSR_EVENT_PSR_DISABLE) && !psr2_enabled)
-		DRM_DEBUG_KMS("\tPSR disabled\n");
+		drm_dbg_kms(&i915->drm, "\tPSR disabled\n");
 }
 
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
@@ -209,7 +211,7 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 
 			intel_de_write(dev_priv, PSR_EVENT(cpu_transcoder),
 				       val);
-			psr_event_print(val, psr2_enabled);
+			psr_event_print(dev_priv, val, psr2_enabled);
 		}
 	}
 
@@ -249,18 +251,21 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp)
 
 static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 val = 8; /* assume the worst if we can't read the value */
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1)
 		val &= DP_MAX_RESYNC_FRAME_COUNT_MASK;
 	else
-		DRM_DEBUG_KMS("Unable to get sink synchronization latency, assuming 8 frames\n");
+		drm_dbg_kms(&i915->drm,
+			    "Unable to get sink synchronization latency, assuming 8 frames\n");
 	return val;
 }
 
 static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u16 val;
 	ssize_t r;
 
@@ -273,7 +278,8 @@ static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp)
 
 	r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_X_GRANULARITY, &val, 2);
 	if (r != 2)
-		DRM_DEBUG_KMS("Unable to read DP_PSR2_SU_X_GRANULARITY\n");
+		drm_dbg_kms(&i915->drm,
+			    "Unable to read DP_PSR2_SU_X_GRANULARITY\n");
 
 	/*
 	 * Spec says that if the value read is 0 the default granularity should
@@ -352,39 +358,6 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	}
 }
 
-static void intel_psr_setup_vsc(struct intel_dp *intel_dp,
-				const struct intel_crtc_state *crtc_state)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	struct dp_sdp psr_vsc;
-
-	if (dev_priv->psr.psr2_enabled) {
-		/* Prepare VSC Header for SU as per EDP 1.4 spec, Table 6.11 */
-		memset(&psr_vsc, 0, sizeof(psr_vsc));
-		psr_vsc.sdp_header.HB0 = 0;
-		psr_vsc.sdp_header.HB1 = 0x7;
-		if (dev_priv->psr.colorimetry_support) {
-			psr_vsc.sdp_header.HB2 = 0x5;
-			psr_vsc.sdp_header.HB3 = 0x13;
-		} else {
-			psr_vsc.sdp_header.HB2 = 0x4;
-			psr_vsc.sdp_header.HB3 = 0xe;
-		}
-	} else {
-		/* Prepare VSC packet as per EDP 1.3 spec, Table 3.10 */
-		memset(&psr_vsc, 0, sizeof(psr_vsc));
-		psr_vsc.sdp_header.HB0 = 0;
-		psr_vsc.sdp_header.HB1 = 0x7;
-		psr_vsc.sdp_header.HB2 = 0x2;
-		psr_vsc.sdp_header.HB3 = 0x8;
-	}
-
-	intel_dig_port->write_infoframe(&intel_dig_port->base,
-					crtc_state,
-					DP_SDP_VSC, &psr_vsc, sizeof(psr_vsc));
-}
-
 static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
@@ -751,6 +724,8 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 	if (intel_dp != dev_priv->psr.dp)
 		return;
 
+	if (!psr_global_enabled(dev_priv))
+		return;
 	/*
 	 * HSW spec explicitly says PSR is tied to port A.
 	 * BDW+ platforms have a instance of PSR registers per transcoder but
@@ -793,6 +768,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 
 	crtc_state->has_psr = true;
 	crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state);
+	crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_VSC);
 }
 
 static void intel_psr_activate(struct intel_dp *intel_dp)
@@ -875,9 +851,12 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
-				    const struct intel_crtc_state *crtc_state)
+				    const struct intel_crtc_state *crtc_state,
+				    const struct drm_connector_state *conn_state)
 {
 	struct intel_dp *intel_dp = dev_priv->psr.dp;
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *encoder = &intel_dig_port->base;
 	u32 val;
 
 	drm_WARN_ON(&dev_priv->drm, dev_priv->psr.enabled);
@@ -916,7 +895,9 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 
 	drm_dbg_kms(&dev_priv->drm, "Enabling PSR%s\n",
 		    dev_priv->psr.psr2_enabled ? "2" : "1");
-	intel_psr_setup_vsc(intel_dp, crtc_state);
+	intel_dp_compute_psr_vsc_sdp(intel_dp, crtc_state, conn_state,
+				     &dev_priv->psr.vsc);
+	intel_write_dp_vsc_sdp(encoder, crtc_state, &dev_priv->psr.vsc);
 	intel_psr_enable_sink(intel_dp);
 	intel_psr_enable_source(intel_dp, crtc_state);
 	dev_priv->psr.enabled = true;
@@ -928,11 +909,13 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
  * intel_psr_enable - Enable PSR
  * @intel_dp: Intel DP
  * @crtc_state: new CRTC state
+ * @conn_state: new CONNECTOR state
  *
  * This function can only be called after the pipe is fully trained and enabled.
  */
 void intel_psr_enable(struct intel_dp *intel_dp,
-		      const struct intel_crtc_state *crtc_state)
+		      const struct intel_crtc_state *crtc_state,
+		      const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
@@ -953,7 +936,7 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 		goto unlock;
 	}
 
-	intel_psr_enable_locked(dev_priv, crtc_state);
+	intel_psr_enable_locked(dev_priv, crtc_state, conn_state);
 
 unlock:
 	mutex_unlock(&dev_priv->psr.lock);
@@ -1086,13 +1069,15 @@ static void psr_force_hw_tracking_exit(struct drm_i915_private *dev_priv)
  * intel_psr_update - Update PSR state
  * @intel_dp: Intel DP
  * @crtc_state: new CRTC state
+ * @conn_state: new CONNECTOR state
  *
  * This functions will update PSR states, disabling, enabling or switching PSR
  * version when executing fastsets. For full modeset, intel_psr_disable() and
  * intel_psr_enable() should be called instead.
  */
 void intel_psr_update(struct intel_dp *intel_dp,
-		      const struct intel_crtc_state *crtc_state)
+		      const struct intel_crtc_state *crtc_state,
+		      const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	struct i915_psr *psr = &dev_priv->psr;
@@ -1129,7 +1114,7 @@ void intel_psr_update(struct intel_dp *intel_dp,
 		intel_psr_disable_locked(intel_dp);
 
 	if (enable)
-		intel_psr_enable_locked(dev_priv, crtc_state);
+		intel_psr_enable_locked(dev_priv, crtc_state, conn_state);
 
 unlock:
 	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 274fc6bb6221..b4515186d5f4 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -17,11 +17,13 @@ struct intel_dp;
 #define CAN_PSR(dev_priv) (HAS_PSR(dev_priv) && dev_priv->psr.sink_support)
 void intel_psr_init_dpcd(struct intel_dp *intel_dp);
 void intel_psr_enable(struct intel_dp *intel_dp,
-		      const struct intel_crtc_state *crtc_state);
+		      const struct intel_crtc_state *crtc_state,
+		      const struct drm_connector_state *conn_state);
 void intel_psr_disable(struct intel_dp *intel_dp,
 		       const struct intel_crtc_state *old_crtc_state);
 void intel_psr_update(struct intel_dp *intel_dp,
-		      const struct intel_crtc_state *crtc_state);
+		      const struct intel_crtc_state *crtc_state,
+		      const struct drm_connector_state *conn_state);
 int intel_psr_debug_set(struct drm_i915_private *dev_priv, u64 value);
 void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 			  unsigned frontbuffer_bits,
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 637d8fe2f8c2..bc6c26818e15 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1430,7 +1430,8 @@ static void intel_sdvo_update_props(struct intel_sdvo *intel_sdvo,
 #undef UPDATE_PROPERTY
 }
 
-static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
+static void intel_sdvo_pre_enable(struct intel_atomic_state *state,
+				  struct intel_encoder *intel_encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
@@ -1727,7 +1728,8 @@ static void intel_sdvo_enable_audio(struct intel_sdvo *intel_sdvo,
 				   SDVO_AUDIO_PRESENCE_DETECT);
 }
 
-static void intel_disable_sdvo(struct intel_encoder *encoder,
+static void intel_disable_sdvo(struct intel_atomic_state *state,
+			       struct intel_encoder *encoder,
 			       const struct intel_crtc_state *old_crtc_state,
 			       const struct drm_connector_state *conn_state)
 {
@@ -1775,20 +1777,23 @@ static void intel_disable_sdvo(struct intel_encoder *encoder,
 	}
 }
 
-static void pch_disable_sdvo(struct intel_encoder *encoder,
+static void pch_disable_sdvo(struct intel_atomic_state *state,
+			     struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
 }
 
-static void pch_post_disable_sdvo(struct intel_encoder *encoder,
+static void pch_post_disable_sdvo(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *old_crtc_state,
 				  const struct drm_connector_state *old_conn_state)
 {
-	intel_disable_sdvo(encoder, old_crtc_state, old_conn_state);
+	intel_disable_sdvo(state, encoder, old_crtc_state, old_conn_state);
 }
 
-static void intel_enable_sdvo(struct intel_encoder *encoder,
+static void intel_enable_sdvo(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
@@ -1934,12 +1939,11 @@ static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder)
 
 static enum intel_hotplug_state
 intel_sdvo_hotplug(struct intel_encoder *encoder,
-		   struct intel_connector *connector,
-		   bool irq_received)
+		   struct intel_connector *connector)
 {
 	intel_sdvo_enable_hotplug(encoder);
 
-	return intel_encoder_hotplug(encoder, connector, irq_received);
+	return intel_encoder_hotplug(encoder, connector);
 }
 
 static bool
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 33d886141138..0000ec7055f7 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2503,6 +2503,7 @@ static const u32 skl_plane_formats[] = {
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_VYUY,
+	DRM_FORMAT_XYUV8888,
 };
 
 static const u32 skl_planar_formats[] = {
@@ -2521,6 +2522,7 @@ static const u32 skl_planar_formats[] = {
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_VYUY,
 	DRM_FORMAT_NV12,
+	DRM_FORMAT_XYUV8888,
 };
 
 static const u32 glk_planar_formats[] = {
@@ -2539,6 +2541,7 @@ static const u32 glk_planar_formats[] = {
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_VYUY,
 	DRM_FORMAT_NV12,
+	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_P010,
 	DRM_FORMAT_P012,
 	DRM_FORMAT_P016,
@@ -2562,6 +2565,7 @@ static const u32 icl_sdr_y_plane_formats[] = {
 	DRM_FORMAT_Y210,
 	DRM_FORMAT_Y212,
 	DRM_FORMAT_Y216,
+	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
 	DRM_FORMAT_XVYU12_16161616,
 	DRM_FORMAT_XVYU16161616,
@@ -2589,6 +2593,7 @@ static const u32 icl_sdr_uv_plane_formats[] = {
 	DRM_FORMAT_Y210,
 	DRM_FORMAT_Y212,
 	DRM_FORMAT_Y216,
+	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
 	DRM_FORMAT_XVYU12_16161616,
 	DRM_FORMAT_XVYU16161616,
@@ -2620,6 +2625,7 @@ static const u32 icl_hdr_plane_formats[] = {
 	DRM_FORMAT_Y210,
 	DRM_FORMAT_Y212,
 	DRM_FORMAT_Y216,
+	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
 	DRM_FORMAT_XVYU12_16161616,
 	DRM_FORMAT_XVYU16161616,
@@ -2790,6 +2796,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
 	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_XYUV8888:
 	case DRM_FORMAT_P010:
 	case DRM_FORMAT_P012:
 	case DRM_FORMAT_P016:
@@ -2860,6 +2867,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
 	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_XYUV8888:
 	case DRM_FORMAT_P010:
 	case DRM_FORMAT_P012:
 	case DRM_FORMAT_P016:
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 9b850c11aa78..b161c15baf86 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -34,6 +34,7 @@ tc_port_load_fia_params(struct drm_i915_private *i915,
 	if (INTEL_INFO(i915)->display.has_modular_fia) {
 		modular_fia = intel_uncore_read(&i915->uncore,
 						PORT_TX_DFLEXDPSP(FIA1));
+		drm_WARN_ON(&i915->drm, modular_fia == 0xffffffff);
 		modular_fia &= MODULAR_FIA_MASK;
 	} else {
 		modular_fia = 0;
@@ -52,6 +53,62 @@ tc_port_load_fia_params(struct drm_i915_private *i915,
 	}
 }
 
+static enum intel_display_power_domain
+tc_cold_get_power_domain(struct intel_digital_port *dig_port)
+{
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+
+	if (INTEL_GEN(i915) == 11)
+		return intel_legacy_aux_to_power_domain(dig_port->aux_ch);
+	else
+		return POWER_DOMAIN_TC_COLD_OFF;
+}
+
+static intel_wakeref_t
+tc_cold_block(struct intel_digital_port *dig_port)
+{
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	enum intel_display_power_domain domain;
+
+	if (INTEL_GEN(i915) == 11 && !dig_port->tc_legacy_port)
+		return 0;
+
+	domain = tc_cold_get_power_domain(dig_port);
+	return intel_display_power_get(i915, domain);
+}
+
+static void
+tc_cold_unblock(struct intel_digital_port *dig_port, intel_wakeref_t wakeref)
+{
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	enum intel_display_power_domain domain;
+
+	/*
+	 * wakeref == -1, means some error happened saving save_depot_stack but
+	 * power should still be put down and 0 is a invalid save_depot_stack
+	 * id so can be used to skip it for non TC legacy ports.
+	 */
+	if (wakeref == 0)
+		return;
+
+	domain = tc_cold_get_power_domain(dig_port);
+	intel_display_power_put_async(i915, domain, wakeref);
+}
+
+static void
+assert_tc_cold_blocked(struct intel_digital_port *dig_port)
+{
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	bool enabled;
+
+	if (INTEL_GEN(i915) == 11 && !dig_port->tc_legacy_port)
+		return;
+
+	enabled = intel_display_power_is_enabled(i915,
+						 tc_cold_get_power_domain(dig_port));
+	drm_WARN_ON(&i915->drm, !enabled);
+}
+
 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);
@@ -62,6 +119,7 @@ u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 				      PORT_TX_DFLEXDPSP(dig_port->tc_phy_fia));
 
 	drm_WARN_ON(&i915->drm, lane_mask == 0xffffffff);
+	assert_tc_cold_blocked(dig_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);
@@ -77,6 +135,7 @@ u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port)
 				     PORT_TX_DFLEXPA1(dig_port->tc_phy_fia));
 
 	drm_WARN_ON(&i915->drm, pin_mask == 0xffffffff);
+	assert_tc_cold_blocked(dig_port);
 
 	return (pin_mask & DP_PIN_ASSIGNMENT_MASK(dig_port->tc_phy_fia_idx)) >>
 	       DP_PIN_ASSIGNMENT_SHIFT(dig_port->tc_phy_fia_idx);
@@ -91,6 +150,8 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port)
 	if (dig_port->tc_mode != TC_PORT_DP_ALT)
 		return 4;
 
+	assert_tc_cold_blocked(dig_port);
+
 	lane_mask = 0;
 	with_intel_display_power(i915, POWER_DOMAIN_DISPLAY_CORE, wakeref)
 		lane_mask = intel_tc_port_get_lane_mask(dig_port);
@@ -123,6 +184,8 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 	drm_WARN_ON(&i915->drm,
 		    lane_reversal && dig_port->tc_mode != TC_PORT_LEGACY);
 
+	assert_tc_cold_blocked(dig_port);
+
 	val = intel_uncore_read(uncore,
 				PORT_TX_DFLEXDPMLE1(dig_port->tc_phy_fia));
 	val &= ~DFLEXDPMLE1_DPMLETC_MASK(dig_port->tc_phy_fia_idx);
@@ -152,6 +215,7 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port,
 				      u32 live_status_mask)
 {
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	u32 valid_hpd_mask;
 
 	if (dig_port->tc_legacy_port)
@@ -164,8 +228,9 @@ static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port,
 		return;
 
 	/* If live status mismatches the VBT flag, trust the live status. */
-	DRM_ERROR("Port %s: live status %08x mismatches the legacy port flag, fix flag\n",
-		  dig_port->tc_port_name, live_status_mask);
+	drm_err(&i915->drm,
+		"Port %s: live status %08x mismatches the legacy port flag, fix flag\n",
+		dig_port->tc_port_name, live_status_mask);
 
 	dig_port->tc_legacy_port = !dig_port->tc_legacy_port;
 }
@@ -173,8 +238,8 @@ static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port,
 static u32 tc_port_live_status_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 isr_bit = i915->hotplug.pch_hpd[dig_port->base.hpd_pin];
 	u32 mask = 0;
 	u32 val;
 
@@ -193,7 +258,7 @@ static u32 tc_port_live_status_mask(struct intel_digital_port *dig_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))
+	if (intel_uncore_read(uncore, SDEISR) & isr_bit)
 		mask |= BIT(TC_PORT_LEGACY);
 
 	/* The sink can be connected only in a single mode. */
@@ -233,8 +298,7 @@ static bool icl_tc_phy_set_safe_mode(struct intel_digital_port *dig_port,
 	if (val == 0xffffffff) {
 		drm_dbg_kms(&i915->drm,
 			    "Port %s: PHY in TCCOLD, can't set safe-mode to %s\n",
-			    dig_port->tc_port_name,
-			      enableddisabled(enable));
+			    dig_port->tc_port_name, enableddisabled(enable));
 
 		return false;
 	}
@@ -286,11 +350,12 @@ static bool icl_tc_phy_is_in_safe_mode(struct intel_digital_port *dig_port)
 static void icl_tc_phy_connect(struct intel_digital_port *dig_port,
 			       int required_lanes)
 {
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	int max_lanes;
 
 	if (!icl_tc_phy_status_complete(dig_port)) {
-		DRM_DEBUG_KMS("Port %s: PHY not ready\n",
-			      dig_port->tc_port_name);
+		drm_dbg_kms(&i915->drm, "Port %s: PHY not ready\n",
+			    dig_port->tc_port_name);
 		goto out_set_tbt_alt_mode;
 	}
 
@@ -311,15 +376,16 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port,
 	 * became disconnected. Not necessary for legacy mode.
 	 */
 	if (!(tc_port_live_status_mask(dig_port) & BIT(TC_PORT_DP_ALT))) {
-		DRM_DEBUG_KMS("Port %s: PHY sudden disconnect\n",
-			      dig_port->tc_port_name);
+		drm_dbg_kms(&i915->drm, "Port %s: PHY sudden disconnect\n",
+			    dig_port->tc_port_name);
 		goto out_set_safe_mode;
 	}
 
 	if (max_lanes < required_lanes) {
-		DRM_DEBUG_KMS("Port %s: PHY max lanes %d < required lanes %d\n",
-			      dig_port->tc_port_name,
-			      max_lanes, required_lanes);
+		drm_dbg_kms(&i915->drm,
+			    "Port %s: PHY max lanes %d < required lanes %d\n",
+			    dig_port->tc_port_name,
+			    max_lanes, required_lanes);
 		goto out_set_safe_mode;
 	}
 
@@ -357,15 +423,17 @@ static void icl_tc_phy_disconnect(struct intel_digital_port *dig_port)
 
 static bool icl_tc_phy_is_connected(struct intel_digital_port *dig_port)
 {
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+
 	if (!icl_tc_phy_status_complete(dig_port)) {
-		DRM_DEBUG_KMS("Port %s: PHY status not complete\n",
-			      dig_port->tc_port_name);
+		drm_dbg_kms(&i915->drm, "Port %s: PHY status not complete\n",
+			    dig_port->tc_port_name);
 		return dig_port->tc_mode == TC_PORT_TBT_ALT;
 	}
 
 	if (icl_tc_phy_is_in_safe_mode(dig_port)) {
-		DRM_DEBUG_KMS("Port %s: PHY still in safe mode\n",
-			      dig_port->tc_port_name);
+		drm_dbg_kms(&i915->drm, "Port %s: PHY still in safe mode\n",
+			    dig_port->tc_port_name);
 
 		return false;
 	}
@@ -415,9 +483,14 @@ static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port,
 	enum tc_port_mode old_tc_mode = dig_port->tc_mode;
 
 	intel_display_power_flush_work(i915);
-	drm_WARN_ON(&i915->drm,
-		    intel_display_power_is_enabled(i915,
-					intel_aux_power_domain(dig_port)));
+	if (INTEL_GEN(i915) != 11 || !dig_port->tc_legacy_port) {
+		enum intel_display_power_domain aux_domain;
+		bool aux_powered;
+
+		aux_domain = intel_aux_power_domain(dig_port);
+		aux_powered = intel_display_power_is_enabled(i915, aux_domain);
+		drm_WARN_ON(&i915->drm, aux_powered);
+	}
 
 	icl_tc_phy_disconnect(dig_port);
 	icl_tc_phy_connect(dig_port, required_lanes);
@@ -438,10 +511,13 @@ intel_tc_port_link_init_refcount(struct intel_digital_port *dig_port,
 
 void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 {
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	struct intel_encoder *encoder = &dig_port->base;
+	intel_wakeref_t tc_cold_wref;
 	int active_links = 0;
 
 	mutex_lock(&dig_port->tc_lock);
+	tc_cold_wref = tc_cold_block(dig_port);
 
 	dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port);
 	if (dig_port->dp.is_mst)
@@ -451,8 +527,9 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 
 	if (active_links) {
 		if (!icl_tc_phy_is_connected(dig_port))
-			DRM_DEBUG_KMS("Port %s: PHY disconnected with %d active link(s)\n",
-				      dig_port->tc_port_name, active_links);
+			drm_dbg_kms(&i915->drm,
+				    "Port %s: PHY disconnected with %d active link(s)\n",
+				    dig_port->tc_port_name, active_links);
 		intel_tc_port_link_init_refcount(dig_port, active_links);
 
 		goto out;
@@ -462,10 +539,11 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 		icl_tc_phy_connect(dig_port, 1);
 
 out:
-	DRM_DEBUG_KMS("Port %s: sanitize mode (%s)\n",
-		      dig_port->tc_port_name,
-		      tc_port_mode_name(dig_port->tc_mode));
+	drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n",
+		    dig_port->tc_port_name,
+		    tc_port_mode_name(dig_port->tc_mode));
 
+	tc_cold_unblock(dig_port, tc_cold_wref);
 	mutex_unlock(&dig_port->tc_lock);
 }
 
@@ -484,13 +562,19 @@ static bool intel_tc_port_needs_reset(struct intel_digital_port *dig_port)
  * connected ports are usable, and avoids exposing to the users objects they
  * can't really use.
  */
-bool intel_tc_port_connected(struct intel_digital_port *dig_port)
+bool intel_tc_port_connected(struct intel_encoder *encoder)
 {
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_connected;
+	intel_wakeref_t tc_cold_wref;
 
 	intel_tc_port_lock(dig_port);
+	tc_cold_wref = tc_cold_block(dig_port);
+
 	is_connected = tc_port_live_status_mask(dig_port) &
 		       BIT(dig_port->tc_mode);
+
+	tc_cold_unblock(dig_port, tc_cold_wref);
 	intel_tc_port_unlock(dig_port);
 
 	return is_connected;
@@ -506,9 +590,16 @@ static void __intel_tc_port_lock(struct intel_digital_port *dig_port,
 
 	mutex_lock(&dig_port->tc_lock);
 
-	if (!dig_port->tc_link_refcount &&
-	    intel_tc_port_needs_reset(dig_port))
-		intel_tc_port_reset_mode(dig_port, required_lanes);
+	if (!dig_port->tc_link_refcount) {
+		intel_wakeref_t tc_cold_wref;
+
+		tc_cold_wref = tc_cold_block(dig_port);
+
+		if (intel_tc_port_needs_reset(dig_port))
+			intel_tc_port_reset_mode(dig_port, required_lanes);
+
+		tc_cold_unblock(dig_port, tc_cold_wref);
+	}
 
 	drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref);
 	dig_port->tc_lock_wakeref = wakeref;
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 463f1b3c836f..b619e4736f85 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -10,8 +10,9 @@
 #include <linux/types.h>
 
 struct intel_digital_port;
+struct intel_encoder;
 
-bool intel_tc_port_connected(struct intel_digital_port *dig_port);
+bool intel_tc_port_connected(struct intel_encoder *encoder);
 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);
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index d2e3a3a323e9..fbe12aad7d58 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -914,7 +914,8 @@ intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe)
 }
 
 static void
-intel_enable_tv(struct intel_encoder *encoder,
+intel_enable_tv(struct intel_atomic_state *state,
+		struct intel_encoder *encoder,
 		const struct intel_crtc_state *pipe_config,
 		const struct drm_connector_state *conn_state)
 {
@@ -930,7 +931,8 @@ intel_enable_tv(struct intel_encoder *encoder,
 }
 
 static void
-intel_disable_tv(struct intel_encoder *encoder,
+intel_disable_tv(struct intel_atomic_state *state,
+		 struct intel_encoder *encoder,
 		 const struct intel_crtc_state *old_crtc_state,
 		 const struct drm_connector_state *old_conn_state)
 {
@@ -1414,7 +1416,8 @@ static void set_color_conversion(struct drm_i915_private *dev_priv,
 		       (color_conversion->bv << 16) | color_conversion->av);
 }
 
-static void intel_tv_pre_enable(struct intel_encoder *encoder,
+static void intel_tv_pre_enable(struct intel_atomic_state *state,
+				struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
@@ -1698,13 +1701,13 @@ intel_tv_detect(struct drm_connector *connector,
 		struct drm_modeset_acquire_ctx *ctx,
 		bool force)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector));
 	enum drm_connector_status status;
 	int type;
 
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
-		      connector->base.id, connector->name,
-		      force);
+	drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] force=%d\n",
+		    connector->base.id, connector->name, force);
 
 	if (force) {
 		struct intel_load_detect_pipe tmp;
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 05c7cbe32eb4..aef7fe932d1a 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -462,7 +462,7 @@ struct bdb_general_definitions {
 	 * number = (block_size - sizeof(bdb_general_definitions))/
 	 *	     defs->child_dev_size;
 	 */
-	u8 devices[0];
+	u8 devices[];
 } __packed;
 
 /*
@@ -839,7 +839,7 @@ struct bdb_mipi_config {
 
 struct bdb_mipi_sequence {
 	u8 version;
-	u8 data[0]; /* up to 6 variable length blocks */
+	u8 data[]; /* up to 6 variable length blocks */
 } __packed;
 
 /*
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index f4c362dc6e15..f582ab52f0b0 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -267,7 +267,6 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int ret;
@@ -279,11 +278,11 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
 		if (HAS_GMCH(dev_priv))
-			intel_gmch_panel_fitting(crtc, pipe_config,
-						 conn_state->scaling_mode);
+			ret = intel_gmch_panel_fitting(pipe_config, conn_state);
 		else
-			intel_pch_panel_fitting(crtc, pipe_config,
-						conn_state->scaling_mode);
+			ret = intel_pch_panel_fitting(pipe_config, conn_state);
+		if (ret)
+			return ret;
 	}
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
@@ -759,7 +758,8 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder);
  * DSI port enable has to be done before pipe and plane enable, so we do it in
  * the pre_enable hook instead of the enable hook.
  */
-static void intel_dsi_pre_enable(struct intel_encoder *encoder,
+static void intel_dsi_pre_enable(struct intel_atomic_state *state,
+				 struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
@@ -858,11 +858,12 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
 }
 
-static void bxt_dsi_enable(struct intel_encoder *encoder,
+static void bxt_dsi_enable(struct intel_atomic_state *state,
+			   struct intel_encoder *encoder,
 			   const struct intel_crtc_state *crtc_state,
 			   const struct drm_connector_state *conn_state)
 {
-	WARN_ON(crtc_state->has_pch_encoder);
+	drm_WARN_ON(state->base.dev, crtc_state->has_pch_encoder);
 
 	intel_crtc_vblank_on(crtc_state);
 }
@@ -871,14 +872,16 @@ static void bxt_dsi_enable(struct intel_encoder *encoder,
  * DSI port disable has to be done after pipe and plane disable, so we do it in
  * the post_disable hook.
  */
-static void intel_dsi_disable(struct intel_encoder *encoder,
+static void intel_dsi_disable(struct intel_atomic_state *state,
+			      struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(&i915->drm, "\n");
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
 	intel_panel_disable_backlight(old_conn_state);
@@ -906,7 +909,8 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 		vlv_dsi_clear_device_ready(encoder);
 }
 
-static void intel_dsi_post_disable(struct intel_encoder *encoder,
+static void intel_dsi_post_disable(struct intel_atomic_state *state,
+				   struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 34be4c0ee7c5..bc0223716906 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -108,7 +108,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	if (clflush) {
 		i915_sw_fence_await_reservation(&clflush->base.chain,
 						obj->base.resv, NULL, true,
-						I915_FENCE_TIMEOUT,
+						i915_fence_timeout(to_i915(obj->base.dev)),
 						I915_FENCE_GFP);
 		dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma);
 		dma_fence_work_commit(&clflush->base);
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 0598e5382a1d..d3a86a4d5c04 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -6,7 +6,6 @@
 #include "i915_drv.h"
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
-#include "gt/intel_engine_pool.h"
 #include "i915_gem_client_blt.h"
 #include "i915_gem_object_blt.h"
 
@@ -289,8 +288,7 @@ int i915_gem_schedule_fill_pages_blt(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_lock(obj);
 	err = i915_sw_fence_await_reservation(&work->wait,
-					      obj->base.resv, NULL,
-					      true, I915_FENCE_TIMEOUT,
+					      obj->base.resv, NULL, true, 0,
 					      I915_FENCE_GFP);
 	if (err < 0) {
 		dma_fence_set_error(&work->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 68326ad3b2e0..900ea8b7fc8f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -130,9 +130,7 @@ static void lut_close(struct i915_gem_context *ctx)
 		if (&lut->obj_link != &obj->lut_list) {
 			i915_lut_handle_free(lut);
 			radix_tree_iter_delete(&ctx->handles_vma, &iter, slot);
-			if (atomic_dec_and_test(&vma->open_count) &&
-			    !i915_vma_is_ggtt(vma))
-				i915_vma_close(vma);
+			i915_vma_close(vma);
 			i915_gem_object_put(obj);
 		}
 
@@ -570,23 +568,19 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 	engines->ctx = i915_gem_context_get(ctx);
 
 	for_each_gem_engine(ce, engines, it) {
-		struct dma_fence *fence;
-		int err = 0;
+		int err;
 
 		/* serialises with execbuf */
 		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
 		if (!intel_context_pin_if_active(ce))
 			continue;
 
-		fence = i915_active_fence_get(&ce->timeline->last_request);
-		if (fence) {
-			err = i915_sw_fence_await_dma_fence(&engines->fence,
-							    fence, 0,
-							    GFP_KERNEL);
-			dma_fence_put(fence);
-		}
+		/* Wait until context is finally scheduled out and retired */
+		err = i915_sw_fence_await_active(&engines->fence,
+						 &ce->active,
+						 I915_ACTIVE_AWAIT_BARRIER);
 		intel_context_unpin(ce);
-		if (err < 0)
+		if (err)
 			goto kill;
 	}
 
@@ -757,21 +751,46 @@ err_free:
 	return ERR_PTR(err);
 }
 
+static inline struct i915_gem_engines *
+__context_engines_await(const struct i915_gem_context *ctx)
+{
+	struct i915_gem_engines *engines;
+
+	rcu_read_lock();
+	do {
+		engines = rcu_dereference(ctx->engines);
+		GEM_BUG_ON(!engines);
+
+		if (unlikely(!i915_sw_fence_await(&engines->fence)))
+			continue;
+
+		if (likely(engines == rcu_access_pointer(ctx->engines)))
+			break;
+
+		i915_sw_fence_complete(&engines->fence);
+	} while (1);
+	rcu_read_unlock();
+
+	return engines;
+}
+
 static int
 context_apply_all(struct i915_gem_context *ctx,
 		  int (*fn)(struct intel_context *ce, void *data),
 		  void *data)
 {
 	struct i915_gem_engines_iter it;
+	struct i915_gem_engines *e;
 	struct intel_context *ce;
 	int err = 0;
 
-	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+	e = __context_engines_await(ctx);
+	for_each_gem_engine(ce, e, it) {
 		err = fn(ce, data);
 		if (err)
 			break;
 	}
-	i915_gem_context_unlock_engines(ctx);
+	i915_sw_fence_complete(&e->fence);
 
 	return err;
 }
@@ -786,11 +805,13 @@ static int __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 = i915_gem_context_vm(ctx);
+	struct i915_address_space *old;
 
+	old = rcu_replace_pointer(ctx->vm,
+				  i915_vm_open(vm),
+				  lockdep_is_held(&ctx->mutex));
 	GEM_BUG_ON(old && i915_vm_is_4lvl(vm) != i915_vm_is_4lvl(old));
 
-	rcu_assign_pointer(ctx->vm, i915_vm_open(vm));
 	context_apply_all(ctx, __apply_ppgtt, vm);
 
 	return old;
@@ -1069,30 +1090,6 @@ static void cb_retire(struct i915_active *base)
 	kfree(cb);
 }
 
-static inline struct i915_gem_engines *
-__context_engines_await(const struct i915_gem_context *ctx)
-{
-	struct i915_gem_engines *engines;
-
-	rcu_read_lock();
-	do {
-		engines = rcu_dereference(ctx->engines);
-		if (unlikely(!engines))
-			break;
-
-		if (unlikely(!i915_sw_fence_await(&engines->fence)))
-			continue;
-
-		if (likely(engines == rcu_access_pointer(ctx->engines)))
-			break;
-
-		i915_sw_fence_complete(&engines->fence);
-	} while (1);
-	rcu_read_unlock();
-
-	return engines;
-}
-
 I915_SELFTEST_DECLARE(static intel_engine_mask_t context_barrier_inject_fault);
 static int context_barrier_task(struct i915_gem_context *ctx,
 				intel_engine_mask_t engines,
@@ -1401,10 +1398,10 @@ static int get_ringsize(struct i915_gem_context *ctx,
 	return 0;
 }
 
-static int
-user_to_context_sseu(struct drm_i915_private *i915,
-		     const struct drm_i915_gem_context_param_sseu *user,
-		     struct intel_sseu *context)
+int
+i915_gem_user_to_context_sseu(struct drm_i915_private *i915,
+			      const struct drm_i915_gem_context_param_sseu *user,
+			      struct intel_sseu *context)
 {
 	const struct sseu_dev_info *device = &RUNTIME_INFO(i915)->sseu;
 
@@ -1539,7 +1536,7 @@ static int set_sseu(struct i915_gem_context *ctx,
 		goto out_ce;
 	}
 
-	ret = user_to_context_sseu(i915, &user_sseu, &sseu);
+	ret = i915_gem_user_to_context_sseu(i915, &user_sseu, &sseu);
 	if (ret)
 		goto out_ce;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index f1d884d304bd..3702b2fb27ab 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -225,4 +225,8 @@ i915_gem_engines_iter_next(struct i915_gem_engines_iter *it);
 struct i915_lut_handle *i915_lut_handle_alloc(void);
 void i915_lut_handle_free(struct i915_lut_handle *lut);
 
+int i915_gem_user_to_context_sseu(struct drm_i915_private *i915,
+				  const struct drm_i915_gem_context_param_sseu *user,
+				  struct intel_sseu *context);
+
 #endif /* !__I915_GEM_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 4f96c8788a2e..7f76fc68f498 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -368,7 +368,7 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 
-	if (!atomic_read(&obj->bind_count))
+	if (list_empty(&obj->vma.list))
 		return;
 
 	mutex_lock(&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 8a4e9c1cbf6c..3ce185670ca4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -15,8 +15,8 @@
 
 #include "gem/i915_gem_ioctls.h"
 #include "gt/intel_context.h"
-#include "gt/intel_engine_pool.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_buffer_pool.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_ring.h"
 
@@ -40,6 +40,11 @@ struct eb_vma {
 	u32 handle;
 };
 
+struct eb_vma_array {
+	struct kref kref;
+	struct eb_vma vma[];
+};
+
 enum {
 	FORCE_CPU_RELOC = 1,
 	FORCE_GTT_RELOC,
@@ -52,7 +57,6 @@ enum {
 #define __EXEC_OBJECT_NEEDS_MAP		BIT(29)
 #define __EXEC_OBJECT_NEEDS_BIAS	BIT(28)
 #define __EXEC_OBJECT_INTERNAL_FLAGS	(~0u << 28) /* all of the above */
-#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE)
 
 #define __EXEC_HAS_RELOC	BIT(31)
 #define __EXEC_INTERNAL_FLAGS	(~0u << 31)
@@ -264,7 +268,9 @@ struct i915_execbuffer {
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
 
+		struct i915_vma *target;
 		struct i915_request *rq;
+		struct i915_vma *rq_vma;
 		u32 *rq_cmd;
 		unsigned int rq_size;
 	} reloc_cache;
@@ -283,6 +289,7 @@ struct i915_execbuffer {
 	 */
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
+	struct eb_vma_array *array;
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -292,8 +299,62 @@ static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 		 eb->args->batch_len);
 }
 
+static struct eb_vma_array *eb_vma_array_create(unsigned int count)
+{
+	struct eb_vma_array *arr;
+
+	arr = kvmalloc(struct_size(arr, vma, count), GFP_KERNEL | __GFP_NOWARN);
+	if (!arr)
+		return NULL;
+
+	kref_init(&arr->kref);
+	arr->vma[0].vma = NULL;
+
+	return arr;
+}
+
+static inline void eb_unreserve_vma(struct eb_vma *ev)
+{
+	struct i915_vma *vma = ev->vma;
+
+	if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE))
+		__i915_vma_unpin_fence(vma);
+
+	if (ev->flags & __EXEC_OBJECT_HAS_PIN)
+		__i915_vma_unpin(vma);
+
+	ev->flags &= ~(__EXEC_OBJECT_HAS_PIN |
+		       __EXEC_OBJECT_HAS_FENCE);
+}
+
+static void eb_vma_array_destroy(struct kref *kref)
+{
+	struct eb_vma_array *arr = container_of(kref, typeof(*arr), kref);
+	struct eb_vma *ev = arr->vma;
+
+	while (ev->vma) {
+		eb_unreserve_vma(ev);
+		i915_vma_put(ev->vma);
+		ev++;
+	}
+
+	kvfree(arr);
+}
+
+static void eb_vma_array_put(struct eb_vma_array *arr)
+{
+	kref_put(&arr->kref, eb_vma_array_destroy);
+}
+
 static int eb_create(struct i915_execbuffer *eb)
 {
+	/* Allocate an extra slot for use by the command parser + sentinel */
+	eb->array = eb_vma_array_create(eb->buffer_count + 2);
+	if (!eb->array)
+		return -ENOMEM;
+
+	eb->vma = eb->array->vma;
+
 	if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) {
 		unsigned int size = 1 + ilog2(eb->buffer_count);
 
@@ -327,8 +388,10 @@ static int eb_create(struct i915_execbuffer *eb)
 				break;
 		} while (--size);
 
-		if (unlikely(!size))
+		if (unlikely(!size)) {
+			eb_vma_array_put(eb->array);
 			return -ENOMEM;
+		}
 
 		eb->lut_size = size;
 	} else {
@@ -368,6 +431,32 @@ eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry,
 	return false;
 }
 
+static u64 eb_pin_flags(const struct drm_i915_gem_exec_object2 *entry,
+			unsigned int exec_flags)
+{
+	u64 pin_flags = 0;
+
+	if (exec_flags & EXEC_OBJECT_NEEDS_GTT)
+		pin_flags |= PIN_GLOBAL;
+
+	/*
+	 * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
+	 * limit address to the first 4GBs for unflagged objects.
+	 */
+	if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
+		pin_flags |= PIN_ZONE_4G;
+
+	if (exec_flags & __EXEC_OBJECT_NEEDS_MAP)
+		pin_flags |= PIN_MAPPABLE;
+
+	if (exec_flags & EXEC_OBJECT_PINNED)
+		pin_flags |= entry->offset | PIN_OFFSET_FIXED;
+	else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS)
+		pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
+
+	return pin_flags;
+}
+
 static inline bool
 eb_pin_vma(struct i915_execbuffer *eb,
 	   const struct drm_i915_gem_exec_object2 *entry,
@@ -385,8 +474,19 @@ eb_pin_vma(struct i915_execbuffer *eb,
 	if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_GTT))
 		pin_flags |= PIN_GLOBAL;
 
-	if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags)))
-		return false;
+	/* Attempt to reuse the current location if available */
+	if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags))) {
+		if (entry->flags & EXEC_OBJECT_PINNED)
+			return false;
+
+		/* Failing that pick any _free_ space if suitable */
+		if (unlikely(i915_vma_pin(vma,
+					  entry->pad_to_size,
+					  entry->alignment,
+					  eb_pin_flags(entry, ev->flags) |
+					  PIN_USER | PIN_NOEVICT)))
+			return false;
+	}
 
 	if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) {
 		if (unlikely(i915_vma_pin_fence(vma))) {
@@ -402,26 +502,6 @@ eb_pin_vma(struct i915_execbuffer *eb,
 	return !eb_vma_misplaced(entry, vma, ev->flags);
 }
 
-static inline void __eb_unreserve_vma(struct i915_vma *vma, unsigned int flags)
-{
-	GEM_BUG_ON(!(flags & __EXEC_OBJECT_HAS_PIN));
-
-	if (unlikely(flags & __EXEC_OBJECT_HAS_FENCE))
-		__i915_vma_unpin_fence(vma);
-
-	__i915_vma_unpin(vma);
-}
-
-static inline void
-eb_unreserve_vma(struct eb_vma *ev)
-{
-	if (!(ev->flags & __EXEC_OBJECT_HAS_PIN))
-		return;
-
-	__eb_unreserve_vma(ev->vma, ev->flags);
-	ev->flags &= ~__EXEC_OBJECT_RESERVED;
-}
-
 static int
 eb_validate_vma(struct i915_execbuffer *eb,
 		struct drm_i915_gem_exec_object2 *entry,
@@ -481,7 +561,7 @@ eb_add_vma(struct i915_execbuffer *eb,
 
 	GEM_BUG_ON(i915_vma_is_closed(vma));
 
-	ev->vma = i915_vma_get(vma);
+	ev->vma = vma;
 	ev->exec = entry;
 	ev->flags = entry->flags;
 
@@ -547,28 +627,9 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 			  u64 pin_flags)
 {
 	struct drm_i915_gem_exec_object2 *entry = ev->exec;
-	unsigned int exec_flags = ev->flags;
 	struct i915_vma *vma = ev->vma;
 	int err;
 
-	if (exec_flags & EXEC_OBJECT_NEEDS_GTT)
-		pin_flags |= PIN_GLOBAL;
-
-	/*
-	 * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
-	 * limit address to the first 4GBs for unflagged objects.
-	 */
-	if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
-		pin_flags |= PIN_ZONE_4G;
-
-	if (exec_flags & __EXEC_OBJECT_NEEDS_MAP)
-		pin_flags |= PIN_MAPPABLE;
-
-	if (exec_flags & EXEC_OBJECT_PINNED)
-		pin_flags |= entry->offset | PIN_OFFSET_FIXED;
-	else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS)
-		pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
-
 	if (drm_mm_node_allocated(&vma->node) &&
 	    eb_vma_misplaced(entry, vma, ev->flags)) {
 		err = i915_vma_unbind(vma);
@@ -578,7 +639,7 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 
 	err = i915_vma_pin(vma,
 			   entry->pad_to_size, entry->alignment,
-			   pin_flags);
+			   eb_pin_flags(entry, ev->flags) | pin_flags);
 	if (err)
 		return err;
 
@@ -587,7 +648,7 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 		eb->args->flags |= __EXEC_HAS_RELOC;
 	}
 
-	if (unlikely(exec_flags & EXEC_OBJECT_NEEDS_FENCE)) {
+	if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) {
 		err = i915_vma_pin_fence(vma);
 		if (unlikely(err)) {
 			i915_vma_unpin(vma);
@@ -595,10 +656,10 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 		}
 
 		if (vma->fence)
-			exec_flags |= __EXEC_OBJECT_HAS_FENCE;
+			ev->flags |= __EXEC_OBJECT_HAS_FENCE;
 	}
 
-	ev->flags = exec_flags | __EXEC_OBJECT_HAS_PIN;
+	ev->flags |= __EXEC_OBJECT_HAS_PIN;
 	GEM_BUG_ON(eb_vma_misplaced(entry, vma, ev->flags));
 
 	return 0;
@@ -728,77 +789,117 @@ static int eb_select_context(struct i915_execbuffer *eb)
 	return 0;
 }
 
-static int eb_lookup_vmas(struct i915_execbuffer *eb)
+static int __eb_add_lut(struct i915_execbuffer *eb,
+			u32 handle, struct i915_vma *vma)
 {
-	struct radix_tree_root *handles_vma = &eb->gem_context->handles_vma;
-	struct drm_i915_gem_object *obj;
-	unsigned int i, batch;
+	struct i915_gem_context *ctx = eb->gem_context;
+	struct i915_lut_handle *lut;
 	int err;
 
-	if (unlikely(i915_gem_context_is_closed(eb->gem_context)))
-		return -ENOENT;
+	lut = i915_lut_handle_alloc();
+	if (unlikely(!lut))
+		return -ENOMEM;
 
-	INIT_LIST_HEAD(&eb->relocs);
-	INIT_LIST_HEAD(&eb->unbound);
+	i915_vma_get(vma);
+	if (!atomic_fetch_inc(&vma->open_count))
+		i915_vma_reopen(vma);
+	lut->handle = handle;
+	lut->ctx = ctx;
+
+	/* Check that the context hasn't been closed in the meantime */
+	err = -EINTR;
+	if (!mutex_lock_interruptible(&ctx->mutex)) {
+		err = -ENOENT;
+		if (likely(!i915_gem_context_is_closed(ctx)))
+			err = radix_tree_insert(&ctx->handles_vma, handle, vma);
+		if (err == 0) { /* And nor has this handle */
+			struct drm_i915_gem_object *obj = vma->obj;
+
+			i915_gem_object_lock(obj);
+			if (idr_find(&eb->file->object_idr, handle) == obj) {
+				list_add(&lut->obj_link, &obj->lut_list);
+			} else {
+				radix_tree_delete(&ctx->handles_vma, handle);
+				err = -ENOENT;
+			}
+			i915_gem_object_unlock(obj);
+		}
+		mutex_unlock(&ctx->mutex);
+	}
+	if (unlikely(err))
+		goto err;
 
-	batch = eb_batch_index(eb);
+	return 0;
 
-	for (i = 0; i < eb->buffer_count; i++) {
-		u32 handle = eb->exec[i].handle;
-		struct i915_lut_handle *lut;
+err:
+	i915_vma_close(vma);
+	i915_vma_put(vma);
+	i915_lut_handle_free(lut);
+	return err;
+}
+
+static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
+{
+	do {
+		struct drm_i915_gem_object *obj;
 		struct i915_vma *vma;
+		int err;
 
-		vma = radix_tree_lookup(handles_vma, handle);
+		rcu_read_lock();
+		vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle);
 		if (likely(vma))
-			goto add_vma;
+			vma = i915_vma_tryget(vma);
+		rcu_read_unlock();
+		if (likely(vma))
+			return vma;
 
 		obj = i915_gem_object_lookup(eb->file, handle);
-		if (unlikely(!obj)) {
-			err = -ENOENT;
-			goto err_vma;
-		}
+		if (unlikely(!obj))
+			return ERR_PTR(-ENOENT);
 
 		vma = i915_vma_instance(obj, eb->context->vm, NULL);
 		if (IS_ERR(vma)) {
-			err = PTR_ERR(vma);
-			goto err_obj;
+			i915_gem_object_put(obj);
+			return vma;
 		}
 
-		lut = i915_lut_handle_alloc();
-		if (unlikely(!lut)) {
-			err = -ENOMEM;
-			goto err_obj;
-		}
+		err = __eb_add_lut(eb, handle, vma);
+		if (likely(!err))
+			return vma;
 
-		err = radix_tree_insert(handles_vma, handle, vma);
-		if (unlikely(err)) {
-			i915_lut_handle_free(lut);
-			goto err_obj;
-		}
+		i915_gem_object_put(obj);
+		if (err != -EEXIST)
+			return ERR_PTR(err);
+	} while (1);
+}
 
-		/* transfer ref to lut */
-		if (!atomic_fetch_inc(&vma->open_count))
-			i915_vma_reopen(vma);
-		lut->handle = handle;
-		lut->ctx = eb->gem_context;
+static int eb_lookup_vmas(struct i915_execbuffer *eb)
+{
+	unsigned int batch = eb_batch_index(eb);
+	unsigned int i;
+	int err = 0;
 
-		i915_gem_object_lock(obj);
-		list_add(&lut->obj_link, &obj->lut_list);
-		i915_gem_object_unlock(obj);
+	INIT_LIST_HEAD(&eb->relocs);
+	INIT_LIST_HEAD(&eb->unbound);
+
+	for (i = 0; i < eb->buffer_count; i++) {
+		struct i915_vma *vma;
+
+		vma = eb_lookup_vma(eb, eb->exec[i].handle);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			break;
+		}
 
-add_vma:
 		err = eb_validate_vma(eb, &eb->exec[i], vma);
-		if (unlikely(err))
-			goto err_vma;
+		if (unlikely(err)) {
+			i915_vma_put(vma);
+			break;
+		}
 
 		eb_add_vma(eb, i, batch, vma);
 	}
 
-	return 0;
-
-err_obj:
-	i915_gem_object_put(obj);
-err_vma:
 	eb->vma[i].vma = NULL;
 	return err;
 }
@@ -823,31 +924,13 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
 	}
 }
 
-static void eb_release_vmas(const struct i915_execbuffer *eb)
-{
-	const unsigned int count = eb->buffer_count;
-	unsigned int i;
-
-	for (i = 0; i < count; i++) {
-		struct eb_vma *ev = &eb->vma[i];
-		struct i915_vma *vma = ev->vma;
-
-		if (!vma)
-			break;
-
-		eb->vma[i].vma = NULL;
-
-		if (ev->flags & __EXEC_OBJECT_HAS_PIN)
-			__eb_unreserve_vma(vma, ev->flags);
-
-		i915_vma_put(vma);
-	}
-}
-
 static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
+	if (eb->array)
+		eb_vma_array_put(eb->array);
+
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -872,7 +955,7 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
 	cache->rq = NULL;
-	cache->rq_size = 0;
+	cache->target = NULL;
 }
 
 static inline void *unmask_page(unsigned long p)
@@ -894,29 +977,122 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
 	return &i915->ggtt;
 }
 
-static void reloc_gpu_flush(struct reloc_cache *cache)
+#define RELOC_TAIL 4
+
+static int reloc_gpu_chain(struct reloc_cache *cache)
+{
+	struct intel_gt_buffer_pool_node *pool;
+	struct i915_request *rq = cache->rq;
+	struct i915_vma *batch;
+	u32 *cmd;
+	int err;
+
+	pool = intel_gt_get_buffer_pool(rq->engine->gt, PAGE_SIZE);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	batch = i915_vma_instance(pool->obj, rq->context->vm, NULL);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_pool;
+	}
+
+	err = i915_vma_pin(batch, 0, 0, PIN_USER | PIN_NONBLOCK);
+	if (err)
+		goto out_pool;
+
+	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
+	cmd = cache->rq_cmd + cache->rq_size;
+	*cmd++ = MI_ARB_CHECK;
+	if (cache->gen >= 8)
+		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
+	else if (cache->gen >= 6)
+		*cmd++ = MI_BATCH_BUFFER_START;
+	else
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
+	*cmd++ = lower_32_bits(batch->node.start);
+	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
+	i915_gem_object_flush_map(cache->rq_vma->obj);
+	i915_gem_object_unpin_map(cache->rq_vma->obj);
+	cache->rq_vma = NULL;
+
+	err = intel_gt_buffer_pool_mark_active(pool, rq);
+	if (err == 0) {
+		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);
+	}
+	i915_vma_unpin(batch);
+	if (err)
+		goto out_pool;
+
+	cmd = i915_gem_object_pin_map(batch->obj,
+				      cache->has_llc ?
+				      I915_MAP_FORCE_WB :
+				      I915_MAP_FORCE_WC);
+	if (IS_ERR(cmd)) {
+		err = PTR_ERR(cmd);
+		goto out_pool;
+	}
+
+	/* Return with batch mapping (cmd) still pinned */
+	cache->rq_cmd = cmd;
+	cache->rq_size = 0;
+	cache->rq_vma = batch;
+
+out_pool:
+	intel_gt_buffer_pool_put(pool);
+	return err;
+}
+
+static unsigned int reloc_bb_flags(const struct reloc_cache *cache)
 {
-	struct drm_i915_gem_object *obj = cache->rq->batch->obj;
+	return cache->gen > 5 ? 0 : I915_DISPATCH_SECURE;
+}
+
+static int reloc_gpu_flush(struct reloc_cache *cache)
+{
+	struct i915_request *rq;
+	int err;
 
-	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
-	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
+	rq = fetch_and_zero(&cache->rq);
+	if (!rq)
+		return 0;
 
-	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
-	i915_gem_object_unpin_map(obj);
+	if (cache->rq_vma) {
+		struct drm_i915_gem_object *obj = cache->rq_vma->obj;
 
-	intel_gt_chipset_flush(cache->rq->engine->gt);
+		GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
+		cache->rq_cmd[cache->rq_size++] = MI_BATCH_BUFFER_END;
 
-	i915_request_add(cache->rq);
-	cache->rq = NULL;
+		__i915_gem_object_flush_map(obj,
+					    0, sizeof(u32) * cache->rq_size);
+		i915_gem_object_unpin_map(obj);
+	}
+
+	err = 0;
+	if (rq->engine->emit_init_breadcrumb)
+		err = rq->engine->emit_init_breadcrumb(rq);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						rq->batch->node.start,
+						PAGE_SIZE,
+						reloc_bb_flags(cache));
+	if (err)
+		i915_request_set_error_once(rq, err);
+
+	intel_gt_chipset_flush(rq->engine->gt);
+	i915_request_add(rq);
+
+	return err;
 }
 
 static void reloc_cache_reset(struct reloc_cache *cache)
 {
 	void *vaddr;
 
-	if (cache->rq)
-		reloc_gpu_flush(cache);
-
 	if (!cache->vaddr)
 		return;
 
@@ -1109,17 +1285,17 @@ static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 }
 
 static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
-			     struct i915_vma *vma,
+			     struct intel_engine_cs *engine,
 			     unsigned int len)
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
-	struct intel_engine_pool_node *pool;
+	struct intel_gt_buffer_pool_node *pool;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	u32 *cmd;
 	int err;
 
-	pool = intel_engine_get_pool(eb->engine, PAGE_SIZE);
+	pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 
@@ -1132,7 +1308,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto out_pool;
 	}
 
-	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
+	batch = i915_vma_instance(pool->obj, eb->context->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		goto err_unmap;
@@ -1142,26 +1318,32 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_unmap;
 
-	rq = i915_request_create(eb->context);
+	if (engine == eb->context->engine) {
+		rq = i915_request_create(eb->context);
+	} else {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			goto err_unpin;
+		}
+
+		i915_vm_put(ce->vm);
+		ce->vm = i915_vm_get(eb->context->vm);
+
+		rq = intel_context_create_request(ce);
+		intel_context_put(ce);
+	}
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
 	}
 
-	err = intel_engine_pool_mark_active(pool, rq);
+	err = intel_gt_buffer_pool_mark_active(pool, rq);
 	if (err)
 		goto err_request;
 
-	err = reloc_move_to_gpu(rq, vma);
-	if (err)
-		goto err_request;
-
-	err = eb->engine->emit_bb_start(rq,
-					batch->node.start, PAGE_SIZE,
-					cache->gen > 5 ? 0 : I915_DISPATCH_SECURE);
-	if (err)
-		goto skip_request;
-
 	i915_vma_lock(batch);
 	err = i915_request_await_object(rq, batch->obj, false);
 	if (err == 0)
@@ -1176,6 +1358,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	cache->rq = rq;
 	cache->rq_cmd = cmd;
 	cache->rq_size = 0;
+	cache->rq_vma = batch;
 
 	/* Return with batch mapping (cmd) still pinned */
 	goto out_pool;
@@ -1189,124 +1372,206 @@ err_unpin:
 err_unmap:
 	i915_gem_object_unpin_map(pool->obj);
 out_pool:
-	intel_engine_pool_put(pool);
+	intel_gt_buffer_pool_put(pool);
 	return err;
 }
 
+static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
+{
+	return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
+}
+
 static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		      struct i915_vma *vma,
 		      unsigned int len)
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
 	u32 *cmd;
-
-	if (cache->rq_size > PAGE_SIZE/sizeof(u32) - (len + 1))
-		reloc_gpu_flush(cache);
+	int err;
 
 	if (unlikely(!cache->rq)) {
-		int err;
+		struct intel_engine_cs *engine = eb->engine;
 
-		if (!intel_engine_can_store_dword(eb->engine))
-			return ERR_PTR(-ENODEV);
+		if (!reloc_can_use_engine(engine)) {
+			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
+			if (!engine)
+				return ERR_PTR(-ENODEV);
+		}
 
-		err = __reloc_gpu_alloc(eb, vma, len);
+		err = __reloc_gpu_alloc(eb, engine, len);
 		if (unlikely(err))
 			return ERR_PTR(err);
 	}
 
+	if (vma != cache->target) {
+		err = reloc_move_to_gpu(cache->rq, vma);
+		if (unlikely(err)) {
+			i915_request_set_error_once(cache->rq, err);
+			return ERR_PTR(err);
+		}
+
+		cache->target = vma;
+	}
+
+	if (unlikely(cache->rq_size + len >
+		     PAGE_SIZE / sizeof(u32) - RELOC_TAIL)) {
+		err = reloc_gpu_chain(cache);
+		if (unlikely(err)) {
+			i915_request_set_error_once(cache->rq, err);
+			return ERR_PTR(err);
+		}
+	}
+
+	GEM_BUG_ON(cache->rq_size + len >= PAGE_SIZE  / sizeof(u32));
 	cmd = cache->rq_cmd + cache->rq_size;
 	cache->rq_size += len;
 
 	return cmd;
 }
 
-static u64
-relocate_entry(struct i915_vma *vma,
-	       const struct drm_i915_gem_relocation_entry *reloc,
-	       struct i915_execbuffer *eb,
-	       const struct i915_vma *target)
+static inline bool use_reloc_gpu(struct i915_vma *vma)
 {
-	u64 offset = reloc->offset;
-	u64 target_offset = relocation_target(reloc, target);
-	bool wide = eb->reloc_cache.use_64bit_reloc;
-	void *vaddr;
+	if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
+		return true;
 
-	if (!eb->reloc_cache.vaddr &&
-	    (DBG_FORCE_RELOC == FORCE_GPU_RELOC ||
-	     !dma_resv_test_signaled_rcu(vma->resv, true))) {
-		const unsigned int gen = eb->reloc_cache.gen;
-		unsigned int len;
-		u32 *batch;
-		u64 addr;
-
-		if (wide)
-			len = offset & 7 ? 8 : 5;
-		else if (gen >= 4)
-			len = 4;
-		else
-			len = 3;
+	if (DBG_FORCE_RELOC)
+		return false;
 
-		batch = reloc_gpu(eb, vma, len);
-		if (IS_ERR(batch))
-			goto repeat;
+	return !dma_resv_test_signaled_rcu(vma->resv, true);
+}
 
-		addr = gen8_canonical_addr(vma->node.start + offset);
-		if (wide) {
-			if (offset & 7) {
-				*batch++ = MI_STORE_DWORD_IMM_GEN4;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = lower_32_bits(target_offset);
-
-				addr = gen8_canonical_addr(addr + 4);
-
-				*batch++ = MI_STORE_DWORD_IMM_GEN4;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = upper_32_bits(target_offset);
-			} else {
-				*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = lower_32_bits(target_offset);
-				*batch++ = upper_32_bits(target_offset);
-			}
-		} else if (gen >= 6) {
+static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
+{
+	struct page *page;
+	unsigned long addr;
+
+	GEM_BUG_ON(vma->pages != vma->obj->mm.pages);
+
+	page = i915_gem_object_get_page(vma->obj, offset >> PAGE_SHIFT);
+	addr = PFN_PHYS(page_to_pfn(page));
+	GEM_BUG_ON(overflows_type(addr, u32)); /* expected dma32 */
+
+	return addr + offset_in_page(offset);
+}
+
+static bool __reloc_entry_gpu(struct i915_execbuffer *eb,
+			      struct i915_vma *vma,
+			      u64 offset,
+			      u64 target_addr)
+{
+	const unsigned int gen = eb->reloc_cache.gen;
+	unsigned int len;
+	u32 *batch;
+	u64 addr;
+
+	if (gen >= 8)
+		len = offset & 7 ? 8 : 5;
+	else if (gen >= 4)
+		len = 4;
+	else
+		len = 3;
+
+	batch = reloc_gpu(eb, vma, len);
+	if (IS_ERR(batch))
+		return false;
+
+	addr = gen8_canonical_addr(vma->node.start + offset);
+	if (gen >= 8) {
+		if (offset & 7) {
 			*batch++ = MI_STORE_DWORD_IMM_GEN4;
-			*batch++ = 0;
-			*batch++ = addr;
-			*batch++ = target_offset;
-		} else if (gen >= 4) {
-			*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-			*batch++ = 0;
-			*batch++ = addr;
-			*batch++ = target_offset;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = lower_32_bits(target_addr);
+
+			addr = gen8_canonical_addr(addr + 4);
+
+			*batch++ = MI_STORE_DWORD_IMM_GEN4;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = upper_32_bits(target_addr);
 		} else {
-			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
-			*batch++ = addr;
-			*batch++ = target_offset;
+			*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = lower_32_bits(target_addr);
+			*batch++ = upper_32_bits(target_addr);
 		}
-
-		goto out;
+	} else if (gen >= 6) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else if (IS_I965G(eb->i915)) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = vma_phys_addr(vma, offset);
+		*batch++ = target_addr;
+	} else if (gen >= 4) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+		*batch++ = 0;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else if (gen >= 3 &&
+		   !(IS_I915G(eb->i915) || IS_I915GM(eb->i915))) {
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else {
+		*batch++ = MI_STORE_DWORD_IMM;
+		*batch++ = vma_phys_addr(vma, offset);
+		*batch++ = target_addr;
 	}
 
+	return true;
+}
+
+static bool reloc_entry_gpu(struct i915_execbuffer *eb,
+			    struct i915_vma *vma,
+			    u64 offset,
+			    u64 target_addr)
+{
+	if (eb->reloc_cache.vaddr)
+		return false;
+
+	if (!use_reloc_gpu(vma))
+		return false;
+
+	return __reloc_entry_gpu(eb, vma, offset, target_addr);
+}
+
+static u64
+relocate_entry(struct i915_vma *vma,
+	       const struct drm_i915_gem_relocation_entry *reloc,
+	       struct i915_execbuffer *eb,
+	       const struct i915_vma *target)
+{
+	u64 target_addr = relocation_target(reloc, target);
+	u64 offset = reloc->offset;
+
+	if (!reloc_entry_gpu(eb, vma, offset, target_addr)) {
+		bool wide = eb->reloc_cache.use_64bit_reloc;
+		void *vaddr;
+
 repeat:
-	vaddr = reloc_vaddr(vma->obj, &eb->reloc_cache, offset >> PAGE_SHIFT);
-	if (IS_ERR(vaddr))
-		return PTR_ERR(vaddr);
+		vaddr = reloc_vaddr(vma->obj,
+				    &eb->reloc_cache,
+				    offset >> PAGE_SHIFT);
+		if (IS_ERR(vaddr))
+			return PTR_ERR(vaddr);
 
-	clflush_write32(vaddr + offset_in_page(offset),
-			lower_32_bits(target_offset),
-			eb->reloc_cache.vaddr);
+		GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
+		clflush_write32(vaddr + offset_in_page(offset),
+				lower_32_bits(target_addr),
+				eb->reloc_cache.vaddr);
 
-	if (wide) {
-		offset += sizeof(u32);
-		target_offset >>= 32;
-		wide = false;
-		goto repeat;
+		if (wide) {
+			offset += sizeof(u32);
+			target_addr >>= 32;
+			wide = false;
+			goto repeat;
+		}
 	}
 
-out:
 	return target->node.start | UPDATE;
 }
 
@@ -1411,12 +1676,11 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 {
 #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
 	struct drm_i915_gem_relocation_entry stack[N_RELOC(512)];
-	struct drm_i915_gem_relocation_entry __user *urelocs;
 	const struct drm_i915_gem_exec_object2 *entry = ev->exec;
-	unsigned int remain;
+	struct drm_i915_gem_relocation_entry __user *urelocs =
+		u64_to_user_ptr(entry->relocs_ptr);
+	unsigned long remain = entry->relocation_count;
 
-	urelocs = u64_to_user_ptr(entry->relocs_ptr);
-	remain = entry->relocation_count;
 	if (unlikely(remain > N_RELOC(ULONG_MAX)))
 		return -EINVAL;
 
@@ -1425,13 +1689,13 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 	 * to read. However, if the array is not writable the user loses
 	 * the updated relocation values.
 	 */
-	if (unlikely(!access_ok(urelocs, remain*sizeof(*urelocs))))
+	if (unlikely(!access_ok(urelocs, remain * sizeof(*urelocs))))
 		return -EFAULT;
 
 	do {
 		struct drm_i915_gem_relocation_entry *r = stack;
 		unsigned int count =
-			min_t(unsigned int, remain, ARRAY_SIZE(stack));
+			min_t(unsigned long, remain, ARRAY_SIZE(stack));
 		unsigned int copied;
 
 		/*
@@ -1494,9 +1758,7 @@ static int eb_relocate(struct i915_execbuffer *eb)
 {
 	int err;
 
-	mutex_lock(&eb->gem_context->mutex);
 	err = eb_lookup_vmas(eb);
-	mutex_unlock(&eb->gem_context->mutex);
 	if (err)
 		return err;
 
@@ -1509,15 +1771,20 @@ static int eb_relocate(struct i915_execbuffer *eb)
 	/* The objects are in their final locations, apply the relocations. */
 	if (eb->args->flags & __EXEC_HAS_RELOC) {
 		struct eb_vma *ev;
+		int flush;
 
 		list_for_each_entry(ev, &eb->relocs, reloc_link) {
 			err = eb_relocate_vma(eb, ev);
 			if (err)
-				return err;
+				break;
 		}
+
+		flush = reloc_gpu_flush(&eb->reloc_cache);
+		if (!err)
+			err = flush;
 	}
 
-	return 0;
+	return err;
 }
 
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
@@ -1597,19 +1864,15 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 			err = i915_vma_move_to_active(vma, eb->request, flags);
 
 		i915_vma_unlock(vma);
-
-		__eb_unreserve_vma(vma, flags);
-		i915_vma_put(vma);
-
-		ev->vma = NULL;
+		eb_unreserve_vma(ev);
 	}
 	ww_acquire_fini(&acquire);
 
+	eb_vma_array_put(fetch_and_zero(&eb->array));
+
 	if (unlikely(err))
 		goto err_skip;
 
-	eb->exec = NULL;
-
 	/* Unconditionally flush any chipset caches (for streaming writes). */
 	intel_gt_chipset_flush(eb->engine->gt);
 	return 0;
@@ -1784,7 +2047,7 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb,
 	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
 	dma_resv_unlock(shadow->resv);
 
-	dma_fence_work_commit(&pw->base);
+	dma_fence_work_commit_imm(&pw->base);
 	return 0;
 
 err_batch_unlock:
@@ -1804,7 +2067,7 @@ err_free:
 static int eb_parse(struct i915_execbuffer *eb)
 {
 	struct drm_i915_private *i915 = eb->i915;
-	struct intel_engine_pool_node *pool;
+	struct intel_gt_buffer_pool_node *pool;
 	struct i915_vma *shadow, *trampoline;
 	unsigned int len;
 	int err;
@@ -1827,7 +2090,7 @@ static int eb_parse(struct i915_execbuffer *eb)
 		len += I915_CMD_PARSER_TRAMPOLINE_SIZE;
 	}
 
-	pool = intel_engine_get_pool(eb->engine, len);
+	pool = intel_gt_get_buffer_pool(eb->engine->gt, len);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 
@@ -1861,6 +2124,7 @@ static int eb_parse(struct i915_execbuffer *eb)
 	eb->vma[eb->buffer_count].vma = i915_vma_get(shadow);
 	eb->vma[eb->buffer_count].flags = __EXEC_OBJECT_HAS_PIN;
 	eb->batch = &eb->vma[eb->buffer_count++];
+	eb->vma[eb->buffer_count].vma = NULL;
 
 	eb->trampoline = trampoline;
 	eb->batch_start_offset = 0;
@@ -1874,7 +2138,7 @@ err_trampoline:
 err_shadow:
 	i915_vma_unpin(shadow);
 err:
-	intel_engine_pool_put(pool);
+	intel_gt_buffer_pool_put(pool);
 	return err;
 }
 
@@ -2318,39 +2582,13 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	/* Check that the context wasn't destroyed before submission */
 	if (likely(!intel_context_is_closed(eb->context))) {
 		attr = eb->gem_context->sched;
-
-		/*
-		 * Boost actual workloads past semaphores!
-		 *
-		 * With semaphores we spin on one engine waiting for another,
-		 * simply to reduce the latency of starting our work when
-		 * the signaler completes. However, if there is any other
-		 * work that we could be doing on this engine instead, that
-		 * is better utilisation and will reduce the overall duration
-		 * of the current work. To avoid PI boosting a semaphore
-		 * far in the distance past over useful work, we keep a history
-		 * of any semaphore use along our dependency chain.
-		 */
-		if (!(rq->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN))
-			attr.priority |= I915_PRIORITY_NOSEMAPHORE;
-
-		/*
-		 * Boost priorities to new clients (new request flows).
-		 *
-		 * Allow interactive/synchronous clients to jump ahead of
-		 * the bulk clients. (FQ_CODEL)
-		 */
-		if (list_empty(&rq->sched.signalers_list))
-			attr.priority |= I915_PRIORITY_WAIT;
 	} else {
 		/* Serialise with context_close via the add_to_timeline */
 		i915_request_set_error_once(rq, -ENOENT);
 		__i915_request_skip(rq);
 	}
 
-	local_bh_disable();
 	__i915_request_queue(rq, &attr);
-	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
 
 	/* Try to clean up the client's timeline after submitting the request */
 	if (prev)
@@ -2369,7 +2607,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
-	struct dma_fence *exec_fence = NULL;
 	struct sync_file *out_fence = NULL;
 	struct i915_vma *batch;
 	int out_fence_fd = -1;
@@ -2386,8 +2623,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		args->flags |= __EXEC_HAS_RELOC;
 
 	eb.exec = exec;
-	eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1);
-	eb.vma[0].vma = NULL;
 
 	eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
 	reloc_cache_init(&eb.reloc_cache, eb.i915);
@@ -2414,30 +2649,22 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
-	if (args->flags & I915_EXEC_FENCE_IN) {
+#define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
+	if (args->flags & IN_FENCES) {
+		if ((args->flags & IN_FENCES) == IN_FENCES)
+			return -EINVAL;
+
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
 		if (!in_fence)
 			return -EINVAL;
 	}
-
-	if (args->flags & I915_EXEC_FENCE_SUBMIT) {
-		if (in_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-
-		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!exec_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-	}
+#undef IN_FENCES
 
 	if (args->flags & I915_EXEC_FENCE_OUT) {
 		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
 		if (out_fence_fd < 0) {
 			err = out_fence_fd;
-			goto err_exec_fence;
+			goto err_in_fence;
 		}
 	}
 
@@ -2528,14 +2755,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	}
 
 	if (in_fence) {
-		err = i915_request_await_dma_fence(eb.request, in_fence);
-		if (err < 0)
-			goto err_request;
-	}
-
-	if (exec_fence) {
-		err = i915_request_await_execution(eb.request, exec_fence,
-						   eb.engine->bond_execute);
+		if (args->flags & I915_EXEC_FENCE_SUBMIT)
+			err = i915_request_await_execution(eb.request,
+							   in_fence,
+							   eb.engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb.request,
+							   in_fence);
 		if (err < 0)
 			goto err_request;
 	}
@@ -2563,7 +2789,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	 */
 	eb.request->batch = batch;
 	if (batch->private)
-		intel_engine_pool_mark_active(batch->private, eb.request);
+		intel_gt_buffer_pool_mark_active(batch->private, eb.request);
 
 	trace_i915_request_queue(eb.request, eb.batch_flags);
 	err = eb_submit(&eb, batch);
@@ -2592,10 +2818,8 @@ err_batch_unpin:
 		i915_vma_unpin(batch);
 err_parse:
 	if (batch->private)
-		intel_engine_pool_put(batch->private);
+		intel_gt_buffer_pool_put(batch->private);
 err_vma:
-	if (eb.exec)
-		eb_release_vmas(&eb);
 	if (eb.trampoline)
 		i915_vma_unpin(eb.trampoline);
 	eb_unpin_engine(&eb);
@@ -2606,8 +2830,6 @@ err_destroy:
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
-err_exec_fence:
-	dma_fence_put(exec_fence);
 err_in_fence:
 	dma_fence_put(in_fence);
 	return err;
@@ -2615,7 +2837,7 @@ err_in_fence:
 
 static size_t eb_element_size(void)
 {
-	return sizeof(struct drm_i915_gem_exec_object2) + sizeof(struct eb_vma);
+	return sizeof(struct drm_i915_gem_exec_object2);
 }
 
 static bool check_buffer_count(size_t count)
@@ -2671,7 +2893,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 	/* Copy in the exec list from userland */
 	exec_list = kvmalloc_array(count, sizeof(*exec_list),
 				   __GFP_NOWARN | GFP_KERNEL);
-	exec2_list = kvmalloc_array(count + 1, eb_element_size(),
+	exec2_list = kvmalloc_array(count, eb_element_size(),
 				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec_list == NULL || exec2_list == NULL) {
 		drm_dbg(&i915->drm,
@@ -2749,8 +2971,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	if (err)
 		return err;
 
-	/* Allocate an extra slot for use by the command parser */
-	exec2_list = kvmalloc_array(count + 1, eb_element_size(),
+	exec2_list = kvmalloc_array(count, eb_element_size(),
 				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec2_list == NULL) {
 		drm_dbg(&i915->drm, "Failed to allocate exec list for %zd buffers\n",
@@ -2818,3 +3039,7 @@ end:;
 	kvfree(exec2_list);
 	return err;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_gem_execbuffer.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_fence.c b/drivers/gpu/drm/i915/gem/i915_gem_fence.c
index 2f6100ec2608..8ab842c80f99 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_fence.c
@@ -72,8 +72,8 @@ i915_gem_object_lock_fence(struct drm_i915_gem_object *obj)
 		       0, 0);
 
 	if (i915_sw_fence_await_reservation(&stub->chain,
-					    obj->base.resv, NULL,
-					    true, I915_FENCE_TIMEOUT,
+					    obj->base.resv, NULL, true,
+					    i915_fence_timeout(to_i915(obj->base.dev)),
 					    I915_FENCE_GFP) < 0)
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index b39c24dae64e..70f5f82da288 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -396,6 +396,38 @@ err:
 	return i915_error_to_vmf_fault(ret);
 }
 
+static int
+vm_access(struct vm_area_struct *area, unsigned long addr,
+	  void *buf, int len, int write)
+{
+	struct i915_mmap_offset *mmo = area->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
+	void *vaddr;
+
+	if (i915_gem_object_is_readonly(obj) && write)
+		return -EACCES;
+
+	addr -= area->vm_start;
+	if (addr >= obj->base.size)
+		return -EINVAL;
+
+	/* As this is primarily for debugging, let's focus on simplicity */
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_FORCE_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	if (write) {
+		memcpy(vaddr + addr, buf, len);
+		__i915_gem_object_flush_map(obj, addr, len);
+	} else {
+		memcpy(buf, vaddr + addr, len);
+	}
+
+	i915_gem_object_unpin_map(obj);
+
+	return len;
+}
+
 void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
@@ -745,12 +777,14 @@ static void vm_close(struct vm_area_struct *vma)
 
 static const struct vm_operations_struct vm_ops_gtt = {
 	.fault = vm_fault_gtt,
+	.access = vm_access,
 	.open = vm_open,
 	.close = vm_close,
 };
 
 static const struct vm_operations_struct vm_ops_cpu = {
 	.fault = vm_fault_cpu,
+	.access = vm_access,
 	.open = vm_open,
 	.close = vm_close,
 };
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 5da9f9e534b9..99356c00c19e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -135,9 +135,7 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 		if (vma) {
 			GEM_BUG_ON(vma->obj != obj);
 			GEM_BUG_ON(!atomic_read(&vma->open_count));
-			if (atomic_dec_and_test(&vma->open_count) &&
-			    !i915_vma_is_ggtt(vma))
-				i915_vma_close(vma);
+			i915_vma_close(vma);
 		}
 		mutex_unlock(&ctx->mutex);
 
@@ -164,9 +162,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 				    struct llist_node *freed)
 {
 	struct drm_i915_gem_object *obj, *on;
-	intel_wakeref_t wakeref;
 
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	llist_for_each_entry_safe(obj, on, freed, freed) {
 		struct i915_mmap_offset *mmo, *mn;
 
@@ -206,7 +202,6 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		}
 		obj->mmo.offsets = RB_ROOT;
 
-		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
 		GEM_BUG_ON(!list_empty(&obj->lut_list));
 
@@ -227,7 +222,6 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
 		cond_resched();
 	}
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
 void i915_gem_flush_free_objects(struct drm_i915_private *i915)
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 e00792158f13..f457d7130491 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
@@ -6,8 +6,8 @@
 #include "i915_drv.h"
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
-#include "gt/intel_engine_pool.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_buffer_pool.h"
 #include "gt/intel_ring.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_object_blt.h"
@@ -18,7 +18,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 {
 	struct drm_i915_private *i915 = ce->vm->i915;
 	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
-	struct intel_engine_pool_node *pool;
+	struct intel_gt_buffer_pool_node *pool;
 	struct i915_vma *batch;
 	u64 offset;
 	u64 count;
@@ -33,7 +33,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	count = div_u64(round_up(vma->size, block_size), block_size);
 	size = (1 + 8 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
-	pool = intel_engine_get_pool(ce->engine, size);
+	pool = intel_gt_get_buffer_pool(ce->engine->gt, size);
 	if (IS_ERR(pool)) {
 		err = PTR_ERR(pool);
 		goto out_pm;
@@ -78,10 +78,12 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	} while (rem);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(ce->vm->gt);
 
+	i915_gem_object_flush_map(pool->obj);
 	i915_gem_object_unpin_map(pool->obj);
 
+	intel_gt_chipset_flush(ce->vm->gt);
+
 	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
@@ -96,7 +98,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	return batch;
 
 out_put:
-	intel_engine_pool_put(pool);
+	intel_gt_buffer_pool_put(pool);
 out_pm:
 	intel_engine_pm_put(ce->engine);
 	return ERR_PTR(err);
@@ -114,13 +116,13 @@ int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq)
 	if (unlikely(err))
 		return err;
 
-	return intel_engine_pool_mark_active(vma->private, rq);
+	return intel_gt_buffer_pool_mark_active(vma->private, rq);
 }
 
 void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma)
 {
 	i915_vma_unpin(vma);
-	intel_engine_pool_put(vma->private);
+	intel_gt_buffer_pool_put(vma->private);
 	intel_engine_pm_put(ce->engine);
 }
 
@@ -213,7 +215,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 {
 	struct drm_i915_private *i915 = ce->vm->i915;
 	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
-	struct intel_engine_pool_node *pool;
+	struct intel_gt_buffer_pool_node *pool;
 	struct i915_vma *batch;
 	u64 src_offset, dst_offset;
 	u64 count, rem;
@@ -228,7 +230,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	count = div_u64(round_up(dst->size, block_size), block_size);
 	size = (1 + 11 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
-	pool = intel_engine_get_pool(ce->engine, size);
+	pool = intel_gt_get_buffer_pool(ce->engine->gt, size);
 	if (IS_ERR(pool)) {
 		err = PTR_ERR(pool);
 		goto out_pm;
@@ -289,10 +291,12 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	} while (rem);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(ce->vm->gt);
 
+	i915_gem_object_flush_map(pool->obj);
 	i915_gem_object_unpin_map(pool->obj);
 
+	intel_gt_chipset_flush(ce->vm->gt);
+
 	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
@@ -307,7 +311,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	return batch;
 
 out_put:
-	intel_engine_pool_put(pool);
+	intel_gt_buffer_pool_put(pool);
 out_pm:
 	intel_engine_pm_put(ce->engine);
 	return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
index 243a43a87824..8bcd336a90dc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.h
@@ -10,7 +10,6 @@
 
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
-#include "gt/intel_engine_pool.h"
 #include "i915_vma.h"
 
 struct drm_i915_gem_object;
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 a0b10bcd8d8a..54ee658bb168 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -179,9 +179,6 @@ struct drm_i915_gem_object {
 #define TILING_MASK (FENCE_MINIMUM_STRIDE - 1)
 #define STRIDE_MASK (~TILING_MASK)
 
-	/** Count of VMA actually bound by this object */
-	atomic_t bind_count;
-
 	struct {
 		/*
 		 * Protects the pages and their use. Do not use directly, but
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 24f4cadea114..af9e48ee4a33 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -199,8 +199,6 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	if (i915_gem_object_has_pinned_pages(obj))
 		return -EBUSY;
 
-	GEM_BUG_ON(atomic_read(&obj->bind_count));
-
 	/* May be called by shrinker from within get_pages() (on another bo) */
 	mutex_lock(&obj->mm.lock);
 	if (unlikely(atomic_read(&obj->mm.pages_pin_count))) {
@@ -393,6 +391,7 @@ void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(range_overflows_t(typeof(obj->base.size),
 				     offset, size, obj->base.size));
 
+	wmb(); /* let all previous writes be visible to coherent partners */
 	obj->mm.dirty = true;
 
 	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 698e22420dc5..7fe9831aa9ba 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -10,8 +10,6 @@
 
 #include <drm/drm.h> /* for drm_legacy.h! */
 #include <drm/drm_cache.h>
-#include <drm/drm_legacy.h> /* for drm_pci.h! */
-#include <drm/drm_pci.h>
 
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 03e5eb4c99d1..5b65ce738b16 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -27,18 +27,6 @@ static bool can_release_pages(struct drm_i915_gem_object *obj)
 		return false;
 
 	/*
-	 * Only report true if by unbinding the object and putting its pages
-	 * we can actually make forward progress towards freeing physical
-	 * pages.
-	 *
-	 * If the pages are pinned for any other reason than being bound
-	 * to the GPU, simply unbinding from the GPU is not going to succeed
-	 * in releasing our pin count on the pages themselves.
-	 */
-	if (atomic_read(&obj->mm.pages_pin_count) > atomic_read(&obj->bind_count))
-		return false;
-
-	/*
 	 * 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.
@@ -54,6 +42,8 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj,
 	flags = 0;
 	if (shrink & I915_SHRINK_ACTIVE)
 		flags = I915_GEM_OBJECT_UNBIND_ACTIVE;
+	if (!(shrink & I915_SHRINK_BOUND))
+		flags = I915_GEM_OBJECT_UNBIND_TEST;
 
 	if (i915_gem_object_unbind(obj, flags) == 0)
 		__i915_gem_object_put_pages(obj);
@@ -194,10 +184,6 @@ i915_gem_shrink(struct drm_i915_private *i915,
 			    i915_gem_object_is_framebuffer(obj))
 				continue;
 
-			if (!(shrink & I915_SHRINK_BOUND) &&
-			    atomic_read(&obj->bind_count))
-				continue;
-
 			if (!can_release_pages(obj))
 				continue;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 5557dfa83a7b..dc250278bd2c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -381,14 +381,14 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915)
 	mutex_init(&i915->mm.stolen_lock);
 
 	if (intel_vgpu_active(i915)) {
-		dev_notice(i915->drm.dev,
+		drm_notice(&i915->drm,
 			   "%s, disabling use of stolen memory\n",
 			   "iGVT-g active");
 		return 0;
 	}
 
 	if (intel_vtd_active() && INTEL_GEN(i915) < 8) {
-		dev_notice(i915->drm.dev,
+		drm_notice(&i915->drm,
 			   "%s, disabling use of stolen memory\n",
 			   "DMAR active");
 		return 0;
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
index fa16f2c3f3ac..2b46c6530da9 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
@@ -88,8 +88,7 @@ static void huge_put_pages(struct drm_i915_gem_object *obj,
 }
 
 static const struct drm_i915_gem_object_ops huge_ops = {
-	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
-		 I915_GEM_OBJECT_IS_SHRINKABLE,
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = huge_get_pages,
 	.put_pages = huge_put_pages,
 };
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index d4f94ca9ae0d..c9988b6d5c88 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -421,7 +421,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 
 			err = i915_vma_pin(vma, 0, 0, PIN_USER);
 			if (err)
-				goto out_close;
+				goto out_put;
 
 			err = igt_check_page_sizes(vma);
 
@@ -432,8 +432,6 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 			}
 
 			i915_vma_unpin(vma);
-			i915_vma_close(vma);
-
 			i915_gem_object_put(obj);
 
 			if (err)
@@ -443,8 +441,6 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 
 	goto out_device;
 
-out_close:
-	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
 out_device:
@@ -492,7 +488,7 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 
 			err = i915_vma_pin(vma, 0, 0, PIN_USER);
 			if (err)
-				goto out_close;
+				goto out_put;
 
 			err = igt_check_page_sizes(vma);
 			if (err)
@@ -515,8 +511,6 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 			}
 
 			i915_vma_unpin(vma);
-			i915_vma_close(vma);
-
 			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
@@ -526,8 +520,6 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 
 out_unpin:
 	i915_vma_unpin(vma);
-out_close:
-	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
 out_region:
@@ -587,10 +579,8 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		}
 
 		err = i915_vma_pin(vma, 0, 0, flags);
-		if (err) {
-			i915_vma_close(vma);
+		if (err)
 			goto out_unpin;
-		}
 
 
 		err = igt_check_page_sizes(vma);
@@ -603,10 +593,8 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 
 		i915_vma_unpin(vma);
 
-		if (err) {
-			i915_vma_close(vma);
+		if (err)
 			goto out_unpin;
-		}
 
 		/*
 		 * Try all the other valid offsets until the next
@@ -615,16 +603,12 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		 */
 		for (offset = 4096; offset < page_size; offset += 4096) {
 			err = i915_vma_unbind(vma);
-			if (err) {
-				i915_vma_close(vma);
+			if (err)
 				goto out_unpin;
-			}
 
 			err = i915_vma_pin(vma, 0, 0, flags | offset);
-			if (err) {
-				i915_vma_close(vma);
+			if (err)
 				goto out_unpin;
-			}
 
 			err = igt_check_page_sizes(vma);
 
@@ -636,10 +620,8 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 
 			i915_vma_unpin(vma);
 
-			if (err) {
-				i915_vma_close(vma);
+			if (err)
 				goto out_unpin;
-			}
 
 			if (igt_timeout(end_time,
 					"%s timed out at offset %x with page-size %x\n",
@@ -647,8 +629,6 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 				break;
 		}
 
-		i915_vma_close(vma);
-
 		i915_gem_object_unpin_pages(obj);
 		__i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
@@ -670,12 +650,6 @@ static void close_object_list(struct list_head *objects,
 	struct drm_i915_gem_object *obj, *on;
 
 	list_for_each_entry_safe(obj, on, objects, st_link) {
-		struct i915_vma *vma;
-
-		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
-		if (!IS_ERR(vma))
-			i915_vma_close(vma);
-
 		list_del(&obj->st_link);
 		i915_gem_object_unpin_pages(obj);
 		__i915_gem_object_put_pages(obj);
@@ -912,7 +886,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 
 			err = i915_vma_pin(vma, 0, 0, flags);
 			if (err)
-				goto out_vma_close;
+				goto out_object_unpin;
 
 			err = igt_check_page_sizes(vma);
 			if (err)
@@ -945,8 +919,6 @@ static int igt_mock_ppgtt_64K(void *arg)
 			}
 
 			i915_vma_unpin(vma);
-			i915_vma_close(vma);
-
 			i915_gem_object_unpin_pages(obj);
 			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
@@ -957,8 +929,6 @@ static int igt_mock_ppgtt_64K(void *arg)
 
 out_vma_unpin:
 	i915_vma_unpin(vma);
-out_vma_close:
-	i915_vma_close(vma);
 out_object_unpin:
 	i915_gem_object_unpin_pages(obj);
 out_object_put:
@@ -1070,7 +1040,7 @@ static int __igt_write_huge(struct intel_context *ce,
 
 	err = i915_vma_unbind(vma);
 	if (err)
-		goto out_vma_close;
+		return err;
 
 	err = i915_vma_pin(vma, size, 0, flags | offset);
 	if (err) {
@@ -1081,7 +1051,7 @@ static int __igt_write_huge(struct intel_context *ce,
 		if (err == -ENOSPC && i915_is_ggtt(ce->vm))
 			err = 0;
 
-		goto out_vma_close;
+		return err;
 	}
 
 	err = igt_check_page_sizes(vma);
@@ -1102,8 +1072,6 @@ static int __igt_write_huge(struct intel_context *ce,
 
 out_vma_unpin:
 	i915_vma_unpin(vma);
-out_vma_close:
-	__i915_vma_put(vma);
 	return err;
 }
 
@@ -1490,7 +1458,7 @@ static int igt_ppgtt_pin_update(void *arg)
 
 		err = i915_vma_pin(vma, SZ_2M, 0, flags);
 		if (err)
-			goto out_close;
+			goto out_put;
 
 		if (vma->page_sizes.sg < page_size) {
 			pr_info("Unable to allocate page-size %x, finishing test early\n",
@@ -1527,8 +1495,6 @@ static int igt_ppgtt_pin_update(void *arg)
 			goto out_unpin;
 
 		i915_vma_unpin(vma);
-		i915_vma_close(vma);
-
 		i915_gem_object_put(obj);
 	}
 
@@ -1546,7 +1512,7 @@ static int igt_ppgtt_pin_update(void *arg)
 
 	err = i915_vma_pin(vma, 0, 0, flags);
 	if (err)
-		goto out_close;
+		goto out_put;
 
 	/*
 	 * Make sure we don't end up with something like where the pde is still
@@ -1576,8 +1542,6 @@ static int igt_ppgtt_pin_update(void *arg)
 
 out_unpin:
 	i915_vma_unpin(vma);
-out_close:
-	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
 out_vm:
@@ -1629,13 +1593,11 @@ static int igt_tmpfs_fallback(void *arg)
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER);
 	if (err)
-		goto out_close;
+		goto out_put;
 
 	err = igt_check_page_sizes(vma);
 
 	i915_vma_unpin(vma);
-out_close:
-	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
 out_restore:
@@ -1682,7 +1644,7 @@ static int igt_shrink_thp(void *arg)
 
 	err = i915_vma_pin(vma, 0, 0, flags);
 	if (err)
-		goto out_close;
+		goto out_put;
 
 	if (obj->mm.page_sizes.phys < I915_GTT_PAGE_SIZE_2M) {
 		pr_info("failed to allocate THP, finishing test early\n");
@@ -1706,7 +1668,7 @@ static int igt_shrink_thp(void *arg)
 	i915_gem_context_unlock_engines(ctx);
 	i915_vma_unpin(vma);
 	if (err)
-		goto out_close;
+		goto out_put;
 
 	/*
 	 * Now that the pages are *unpinned* shrink-all should invoke
@@ -1716,18 +1678,18 @@ static int igt_shrink_thp(void *arg)
 	if (i915_gem_object_has_pages(obj)) {
 		pr_err("shrink-all didn't truncate the pages\n");
 		err = -EINVAL;
-		goto out_close;
+		goto out_put;
 	}
 
 	if (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys) {
 		pr_err("residual page-size bits left\n");
 		err = -EINVAL;
-		goto out_close;
+		goto out_put;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, flags);
 	if (err)
-		goto out_close;
+		goto out_put;
 
 	while (n--) {
 		err = cpu_check(obj, n, 0xdeadbeaf);
@@ -1737,8 +1699,6 @@ static int igt_shrink_thp(void *arg)
 
 out_unpin:
 	i915_vma_unpin(vma);
-out_close:
-	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
 out_vm:
@@ -1777,21 +1737,20 @@ int i915_gem_huge_page_mock_selftests(void)
 	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
 		pr_err("failed to create 48b PPGTT\n");
 		err = -EINVAL;
-		goto out_close;
+		goto out_put;
 	}
 
 	/* If we were ever hit this then it's time to mock the 64K scratch */
 	if (!i915_vm_has_scratch_64K(&ppgtt->vm)) {
 		pr_err("PPGTT missing 64K scratch page\n");
 		err = -EINVAL;
-		goto out_close;
+		goto out_put;
 	}
 
 	err = i915_subtests(tests, ppgtt);
 
-out_close:
+out_put:
 	i915_vm_put(&ppgtt->vm);
-
 out_unlock:
 	drm_dev_put(&dev_priv->drm);
 	return err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index b972be165e85..8fe3ad2ee34e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -7,9 +7,12 @@
 
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gpu_commands.h"
+#include "gem/i915_gem_lmem.h"
 
 #include "selftests/igt_flush_test.h"
 #include "selftests/mock_drm.h"
+#include "selftests/i915_random.h"
 #include "huge_gem_object.h"
 #include "mock_context.h"
 
@@ -127,10 +130,573 @@ static int igt_client_fill(void *arg)
 	} while (1);
 }
 
+#define WIDTH 512
+#define HEIGHT 32
+
+struct blit_buffer {
+	struct i915_vma *vma;
+	u32 start_val;
+	u32 tiling;
+};
+
+struct tiled_blits {
+	struct intel_context *ce;
+	struct blit_buffer buffers[3];
+	struct blit_buffer scratch;
+	struct i915_vma *batch;
+	u64 hole;
+	u32 width;
+	u32 height;
+};
+
+static int prepare_blit(const struct tiled_blits *t,
+			struct blit_buffer *dst,
+			struct blit_buffer *src,
+			struct drm_i915_gem_object *batch)
+{
+	const int gen = INTEL_GEN(to_i915(batch->base.dev));
+	bool use_64b_reloc = gen >= 8;
+	u32 src_pitch, dst_pitch;
+	u32 cmd, *cs;
+
+	cs = i915_gem_object_pin_map(batch, I915_MAP_WC);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(BCS_SWCTRL);
+	cmd = (BCS_SRC_Y | BCS_DST_Y) << 16;
+	if (src->tiling == I915_TILING_Y)
+		cmd |= BCS_SRC_Y;
+	if (dst->tiling == I915_TILING_Y)
+		cmd |= BCS_DST_Y;
+	*cs++ = cmd;
+
+	cmd = MI_FLUSH_DW;
+	if (gen >= 8)
+		cmd++;
+	*cs++ = cmd;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+
+	cmd = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (8 - 2);
+	if (gen >= 8)
+		cmd += 2;
+
+	src_pitch = t->width * 4;
+	if (src->tiling) {
+		cmd |= XY_SRC_COPY_BLT_SRC_TILED;
+		src_pitch /= 4;
+	}
+
+	dst_pitch = t->width * 4;
+	if (dst->tiling) {
+		cmd |= XY_SRC_COPY_BLT_DST_TILED;
+		dst_pitch /= 4;
+	}
+
+	*cs++ = cmd;
+	*cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | dst_pitch;
+	*cs++ = 0;
+	*cs++ = t->height << 16 | t->width;
+	*cs++ = lower_32_bits(dst->vma->node.start);
+	if (use_64b_reloc)
+		*cs++ = upper_32_bits(dst->vma->node.start);
+	*cs++ = 0;
+	*cs++ = src_pitch;
+	*cs++ = lower_32_bits(src->vma->node.start);
+	if (use_64b_reloc)
+		*cs++ = upper_32_bits(src->vma->node.start);
+
+	*cs++ = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(batch);
+	i915_gem_object_unpin_map(batch);
+
+	return 0;
+}
+
+static void tiled_blits_destroy_buffers(struct tiled_blits *t)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(t->buffers); i++)
+		i915_vma_put(t->buffers[i].vma);
+
+	i915_vma_put(t->scratch.vma);
+	i915_vma_put(t->batch);
+}
+
+static struct i915_vma *
+__create_vma(struct tiled_blits *t, size_t size, bool lmem)
+{
+	struct drm_i915_private *i915 = t->ce->vm->i915;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+
+	if (lmem)
+		obj = i915_gem_object_create_lmem(i915, size, 0);
+	else
+		obj = i915_gem_object_create_shmem(i915, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	vma = i915_vma_instance(obj, t->ce->vm, NULL);
+	if (IS_ERR(vma))
+		i915_gem_object_put(obj);
+
+	return vma;
+}
+
+static struct i915_vma *create_vma(struct tiled_blits *t, bool lmem)
+{
+	return __create_vma(t, PAGE_ALIGN(t->width * t->height * 4), lmem);
+}
+
+static int tiled_blits_create_buffers(struct tiled_blits *t,
+				      int width, int height,
+				      struct rnd_state *prng)
+{
+	struct drm_i915_private *i915 = t->ce->engine->i915;
+	int i;
+
+	t->width = width;
+	t->height = height;
+
+	t->batch = __create_vma(t, PAGE_SIZE, false);
+	if (IS_ERR(t->batch))
+		return PTR_ERR(t->batch);
+
+	t->scratch.vma = create_vma(t, false);
+	if (IS_ERR(t->scratch.vma)) {
+		i915_vma_put(t->batch);
+		return PTR_ERR(t->scratch.vma);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(t->buffers); i++) {
+		struct i915_vma *vma;
+
+		vma = create_vma(t, HAS_LMEM(i915) && i % 2);
+		if (IS_ERR(vma)) {
+			tiled_blits_destroy_buffers(t);
+			return PTR_ERR(vma);
+		}
+
+		t->buffers[i].vma = vma;
+		t->buffers[i].tiling =
+			i915_prandom_u32_max_state(I915_TILING_Y + 1, prng);
+	}
+
+	return 0;
+}
+
+static void fill_scratch(struct tiled_blits *t, u32 *vaddr, u32 val)
+{
+	int i;
+
+	t->scratch.start_val = val;
+	for (i = 0; i < t->width * t->height; i++)
+		vaddr[i] = val++;
+
+	i915_gem_object_flush_map(t->scratch.vma->obj);
+}
+
+static u64 swizzle_bit(unsigned int bit, u64 offset)
+{
+	return (offset & BIT_ULL(bit)) >> (bit - 6);
+}
+
+static u64 tiled_offset(const struct intel_gt *gt,
+			u64 v,
+			unsigned int stride,
+			unsigned int tiling)
+{
+	unsigned int swizzle;
+	u64 x, y;
+
+	if (tiling == I915_TILING_NONE)
+		return v;
+
+	y = div64_u64_rem(v, stride, &x);
+
+	if (tiling == I915_TILING_X) {
+		v = div64_u64_rem(y, 8, &y) * stride * 8;
+		v += y * 512;
+		v += div64_u64_rem(x, 512, &x) << 12;
+		v += x;
+
+		swizzle = gt->ggtt->bit_6_swizzle_x;
+	} else {
+		const unsigned int ytile_span = 16;
+		const unsigned int ytile_height = 512;
+
+		v = div64_u64_rem(y, 32, &y) * stride * 32;
+		v += y * ytile_span;
+		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
+		v += x;
+
+		swizzle = gt->ggtt->bit_6_swizzle_y;
+	}
+
+	switch (swizzle) {
+	case I915_BIT_6_SWIZZLE_9:
+		v ^= swizzle_bit(9, v);
+		break;
+	case I915_BIT_6_SWIZZLE_9_10:
+		v ^= swizzle_bit(9, v) ^ swizzle_bit(10, v);
+		break;
+	case I915_BIT_6_SWIZZLE_9_11:
+		v ^= swizzle_bit(9, v) ^ swizzle_bit(11, v);
+		break;
+	case I915_BIT_6_SWIZZLE_9_10_11:
+		v ^= swizzle_bit(9, v) ^ swizzle_bit(10, v) ^ swizzle_bit(11, v);
+		break;
+	}
+
+	return v;
+}
+
+static const char *repr_tiling(int tiling)
+{
+	switch (tiling) {
+	case I915_TILING_NONE: return "linear";
+	case I915_TILING_X: return "X";
+	case I915_TILING_Y: return "Y";
+	default: return "unknown";
+	}
+}
+
+static int verify_buffer(const struct tiled_blits *t,
+			 struct blit_buffer *buf,
+			 struct rnd_state *prng)
+{
+	const u32 *vaddr;
+	int ret = 0;
+	int x, y, p;
+
+	x = i915_prandom_u32_max_state(t->width, prng);
+	y = i915_prandom_u32_max_state(t->height, prng);
+	p = y * t->width + x;
+
+	vaddr = i915_gem_object_pin_map(buf->vma->obj, I915_MAP_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	if (vaddr[0] != buf->start_val) {
+		ret = -EINVAL;
+	} else {
+		u64 v = tiled_offset(buf->vma->vm->gt,
+				     p * 4, t->width * 4,
+				     buf->tiling);
+
+		if (vaddr[v / sizeof(*vaddr)] != buf->start_val + p)
+			ret = -EINVAL;
+	}
+	if (ret) {
+		pr_err("Invalid %s tiling detected at (%d, %d), start_val %x\n",
+		       repr_tiling(buf->tiling),
+		       x, y, buf->start_val);
+		igt_hexdump(vaddr, 4096);
+	}
+
+	i915_gem_object_unpin_map(buf->vma->obj);
+	return ret;
+}
+
+static int move_to_active(struct i915_vma *vma,
+			  struct i915_request *rq,
+			  unsigned int flags)
+{
+	int err;
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, false);
+	if (err == 0)
+		err = i915_vma_move_to_active(vma, rq, flags);
+	i915_vma_unlock(vma);
+
+	return err;
+}
+
+static int pin_buffer(struct i915_vma *vma, u64 addr)
+{
+	int err;
+
+	if (drm_mm_node_allocated(&vma->node) && vma->node.start != addr) {
+		err = i915_vma_unbind(vma);
+		if (err)
+			return err;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED | addr);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int
+tiled_blit(struct tiled_blits *t,
+	   struct blit_buffer *dst, u64 dst_addr,
+	   struct blit_buffer *src, u64 src_addr)
+{
+	struct i915_request *rq;
+	int err;
+
+	err = pin_buffer(src->vma, src_addr);
+	if (err) {
+		pr_err("Cannot pin src @ %llx\n", src_addr);
+		return err;
+	}
+
+	err = pin_buffer(dst->vma, dst_addr);
+	if (err) {
+		pr_err("Cannot pin dst @ %llx\n", dst_addr);
+		goto err_src;
+	}
+
+	err = i915_vma_pin(t->batch, 0, 0, PIN_USER | PIN_HIGH);
+	if (err) {
+		pr_err("cannot pin batch\n");
+		goto err_dst;
+	}
+
+	err = prepare_blit(t, dst, src, t->batch->obj);
+	if (err)
+		goto err_bb;
+
+	rq = intel_context_create_request(t->ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_bb;
+	}
+
+	err = move_to_active(t->batch, rq, 0);
+	if (!err)
+		err = move_to_active(src->vma, rq, 0);
+	if (!err)
+		err = move_to_active(dst->vma, rq, 0);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						t->batch->node.start,
+						t->batch->node.size,
+						0);
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 2) < 0)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	dst->start_val = src->start_val;
+err_bb:
+	i915_vma_unpin(t->batch);
+err_dst:
+	i915_vma_unpin(dst->vma);
+err_src:
+	i915_vma_unpin(src->vma);
+	return err;
+}
+
+static struct tiled_blits *
+tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng)
+{
+	struct drm_mm_node hole;
+	struct tiled_blits *t;
+	u64 hole_size;
+	int err;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (!t)
+		return ERR_PTR(-ENOMEM);
+
+	t->ce = intel_context_create(engine);
+	if (IS_ERR(t->ce)) {
+		err = PTR_ERR(t->ce);
+		goto err_free;
+	}
+
+	hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4);
+	hole_size *= 2; /* room to maneuver */
+	hole_size += 2 * I915_GTT_MIN_ALIGNMENT;
+
+	mutex_lock(&t->ce->vm->mutex);
+	memset(&hole, 0, sizeof(hole));
+	err = drm_mm_insert_node_in_range(&t->ce->vm->mm, &hole,
+					  hole_size, 0, I915_COLOR_UNEVICTABLE,
+					  0, U64_MAX,
+					  DRM_MM_INSERT_BEST);
+	if (!err)
+		drm_mm_remove_node(&hole);
+	mutex_unlock(&t->ce->vm->mutex);
+	if (err) {
+		err = -ENODEV;
+		goto err_put;
+	}
+
+	t->hole = hole.start + I915_GTT_MIN_ALIGNMENT;
+	pr_info("Using hole at %llx\n", t->hole);
+
+	err = tiled_blits_create_buffers(t, WIDTH, HEIGHT, prng);
+	if (err)
+		goto err_put;
+
+	return t;
+
+err_put:
+	intel_context_put(t->ce);
+err_free:
+	kfree(t);
+	return ERR_PTR(err);
+}
+
+static void tiled_blits_destroy(struct tiled_blits *t)
+{
+	tiled_blits_destroy_buffers(t);
+
+	intel_context_put(t->ce);
+	kfree(t);
+}
+
+static int tiled_blits_prepare(struct tiled_blits *t,
+			       struct rnd_state *prng)
+{
+	u64 offset = PAGE_ALIGN(t->width * t->height * 4);
+	u32 *map;
+	int err;
+	int i;
+
+	map = i915_gem_object_pin_map(t->scratch.vma->obj, I915_MAP_WC);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	/* Use scratch to fill objects */
+	for (i = 0; i < ARRAY_SIZE(t->buffers); i++) {
+		fill_scratch(t, map, prandom_u32_state(prng));
+		GEM_BUG_ON(verify_buffer(t, &t->scratch, prng));
+
+		err = tiled_blit(t,
+				 &t->buffers[i], t->hole + offset,
+				 &t->scratch, t->hole);
+		if (err == 0)
+			err = verify_buffer(t, &t->buffers[i], prng);
+		if (err) {
+			pr_err("Failed to create buffer %d\n", i);
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_map(t->scratch.vma->obj);
+	return err;
+}
+
+static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng)
+{
+	u64 offset =
+		round_up(t->width * t->height * 4, 2 * I915_GTT_MIN_ALIGNMENT);
+	int err;
+
+	/* We want to check position invariant tiling across GTT eviction */
+
+	err = tiled_blit(t,
+			 &t->buffers[1], t->hole + offset / 2,
+			 &t->buffers[0], t->hole + 2 * offset);
+	if (err)
+		return err;
+
+	/* Reposition so that we overlap the old addresses, and slightly off */
+	err = tiled_blit(t,
+			 &t->buffers[2], t->hole + I915_GTT_MIN_ALIGNMENT,
+			 &t->buffers[1], t->hole + 3 * offset / 2);
+	if (err)
+		return err;
+
+	err = verify_buffer(t, &t->buffers[2], prng);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int __igt_client_tiled_blits(struct intel_engine_cs *engine,
+				    struct rnd_state *prng)
+{
+	struct tiled_blits *t;
+	int err;
+
+	t = tiled_blits_create(engine, prng);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+
+	err = tiled_blits_prepare(t, prng);
+	if (err)
+		goto out;
+
+	err = tiled_blits_bounce(t, prng);
+	if (err)
+		goto out;
+
+out:
+	tiled_blits_destroy(t);
+	return err;
+}
+
+static bool has_bit17_swizzle(int sw)
+{
+	return (sw == I915_BIT_6_SWIZZLE_9_10_17 ||
+		sw == I915_BIT_6_SWIZZLE_9_17);
+}
+
+static bool bad_swizzling(struct drm_i915_private *i915)
+{
+	struct i915_ggtt *ggtt = &i915->ggtt;
+
+	if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+		return true;
+
+	if (has_bit17_swizzle(ggtt->bit_6_swizzle_x) ||
+	    has_bit17_swizzle(ggtt->bit_6_swizzle_y))
+		return true;
+
+	return false;
+}
+
+static int igt_client_tiled_blits(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	I915_RND_STATE(prng);
+	int inst = 0;
+
+	/* Test requires explicit BLT tiling controls */
+	if (INTEL_GEN(i915) < 4)
+		return 0;
+
+	if (bad_swizzling(i915)) /* Requires sane (sub-page) swizzling */
+		return 0;
+
+	do {
+		struct intel_engine_cs *engine;
+		int err;
+
+		engine = intel_engine_lookup_user(i915,
+						  I915_ENGINE_CLASS_COPY,
+						  inst++);
+		if (!engine)
+			return 0;
+
+		err = __igt_client_tiled_blits(engine, &prng);
+		if (err == -ENODEV)
+			err = 0;
+		if (err)
+			return err;
+	} while (1);
+}
+
 int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_client_fill),
+		SUBTEST(igt_client_tiled_blits),
 	};
 
 	if (intel_gt_is_wedged(&i915->gt))
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 3f6079e1dfb6..87d7d8aa080f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -158,6 +158,8 @@ static int wc_set(struct context *ctx, unsigned long offset, u32 v)
 		return PTR_ERR(map);
 
 	map[offset / sizeof(*map)] = v;
+
+	__i915_gem_object_flush_map(ctx->obj, offset, sizeof(*map));
 	i915_gem_object_unpin_map(ctx->obj);
 
 	return 0;
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 54b86cf7f5d2..b81978890641 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -972,12 +972,6 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 		goto err_batch;
 	}
 
-	err = rq->engine->emit_bb_start(rq,
-					batch->node.start, batch->node.size,
-					0);
-	if (err)
-		goto err_request;
-
 	i915_vma_lock(batch);
 	err = i915_request_await_object(rq, batch->obj, false);
 	if (err == 0)
@@ -994,6 +988,18 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 	if (err)
 		goto skip_request;
 
+	if (rq->engine->emit_init_breadcrumb) {
+		err = rq->engine->emit_init_breadcrumb(rq);
+		if (err)
+			goto skip_request;
+	}
+
+	err = rq->engine->emit_bb_start(rq,
+					batch->node.start, batch->node.size,
+					0);
+	if (err)
+		goto skip_request;
+
 	i915_vma_unpin_and_release(&batch, 0);
 	i915_vma_unpin(vma);
 
@@ -1005,7 +1011,6 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 
 skip_request:
 	i915_request_set_error_once(rq, err);
-err_request:
 	i915_request_add(rq);
 err_batch:
 	i915_vma_unpin_and_release(&batch, 0);
@@ -1541,10 +1546,6 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 		goto err_unpin;
 	}
 
-	err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, 0);
-	if (err)
-		goto err_request;
-
 	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, false);
 	if (err == 0)
@@ -1553,6 +1554,16 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	if (err)
 		goto skip_request;
 
+	if (rq->engine->emit_init_breadcrumb) {
+		err = rq->engine->emit_init_breadcrumb(rq);
+		if (err)
+			goto skip_request;
+	}
+
+	err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, 0);
+	if (err)
+		goto skip_request;
+
 	i915_vma_unpin(vma);
 
 	i915_request_add(rq);
@@ -1560,7 +1571,6 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	goto out_vm;
 skip_request:
 	i915_request_set_error_once(rq, err);
-err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
@@ -1674,10 +1684,6 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 		goto err_unpin;
 	}
 
-	err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, flags);
-	if (err)
-		goto err_request;
-
 	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, true);
 	if (err == 0)
@@ -1686,8 +1692,17 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	if (err)
 		goto skip_request;
 
+	if (rq->engine->emit_init_breadcrumb) {
+		err = rq->engine->emit_init_breadcrumb(rq);
+		if (err)
+			goto skip_request;
+	}
+
+	err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, flags);
+	if (err)
+		goto skip_request;
+
 	i915_vma_unpin(vma);
-	i915_vma_close(vma);
 
 	i915_request_add(rq);
 
@@ -1709,7 +1724,6 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	goto out_vm;
 skip_request:
 	i915_request_set_error_once(rq, err);
-err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
@@ -1925,7 +1939,7 @@ static int mock_context_barrier(void *arg)
 		goto out;
 	}
 
-	rq = igt_request_alloc(ctx, i915->engine[RCS0]);
+	rq = igt_request_alloc(ctx, i915->gt.engine[RCS0]);
 	if (IS_ERR(rq)) {
 		pr_err("Request allocation failed!\n");
 		goto out;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
new file mode 100644
index 000000000000..a49016f8ee0d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_selftest.h"
+
+#include "gt/intel_engine_pm.h"
+#include "selftests/igt_flush_test.h"
+
+static u64 read_reloc(const u32 *map, int x, const u64 mask)
+{
+	u64 reloc;
+
+	memcpy(&reloc, &map[x], sizeof(reloc));
+	return reloc & mask;
+}
+
+static int __igt_gpu_reloc(struct i915_execbuffer *eb,
+			   struct drm_i915_gem_object *obj)
+{
+	const unsigned int offsets[] = { 8, 3, 0 };
+	const u64 mask =
+		GENMASK_ULL(eb->reloc_cache.use_64bit_reloc ? 63 : 31, 0);
+	const u32 *map = page_mask_bits(obj->mm.mapping);
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	int err;
+	int i;
+
+	vma = i915_vma_instance(obj, eb->context->vm, NULL);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+	if (err)
+		return err;
+
+	/* 8-Byte aligned */
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[0] * sizeof(u32),
+			       0)) {
+		err = -EIO;
+		goto unpin_vma;
+	}
+
+	/* !8-Byte aligned */
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[1] * sizeof(u32),
+			       1)) {
+		err = -EIO;
+		goto unpin_vma;
+	}
+
+	/* Skip to the end of the cmd page */
+	i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1;
+	i -= eb->reloc_cache.rq_size;
+	memset32(eb->reloc_cache.rq_cmd + eb->reloc_cache.rq_size,
+		 MI_NOOP, i);
+	eb->reloc_cache.rq_size += i;
+
+	/* Force batch chaining */
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[2] * sizeof(u32),
+			       2)) {
+		err = -EIO;
+		goto unpin_vma;
+	}
+
+	GEM_BUG_ON(!eb->reloc_cache.rq);
+	rq = i915_request_get(eb->reloc_cache.rq);
+	err = reloc_gpu_flush(&eb->reloc_cache);
+	if (err)
+		goto put_rq;
+	GEM_BUG_ON(eb->reloc_cache.rq);
+
+	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
+	if (err) {
+		intel_gt_set_wedged(eb->engine->gt);
+		goto put_rq;
+	}
+
+	if (!i915_request_completed(rq)) {
+		pr_err("%s: did not wait for relocations!\n", eb->engine->name);
+		err = -EINVAL;
+		goto put_rq;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		u64 reloc = read_reloc(map, offsets[i], mask);
+
+		if (reloc != i) {
+			pr_err("%s[%d]: map[%d] %llx != %x\n",
+			       eb->engine->name, i, offsets[i], reloc, i);
+			err = -EINVAL;
+		}
+	}
+	if (err)
+		igt_hexdump(map, 4096);
+
+put_rq:
+	i915_request_put(rq);
+unpin_vma:
+	i915_vma_unpin(vma);
+	return err;
+}
+
+static int igt_gpu_reloc(void *arg)
+{
+	struct i915_execbuffer eb;
+	struct drm_i915_gem_object *scratch;
+	int err = 0;
+	u32 *map;
+
+	eb.i915 = arg;
+
+	scratch = i915_gem_object_create_internal(eb.i915, 4096);
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
+
+	map = i915_gem_object_pin_map(scratch, I915_MAP_WC);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto err_scratch;
+	}
+
+	for_each_uabi_engine(eb.engine, eb.i915) {
+		reloc_cache_init(&eb.reloc_cache, eb.i915);
+		memset(map, POISON_INUSE, 4096);
+
+		intel_engine_pm_get(eb.engine);
+		eb.context = intel_context_create(eb.engine);
+		if (IS_ERR(eb.context)) {
+			err = PTR_ERR(eb.context);
+			goto err_pm;
+		}
+
+		err = intel_context_pin(eb.context);
+		if (err)
+			goto err_put;
+
+		err = __igt_gpu_reloc(&eb, scratch);
+
+		intel_context_unpin(eb.context);
+err_put:
+		intel_context_put(eb.context);
+err_pm:
+		intel_engine_pm_put(eb.engine);
+		if (err)
+			break;
+	}
+
+	if (igt_flush_test(eb.i915))
+		err = -EIO;
+
+err_scratch:
+	i915_gem_object_put(scratch);
+	return err;
+}
+
+int i915_gem_execbuffer_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_gpu_reloc),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}
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 43912e9b683d..9c7402ce5bf9 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -952,6 +952,129 @@ static int igt_mmap(void *arg)
 	return 0;
 }
 
+static const char *repr_mmap_type(enum i915_mmap_type type)
+{
+	switch (type) {
+	case I915_MMAP_TYPE_GTT: return "gtt";
+	case I915_MMAP_TYPE_WB: return "wb";
+	case I915_MMAP_TYPE_WC: return "wc";
+	case I915_MMAP_TYPE_UC: return "uc";
+	default: return "unknown";
+	}
+}
+
+static bool can_access(const struct drm_i915_gem_object *obj)
+{
+	unsigned int flags =
+		I915_GEM_OBJECT_HAS_STRUCT_PAGE | I915_GEM_OBJECT_HAS_IOMEM;
+
+	return i915_gem_object_type_has(obj, flags);
+}
+
+static int __igt_mmap_access(struct drm_i915_private *i915,
+			     struct drm_i915_gem_object *obj,
+			     enum i915_mmap_type type)
+{
+	struct i915_mmap_offset *mmo;
+	unsigned long __user *ptr;
+	unsigned long A, B;
+	unsigned long x, y;
+	unsigned long addr;
+	int err;
+
+	memset(&A, 0xAA, sizeof(A));
+	memset(&B, 0xBB, sizeof(B));
+
+	if (!can_mmap(obj, type) || !can_access(obj))
+		return 0;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+	ptr = (unsigned long __user *)addr;
+
+	err = __put_user(A, ptr);
+	if (err) {
+		pr_err("%s(%s): failed to write into user mmap\n",
+		       obj->mm.region->name, repr_mmap_type(type));
+		goto out_unmap;
+	}
+
+	intel_gt_flush_ggtt_writes(&i915->gt);
+
+	err = access_process_vm(current, addr, &x, sizeof(x), 0);
+	if (err != sizeof(x)) {
+		pr_err("%s(%s): access_process_vm() read failed\n",
+		       obj->mm.region->name, repr_mmap_type(type));
+		goto out_unmap;
+	}
+
+	err = access_process_vm(current, addr, &B, sizeof(B), FOLL_WRITE);
+	if (err != sizeof(B)) {
+		pr_err("%s(%s): access_process_vm() write failed\n",
+		       obj->mm.region->name, repr_mmap_type(type));
+		goto out_unmap;
+	}
+
+	intel_gt_flush_ggtt_writes(&i915->gt);
+
+	err = __get_user(y, ptr);
+	if (err) {
+		pr_err("%s(%s): failed to read from user mmap\n",
+		       obj->mm.region->name, repr_mmap_type(type));
+		goto out_unmap;
+	}
+
+	if (x != A || y != B) {
+		pr_err("%s(%s): failed to read/write values, found (%lx, %lx)\n",
+		       obj->mm.region->name, repr_mmap_type(type),
+		       x, y);
+		err = -EINVAL;
+		goto out_unmap;
+	}
+
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap_access(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		if (obj == ERR_PTR(-ENODEV))
+			continue;
+
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_GTT);
+		if (err == 0)
+			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WB);
+		if (err == 0)
+			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WC);
+		if (err == 0)
+			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_UC);
+
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int __igt_mmap_gpu(struct drm_i915_private *i915,
 			  struct drm_i915_gem_object *obj,
 			  enum i915_mmap_type type)
@@ -1156,9 +1279,6 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915,
 	if (err)
 		goto out_unmap;
 
-	GEM_BUG_ON(mmo->mmap_type == I915_MMAP_TYPE_GTT &&
-		   !atomic_read(&obj->bind_count));
-
 	err = check_present(addr, obj->base.size);
 	if (err) {
 		pr_err("%s: was not present\n", obj->mm.region->name);
@@ -1175,7 +1295,6 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915,
 		pr_err("Failed to unbind object!\n");
 		goto out_unmap;
 	}
-	GEM_BUG_ON(atomic_read(&obj->bind_count));
 
 	if (type != I915_MMAP_TYPE_GTT) {
 		__i915_gem_object_put_pages(obj);
@@ -1233,6 +1352,7 @@ int i915_gem_mman_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_smoke_tiling),
 		SUBTEST(igt_mmap_offset_exhaustion),
 		SUBTEST(igt_mmap),
+		SUBTEST(igt_mmap_access),
 		SUBTEST(igt_mmap_revoke),
 		SUBTEST(igt_mmap_gpu),
 	};
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
index 2b6db6f799de..faa5b6d91795 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
@@ -14,7 +14,7 @@ static int igt_gem_object(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
-	int err = -ENOMEM;
+	int err;
 
 	/* Basic test to ensure we can create an object */
 
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 772d8cba7da9..e21b5023ca7d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
@@ -83,6 +83,8 @@ igt_emit_store_dw(struct i915_vma *vma,
 		offset += PAGE_SIZE;
 	}
 	*cmd = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	intel_gt_chipset_flush(vma->vm->gt);
@@ -126,16 +128,6 @@ int igt_gpu_fill_dw(struct intel_context *ce,
 		goto err_batch;
 	}
 
-	flags = 0;
-	if (INTEL_GEN(ce->vm->i915) <= 5)
-		flags |= I915_DISPATCH_SECURE;
-
-	err = rq->engine->emit_bb_start(rq,
-					batch->node.start, batch->node.size,
-					flags);
-	if (err)
-		goto err_request;
-
 	i915_vma_lock(batch);
 	err = i915_request_await_object(rq, batch->obj, false);
 	if (err == 0)
@@ -152,15 +144,17 @@ int igt_gpu_fill_dw(struct intel_context *ce,
 	if (err)
 		goto skip_request;
 
-	i915_request_add(rq);
-
-	i915_vma_unpin_and_release(&batch, 0);
+	flags = 0;
+	if (INTEL_GEN(ce->vm->i915) <= 5)
+		flags |= I915_DISPATCH_SECURE;
 
-	return 0;
+	err = rq->engine->emit_bb_start(rq,
+					batch->node.start, batch->node.size,
+					flags);
 
 skip_request:
-	i915_request_set_error_once(rq, err);
-err_request:
+	if (err)
+		i915_request_set_error_once(rq, err);
 	i915_request_add(rq);
 err_batch:
 	i915_vma_unpin_and_release(&batch, 0);
diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.c b/drivers/gpu/drm/i915/gt/debugfs_engines.c
index 6a5e9ab20b94..5e3725e62241 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_engines.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_engines.c
@@ -32,5 +32,5 @@ void debugfs_engines_register(struct intel_gt *gt, struct dentry *root)
 		{ "engines", &engines_fops },
 	};
 
-	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c
index 75255aaacaed..1de5fbaa1cf9 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.c
@@ -9,6 +9,7 @@
 #include "debugfs_engines.h"
 #include "debugfs_gt.h"
 #include "debugfs_gt_pm.h"
+#include "uc/intel_uc_debugfs.h"
 #include "i915_drv.h"
 
 void debugfs_gt_register(struct intel_gt *gt)
@@ -24,17 +25,19 @@ void debugfs_gt_register(struct intel_gt *gt)
 
 	debugfs_engines_register(gt, root);
 	debugfs_gt_pm_register(gt, root);
+
+	intel_uc_debugfs_register(&gt->uc, root);
 }
 
-void debugfs_gt_register_files(struct intel_gt *gt,
-			       struct dentry *root,
-			       const struct debugfs_gt_file *files,
-			       unsigned long count)
+void intel_gt_debugfs_register_files(struct dentry *root,
+				     const struct debugfs_gt_file *files,
+				     unsigned long count, void *data)
 {
 	while (count--) {
-		if (!files->eval || files->eval(gt))
+		umode_t mode = files->fops->write ? 0644 : 0444;
+		if (!files->eval || files->eval(data))
 			debugfs_create_file(files->name,
-					    0444, root, gt,
+					    mode, root, data,
 					    files->fops);
 
 		files++;
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.h b/drivers/gpu/drm/i915/gt/debugfs_gt.h
index 4ea0f06cda8f..f77540f727e9 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt.h
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.h
@@ -28,12 +28,11 @@ void debugfs_gt_register(struct intel_gt *gt);
 struct debugfs_gt_file {
 	const char *name;
 	const struct file_operations *fops;
-	bool (*eval)(const struct intel_gt *gt);
+	bool (*eval)(void *data);
 };
 
-void debugfs_gt_register_files(struct intel_gt *gt,
-			       struct dentry *root,
-			       const struct debugfs_gt_file *files,
-			       unsigned long count);
+void intel_gt_debugfs_register_files(struct dentry *root,
+				     const struct debugfs_gt_file *files,
+				     unsigned long count, void *data);
 
 #endif /* DEBUGFS_GT_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
index 059c9e5c002e..174a24553322 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -10,6 +10,7 @@
 #include "debugfs_gt_pm.h"
 #include "i915_drv.h"
 #include "intel_gt.h"
+#include "intel_gt_clock_utils.h"
 #include "intel_llc.h"
 #include "intel_rc6.h"
 #include "intel_rps.h"
@@ -268,7 +269,7 @@ static int frequency_show(struct seq_file *m, void *unused)
 			   yesno(rpmodectl & GEN6_RP_ENABLE));
 		seq_printf(m, "SW control enabled: %s\n",
 			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
-				  GEN6_RP_MEDIA_SW_MODE));
+				 GEN6_RP_MEDIA_SW_MODE));
 
 		vlv_punit_get(i915);
 		freq_sts = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
@@ -300,8 +301,9 @@ static int frequency_show(struct seq_file *m, void *unused)
 		u32 rp_state_cap;
 		u32 rpmodectl, rpinclimit, rpdeclimit;
 		u32 rpstat, cagf, reqf;
-		u32 rpupei, rpcurup, rpprevup;
-		u32 rpdownei, rpcurdown, rpprevdown;
+		u32 rpcurupei, rpcurup, rpprevup;
+		u32 rpcurdownei, rpcurdown, rpprevdown;
+		u32 rpupei, rpupt, rpdownei, rpdownt;
 		u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
 		int max_freq;
 
@@ -334,12 +336,19 @@ static int frequency_show(struct seq_file *m, void *unused)
 		rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
 
 		rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1);
-		rpupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
+		rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
 		rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK;
 		rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK;
-		rpdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
+		rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
+
+		rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI);
+		rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
+
+		rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI);
+		rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
+
 		cagf = intel_rps_read_actual_frequency(rps);
 
 		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
@@ -372,7 +381,7 @@ static int frequency_show(struct seq_file *m, void *unused)
 			   yesno(rpmodectl & GEN6_RP_ENABLE));
 		seq_printf(m, "SW control enabled: %s\n",
 			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
-				  GEN6_RP_MEDIA_SW_MODE));
+				 GEN6_RP_MEDIA_SW_MODE));
 
 		seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
 			   pm_ier, pm_imr, pm_mask);
@@ -394,23 +403,35 @@ static int frequency_show(struct seq_file *m, void *unused)
 		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
-		seq_printf(m, "RP CUR UP EI: %d (%dus)\n",
-			   rpupei, GT_PM_INTERVAL_TO_US(i915, rpupei));
-		seq_printf(m, "RP CUR UP: %d (%dus)\n",
-			   rpcurup, GT_PM_INTERVAL_TO_US(i915, rpcurup));
-		seq_printf(m, "RP PREV UP: %d (%dus)\n",
-			   rpprevup, GT_PM_INTERVAL_TO_US(i915, rpprevup));
+		seq_printf(m, "RP CUR UP EI: %d (%dns)\n",
+			   rpcurupei,
+			   intel_gt_pm_interval_to_ns(gt, rpcurupei));
+		seq_printf(m, "RP CUR UP: %d (%dns)\n",
+			   rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup));
+		seq_printf(m, "RP PREV UP: %d (%dns)\n",
+			   rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup));
 		seq_printf(m, "Up threshold: %d%%\n",
 			   rps->power.up_threshold);
-
-		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
-			   rpdownei, GT_PM_INTERVAL_TO_US(i915, rpdownei));
-		seq_printf(m, "RP CUR DOWN: %d (%dus)\n",
-			   rpcurdown, GT_PM_INTERVAL_TO_US(i915, rpcurdown));
-		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
-			   rpprevdown, GT_PM_INTERVAL_TO_US(i915, rpprevdown));
+		seq_printf(m, "RP UP EI: %d (%dns)\n",
+			   rpupei, intel_gt_pm_interval_to_ns(gt, rpupei));
+		seq_printf(m, "RP UP THRESHOLD: %d (%dns)\n",
+			   rpupt, intel_gt_pm_interval_to_ns(gt, rpupt));
+
+		seq_printf(m, "RP CUR DOWN EI: %d (%dns)\n",
+			   rpcurdownei,
+			   intel_gt_pm_interval_to_ns(gt, rpcurdownei));
+		seq_printf(m, "RP CUR DOWN: %d (%dns)\n",
+			   rpcurdown,
+			   intel_gt_pm_interval_to_ns(gt, rpcurdown));
+		seq_printf(m, "RP PREV DOWN: %d (%dns)\n",
+			   rpprevdown,
+			   intel_gt_pm_interval_to_ns(gt, rpprevdown));
 		seq_printf(m, "Down threshold: %d%%\n",
 			   rps->power.down_threshold);
+		seq_printf(m, "RP DOWN EI: %d (%dns)\n",
+			   rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei));
+		seq_printf(m, "RP DOWN THRESHOLD: %d (%dns)\n",
+			   rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt));
 
 		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
@@ -506,8 +527,10 @@ static int llc_show(struct seq_file *m, void *data)
 	return 0;
 }
 
-static bool llc_eval(const struct intel_gt *gt)
+static bool llc_eval(void *data)
 {
+	struct intel_gt *gt = data;
+
 	return HAS_LLC(gt->i915);
 }
 
@@ -533,7 +556,8 @@ static int rps_boost_show(struct seq_file *m, void *data)
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_rps *rps = &gt->rps;
 
-	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
+	seq_printf(m, "RPS enabled? %s\n", yesno(intel_rps_is_enabled(rps)));
+	seq_printf(m, "RPS active? %s\n", yesno(intel_rps_is_active(rps)));
 	seq_printf(m, "GPU busy? %s\n", yesno(gt->awake));
 	seq_printf(m, "Boosts outstanding? %d\n",
 		   atomic_read(&rps->num_waiters));
@@ -553,7 +577,7 @@ static int rps_boost_show(struct seq_file *m, void *data)
 
 	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
 
-	if (INTEL_GEN(i915) >= 6 && rps->enabled && gt->awake) {
+	if (INTEL_GEN(i915) >= 6 && intel_rps_is_active(rps)) {
 		struct intel_uncore *uncore = gt->uncore;
 		u32 rpup, rpupei;
 		u32 rpdown, rpdownei;
@@ -580,8 +604,10 @@ static int rps_boost_show(struct seq_file *m, void *data)
 	return 0;
 }
 
-static bool rps_eval(const struct intel_gt *gt)
+static bool rps_eval(void *data)
 {
+	struct intel_gt *gt = data;
+
 	return HAS_RPS(gt->i915);
 }
 
@@ -597,5 +623,5 @@ void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root)
 		{ "rps_boost", &rps_boost_fops, rps_eval },
 	};
 
-	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 94e746af8926..699125928272 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -389,6 +389,16 @@ static int gen8_ppgtt_alloc(struct i915_address_space *vm,
 	return err;
 }
 
+static __always_inline void
+write_pte(gen8_pte_t *pte, const gen8_pte_t val)
+{
+	/* Magic delays? Or can we refine these to flush all in one pass? */
+	*pte = val;
+	wmb(); /* cpu to cache */
+	clflush(pte); /* cache to memory */
+	wmb(); /* visible to all */
+}
+
 static __always_inline u64
 gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      struct i915_page_directory *pdp,
@@ -405,7 +415,8 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
 		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
-		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
+		write_pte(&vaddr[gen8_pd_index(idx, 0)],
+			  pte_encode | iter->dma);
 
 		iter->dma += I915_GTT_PAGE_SIZE;
 		if (iter->dma >= iter->max) {
@@ -487,7 +498,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 
 		do {
 			GEM_BUG_ON(iter->sg->length < page_size);
-			vaddr[index++] = encode | iter->dma;
+			write_pte(&vaddr[index++], encode | iter->dma);
 
 			start += page_size;
 			iter->dma += page_size;
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index cbad7fe722ce..d907d538176e 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -64,7 +64,7 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
 	if (!--b->irq_enabled)
 		irq_disable(engine);
 
-	b->irq_armed = false;
+	WRITE_ONCE(b->irq_armed, false);
 	intel_gt_pm_put_async(engine->gt);
 }
 
@@ -73,7 +73,7 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 	unsigned long flags;
 
-	if (!b->irq_armed)
+	if (!READ_ONCE(b->irq_armed))
 		return;
 
 	spin_lock_irqsave(&b->irq_lock, flags);
@@ -142,6 +142,18 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 	intel_engine_add_retire(engine, tl);
 }
 
+static void __signal_request(struct i915_request *rq, struct list_head *signals)
+{
+	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
+	clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+
+	if (!__dma_fence_signal(&rq->fence))
+		return;
+
+	i915_request_get(rq);
+	list_add_tail(&rq->signal_link, signals);
+}
+
 static void signal_irq_work(struct irq_work *work)
 {
 	struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
@@ -155,6 +167,8 @@ static void signal_irq_work(struct irq_work *work)
 	if (b->irq_armed && list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
 
+	list_splice_init(&b->signaled_requests, &signal);
+
 	list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) {
 		GEM_BUG_ON(list_empty(&ce->signals));
 
@@ -163,24 +177,15 @@ static void signal_irq_work(struct irq_work *work)
 				list_entry(pos, typeof(*rq), signal_link);
 
 			GEM_BUG_ON(!check_signal_order(ce, rq));
-
 			if (!__request_completed(rq))
 				break;
 
-			GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_SIGNAL,
-					     &rq->fence.flags));
-			clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
-
-			if (!__dma_fence_signal(&rq->fence))
-				continue;
-
 			/*
 			 * Queue for execution after dropping the signaling
 			 * spinlock as the callback chain may end up adding
 			 * more signalers to the same context or engine.
 			 */
-			i915_request_get(rq);
-			list_add_tail(&rq->signal_link, &signal);
+			__signal_request(rq, &signal);
 		}
 
 		/*
@@ -233,7 +238,7 @@ static bool __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 	 * which we can add a new waiter and avoid the cost of re-enabling
 	 * the irq.
 	 */
-	b->irq_armed = true;
+	WRITE_ONCE(b->irq_armed, true);
 
 	/*
 	 * Since we are waiting on a request, the GPU should be busy
@@ -255,6 +260,7 @@ void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
 
 	spin_lock_init(&b->irq_lock);
 	INIT_LIST_HEAD(&b->signalers);
+	INIT_LIST_HEAD(&b->signaled_requests);
 
 	init_irq_work(&b->irq_work, signal_irq_work);
 }
@@ -274,6 +280,32 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
+void intel_engine_transfer_stale_breadcrumbs(struct intel_engine_cs *engine,
+					     struct intel_context *ce)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned long flags;
+
+	spin_lock_irqsave(&b->irq_lock, flags);
+	if (!list_empty(&ce->signals)) {
+		struct i915_request *rq, *next;
+
+		/* Queue for executing the signal callbacks in the irq_work */
+		list_for_each_entry_safe(rq, next, &ce->signals, signal_link) {
+			GEM_BUG_ON(rq->engine != engine);
+			GEM_BUG_ON(!__request_completed(rq));
+
+			__signal_request(rq, &b->signaled_requests);
+		}
+
+		INIT_LIST_HEAD(&ce->signals);
+		list_del_init(&ce->signal_link);
+
+		irq_work_queue(&b->irq_work);
+	}
+	spin_unlock_irqrestore(&b->irq_lock, flags);
+}
+
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 {
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index aea992e46c42..74ddb49b2941 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -114,6 +114,11 @@ int __intel_context_do_pin(struct intel_context *ce)
 		goto out_release;
 	}
 
+	if (unlikely(intel_context_is_closed(ce))) {
+		err = -ENOENT;
+		goto out_unlock;
+	}
+
 	if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) {
 		err = intel_context_active_acquire(ce);
 		if (unlikely(err))
diff --git a/drivers/gpu/drm/i915/gt/intel_context_sseu.c b/drivers/gpu/drm/i915/gt/intel_context_sseu.c
index 57a30956c922..487299cb91f2 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_context_sseu.c
@@ -25,8 +25,7 @@ static int gen8_emit_rpcs_config(struct i915_request *rq,
 		return PTR_ERR(cs);
 
 	offset = i915_ggtt_offset(ce->state) +
-		 LRC_STATE_PN * PAGE_SIZE +
-		 CTX_R_PWR_CLK_STATE * 4;
+		 LRC_STATE_OFFSET + 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_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index ca0d4f4f3615..4954b0df4864 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -102,6 +102,8 @@ struct intel_context {
 
 	/** sseu: Control eu/slice partitioning */
 	struct intel_sseu sseu;
+
+	u8 wa_bb_page; /* if set, page num reserved for context workarounds */
 };
 
 #endif /* __INTEL_CONTEXT_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index a1aa0d3e8be1..9bf6d4989968 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -199,6 +199,8 @@ void intel_engine_cleanup(struct intel_engine_cs *engine);
 int intel_engines_init_mmio(struct intel_gt *gt);
 int intel_engines_init(struct intel_gt *gt);
 
+void intel_engine_free_request_pool(struct intel_engine_cs *engine);
+
 void intel_engines_release(struct intel_gt *gt);
 void intel_engines_free(struct intel_gt *gt);
 
@@ -236,22 +238,35 @@ intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
 void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
+void intel_engine_transfer_stale_breadcrumbs(struct intel_engine_cs *engine,
+					     struct intel_context *ce);
+
 void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
 				    struct drm_printer *p);
 
-static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset)
+static inline u32 *__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
 {
 	memset(batch, 0, 6 * sizeof(u32));
 
-	batch[0] = GFX_OP_PIPE_CONTROL(6);
-	batch[1] = flags;
+	batch[0] = GFX_OP_PIPE_CONTROL(6) | flags0;
+	batch[1] = flags1;
 	batch[2] = offset;
 
 	return batch + 6;
 }
 
+static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset)
+{
+	return __gen8_emit_pipe_control(batch, 0, flags, offset);
+}
+
+static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
+{
+	return __gen8_emit_pipe_control(batch, flags0, flags1, offset);
+}
+
 static inline u32 *
-gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
 {
 	/* We're using qword write, offset should be aligned to 8 bytes. */
 	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
@@ -260,8 +275,8 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	 * need a prior CS_STALL, which is emitted by the flush
 	 * following the batch.
 	 */
-	*cs++ = GFX_OP_PIPE_CONTROL(6);
-	*cs++ = flags | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
+	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
 	*cs++ = gtt_offset;
 	*cs++ = 0;
 	*cs++ = value;
@@ -271,6 +286,18 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	return cs;
 }
 
+static inline u32*
+gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+}
+
+static inline u32*
+gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+{
+	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+}
+
 static inline u32 *
 gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 {
@@ -308,9 +335,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...);
 
-int intel_enable_engine_stats(struct intel_engine_cs *engine);
-void intel_disable_engine_stats(struct intel_engine_cs *engine);
-
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 
 struct i915_request *
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 883a9b7fe88d..da5b61085257 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -31,7 +31,6 @@
 #include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
-#include "intel_engine_pool.h"
 #include "intel_engine_user.h"
 #include "intel_gt.h"
 #include "intel_gt_requests.h"
@@ -327,6 +326,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	if (INTEL_GEN(i915) == 12 && engine->class == RENDER_CLASS)
 		engine->props.preempt_timeout_ms = 0;
 
+	engine->defaults = engine->props; /* never to change again */
+
 	engine->context_size = intel_engine_context_size(gt, engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
@@ -347,8 +348,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	gt->engine_class[info->class][info->instance] = engine;
 	gt->engine[id] = engine;
 
-	i915->engine[id] = engine;
-
 	return 0;
 }
 
@@ -425,17 +424,27 @@ void intel_engines_release(struct intel_gt *gt)
 		engine->release = NULL;
 
 		memset(&engine->reset, 0, sizeof(engine->reset));
-
-		gt->i915->engine[id] = NULL;
 	}
 }
 
+void intel_engine_free_request_pool(struct intel_engine_cs *engine)
+{
+	if (!engine->request_pool)
+		return;
+
+	kmem_cache_free(i915_request_slab_cache(), engine->request_pool);
+}
+
 void intel_engines_free(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	/* Free the requests! dma-resv keeps fences around for an eternity */
+	rcu_barrier();
+
 	for_each_engine(engine, gt, id) {
+		intel_engine_free_request_pool(engine);
 		kfree(engine);
 		gt->engine[id] = NULL;
 	}
@@ -623,8 +632,6 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
 
-	intel_engine_pool_init(&engine->pool);
-
 	/* Use the whole device by default */
 	engine->sseu =
 		intel_sseu_from_device_info(&RUNTIME_INFO(engine->i915)->sseu);
@@ -821,12 +828,11 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	cleanup_status_page(engine);
 
 	intel_engine_fini_retire(engine);
-	intel_engine_pool_fini(&engine->pool);
 	intel_engine_fini_breadcrumbs(engine);
 	intel_engine_cleanup_cmd_parser(engine);
 
 	if (engine->default_state)
-		i915_gem_object_put(engine->default_state);
+		fput(engine->default_state);
 
 	if (engine->kernel_context) {
 		intel_context_unpin(engine->kernel_context);
@@ -1225,6 +1231,49 @@ static void print_request(struct drm_printer *m,
 		   name);
 }
 
+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 int print_ring(char *buf, int sz, struct i915_request *rq)
+{
+	int len = 0;
+
+	if (!i915_request_signaled(rq)) {
+		struct intel_timeline *tl = get_timeline(rq);
+
+		len = scnprintf(buf, sz,
+				"ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
+				i915_ggtt_offset(rq->ring->vma),
+				tl ? tl->hwsp_offset : 0,
+				hwsp_seqno(rq),
+				DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
+						      1000 * 1000));
+
+		if (tl)
+			intel_timeline_put(tl);
+	}
+
+	return len;
+}
+
 static void hexdump(struct drm_printer *m, const void *buf, size_t len)
 {
 	const size_t rowsize = 8 * sizeof(u32);
@@ -1254,27 +1303,6 @@ 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 const char *repr_timer(const struct timer_list *t)
 {
 	if (!READ_ONCE(t->expires))
@@ -1393,39 +1421,24 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			int len;
 
 			len = scnprintf(hdr, sizeof(hdr),
-					"\t\tActive[%d]: ",
-					(int)(port - execlists->active));
-			if (!i915_request_signaled(rq)) {
-				struct intel_timeline *tl = get_timeline(rq);
-
-				len += scnprintf(hdr + len, sizeof(hdr) - len,
-						 "ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
-						 i915_ggtt_offset(rq->ring->vma),
-						 tl ? tl->hwsp_offset : 0,
-						 hwsp_seqno(rq),
-						 DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
-								       1000 * 1000));
-
-				if (tl)
-					intel_timeline_put(tl);
-			}
+					"\t\tActive[%d]:  ccid:%08x, ",
+					(int)(port - execlists->active),
+					rq->context->lrc.ccid);
+			len += print_ring(hdr + len, sizeof(hdr) - len, rq);
 			scnprintf(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),
-				 tl ? tl->hwsp_offset : 0,
-				 hwsp_seqno(rq));
-			print_request(m, rq, hdr);
+			char hdr[160];
+			int len;
 
-			if (tl)
-				intel_timeline_put(tl);
+			len = scnprintf(hdr, sizeof(hdr),
+					"\t\tPending[%d]: ccid:%08x, ",
+					(int)(port - execlists->pending),
+					rq->context->lrc.ccid);
+			len += print_ring(hdr + len, sizeof(hdr) - len, rq);
+			scnprintf(hdr + len, sizeof(hdr) - len, "rq: ");
+			print_request(m, rq, hdr);
 		}
 		rcu_read_unlock();
 		execlists_active_unlock_bh(execlists);
@@ -1574,58 +1587,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	intel_engine_print_breadcrumbs(engine, m);
 }
 
-/**
- * intel_enable_engine_stats() - Enable engine busy tracking on engine
- * @engine: engine to enable stats collection
- *
- * Start collecting the engine busyness data for @engine.
- *
- * Returns 0 on success or a negative error code.
- */
-int intel_enable_engine_stats(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists *execlists = &engine->execlists;
-	unsigned long flags;
-	int err = 0;
-
-	if (!intel_engine_supports_stats(engine))
-		return -ENODEV;
-
-	execlists_active_lock_bh(execlists);
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-
-	if (unlikely(engine->stats.enabled == ~0)) {
-		err = -EBUSY;
-		goto unlock;
-	}
-
-	if (engine->stats.enabled++ == 0) {
-		struct i915_request * const *port;
-		struct i915_request *rq;
-
-		engine->stats.enabled_at = ktime_get();
-
-		/* XXX submission method oblivious? */
-		for (port = execlists->active; (rq = *port); port++)
-			engine->stats.active++;
-
-		for (port = execlists->pending; (rq = *port); port++) {
-			/* Exclude any contexts already counted in active */
-			if (!intel_context_inflight_count(rq->context))
-				engine->stats.active++;
-		}
-
-		if (engine->stats.active)
-			engine->stats.start = engine->stats.enabled_at;
-	}
-
-unlock:
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-	execlists_active_unlock_bh(execlists);
-
-	return err;
-}
-
 static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
 {
 	ktime_t total = engine->stats.total;
@@ -1634,7 +1595,7 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
 	 * If the engine is executing something at the moment
 	 * add it to the total.
 	 */
-	if (engine->stats.active)
+	if (atomic_read(&engine->stats.active))
 		total = ktime_add(total,
 				  ktime_sub(ktime_get(), engine->stats.start));
 
@@ -1660,28 +1621,6 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
 	return total;
 }
 
-/**
- * intel_disable_engine_stats() - Disable engine busy tracking on engine
- * @engine: engine to disable stats collection
- *
- * Stops collecting the engine busyness data for @engine.
- */
-void intel_disable_engine_stats(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	if (!intel_engine_supports_stats(engine))
-		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	WARN_ON_ONCE(engine->stats.enabled == 0);
-	if (--engine->stats.enabled == 0) {
-		engine->stats.total = __intel_engine_get_busy_time(engine);
-		engine->stats.active = 0;
-	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-}
-
 static bool match_ring(struct i915_request *rq)
 {
 	u32 ring = ENGINE_READ(rq->engine, RING_START);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index dd825718e4e5..5136c8bf112d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -31,7 +31,7 @@ static bool next_heartbeat(struct intel_engine_cs *engine)
 	delay = msecs_to_jiffies_timeout(delay);
 	if (delay >= HZ)
 		delay = round_jiffies_up_relative(delay);
-	schedule_delayed_work(&engine->heartbeat.work, delay);
+	mod_delayed_work(system_wq, &engine->heartbeat.work, delay);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index b6cf284e3a2d..d0a1078ef632 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -10,31 +10,22 @@
 #include "intel_engine.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
-#include "intel_engine_pool.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_rc6.h"
 #include "intel_ring.h"
+#include "shmem_utils.h"
 
 static int __engine_unpark(struct intel_wakeref *wf)
 {
 	struct intel_engine_cs *engine =
 		container_of(wf, typeof(*engine), wakeref);
 	struct intel_context *ce;
-	void *map;
 
 	ENGINE_TRACE(engine, "\n");
 
 	intel_gt_pm_get(engine->gt);
 
-	/* Pin the default state for fast resets from atomic context. */
-	map = NULL;
-	if (engine->default_state)
-		map = i915_gem_object_pin_map(engine->default_state,
-					      I915_MAP_WB);
-	if (!IS_ERR_OR_NULL(map))
-		engine->pinned_default_state = map;
-
 	/* Discard stale context state from across idling */
 	ce = engine->kernel_context;
 	if (ce) {
@@ -44,6 +35,7 @@ static int __engine_unpark(struct intel_wakeref *wf)
 		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && ce->state) {
 			struct drm_i915_gem_object *obj = ce->state->obj;
 			int type = i915_coherent_map_type(engine->i915);
+			void *map;
 
 			map = i915_gem_object_pin_map(obj, type);
 			if (!IS_ERR(map)) {
@@ -181,7 +173,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * Ergo, if we put ourselves on the timelines.active_list
 	 * (se intel_timeline_enter()) before we increment the
 	 * engine->wakeref.count, we may see the request completion and retire
-	 * it causing an undeflow of the engine->wakeref.
+	 * it causing an underflow of the engine->wakeref.
 	 */
 	flags = __timeline_mark_lock(ce);
 	GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0);
@@ -255,7 +247,6 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	intel_engine_park_heartbeat(engine);
 	intel_engine_disarm_breadcrumbs(engine);
-	intel_engine_pool_park(&engine->pool);
 
 	/* Must be reset upon idling, or we may miss the busy wakeup. */
 	GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
@@ -263,11 +254,6 @@ static int __engine_park(struct intel_wakeref *wf)
 	if (engine->park)
 		engine->park(engine);
 
-	if (engine->pinned_default_state) {
-		i915_gem_object_unpin_map(engine->default_state);
-		engine->pinned_default_state = NULL;
-	}
-
 	engine->execlists.no_priolist = false;
 
 	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index e52c2b0cb245..418df0a13145 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -37,6 +37,12 @@ static inline void intel_engine_pm_put_async(struct intel_engine_cs *engine)
 	intel_wakeref_put_async(&engine->wakeref);
 }
 
+static inline void intel_engine_pm_put_delay(struct intel_engine_cs *engine,
+					     unsigned long delay)
+{
+	intel_wakeref_put_delay(&engine->wakeref, delay);
+}
+
 static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
 {
 	intel_wakeref_unlock_wait(&engine->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.h b/drivers/gpu/drm/i915/gt/intel_engine_pool.h
deleted file mode 100644
index 1bd89cadc3b7..000000000000
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * SPDX-License-Identifier: MIT
- *
- * Copyright © 2014-2018 Intel Corporation
- */
-
-#ifndef INTEL_ENGINE_POOL_H
-#define INTEL_ENGINE_POOL_H
-
-#include "intel_engine_pool_types.h"
-#include "i915_active.h"
-#include "i915_request.h"
-
-struct intel_engine_pool_node *
-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,
-			      struct i915_request *rq)
-{
-	return i915_active_add_request(&node->active, rq);
-}
-
-static inline void
-intel_engine_pool_put(struct intel_engine_pool_node *node)
-{
-	i915_active_release(&node->active);
-}
-
-void intel_engine_pool_init(struct intel_engine_pool *pool);
-void intel_engine_pool_park(struct intel_engine_pool *pool);
-void intel_engine_pool_fini(struct intel_engine_pool *pool);
-
-#endif /* INTEL_ENGINE_POOL_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 0be674ae1cf6..2b6cdf47d428 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -22,7 +22,6 @@
 #include "i915_pmu.h"
 #include "i915_priolist_types.h"
 #include "i915_selftest.h"
-#include "intel_engine_pool_types.h"
 #include "intel_sseu.h"
 #include "intel_timeline_types.h"
 #include "intel_wakeref.h"
@@ -181,6 +180,11 @@ struct intel_engine_execlists {
 	u32 error_interrupt;
 
 	/**
+	 * @reset_ccid: Active CCID [EXECLISTS_STATUS_HI] at the time of reset
+	 */
+	u32 reset_ccid;
+
+	/**
 	 * @no_priolist: priority lists disabled
 	 */
 	bool no_priolist;
@@ -321,6 +325,9 @@ struct intel_engine_cs {
 		struct list_head hold; /* ready requests, but on hold */
 	} active;
 
+	/* keep a request in reserve for a [pm] barrier under oom */
+	struct i915_request *request_pool;
+
 	struct llist_head barrier_tasks;
 
 	struct intel_context *kernel_context; /* pinned */
@@ -336,8 +343,7 @@ struct intel_engine_cs {
 
 	unsigned long wakeref_serial;
 	struct intel_wakeref wakeref;
-	struct drm_i915_gem_object *default_state;
-	void *pinned_default_state;
+	struct file *default_state;
 
 	struct {
 		struct intel_ring *ring;
@@ -371,6 +377,8 @@ struct intel_engine_cs {
 		spinlock_t irq_lock;
 		struct list_head signalers;
 
+		struct list_head signaled_requests;
+
 		struct irq_work irq_work; /* for use from inside irq_lock */
 
 		unsigned int irq_enabled;
@@ -402,13 +410,6 @@ struct intel_engine_cs {
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_COUNT];
 	} pmu;
 
-	/*
-	 * A pool of objects to use as shadow copies of client batch buffers
-	 * when the command parser is enabled. Prevents the client from
-	 * modifying the batch contents after software parsing.
-	 */
-	struct intel_engine_pool pool;
-
 	struct intel_hw_status_page status_page;
 	struct i915_ctx_workarounds wa_ctx;
 	struct i915_wa_list ctx_wa_list;
@@ -420,6 +421,7 @@ struct intel_engine_cs {
 	void		(*irq_enable)(struct intel_engine_cs *engine);
 	void		(*irq_disable)(struct intel_engine_cs *engine);
 
+	void		(*sanitize)(struct intel_engine_cs *engine);
 	int		(*resume)(struct intel_engine_cs *engine);
 
 	struct {
@@ -529,34 +531,34 @@ struct intel_engine_cs {
 
 	struct {
 		/**
-		 * @lock: Lock protecting the below fields.
-		 */
-		seqlock_t lock;
-		/**
-		 * @enabled: Reference count indicating number of listeners.
+		 * @active: Number of contexts currently scheduled in.
 		 */
-		unsigned int enabled;
+		atomic_t active;
+
 		/**
-		 * @active: Number of contexts currently scheduled in.
+		 * @lock: Lock protecting the below fields.
 		 */
-		unsigned int active;
+		seqlock_t lock;
+
 		/**
-		 * @enabled_at: Timestamp when busy stats were enabled.
+		 * @total: Total time this engine was busy.
+		 *
+		 * Accumulated time not counting the most recent block in cases
+		 * where engine is currently busy (active > 0).
 		 */
-		ktime_t enabled_at;
+		ktime_t total;
+
 		/**
 		 * @start: Timestamp of the last idle to active transition.
 		 *
 		 * Idle is defined as active == 0, active is active > 0.
 		 */
 		ktime_t start;
+
 		/**
-		 * @total: Total time this engine was busy.
-		 *
-		 * Accumulated time not counting the most recent block in cases
-		 * where engine is currently busy (active > 0).
+		 * @rps: Utilisation at last RPS sampling.
 		 */
-		ktime_t total;
+		ktime_t rps;
 	} stats;
 
 	struct {
@@ -565,7 +567,7 @@ struct intel_engine_cs {
 		unsigned long preempt_timeout_ms;
 		unsigned long stop_timeout_ms;
 		unsigned long timeslice_duration_ms;
-	} props;
+	} props, defaults;
 };
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 4c5a209cb669..66165b10256e 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -65,7 +65,7 @@ static int ggtt_init_hw(struct i915_ggtt *ggtt)
 					      ggtt->mappable_end);
 	}
 
-	i915_ggtt_init_fences(ggtt);
+	intel_ggtt_init_fences(ggtt);
 
 	return 0;
 }
@@ -715,11 +715,13 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
  */
 void i915_ggtt_driver_release(struct drm_i915_private *i915)
 {
+	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct pagevec *pvec;
 
-	fini_aliasing_ppgtt(&i915->ggtt);
+	fini_aliasing_ppgtt(ggtt);
 
-	ggtt_cleanup_hw(&i915->ggtt);
+	intel_ggtt_fini_fences(ggtt);
+	ggtt_cleanup_hw(ggtt);
 
 	pvec = &i915->mm.wc_stash.pvec;
 	if (pvec->nr) {
@@ -784,13 +786,13 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	else
 		ggtt->gsm = ioremap_wc(phys_addr, size);
 	if (!ggtt->gsm) {
-		DRM_ERROR("Failed to map the ggtt page table\n");
+		drm_err(&i915->drm, "Failed to map the ggtt page table\n");
 		return -ENOMEM;
 	}
 
 	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
 	if (ret) {
-		DRM_ERROR("Scratch setup failed\n");
+		drm_err(&i915->drm, "Scratch setup failed\n");
 		/* iounmap will also get called at remove, but meh */
 		iounmap(ggtt->gsm);
 		return ret;
@@ -838,7 +840,6 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	struct pci_dev *pdev = i915->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
-	int err;
 
 	/* TODO: We're not aware of mappable constraints on gen8 yet */
 	if (!IS_DGFX(i915)) {
@@ -846,12 +847,6 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 		ggtt->mappable_end = resource_size(&ggtt->gmadr);
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
-
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 	if (IS_CHERRYVIEW(i915))
 		size = chv_get_total_gtt_size(snb_gmch_ctl);
@@ -987,7 +982,6 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	struct pci_dev *pdev = i915->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
-	int err;
 
 	ggtt->gmadr = pci_resource(pdev, 2);
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
@@ -997,15 +991,11 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	 * just a coarse sanity check.
 	 */
 	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
-		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
+		drm_err(&i915->drm, "Unknown GMADR size (%pa)\n",
+			&ggtt->mappable_end);
 		return -ENXIO;
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
 	size = gen6_get_total_gtt_size(snb_gmch_ctl);
@@ -1052,7 +1042,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 
 	ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL);
 	if (!ret) {
-		DRM_ERROR("failed to set up gmch\n");
+		drm_err(&i915->drm, "failed to set up gmch\n");
 		return -EIO;
 	}
 
@@ -1075,7 +1065,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.vma_ops.clear_pages = clear_pages;
 
 	if (unlikely(ggtt->do_idle_maps))
-		dev_notice(i915->drm.dev,
+		drm_notice(&i915->drm,
 			   "Applying Ironlake quirks for intel_iommu\n");
 
 	return 0;
@@ -1100,26 +1090,29 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
 		return ret;
 
 	if ((ggtt->vm.total - 1) >> 32) {
-		DRM_ERROR("We never expected a Global GTT with more than 32bits"
-			  " of address space! Found %lldM!\n",
-			  ggtt->vm.total >> 20);
+		drm_err(&i915->drm,
+			"We never expected a Global GTT with more than 32bits"
+			" of address space! Found %lldM!\n",
+			ggtt->vm.total >> 20);
 		ggtt->vm.total = 1ULL << 32;
 		ggtt->mappable_end =
 			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
 	}
 
 	if (ggtt->mappable_end > ggtt->vm.total) {
-		DRM_ERROR("mappable aperture extends past end of GGTT,"
-			  " aperture=%pa, total=%llx\n",
-			  &ggtt->mappable_end, ggtt->vm.total);
+		drm_err(&i915->drm,
+			"mappable aperture extends past end of GGTT,"
+			" aperture=%pa, total=%llx\n",
+			&ggtt->mappable_end, ggtt->vm.total);
 		ggtt->mappable_end = ggtt->vm.total;
 	}
 
 	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
-	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
-	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
-			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
+	drm_dbg(&i915->drm, "GGTT size = %lluM\n", ggtt->vm.total >> 20);
+	drm_dbg(&i915->drm, "GMADR size = %lluM\n",
+		(u64)ggtt->mappable_end >> 20);
+	drm_dbg(&i915->drm, "DSM size = %lluM\n",
+		(u64)resource_size(&intel_graphics_stolen_res) >> 20);
 
 	return 0;
 }
@@ -1137,7 +1130,7 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915)
 		return ret;
 
 	if (intel_vtd_active())
-		dev_info(i915->drm.dev, "VT-d active for gfx access\n");
+		drm_info(&i915->drm, "VT-d active for gfx access\n");
 
 	return 0;
 }
@@ -1212,6 +1205,8 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
 
 	if (INTEL_GEN(ggtt->vm.i915) >= 8)
 		setup_private_pat(ggtt->vm.gt->uncore);
+
+	intel_ggtt_restore_fences(ggtt);
 }
 
 static struct scatterlist *
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index d152b648c73c..7fb36b12fe7a 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -68,8 +68,7 @@ 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)
+static void i965_write_fence_reg(struct i915_fence_reg *fence)
 {
 	i915_reg_t fence_reg_lo, fence_reg_hi;
 	int fence_pitch_shift;
@@ -87,18 +86,16 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence,
 	}
 
 	val = 0;
-	if (vma) {
-		unsigned int stride = i915_gem_object_get_stride(vma->obj);
+	if (fence->tiling) {
+		unsigned int stride = fence->stride;
 
-		GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
-		GEM_BUG_ON(!IS_ALIGNED(vma->node.start, I965_FENCE_PAGE));
-		GEM_BUG_ON(!IS_ALIGNED(vma->fence_size, I965_FENCE_PAGE));
 		GEM_BUG_ON(!IS_ALIGNED(stride, 128));
 
-		val = (vma->node.start + vma->fence_size - I965_FENCE_PAGE) << 32;
-		val |= vma->node.start;
+		val = fence->start + fence->size - I965_FENCE_PAGE;
+		val <<= 32;
+		val |= fence->start;
 		val |= (u64)((stride / 128) - 1) << fence_pitch_shift;
-		if (i915_gem_object_get_tiling(vma->obj) == I915_TILING_Y)
+		if (fence->tiling == I915_TILING_Y)
 			val |= BIT(I965_FENCE_TILING_Y_SHIFT);
 		val |= I965_FENCE_REG_VALID;
 	}
@@ -125,21 +122,15 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence,
 	}
 }
 
-static void i915_write_fence_reg(struct i915_fence_reg *fence,
-				 struct i915_vma *vma)
+static void i915_write_fence_reg(struct i915_fence_reg *fence)
 {
 	u32 val;
 
 	val = 0;
-	if (vma) {
-		unsigned int tiling = i915_gem_object_get_tiling(vma->obj);
+	if (fence->tiling) {
+		unsigned int stride = fence->stride;
+		unsigned int tiling = fence->tiling;
 		bool is_y_tiled = tiling == I915_TILING_Y;
-		unsigned int stride = i915_gem_object_get_stride(vma->obj);
-
-		GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
-		GEM_BUG_ON(vma->node.start & ~I915_FENCE_START_MASK);
-		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_to_i915(fence)))
 			stride /= 128;
@@ -147,10 +138,10 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence,
 			stride /= 512;
 		GEM_BUG_ON(!is_power_of_2(stride));
 
-		val = vma->node.start;
+		val = fence->start;
 		if (is_y_tiled)
 			val |= BIT(I830_FENCE_TILING_Y_SHIFT);
-		val |= I915_FENCE_SIZE_BITS(vma->fence_size);
+		val |= I915_FENCE_SIZE_BITS(fence->size);
 		val |= ilog2(stride) << I830_FENCE_PITCH_SHIFT;
 
 		val |= I830_FENCE_REG_VALID;
@@ -165,25 +156,18 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence,
 	}
 }
 
-static void i830_write_fence_reg(struct i915_fence_reg *fence,
-				 struct i915_vma *vma)
+static void i830_write_fence_reg(struct i915_fence_reg *fence)
 {
 	u32 val;
 
 	val = 0;
-	if (vma) {
-		unsigned int stride = i915_gem_object_get_stride(vma->obj);
-
-		GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
-		GEM_BUG_ON(vma->node.start & ~I830_FENCE_START_MASK);
-		GEM_BUG_ON(!is_power_of_2(vma->fence_size));
-		GEM_BUG_ON(!is_power_of_2(stride / 128));
-		GEM_BUG_ON(!IS_ALIGNED(vma->node.start, vma->fence_size));
+	if (fence->tiling) {
+		unsigned int stride = fence->stride;
 
-		val = vma->node.start;
-		if (i915_gem_object_get_tiling(vma->obj) == I915_TILING_Y)
+		val = fence->start;
+		if (fence->tiling == I915_TILING_Y)
 			val |= BIT(I830_FENCE_TILING_Y_SHIFT);
-		val |= I830_FENCE_SIZE_BITS(vma->fence_size);
+		val |= I830_FENCE_SIZE_BITS(fence->size);
 		val |= ilog2(stride / 128) << I830_FENCE_PITCH_SHIFT;
 		val |= I830_FENCE_REG_VALID;
 	}
@@ -197,8 +181,7 @@ static void i830_write_fence_reg(struct i915_fence_reg *fence,
 	}
 }
 
-static void fence_write(struct i915_fence_reg *fence,
-			struct i915_vma *vma)
+static void fence_write(struct i915_fence_reg *fence)
 {
 	struct drm_i915_private *i915 = fence_to_i915(fence);
 
@@ -209,18 +192,21 @@ static void fence_write(struct i915_fence_reg *fence,
 	 */
 
 	if (IS_GEN(i915, 2))
-		i830_write_fence_reg(fence, vma);
+		i830_write_fence_reg(fence);
 	else if (IS_GEN(i915, 3))
-		i915_write_fence_reg(fence, vma);
+		i915_write_fence_reg(fence);
 	else
-		i965_write_fence_reg(fence, vma);
+		i965_write_fence_reg(fence);
 
 	/*
 	 * Access through the fenced region afterwards is
 	 * ordered by the posting reads whilst writing the registers.
 	 */
+}
 
-	fence->dirty = false;
+static bool gpu_uses_fence_registers(struct i915_fence_reg *fence)
+{
+	return INTEL_GEN(fence_to_i915(fence)) < 4;
 }
 
 static int fence_update(struct i915_fence_reg *fence,
@@ -232,27 +218,32 @@ static int fence_update(struct i915_fence_reg *fence,
 	struct i915_vma *old;
 	int ret;
 
+	fence->tiling = 0;
 	if (vma) {
+		GEM_BUG_ON(!i915_gem_object_get_stride(vma->obj) ||
+			   !i915_gem_object_get_tiling(vma->obj));
+
 		if (!i915_vma_is_map_and_fenceable(vma))
 			return -EINVAL;
 
-		if (drm_WARN(&uncore->i915->drm,
-			     !i915_gem_object_get_stride(vma->obj) ||
-			     !i915_gem_object_get_tiling(vma->obj),
-			     "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
-			     i915_gem_object_get_stride(vma->obj),
-			     i915_gem_object_get_tiling(vma->obj)))
-			return -EINVAL;
+		if (gpu_uses_fence_registers(fence)) {
+			/* implicit 'unfenced' GPU blits */
+			ret = i915_vma_sync(vma);
+			if (ret)
+				return ret;
+		}
 
-		ret = i915_vma_sync(vma);
-		if (ret)
-			return ret;
+		fence->start = vma->node.start;
+		fence->size = vma->fence_size;
+		fence->stride = i915_gem_object_get_stride(vma->obj);
+		fence->tiling = i915_gem_object_get_tiling(vma->obj);
 	}
+	WRITE_ONCE(fence->dirty, false);
 
 	old = xchg(&fence->vma, NULL);
 	if (old) {
 		/* XXX Ideally we would move the waiting to outside the mutex */
-		ret = i915_vma_sync(old);
+		ret = i915_active_wait(&fence->active);
 		if (ret) {
 			fence->vma = old;
 			return ret;
@@ -276,7 +267,7 @@ static int fence_update(struct i915_fence_reg *fence,
 	/*
 	 * We only need to update the register itself if the device is awake.
 	 * If the device is currently powered down, we will defer the write
-	 * to the runtime resume, see i915_gem_restore_fences().
+	 * to the runtime resume, see intel_ggtt_restore_fences().
 	 *
 	 * This only works for removing the fence register, on acquisition
 	 * the caller must hold the rpm wakeref. The fence register must
@@ -290,7 +281,7 @@ static int fence_update(struct i915_fence_reg *fence,
 	}
 
 	WRITE_ONCE(fence->vma, vma);
-	fence_write(fence, vma);
+	fence_write(fence);
 
 	if (vma) {
 		vma->fence = fence;
@@ -307,23 +298,26 @@ static int fence_update(struct i915_fence_reg *fence,
  *
  * This function force-removes any fence from the given object, which is useful
  * if the kernel wants to do untiled GTT access.
- *
- * Returns:
- *
- * 0 on success, negative error code on failure.
  */
-int i915_vma_revoke_fence(struct i915_vma *vma)
+void i915_vma_revoke_fence(struct i915_vma *vma)
 {
 	struct i915_fence_reg *fence = vma->fence;
+	intel_wakeref_t wakeref;
 
 	lockdep_assert_held(&vma->vm->mutex);
 	if (!fence)
-		return 0;
+		return;
 
-	if (atomic_read(&fence->pin_count))
-		return -EBUSY;
+	GEM_BUG_ON(fence->vma != vma);
+	GEM_BUG_ON(!i915_active_is_idle(&fence->active));
+	GEM_BUG_ON(atomic_read(&fence->pin_count));
 
-	return fence_update(fence, NULL);
+	fence->tiling = 0;
+	WRITE_ONCE(fence->vma, NULL);
+	vma->fence = NULL;
+
+	with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref)
+		fence_write(fence);
 }
 
 static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt)
@@ -487,34 +481,19 @@ void i915_unreserve_fence(struct i915_fence_reg *fence)
 }
 
 /**
- * i915_gem_restore_fences - restore fence state
+ * intel_ggtt_restore_fences - restore fence state
  * @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 i915_ggtt *ggtt)
+void intel_ggtt_restore_fences(struct i915_ggtt *ggtt)
 {
 	int i;
 
-	rcu_read_lock(); /* keep obj alive as we dereference */
-	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);
-
-		/*
-		 * Commit delayed tiling changes if we have an object still
-		 * attached to the fence, otherwise just clear the fence.
-		 */
-		if (vma && !i915_gem_object_is_tiled(vma->obj))
-			vma = NULL;
-
-		fence_write(reg, vma);
-	}
-	rcu_read_unlock();
+	for (i = 0; i < ggtt->num_fences; i++)
+		fence_write(&ggtt->fence_regs[i]);
 }
 
 /**
@@ -746,7 +725,7 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt)
  * bit 17 of its physical address and therefore being interpreted differently
  * by the GPU.
  */
-static void i915_gem_swizzle_page(struct page *page)
+static void swizzle_page(struct page *page)
 {
 	char temp[64];
 	char *vaddr;
@@ -791,7 +770,7 @@ i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj,
 	for_each_sgt_page(page, sgt_iter, pages) {
 		char new_bit_17 = page_to_phys(page) >> 17;
 		if ((new_bit_17 & 0x1) != (test_bit(i, obj->bit_17) != 0)) {
-			i915_gem_swizzle_page(page);
+			swizzle_page(page);
 			set_page_dirty(page);
 		}
 		i++;
@@ -836,7 +815,7 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj,
 	}
 }
 
-void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
+void intel_ggtt_init_fences(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *i915 = ggtt->vm.i915;
 	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
@@ -864,18 +843,37 @@ void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
 	if (intel_vgpu_active(i915))
 		num_fences = intel_uncore_read(uncore,
 					       vgtif_reg(avail_rs.fence_num));
+	ggtt->fence_regs = kcalloc(num_fences,
+				   sizeof(*ggtt->fence_regs),
+				   GFP_KERNEL);
+	if (!ggtt->fence_regs)
+		num_fences = 0;
 
 	/* Initialize fence registers to zero */
 	for (i = 0; i < num_fences; i++) {
 		struct i915_fence_reg *fence = &ggtt->fence_regs[i];
 
+		i915_active_init(&fence->active, NULL, NULL);
 		fence->ggtt = ggtt;
 		fence->id = i;
 		list_add_tail(&fence->link, &ggtt->fence_list);
 	}
 	ggtt->num_fences = num_fences;
 
-	i915_gem_restore_fences(ggtt);
+	intel_ggtt_restore_fences(ggtt);
+}
+
+void intel_ggtt_fini_fences(struct i915_ggtt *ggtt)
+{
+	int i;
+
+	for (i = 0; i < ggtt->num_fences; i++) {
+		struct i915_fence_reg *fence = &ggtt->fence_regs[i];
+
+		i915_active_fini(&fence->active);
+	}
+
+	kfree(ggtt->fence_regs);
 }
 
 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/gt/intel_ggtt_fencing.h
index 7bd521cd7cd7..9eef679e1311 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h
@@ -22,12 +22,14 @@
  *
  */
 
-#ifndef __I915_FENCE_REG_H__
-#define __I915_FENCE_REG_H__
+#ifndef __INTEL_GGTT_FENCING_H__
+#define __INTEL_GGTT_FENCING_H__
 
 #include <linux/list.h>
 #include <linux/types.h>
 
+#include "i915_active.h"
+
 struct drm_i915_gem_object;
 struct i915_ggtt;
 struct i915_vma;
@@ -41,6 +43,7 @@ struct i915_fence_reg {
 	struct i915_ggtt *ggtt;
 	struct i915_vma *vma;
 	atomic_t pin_count;
+	struct i915_active active;
 	int id;
 	/**
 	 * Whether the tiling parameters for the currently
@@ -51,20 +54,24 @@ struct i915_fence_reg {
 	 * command (such as BLT on gen2/3), as a "fence".
 	 */
 	bool dirty;
+	u32 start;
+	u32 size;
+	u32 tiling;
+	u32 stride;
 };
 
-/* i915_gem_fence_reg.c */
 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 i915_ggtt *ggtt);
+void intel_ggtt_restore_fences(struct i915_ggtt *ggtt);
 
 void i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj,
 				       struct sg_table *pages);
 void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj,
 					 struct sg_table *pages);
 
-void i915_ggtt_init_fences(struct i915_ggtt *ggtt);
+void intel_ggtt_init_fences(struct i915_ggtt *ggtt);
+void intel_ggtt_fini_fences(struct i915_ggtt *ggtt);
 
 void intel_gt_init_swizzling(struct intel_gt *gt);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index f04214a54f75..534e435f20bc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -138,7 +138,7 @@
  */
 #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_LRM_CS_MMIO		REG_BIT(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)
@@ -156,6 +156,7 @@
 #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_LRR_SOURCE_CS_MMIO		REG_BIT(18)
 #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. */
@@ -235,9 +236,8 @@
 #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_HDC_PIPELINE_FLUSH		REG_BIT(9)  /* gen12 */
+#define   PIPE_CONTROL0_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_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index d09f7596cb98..f069551e412f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -7,6 +7,8 @@
 #include "i915_drv.h"
 #include "intel_context.h"
 #include "intel_gt.h"
+#include "intel_gt_buffer_pool.h"
+#include "intel_gt_clock_utils.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_mocs.h"
@@ -15,6 +17,7 @@
 #include "intel_rps.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
+#include "shmem_utils.h"
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 {
@@ -26,6 +29,7 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
+	intel_gt_init_buffer_pool(gt);
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_init_timelines(gt);
@@ -370,18 +374,6 @@ static struct i915_address_space *kernel_vm(struct intel_gt *gt)
 		return i915_vm_get(&gt->ggtt->vm);
 }
 
-static int __intel_context_flush_retire(struct intel_context *ce)
-{
-	struct intel_timeline *tl;
-
-	tl = intel_context_timeline_lock(ce);
-	if (IS_ERR(tl))
-		return PTR_ERR(tl);
-
-	intel_context_timeline_unlock(tl);
-	return 0;
-}
-
 static int __engines_record_defaults(struct intel_gt *gt)
 {
 	struct i915_request *requests[I915_NUM_ENGINES] = {};
@@ -447,8 +439,7 @@ err_rq:
 
 	for (id = 0; id < ARRAY_SIZE(requests); id++) {
 		struct i915_request *rq;
-		struct i915_vma *state;
-		void *vaddr;
+		struct file *state;
 
 		rq = requests[id];
 		if (!rq)
@@ -460,48 +451,16 @@ err_rq:
 		}
 
 		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT, &rq->context->flags));
-		state = rq->context->state;
-		if (!state)
+		if (!rq->context->state)
 			continue;
 
-		/* Serialise with retirement on another CPU */
-		GEM_BUG_ON(!i915_request_completed(rq));
-		err = __intel_context_flush_retire(rq->context);
-		if (err)
-			goto out;
-
-		/* We want to be able to unbind the state from the GGTT */
-		GEM_BUG_ON(intel_context_is_pinned(rq->context));
-
-		/*
-		 * As we will hold a reference to the logical state, it will
-		 * not be torn down with the context, and importantly the
-		 * object will hold onto its vma (making it possible for a
-		 * stray GTT write to corrupt our defaults). Unmap the vma
-		 * from the GTT to prevent such accidents and reclaim the
-		 * space.
-		 */
-		err = i915_vma_unbind(state);
-		if (err)
-			goto out;
-
-		i915_gem_object_lock(state->obj);
-		err = i915_gem_object_set_to_cpu_domain(state->obj, false);
-		i915_gem_object_unlock(state->obj);
-		if (err)
-			goto out;
-
-		i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
-
-		/* Check we can acquire the image of the context state */
-		vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
+		/* Keep a copy of the state's backing pages; free the obj */
+		state = shmem_create_from_object(rq->context->state->obj);
+		if (IS_ERR(state)) {
+			err = PTR_ERR(state);
 			goto out;
 		}
-
-		rq->engine->default_state = i915_gem_object_get(state->obj);
-		i915_gem_object_unpin_map(state->obj);
+		rq->engine->default_state = state;
 	}
 
 out:
@@ -576,6 +535,8 @@ int intel_gt_init(struct intel_gt *gt)
 	 */
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 
+	intel_gt_init_clock_frequency(gt);
+
 	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
 	if (err)
 		goto out_fw;
@@ -635,8 +596,7 @@ void intel_gt_driver_remove(struct intel_gt *gt)
 {
 	__intel_gt_disable(gt);
 
-	intel_uc_fini_hw(&gt->uc);
-	intel_uc_fini(&gt->uc);
+	intel_uc_driver_remove(&gt->uc);
 
 	intel_engines_release(gt);
 }
@@ -663,6 +623,7 @@ void intel_gt_driver_release(struct intel_gt *gt)
 
 	intel_gt_pm_fini(gt);
 	intel_gt_fini_scratch(gt);
+	intel_gt_fini_buffer_pool(gt);
 }
 
 void intel_gt_driver_late_release(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
index 397186818305..1495054a4305 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: MIT
 /*
- * SPDX-License-Identifier: MIT
- *
  * Copyright © 2014-2018 Intel Corporation
  */
 
@@ -8,15 +7,15 @@
 
 #include "i915_drv.h"
 #include "intel_engine_pm.h"
-#include "intel_engine_pool.h"
+#include "intel_gt_buffer_pool.h"
 
-static struct intel_engine_cs *to_engine(struct intel_engine_pool *pool)
+static struct intel_gt *to_gt(struct intel_gt_buffer_pool *pool)
 {
-	return container_of(pool, struct intel_engine_cs, pool);
+	return container_of(pool, struct intel_gt, buffer_pool);
 }
 
 static struct list_head *
-bucket_for_size(struct intel_engine_pool *pool, size_t sz)
+bucket_for_size(struct intel_gt_buffer_pool *pool, size_t sz)
 {
 	int n;
 
@@ -32,16 +31,50 @@ bucket_for_size(struct intel_engine_pool *pool, size_t sz)
 	return &pool->cache_list[n];
 }
 
-static void node_free(struct intel_engine_pool_node *node)
+static void node_free(struct intel_gt_buffer_pool_node *node)
 {
 	i915_gem_object_put(node->obj);
 	i915_active_fini(&node->active);
 	kfree(node);
 }
 
+static void pool_free_work(struct work_struct *wrk)
+{
+	struct intel_gt_buffer_pool *pool =
+		container_of(wrk, typeof(*pool), work.work);
+	struct intel_gt_buffer_pool_node *node, *next;
+	unsigned long old = jiffies - HZ;
+	bool active = false;
+	LIST_HEAD(stale);
+	int n;
+
+	/* Free buffers that have not been used in the past second */
+	spin_lock_irq(&pool->lock);
+	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) {
+		struct list_head *list = &pool->cache_list[n];
+
+		/* Most recent at head; oldest at tail */
+		list_for_each_entry_safe_reverse(node, next, list, link) {
+			if (time_before(node->age, old))
+				break;
+
+			list_move(&node->link, &stale);
+		}
+		active |= !list_empty(list);
+	}
+	spin_unlock_irq(&pool->lock);
+
+	list_for_each_entry_safe(node, next, &stale, link)
+		node_free(node);
+
+	if (active)
+		schedule_delayed_work(&pool->work,
+				      round_jiffies_up_relative(HZ));
+}
+
 static int pool_active(struct i915_active *ref)
 {
-	struct intel_engine_pool_node *node =
+	struct intel_gt_buffer_pool_node *node =
 		container_of(ref, typeof(*node), active);
 	struct dma_resv *resv = node->obj->base.resv;
 	int err;
@@ -64,29 +97,31 @@ static int pool_active(struct i915_active *ref)
 __i915_active_call
 static void pool_retire(struct i915_active *ref)
 {
-	struct intel_engine_pool_node *node =
+	struct intel_gt_buffer_pool_node *node =
 		container_of(ref, typeof(*node), active);
-	struct intel_engine_pool *pool = node->pool;
+	struct intel_gt_buffer_pool *pool = node->pool;
 	struct list_head *list = bucket_for_size(pool, node->obj->base.size);
 	unsigned long flags;
 
-	GEM_BUG_ON(!intel_engine_pm_is_awake(to_engine(pool)));
-
 	i915_gem_object_unpin_pages(node->obj);
 
 	/* Return this object to the shrinker pool */
 	i915_gem_object_make_purgeable(node->obj);
 
 	spin_lock_irqsave(&pool->lock, flags);
+	node->age = jiffies;
 	list_add(&node->link, list);
 	spin_unlock_irqrestore(&pool->lock, flags);
+
+	schedule_delayed_work(&pool->work,
+			      round_jiffies_up_relative(HZ));
 }
 
-static struct intel_engine_pool_node *
-node_create(struct intel_engine_pool *pool, size_t sz)
+static struct intel_gt_buffer_pool_node *
+node_create(struct intel_gt_buffer_pool *pool, size_t sz)
 {
-	struct intel_engine_cs *engine = to_engine(pool);
-	struct intel_engine_pool_node *node;
+	struct intel_gt *gt = to_gt(pool);
+	struct intel_gt_buffer_pool_node *node;
 	struct drm_i915_gem_object *obj;
 
 	node = kmalloc(sizeof(*node),
@@ -97,7 +132,7 @@ node_create(struct intel_engine_pool *pool, size_t sz)
 	node->pool = pool;
 	i915_active_init(&node->active, pool_active, pool_retire);
 
-	obj = i915_gem_object_create_internal(engine->i915, sz);
+	obj = i915_gem_object_create_internal(gt->i915, sz);
 	if (IS_ERR(obj)) {
 		i915_active_fini(&node->active);
 		kfree(node);
@@ -110,26 +145,15 @@ node_create(struct intel_engine_pool *pool, size_t sz)
 	return node;
 }
 
-static struct intel_engine_pool *lookup_pool(struct intel_engine_cs *engine)
+struct intel_gt_buffer_pool_node *
+intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size)
 {
-	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_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 intel_gt_buffer_pool *pool = &gt->buffer_pool;
+	struct intel_gt_buffer_pool_node *node;
 	struct list_head *list;
 	unsigned long flags;
 	int ret;
 
-	GEM_BUG_ON(!intel_engine_pm_is_awake(to_engine(pool)));
-
 	size = PAGE_ALIGN(size);
 	list = bucket_for_size(pool, size);
 
@@ -157,34 +181,48 @@ intel_engine_get_pool(struct intel_engine_cs *engine, size_t size)
 	return node;
 }
 
-void intel_engine_pool_init(struct intel_engine_pool *pool)
+void intel_gt_init_buffer_pool(struct intel_gt *gt)
 {
+	struct intel_gt_buffer_pool *pool = &gt->buffer_pool;
 	int n;
 
 	spin_lock_init(&pool->lock);
 	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++)
 		INIT_LIST_HEAD(&pool->cache_list[n]);
+	INIT_DELAYED_WORK(&pool->work, pool_free_work);
 }
 
-void intel_engine_pool_park(struct intel_engine_pool *pool)
+static void pool_free_imm(struct intel_gt_buffer_pool *pool)
 {
 	int n;
 
+	spin_lock_irq(&pool->lock);
 	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) {
+		struct intel_gt_buffer_pool_node *node, *next;
 		struct list_head *list = &pool->cache_list[n];
-		struct intel_engine_pool_node *node, *nn;
 
-		list_for_each_entry_safe(node, nn, list, link)
+		list_for_each_entry_safe(node, next, list, link)
 			node_free(node);
-
 		INIT_LIST_HEAD(list);
 	}
+	spin_unlock_irq(&pool->lock);
+}
+
+void intel_gt_flush_buffer_pool(struct intel_gt *gt)
+{
+	struct intel_gt_buffer_pool *pool = &gt->buffer_pool;
+
+	if (cancel_delayed_work_sync(&pool->work))
+		pool_free_imm(pool);
 }
 
-void intel_engine_pool_fini(struct intel_engine_pool *pool)
+void intel_gt_fini_buffer_pool(struct intel_gt *gt)
 {
+	struct intel_gt_buffer_pool *pool = &gt->buffer_pool;
 	int n;
 
+	intel_gt_flush_buffer_pool(gt);
+
 	for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++)
 		GEM_BUG_ON(!list_empty(&pool->cache_list[n]));
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h
new file mode 100644
index 000000000000..42cbac003e8a
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2014-2018 Intel Corporation
+ */
+
+#ifndef INTEL_GT_BUFFER_POOL_H
+#define INTEL_GT_BUFFER_POOL_H
+
+#include <linux/types.h>
+
+#include "i915_active.h"
+#include "intel_gt_buffer_pool_types.h"
+
+struct intel_gt;
+struct i915_request;
+
+struct intel_gt_buffer_pool_node *
+intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size);
+
+static inline int
+intel_gt_buffer_pool_mark_active(struct intel_gt_buffer_pool_node *node,
+				 struct i915_request *rq)
+{
+	return i915_active_add_request(&node->active, rq);
+}
+
+static inline void
+intel_gt_buffer_pool_put(struct intel_gt_buffer_pool_node *node)
+{
+	i915_active_release(&node->active);
+}
+
+void intel_gt_init_buffer_pool(struct intel_gt *gt);
+void intel_gt_flush_buffer_pool(struct intel_gt *gt);
+void intel_gt_fini_buffer_pool(struct intel_gt *gt);
+
+#endif /* INTEL_GT_BUFFER_POOL_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool_types.h b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h
index e31ee361b76f..e28bdda771ed 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h
@@ -4,26 +4,29 @@
  * Copyright © 2014-2018 Intel Corporation
  */
 
-#ifndef INTEL_ENGINE_POOL_TYPES_H
-#define INTEL_ENGINE_POOL_TYPES_H
+#ifndef INTEL_GT_BUFFER_POOL_TYPES_H
+#define INTEL_GT_BUFFER_POOL_TYPES_H
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <linux/workqueue.h>
 
 #include "i915_active_types.h"
 
 struct drm_i915_gem_object;
 
-struct intel_engine_pool {
+struct intel_gt_buffer_pool {
 	spinlock_t lock;
 	struct list_head cache_list[4];
+	struct delayed_work work;
 };
 
-struct intel_engine_pool_node {
+struct intel_gt_buffer_pool_node {
 	struct i915_active active;
 	struct drm_i915_gem_object *obj;
 	struct list_head link;
-	struct intel_engine_pool *pool;
+	struct intel_gt_buffer_pool *pool;
+	unsigned long age;
 };
 
-#endif /* INTEL_ENGINE_POOL_TYPES_H */
+#endif /* INTEL_GT_BUFFER_POOL_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
new file mode 100644
index 000000000000..999079686846
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_clock_utils.h"
+
+#define MHZ_12   12000000 /* 12MHz (24MHz/2), 83.333ns */
+#define MHZ_12_5 12500000 /* 12.5MHz (25MHz/2), 80ns */
+#define MHZ_19_2 19200000 /* 19.2MHz, 52.083ns */
+
+static u32 read_clock_frequency(const struct intel_gt *gt)
+{
+	if (INTEL_GEN(gt->i915) >= 11) {
+		u32 config;
+
+		config = intel_uncore_read(gt->uncore, RPM_CONFIG0);
+		config &= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK;
+		config >>= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
+
+		switch (config) {
+		case 0: return MHZ_12;
+		case 1:
+		case 2: return MHZ_19_2;
+		default:
+		case 3: return MHZ_12_5;
+		}
+	} else if (INTEL_GEN(gt->i915) >= 9) {
+		if (IS_GEN9_LP(gt->i915))
+			return MHZ_19_2;
+		else
+			return MHZ_12;
+	} else {
+		return MHZ_12_5;
+	}
+}
+
+void intel_gt_init_clock_frequency(struct intel_gt *gt)
+{
+	/*
+	 * Note that on gen11+, the clock frequency may be reconfigured.
+	 * We do not, and we assume nobody else does.
+	 */
+	gt->clock_frequency = read_clock_frequency(gt);
+	GT_TRACE(gt,
+		 "Using clock frequency: %dkHz\n",
+		 gt->clock_frequency / 1000);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_gt_check_clock_frequency(const struct intel_gt *gt)
+{
+	if (gt->clock_frequency != read_clock_frequency(gt)) {
+		dev_err(gt->i915->drm.dev,
+			"GT clock frequency changed, was %uHz, now %uHz!\n",
+			gt->clock_frequency,
+			read_clock_frequency(gt));
+	}
+}
+#endif
+
+static u64 div_u64_roundup(u64 nom, u32 den)
+{
+	return div_u64(nom + den - 1, den);
+}
+
+u32 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u32 count)
+{
+	return div_u64_roundup(mul_u32_u32(count, 1000 * 1000 * 1000),
+			       gt->clock_frequency);
+}
+
+u32 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u32 count)
+{
+	return intel_gt_clock_interval_to_ns(gt, 16 * count);
+}
+
+u32 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u32 ns)
+{
+	return div_u64_roundup(mul_u32_u32(gt->clock_frequency, ns),
+			       1000 * 1000 * 1000);
+}
+
+u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns)
+{
+	u32 val;
+
+	/*
+	 * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
+	 * 8300) freezing up around GPU hangs. Looks as if even
+	 * scheduling/timer interrupts start misbehaving if the RPS
+	 * EI/thresholds are "bad", leading to a very sluggish or even
+	 * frozen machine.
+	 */
+	val = DIV_ROUND_UP(intel_gt_ns_to_clock_interval(gt, ns), 16);
+	if (IS_GEN(gt->i915, 6))
+		val = roundup(val, 25);
+
+	return val;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h
new file mode 100644
index 000000000000..f793c89f2cbd
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_CLOCK_UTILS_H__
+#define __INTEL_GT_CLOCK_UTILS_H__
+
+#include <linux/types.h>
+
+struct intel_gt;
+
+void intel_gt_init_clock_frequency(struct intel_gt *gt);
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_gt_check_clock_frequency(const struct intel_gt *gt);
+#else
+static inline void intel_gt_check_clock_frequency(const struct intel_gt *gt) {}
+#endif
+
+u32 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u32 count);
+u32 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u32 count);
+
+u32 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u32 ns);
+u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns);
+
+#endif /* __INTEL_GT_CLOCK_UTILS_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 8b653c0f5e5f..6bdb434a442d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -12,6 +12,7 @@
 #include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
+#include "intel_gt_clock_utils.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_llc.h"
@@ -138,6 +139,8 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 
+	intel_gt_check_clock_frequency(gt);
+
 	/*
 	 * As we have just resumed the machine and woken the device up from
 	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
@@ -155,6 +158,10 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 
 	intel_uc_reset_prepare(&gt->uc);
 
+	for_each_engine(engine, gt, id)
+		if (engine->sanitize)
+			engine->sanitize(engine);
+
 	if (reset_engines(gt) || force) {
 		for_each_engine(engine, gt, id)
 			__intel_engine_reset(engine, false);
@@ -164,6 +171,8 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 		if (engine->reset.finish)
 			engine->reset.finish(engine);
 
+	intel_rps_sanitize(&gt->rps);
+
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 }
@@ -191,11 +200,12 @@ int intel_gt_resume(struct intel_gt *gt)
 	 * Only the kernel contexts should remain pinned over suspend,
 	 * allowing us to fixup the user contexts on their first pin.
 	 */
+	gt_sanitize(gt, true);
+
 	intel_gt_pm_get(gt);
 
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
-	gt_sanitize(gt, true);
 	if (intel_gt_is_wedged(gt)) {
 		err = -EIO;
 		goto out_fw;
@@ -204,7 +214,7 @@ int intel_gt_resume(struct intel_gt *gt)
 	/* Only when the HW is re-initialised, can we replay the requests */
 	err = intel_gt_init_hw(gt);
 	if (err) {
-		dev_err(gt->i915->drm.dev,
+		drm_err(&gt->i915->drm,
 			"Failed to initialize GPU, declaring it wedged!\n");
 		goto err_wedged;
 	}
@@ -220,7 +230,7 @@ int intel_gt_resume(struct intel_gt *gt)
 
 		intel_engine_pm_put(engine);
 		if (err) {
-			dev_err(gt->i915->drm.dev,
+			drm_err(&gt->i915->drm,
 				"Failed to restart %s (%d)\n",
 				engine->name, err);
 			goto err_wedged;
@@ -324,6 +334,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt)
 {
 	GT_TRACE(gt, "\n");
 	intel_gt_init_swizzling(gt);
+	intel_ggtt_restore_fences(gt->ggtt);
 
 	return intel_uc_runtime_resume(&gt->uc);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 24c99d0838af..16ff47c83bd5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -26,6 +26,11 @@ static bool retire_requests(struct intel_timeline *tl)
 	return !i915_active_fence_isset(&tl->last_request);
 }
 
+static bool engine_active(const struct intel_engine_cs *engine)
+{
+	return !list_empty(&engine->kernel_context->timeline->requests);
+}
+
 static bool flush_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
@@ -37,8 +42,13 @@ static bool flush_submission(struct intel_gt *gt)
 
 	for_each_engine(engine, gt, id) {
 		intel_engine_flush_submission(engine);
-		active |= flush_work(&engine->retire_work);
-		active |= flush_work(&engine->wakeref.work);
+
+		/* Flush the background retirement and idle barriers */
+		flush_work(&engine->retire_work);
+		flush_delayed_work(&engine->wakeref.work);
+
+		/* Is the idle barrier still outstanding? */
+		active |= engine_active(engine);
 	}
 
 	return active;
@@ -162,7 +172,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			}
 		}
 
-		if (!retire_requests(tl) || flush_submission(gt))
+		if (!retire_requests(tl))
 			active_count++;
 		mutex_unlock(&tl->mutex);
 
@@ -173,7 +183,6 @@ out_active:	spin_lock(&timelines->lock);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
 			GEM_BUG_ON(atomic_read(&tl->active_count));
@@ -185,6 +194,9 @@ out_active:	spin_lock(&timelines->lock);
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);
 
+	if (flush_submission(gt)) /* Wait, there's more! */
+		active_count++;
+
 	return active_count ? timeout : 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 96890dd12b5f..0cc1d6b185dc 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_gt_buffer_pool_types.h"
 #include "intel_llc_types.h"
 #include "intel_reset_types.h"
 #include "intel_rc6_types.h"
@@ -61,6 +62,7 @@ struct intel_gt {
 	struct list_head closed_vma;
 	spinlock_t closed_lock; /* guards the list of closed_vma */
 
+	ktime_t last_init_time;
 	struct intel_reset reset;
 
 	/**
@@ -72,14 +74,12 @@ struct intel_gt {
 	 */
 	intel_wakeref_t awake;
 
+	u32 clock_frequency;
+
 	struct intel_llc llc;
 	struct intel_rc6 rc6;
 	struct intel_rps rps;
 
-	ktime_t last_init_time;
-
-	struct i915_vma *scratch;
-
 	spinlock_t irq_lock;
 	u32 gt_imr;
 	u32 pm_ier;
@@ -97,6 +97,18 @@ struct intel_gt {
 	 * Reserved for exclusive use by the kernel.
 	 */
 	struct i915_address_space *vm;
+
+	/*
+	 * A pool of objects to use as shadow copies of client batch buffers
+	 * when the command parser is enabled. Prevents the client from
+	 * modifying the batch contents after software parsing.
+	 *
+	 * Buffers older than 1s are periodically reaped from the pool,
+	 * or may be reclaimed by the shrinker before then.
+	 */
+	struct intel_gt_buffer_pool buffer_pool;
+
+	struct i915_vma *scratch;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index b3116fe8d180..d93ebdf3fa0e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -26,7 +26,6 @@
 #include <drm/drm_mm.h>
 
 #include "gt/intel_reset.h"
-#include "i915_gem_fence_reg.h"
 #include "i915_selftest.h"
 #include "i915_vma_types.h"
 
@@ -135,6 +134,8 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
+struct i915_fence_reg;
+
 #define for_each_sgt_daddr(__dp, __iter, __sgt) \
 	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
 
@@ -333,7 +334,7 @@ struct i915_ggtt {
 	u32 pin_bias;
 
 	unsigned int num_fences;
-	struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
+	struct i915_fence_reg *fence_regs;
 	struct list_head fence_list;
 
 	/**
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 2dfaddb8811e..87e6c5bdd2dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -147,6 +147,7 @@
 #include "intel_reset.h"
 #include "intel_ring.h"
 #include "intel_workarounds.h"
+#include "shmem_utils.h"
 
 #define RING_EXECLIST_QFULL		(1 << 0x2)
 #define RING_EXECLIST1_VALID		(1 << 0x3)
@@ -216,7 +217,7 @@ struct virtual_engine {
 
 	/* And finally, which physical engines this virtual engine maps onto. */
 	unsigned int num_siblings;
-	struct intel_engine_cs *siblings[0];
+	struct intel_engine_cs *siblings[];
 };
 
 static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
@@ -238,6 +239,123 @@ __execlists_update_reg_state(const struct intel_context *ce,
 			     const struct intel_engine_cs *engine,
 			     u32 head);
 
+static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x60;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x54;
+	else if (engine->class == RENDER_CLASS)
+		return 0x58;
+	else
+		return -1;
+}
+
+static int lrc_ring_gpr0(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x74;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x68;
+	else if (engine->class == RENDER_CLASS)
+		return 0xd8;
+	else
+		return -1;
+}
+
+static int lrc_ring_wa_bb_per_ctx(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x12;
+	else if (INTEL_GEN(engine->i915) >= 9 || engine->class == RENDER_CLASS)
+		return 0x18;
+	else
+		return -1;
+}
+
+static int lrc_ring_indirect_ptr(const struct intel_engine_cs *engine)
+{
+	int x;
+
+	x = lrc_ring_wa_bb_per_ctx(engine);
+	if (x < 0)
+		return x;
+
+	return x + 2;
+}
+
+static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
+{
+	int x;
+
+	x = lrc_ring_indirect_ptr(engine);
+	if (x < 0)
+		return x;
+
+	return x + 2;
+}
+
+static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
+{
+	if (engine->class != RENDER_CLASS)
+		return -1;
+
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0xb6;
+	else if (INTEL_GEN(engine->i915) >= 11)
+		return 0xaa;
+	else
+		return -1;
+}
+
+static u32
+lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
+{
+	switch (INTEL_GEN(engine->i915)) {
+	default:
+		MISSING_CASE(INTEL_GEN(engine->i915));
+		fallthrough;
+	case 12:
+		return GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+	case 11:
+		return GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+	case 10:
+		return GEN10_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+	case 9:
+		return GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+	case 8:
+		return GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+	}
+}
+
+static void
+lrc_ring_setup_indirect_ctx(u32 *regs,
+			    const struct intel_engine_cs *engine,
+			    u32 ctx_bb_ggtt_addr,
+			    u32 size)
+{
+	GEM_BUG_ON(!size);
+	GEM_BUG_ON(!IS_ALIGNED(size, CACHELINE_BYTES));
+	GEM_BUG_ON(lrc_ring_indirect_ptr(engine) == -1);
+	regs[lrc_ring_indirect_ptr(engine) + 1] =
+		ctx_bb_ggtt_addr | (size / CACHELINE_BYTES);
+
+	GEM_BUG_ON(lrc_ring_indirect_offset(engine) == -1);
+	regs[lrc_ring_indirect_offset(engine) + 1] =
+		lrc_ring_indirect_offset_default(engine) << 6;
+}
+
+static u32 intel_context_get_runtime(const struct intel_context *ce)
+{
+	/*
+	 * We can use either ppHWSP[16] which is recorded before the context
+	 * switch (and so excludes the cost of context switches) or use the
+	 * value from the context image itself, which is saved/restored earlier
+	 * and so includes the cost of the save.
+	 */
+	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
+}
+
 static void mark_eio(struct i915_request *rq)
 {
 	if (i915_request_completed(rq))
@@ -311,18 +429,7 @@ static int effective_prio(const struct i915_request *rq)
 	if (i915_request_has_nopreempt(rq))
 		prio = I915_PRIORITY_UNPREEMPTABLE;
 
-	/*
-	 * On unwinding the active request, we give it a priority bump
-	 * if it has completed waiting on any semaphore. If we know that
-	 * the request has already started, we can prevent an unwanted
-	 * preempt-to-idle cycle by taking that into account now.
-	 */
-	if (__i915_request_has_started(rq))
-		prio |= I915_PRIORITY_NOSEMAPHORE;
-
-	/* Restrict mere WAIT boosts from triggering preemption */
-	BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); /* only internal */
-	return prio | __NO_PREEMPTION;
+	return prio;
 }
 
 static int queue_prio(const struct intel_engine_execlists *execlists)
@@ -489,7 +596,7 @@ static void set_offsets(u32 *regs,
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END(x) 0, (x)
+#define END(total_state_size) 0, (total_state_size)
 {
 	const u32 base = engine->mmio_base;
 
@@ -512,7 +619,7 @@ static void set_offsets(u32 *regs,
 		if (flags & POSTED)
 			*regs |= MI_LRI_FORCE_POSTED;
 		if (INTEL_GEN(engine->i915) >= 11)
-			*regs |= MI_LRI_CS_MMIO;
+			*regs |= MI_LRI_LRM_CS_MMIO;
 		regs++;
 
 		GEM_BUG_ON(!count);
@@ -897,8 +1004,63 @@ static const u8 gen12_rcs_offsets[] = {
 	NOP(6),
 	LRI(1, 0),
 	REG(0x0c8),
+	NOP(3 + 9 + 1),
+
+	LRI(51, 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),
+	REG(0x084),
+	NOP(1),
 
-	END(80)
+	END(192)
 };
 
 #undef END
@@ -1026,17 +1188,14 @@ static void intel_engine_context_in(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	if (READ_ONCE(engine->stats.enabled) == 0)
+	if (atomic_add_unless(&engine->stats.active, 1, 0))
 		return;
 
 	write_seqlock_irqsave(&engine->stats.lock, flags);
-
-	if (engine->stats.enabled > 0) {
-		if (engine->stats.active++ == 0)
-			engine->stats.start = ktime_get();
-		GEM_BUG_ON(engine->stats.active == 0);
+	if (!atomic_add_unless(&engine->stats.active, 1, 0)) {
+		engine->stats.start = ktime_get();
+		atomic_inc(&engine->stats.active);
 	}
-
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
@@ -1044,51 +1203,20 @@ static void intel_engine_context_out(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	if (READ_ONCE(engine->stats.enabled) == 0)
+	GEM_BUG_ON(!atomic_read(&engine->stats.active));
+
+	if (atomic_add_unless(&engine->stats.active, -1, 1))
 		return;
 
 	write_seqlock_irqsave(&engine->stats.lock, flags);
-
-	if (engine->stats.enabled > 0) {
-		ktime_t last;
-
-		if (engine->stats.active && --engine->stats.active == 0) {
-			/*
-			 * Decrement the active context count and in case GPU
-			 * is now idle add up to the running total.
-			 */
-			last = ktime_sub(ktime_get(), engine->stats.start);
-
-			engine->stats.total = ktime_add(engine->stats.total,
-							last);
-		} else if (engine->stats.active == 0) {
-			/*
-			 * After turning on engine stats, context out might be
-			 * the first event in which case we account from the
-			 * time stats gathering was turned on.
-			 */
-			last = ktime_sub(ktime_get(), engine->stats.enabled_at);
-
-			engine->stats.total = ktime_add(engine->stats.total,
-							last);
-		}
+	if (atomic_dec_and_test(&engine->stats.active)) {
+		engine->stats.total =
+			ktime_add(engine->stats.total,
+				  ktime_sub(ktime_get(), engine->stats.start));
 	}
-
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
-static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
-{
-	if (INTEL_GEN(engine->i915) >= 12)
-		return 0x60;
-	else if (INTEL_GEN(engine->i915) >= 9)
-		return 0x54;
-	else if (engine->class == RENDER_CLASS)
-		return 0x58;
-	else
-		return -1;
-}
-
 static void
 execlists_check_context(const struct intel_context *ce,
 			const struct intel_engine_cs *engine)
@@ -1132,14 +1260,12 @@ execlists_check_context(const struct intel_context *ce,
 static void restore_default_state(struct intel_context *ce,
 				  struct intel_engine_cs *engine)
 {
-	u32 *regs = ce->lrc_reg_state;
+	u32 *regs;
 
-	if (engine->pinned_default_state)
-		memcpy(regs, /* skip restoring the vanilla PPHWSP */
-		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
-		       engine->context_size - PAGE_SIZE);
+	regs = memset(ce->lrc_reg_state, 0, engine->context_size - PAGE_SIZE);
+	execlists_init_reg_state(regs, ce, engine, ce->ring, true);
 
-	execlists_init_reg_state(regs, ce, engine, ce->ring, false);
+	ce->runtime.last = intel_context_get_runtime(ce);
 }
 
 static void reset_active(struct i915_request *rq,
@@ -1181,17 +1307,6 @@ static void reset_active(struct i915_request *rq,
 	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 }
 
-static u32 intel_context_get_runtime(const struct intel_context *ce)
-{
-	/*
-	 * We can use either ppHWSP[16] which is recorded before the context
-	 * switch (and so excludes the cost of context switches) or use the
-	 * value from the context image itself, which is saved/restored earlier
-	 * and so includes the cost of the save.
-	 */
-	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
-}
-
 static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
 {
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
@@ -1243,7 +1358,7 @@ __execlists_schedule_in(struct i915_request *rq)
 		ce->lrc.ccid = ce->tag;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		unsigned int tag = ffs(engine->context_tag);
+		unsigned int tag = ffs(READ_ONCE(engine->context_tag));
 
 		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
 		clear_bit(tag - 1, &engine->context_tag);
@@ -1417,6 +1532,24 @@ static inline void write_desc(struct intel_engine_execlists *execlists, u64 desc
 	}
 }
 
+static __maybe_unused char *
+dump_port(char *buf, int buflen, const char *prefix, struct i915_request *rq)
+{
+	if (!rq)
+		return "";
+
+	snprintf(buf, buflen, "%sccid:%x %llx:%lld%s prio %d",
+		 prefix,
+		 rq->context->lrc.ccid,
+		 rq->fence.context, rq->fence.seqno,
+		 i915_request_completed(rq) ? "!" :
+		 i915_request_started(rq) ? "*" :
+		 "",
+		 rq_prio(rq));
+
+	return buf;
+}
+
 static __maybe_unused void
 trace_ports(const struct intel_engine_execlists *execlists,
 	    const char *msg,
@@ -1424,18 +1557,14 @@ trace_ports(const struct intel_engine_execlists *execlists,
 {
 	const struct intel_engine_cs *engine =
 		container_of(execlists, typeof(*engine), execlists);
+	char __maybe_unused p0[40], p1[40];
 
 	if (!ports[0])
 		return;
 
-	ENGINE_TRACE(engine, "%s { %llx:%lld%s, %llx:%lld }\n", msg,
-		     ports[0]->fence.context,
-		     ports[0]->fence.seqno,
-		     i915_request_completed(ports[0]) ? "!" :
-		     i915_request_started(ports[0]) ? "*" :
-		     "",
-		     ports[1] ? ports[1]->fence.context : 0,
-		     ports[1] ? ports[1]->fence.seqno : 0);
+	ENGINE_TRACE(engine, "%s { %s%s }\n", msg,
+		     dump_port(p0, sizeof(p0), "", ports[0]),
+		     dump_port(p1, sizeof(p1), ", ", ports[1]));
 }
 
 static inline bool
@@ -1448,9 +1577,12 @@ static __maybe_unused bool
 assert_pending_valid(const struct intel_engine_execlists *execlists,
 		     const char *msg)
 {
+	struct intel_engine_cs *engine =
+		container_of(execlists, typeof(*engine), execlists);
 	struct i915_request * const *port, *rq;
 	struct intel_context *ce = NULL;
 	bool sentinel = false;
+	u32 ccid = -1;
 
 	trace_ports(execlists, msg, execlists->pending);
 
@@ -1459,13 +1591,14 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		return true;
 
 	if (!execlists->pending[0]) {
-		GEM_TRACE_ERR("Nothing pending for promotion!\n");
+		GEM_TRACE_ERR("%s: Nothing pending for promotion!\n",
+			      engine->name);
 		return false;
 	}
 
 	if (execlists->pending[execlists_num_ports(execlists)]) {
-		GEM_TRACE_ERR("Excess pending[%d] for promotion!\n",
-			      execlists_num_ports(execlists));
+		GEM_TRACE_ERR("%s: Excess pending[%d] for promotion!\n",
+			      engine->name, execlists_num_ports(execlists));
 		return false;
 	}
 
@@ -1477,20 +1610,31 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		GEM_BUG_ON(!i915_request_is_active(rq));
 
 		if (ce == rq->context) {
-			GEM_TRACE_ERR("Dup context:%llx in pending[%zd]\n",
+			GEM_TRACE_ERR("%s: Dup context:%llx in pending[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
 		}
 		ce = rq->context;
 
+		if (ccid == ce->lrc.ccid) {
+			GEM_TRACE_ERR("%s: Dup ccid:%x context:%llx in pending[%zd]\n",
+				      engine->name,
+				      ccid, ce->timeline->fence_context,
+				      port - execlists->pending);
+			return false;
+		}
+		ccid = ce->lrc.ccid;
+
 		/*
 		 * Sentinels are supposed to be lonely so they flush the
 		 * current exection off the HW. Check that they are the
 		 * only request in the pending submission.
 		 */
 		if (sentinel) {
-			GEM_TRACE_ERR("context:%llx after sentinel in pending[%zd]\n",
+			GEM_TRACE_ERR("%s: context:%llx after sentinel in pending[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
@@ -1498,7 +1642,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 
 		sentinel = i915_request_has_sentinel(rq);
 		if (sentinel && port != execlists->pending) {
-			GEM_TRACE_ERR("sentinel context:%llx not in prime position[%zd]\n",
+			GEM_TRACE_ERR("%s: sentinel context:%llx not in prime position[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
@@ -1513,7 +1658,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 
 		if (i915_active_is_idle(&ce->active) &&
 		    !intel_context_is_barrier(ce)) {
-			GEM_TRACE_ERR("Inactive context:%llx in pending[%zd]\n",
+			GEM_TRACE_ERR("%s: Inactive context:%llx in pending[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			ok = false;
@@ -1521,7 +1667,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		}
 
 		if (!i915_vma_is_pinned(ce->state)) {
-			GEM_TRACE_ERR("Unpinned context:%llx in pending[%zd]\n",
+			GEM_TRACE_ERR("%s: Unpinned context:%llx in pending[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			ok = false;
@@ -1529,7 +1676,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		}
 
 		if (!i915_vma_is_pinned(ce->ring->vma)) {
-			GEM_TRACE_ERR("Unpinned ring:%llx in pending[%zd]\n",
+			GEM_TRACE_ERR("%s: Unpinned ring:%llx in pending[%zd]\n",
+				      engine->name,
 				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			ok = false;
@@ -1664,30 +1812,16 @@ static bool virtual_matches(const struct virtual_engine *ve,
 	return true;
 }
 
-static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
-				     struct i915_request *rq)
+static void virtual_xfer_breadcrumbs(struct virtual_engine *ve)
 {
-	struct intel_engine_cs *old = ve->siblings[0];
-
-	/* All unattached (rq->engine == old) must already be completed */
-
-	spin_lock(&old->breadcrumbs.irq_lock);
-	if (!list_empty(&ve->context.signal_link)) {
-		list_del_init(&ve->context.signal_link);
-
-		/*
-		 * We cannot acquire the new engine->breadcrumbs.irq_lock
-		 * (as we are holding a breadcrumbs.irq_lock already),
-		 * so attach this request to the signaler on submission.
-		 * The queued irq_work will occur when we finally drop
-		 * the engine->active.lock after dequeue.
-		 */
-		set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags);
-
-		/* Also transfer the pending irq_work for the old breadcrumb. */
-		intel_engine_signal_breadcrumbs(rq->engine);
-	}
-	spin_unlock(&old->breadcrumbs.irq_lock);
+	/*
+	 * All the outstanding signals on ve->siblings[0] must have
+	 * been completed, just pending the interrupt handler. As those
+	 * signals still refer to the old sibling (via rq->engine), we must
+	 * transfer those to the old irq_worker to keep our locking
+	 * consistent.
+	 */
+	intel_engine_transfer_stale_breadcrumbs(ve->siblings[0], &ve->context);
 }
 
 #define for_each_waiter(p__, rq__) \
@@ -1729,7 +1863,8 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 				continue;
 
 			/* No waiter should start before its signaler */
-			GEM_BUG_ON(i915_request_started(w) &&
+			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
+				   i915_request_started(w) &&
 				   !i915_request_completed(rq));
 
 			GEM_BUG_ON(i915_request_is_active(w));
@@ -1831,16 +1966,25 @@ static unsigned long active_timeslice(const struct intel_engine_cs *engine)
 
 static void set_timeslice(struct intel_engine_cs *engine)
 {
+	unsigned long duration;
+
 	if (!intel_engine_has_timeslices(engine))
 		return;
 
-	set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
+	duration = active_timeslice(engine);
+	ENGINE_TRACE(engine, "bump timeslicing, interval:%lu", duration);
+
+	set_timer_ms(&engine->execlists.timer, duration);
 }
 
 static void start_timeslice(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
-	int prio = queue_prio(execlists);
+	const int prio = queue_prio(execlists);
+	unsigned long duration;
+
+	if (!intel_engine_has_timeslices(engine))
+		return;
 
 	WRITE_ONCE(execlists->switch_priority_hint, prio);
 	if (prio == INT_MIN)
@@ -1849,7 +1993,12 @@ static void start_timeslice(struct intel_engine_cs *engine)
 	if (timer_pending(&execlists->timer))
 		return;
 
-	set_timer_ms(&execlists->timer, timeslice(engine));
+	duration = timeslice(engine);
+	ENGINE_TRACE(engine,
+		     "start timeslicing, prio:%d, interval:%lu",
+		     prio, duration);
+
+	set_timer_ms(&execlists->timer, duration);
 }
 
 static void record_preemption(struct intel_engine_execlists *execlists)
@@ -1946,11 +2095,26 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * of trouble.
 	 */
 	active = READ_ONCE(execlists->active);
-	while ((last = *active) && i915_request_completed(last))
-		active++;
 
-	if (last) {
+	/*
+	 * In theory we can skip over completed contexts that have not
+	 * yet been processed by events (as those events are in flight):
+	 *
+	 * while ((last = *active) && i915_request_completed(last))
+	 *	active++;
+	 *
+	 * However, the GPU cannot handle this as it will ultimately
+	 * find itself trying to jump back into a context it has just
+	 * completed and barf.
+	 */
+
+	if ((last = *active)) {
 		if (need_preempt(engine, last, rb)) {
+			if (i915_request_completed(last)) {
+				tasklet_hi_schedule(&execlists->tasklet);
+				return;
+			}
+
 			ENGINE_TRACE(engine,
 				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
 				     last->fence.context,
@@ -1978,6 +2142,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timeslice_expired(execlists, last)) {
+			if (i915_request_completed(last)) {
+				tasklet_hi_schedule(&execlists->tasklet);
+				return;
+			}
+
 			ENGINE_TRACE(engine,
 				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
 				     last->fence.context,
@@ -2087,7 +2256,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 									engine);
 
 				if (!list_empty(&ve->context.signals))
-					virtual_xfer_breadcrumbs(ve, rq);
+					virtual_xfer_breadcrumbs(ve);
 
 				/*
 				 * Move the bound engine to the top of the list
@@ -2246,8 +2415,8 @@ done:
 		clear_ports(port + 1, last_port - port);
 
 		WRITE_ONCE(execlists->yield, -1);
-		execlists_submit_ports(engine);
 		set_preempt_timeout(engine, *active);
+		execlists_submit_ports(engine);
 	} else {
 skip_submit:
 		ring_set_paused(engine, 0);
@@ -2417,8 +2586,6 @@ static void process_csb(struct intel_engine_cs *engine)
 		if (promote) {
 			struct i915_request * const *old = execlists->active;
 
-			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-
 			ring_set_paused(engine, 0);
 
 			/* Point active to the new ELSP; prevent overwriting */
@@ -2431,6 +2598,7 @@ static void process_csb(struct intel_engine_cs *engine)
 				execlists_schedule_out(*old++);
 
 			/* switch pending to inflight */
+			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
 			memcpy(execlists->inflight,
 			       execlists->pending,
 			       execlists_num_ports(execlists) *
@@ -2449,17 +2617,21 @@ static void process_csb(struct intel_engine_cs *engine)
 			 * We rely on the hardware being strongly
 			 * ordered, that the breadcrumb write is
 			 * coherent (visible from the CPU) before the
-			 * user interrupt and CSB is processed.
+			 * user interrupt is processed. One might assume
+			 * that the breadcrumb write being before the
+			 * user interrupt and the CS event for the context
+			 * switch would therefore be before the CS event
+			 * itself...
 			 */
 			if (GEM_SHOW_DEBUG() &&
-			    !i915_request_completed(*execlists->active) &&
-			    !reset_in_progress(execlists)) {
-				struct i915_request *rq __maybe_unused =
-					*execlists->active;
+			    !i915_request_completed(*execlists->active)) {
+				struct i915_request *rq = *execlists->active;
 				const u32 *regs __maybe_unused =
 					rq->context->lrc_reg_state;
 
 				ENGINE_TRACE(engine,
+					     "context completed before request!\n");
+				ENGINE_TRACE(engine,
 					     "ring:{start:0x%08x, head:%04x, tail:%04x, ctl:%08x, mode:%08x}\n",
 					     ENGINE_READ(engine, RING_START),
 					     ENGINE_READ(engine, RING_HEAD) & HEAD_ADDR,
@@ -2478,8 +2650,6 @@ static void process_csb(struct intel_engine_cs *engine)
 					     regs[CTX_RING_START],
 					     regs[CTX_RING_HEAD],
 					     regs[CTX_RING_TAIL]);
-
-				GEM_BUG_ON("context completed before request");
 			}
 
 			execlists_schedule_out(*execlists->active++);
@@ -2769,6 +2939,45 @@ err_cap:
 	return NULL;
 }
 
+static struct i915_request *
+active_context(struct intel_engine_cs *engine, u32 ccid)
+{
+	const struct intel_engine_execlists * const el = &engine->execlists;
+	struct i915_request * const *port, *rq;
+
+	/*
+	 * Use the most recent result from process_csb(), but just in case
+	 * we trigger an error (via interrupt) before the first CS event has
+	 * been written, peek at the next submission.
+	 */
+
+	for (port = el->active; (rq = *port); port++) {
+		if (rq->context->lrc.ccid == ccid) {
+			ENGINE_TRACE(engine,
+				     "ccid found at active:%zd\n",
+				     port - el->active);
+			return rq;
+		}
+	}
+
+	for (port = el->pending; (rq = *port); port++) {
+		if (rq->context->lrc.ccid == ccid) {
+			ENGINE_TRACE(engine,
+				     "ccid found at pending:%zd\n",
+				     port - el->pending);
+			return rq;
+		}
+	}
+
+	ENGINE_TRACE(engine, "ccid:%x not found\n", ccid);
+	return NULL;
+}
+
+static u32 active_ccid(struct intel_engine_cs *engine)
+{
+	return ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI);
+}
+
 static bool execlists_capture(struct intel_engine_cs *engine)
 {
 	struct execlists_capture *cap;
@@ -2786,7 +2995,7 @@ static bool execlists_capture(struct intel_engine_cs *engine)
 		return true;
 
 	spin_lock_irq(&engine->active.lock);
-	cap->rq = execlists_active(&engine->execlists);
+	cap->rq = active_context(engine, active_ccid(engine));
 	if (cap->rq) {
 		cap->rq = active_request(cap->rq->context->timeline, cap->rq);
 		cap->rq = i915_request_get_rcu(cap->rq);
@@ -2934,10 +3143,14 @@ static void __submit_queue_imm(struct intel_engine_cs *engine)
 	if (reset_in_progress(execlists))
 		return; /* defer until we restart the engine following reset */
 
-	if (execlists->tasklet.func == execlists_submission_tasklet)
-		__execlists_submission_tasklet(engine);
-	else
-		tasklet_hi_schedule(&execlists->tasklet);
+	/* Hopefully we clear execlists->pending[] to let us through */
+	if (READ_ONCE(execlists->pending[0]) &&
+	    tasklet_trylock(&execlists->tasklet)) {
+		process_csb(engine);
+		tasklet_unlock(&execlists->tasklet);
+	}
+
+	__execlists_submission_tasklet(engine);
 }
 
 static void submit_queue(struct intel_engine_cs *engine,
@@ -3023,19 +3236,139 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
 	vaddr += engine->context_size;
 
 	if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE))
-		dev_err_once(engine->i915->drm.dev,
+		drm_err_once(&engine->i915->drm,
 			     "%s context redzone overwritten!\n",
 			     engine->name);
 }
 
 static void execlists_context_unpin(struct intel_context *ce)
 {
-	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_PN * PAGE_SIZE,
+	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
 		      ce->engine);
 
 	i915_gem_object_unpin_map(ce->state->obj);
 }
 
+static u32 *
+gen12_emit_timestamp_wa(const struct intel_context *ce, u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
+		CTX_TIMESTAMP * sizeof(u32);
+	*cs++ = 0;
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_mmio_reg_offset(RING_CTX_TIMESTAMP(0));
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_mmio_reg_offset(RING_CTX_TIMESTAMP(0));
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_restore_scratch(const struct intel_context *ce, u32 *cs)
+{
+	GEM_BUG_ON(lrc_ring_gpr0(ce->engine) == -1);
+
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
+		(lrc_ring_gpr0(ce->engine) + 1) * sizeof(u32);
+	*cs++ = 0;
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs)
+{
+	GEM_BUG_ON(lrc_ring_cmd_buf_cctl(ce->engine) == -1);
+
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
+		(lrc_ring_cmd_buf_cctl(ce->engine) + 1) * sizeof(u32);
+	*cs++ = 0;
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
+{
+	cs = gen12_emit_timestamp_wa(ce, cs);
+	cs = gen12_emit_cmd_buf_wa(ce, cs);
+	cs = gen12_emit_restore_scratch(ce, cs);
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
+{
+	cs = gen12_emit_timestamp_wa(ce, cs);
+	cs = gen12_emit_restore_scratch(ce, cs);
+
+	return cs;
+}
+
+static inline u32 context_wa_bb_offset(const struct intel_context *ce)
+{
+	return PAGE_SIZE * ce->wa_bb_page;
+}
+
+static u32 *context_indirect_bb(const struct intel_context *ce)
+{
+	void *ptr;
+
+	GEM_BUG_ON(!ce->wa_bb_page);
+
+	ptr = ce->lrc_reg_state;
+	ptr -= LRC_STATE_OFFSET; /* back to start of context image */
+	ptr += context_wa_bb_offset(ce);
+
+	return ptr;
+}
+
+static void
+setup_indirect_ctx_bb(const struct intel_context *ce,
+		      const struct intel_engine_cs *engine,
+		      u32 *(*emit)(const struct intel_context *, u32 *))
+{
+	u32 * const start = context_indirect_bb(ce);
+	u32 *cs;
+
+	cs = emit(ce, start);
+	GEM_BUG_ON(cs - start > I915_GTT_PAGE_SIZE / sizeof(*cs));
+	while ((unsigned long)cs % CACHELINE_BYTES)
+		*cs++ = MI_NOOP;
+
+	lrc_ring_setup_indirect_ctx(ce->lrc_reg_state, engine,
+				    i915_ggtt_offset(ce->state) +
+				    context_wa_bb_offset(ce),
+				    (cs - start) * sizeof(*cs));
+}
+
 static void
 __execlists_update_reg_state(const struct intel_context *ce,
 			     const struct intel_engine_cs *engine,
@@ -3059,6 +3392,18 @@ __execlists_update_reg_state(const struct intel_context *ce,
 
 		i915_oa_init_reg_state(ce, engine);
 	}
+
+	if (ce->wa_bb_page) {
+		u32 *(*fn)(const struct intel_context *ce, u32 *cs);
+
+		fn = gen12_emit_indirect_ctx_xcs;
+		if (ce->engine->class == RENDER_CLASS)
+			fn = gen12_emit_indirect_ctx_rcs;
+
+		/* Mutually exclusive wrt to global indirect bb */
+		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
+		setup_indirect_ctx_bb(ce, engine, fn);
+	}
 }
 
 static int
@@ -3077,7 +3422,7 @@ __execlists_context_pin(struct intel_context *ce,
 		return PTR_ERR(vaddr);
 
 	ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
-	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
+	ce->lrc_reg_state = vaddr + LRC_STATE_OFFSET;
 	__execlists_update_reg_state(ce, engine, ce->ring->tail);
 
 	return 0;
@@ -3125,6 +3470,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
 
+	GEM_BUG_ON(i915_request_has_initial_breadcrumb(rq));
 	if (!i915_request_timeline(rq)->has_initial_breadcrumb)
 		return 0;
 
@@ -3151,6 +3497,56 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	/* Record the updated position of the request's payload */
 	rq->infix = intel_ring_offset(rq, cs);
 
+	__set_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
+
+	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->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);
+
 	return 0;
 }
 
@@ -3175,6 +3571,12 @@ static int execlists_request_alloc(struct i915_request *request)
 	 * to cancel/unwind this request now.
 	 */
 
+	if (!i915_vm_is_4lvl(request->context->vm)) {
+		ret = emit_pdps(request);
+		if (ret)
+			return ret;
+	}
+
 	/* Unconditionally invalidate GPU caches and TLBs. */
 	ret = request->engine->emit_flush(request, EMIT_INVALIDATE);
 	if (ret)
@@ -3475,7 +3877,8 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 
 	ret = lrc_setup_wa_ctx(engine);
 	if (ret) {
-		DRM_DEBUG_DRIVER("Failed to setup context WA page: %d\n", ret);
+		drm_dbg(&engine->i915->drm,
+			"Failed to setup context WA page: %d\n", ret);
 		return ret;
 	}
 
@@ -3508,6 +3911,72 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	return ret;
 }
 
+static void reset_csb_pointers(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	const unsigned int reset_value = execlists->csb_size - 1;
+
+	ring_set_paused(engine, 0);
+
+	/*
+	 * Sometimes Icelake forgets to reset its pointers on a GPU reset.
+	 * Bludgeon them with a mmio update to be sure.
+	 */
+	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
+		     0xffff << 16 | reset_value << 8 | reset_value);
+	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
+	/*
+	 * After a reset, the HW starts writing into CSB entry [0]. We
+	 * therefore have to set our HEAD pointer back one entry so that
+	 * the *first* entry we check is entry 0. To complicate this further,
+	 * as we don't wait for the first interrupt after reset, we have to
+	 * fake the HW write to point back to the last entry so that our
+	 * inline comparison of our cached head position against the last HW
+	 * write works even before the first interrupt.
+	 */
+	execlists->csb_head = reset_value;
+	WRITE_ONCE(*execlists->csb_write, reset_value);
+	wmb(); /* Make sure this is visible to HW (paranoia?) */
+
+	invalidate_csb_entries(&execlists->csb_status[0],
+			       &execlists->csb_status[reset_value]);
+
+	/* Once more for luck and our trusty paranoia */
+	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
+		     0xffff << 16 | reset_value << 8 | reset_value);
+	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
+	GEM_BUG_ON(READ_ONCE(*execlists->csb_write) != reset_value);
+}
+
+static void execlists_sanitize(struct intel_engine_cs *engine)
+{
+	/*
+	 * Poison residual state on resume, in case the suspend didn't!
+	 *
+	 * We have to assume that across suspend/resume (or other loss
+	 * of control) that the contents of our pinned buffers has been
+	 * lost, replaced by garbage. Since this doesn't always happen,
+	 * let's poison such state so that we more quickly spot when
+	 * we falsely assume it has been preserved.
+	 */
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		memset(engine->status_page.addr, POISON_INUSE, PAGE_SIZE);
+
+	reset_csb_pointers(engine);
+
+	/*
+	 * The kernel_context HWSP is stored in the status_page. As above,
+	 * that may be lost on resume/initialisation, and so we need to
+	 * reset the value in the HWSP.
+	 */
+	intel_timeline_reset_seqno(engine->kernel_context->timeline);
+
+	/* And scrub the dirty cachelines for the HWSP */
+	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+}
+
 static void enable_error_interrupt(struct intel_engine_cs *engine)
 {
 	u32 status;
@@ -3518,7 +3987,7 @@ static void enable_error_interrupt(struct intel_engine_cs *engine)
 
 	status = ENGINE_READ(engine, RING_ESR);
 	if (unlikely(status)) {
-		dev_err(engine->i915->drm.dev,
+		drm_err(&engine->i915->drm,
 			"engine '%s' resumed still in error: %08x\n",
 			engine->name, status);
 		__intel_gt_reset(engine->gt, engine->mask);
@@ -3582,7 +4051,8 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine)
 	bool unexpected = false;
 
 	if (ENGINE_READ_FW(engine, RING_MI_MODE) & STOP_RING) {
-		DRM_DEBUG_DRIVER("STOP_RING still set in RING_MI_MODE\n");
+		drm_dbg(&engine->i915->drm,
+			"STOP_RING still set in RING_MI_MODE\n");
 		unexpected = true;
 	}
 
@@ -3642,39 +4112,10 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	 *
 	 * FIXME: Wa for more modern gens needs to be validated
 	 */
+	ring_set_paused(engine, 1);
 	intel_engine_stop_cs(engine);
-}
-
-static void reset_csb_pointers(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	const unsigned int reset_value = execlists->csb_size - 1;
-
-	ring_set_paused(engine, 0);
-
-	/*
-	 * After a reset, the HW starts writing into CSB entry [0]. We
-	 * therefore have to set our HEAD pointer back one entry so that
-	 * the *first* entry we check is entry 0. To complicate this further,
-	 * as we don't wait for the first interrupt after reset, we have to
-	 * fake the HW write to point back to the last entry so that our
-	 * inline comparison of our cached head position against the last HW
-	 * write works even before the first interrupt.
-	 */
-	execlists->csb_head = reset_value;
-	WRITE_ONCE(*execlists->csb_write, reset_value);
-	wmb(); /* Make sure this is visible to HW (paranoia?) */
 
-	/*
-	 * Sometimes Icelake forgets to reset its pointers on a GPU reset.
-	 * Bludgeon them with a mmio update to be sure.
-	 */
-	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
-		     reset_value << 8 | reset_value);
-	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
-
-	invalidate_csb_entries(&execlists->csb_status[0],
-			       &execlists->csb_status[reset_value]);
+	engine->execlists.reset_ccid = active_ccid(engine);
 }
 
 static void __reset_stop_ring(u32 *regs, const struct intel_engine_cs *engine)
@@ -3717,7 +4158,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * its request, it was still running at the time of the
 	 * reset and will have been clobbered.
 	 */
-	rq = execlists_active(execlists);
+	rq = active_context(engine, engine->execlists.reset_ccid);
 	if (!rq)
 		goto unwind;
 
@@ -3767,8 +4208,6 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * image back to the expected values to skip over the guilty request.
 	 */
 	__i915_request_reset(rq, stalled);
-	if (!stalled)
-		goto out_replay;
 
 	/*
 	 * We want a simple context + ring to execute the breadcrumb update.
@@ -3778,9 +4217,6 @@ 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));
-	restore_default_state(ce, engine);
-
 out_replay:
 	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
 		     head, ce->ring->tail);
@@ -4146,6 +4582,42 @@ static u32 preparser_disable(bool state)
 	return MI_ARB_CHECK | 1 << 8 | state;
 }
 
+static i915_reg_t aux_inv_reg(const struct intel_engine_cs *engine)
+{
+	static const i915_reg_t vd[] = {
+		GEN12_VD0_AUX_NV,
+		GEN12_VD1_AUX_NV,
+		GEN12_VD2_AUX_NV,
+		GEN12_VD3_AUX_NV,
+	};
+
+	static const i915_reg_t ve[] = {
+		GEN12_VE0_AUX_NV,
+		GEN12_VE1_AUX_NV,
+	};
+
+	if (engine->class == VIDEO_DECODE_CLASS)
+		return vd[engine->instance];
+
+	if (engine->class == VIDEO_ENHANCEMENT_CLASS)
+		return ve[engine->instance];
+
+	GEM_BUG_ON("unknown aux_inv_reg\n");
+
+	return INVALID_MMIO_REG;
+}
+
+static u32 *
+gen12_emit_aux_table_inv(const i915_reg_t inv_reg, u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(inv_reg);
+	*cs++ = AUX_INV;
+	*cs++ = MI_NOOP;
+
+	return cs;
+}
+
 static int gen12_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
@@ -4154,13 +4626,13 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		u32 *cs;
 
 		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_FLUSH_L3;
 		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;
 
 		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
@@ -4171,7 +4643,9 @@ 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, LRC_PPHWSP_SCRATCH_ADDR);
+		cs = gen12_emit_pipe_control(cs,
+					     PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
+					     flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -4186,14 +4660,13 @@ 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;
 
 		flags |= PIPE_CONTROL_CS_STALL;
 
-		cs = intel_ring_begin(request, 8);
+		cs = intel_ring_begin(request, 8 + 4);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
@@ -4206,6 +4679,9 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
+		/* hsdes: 1809175790 */
+		cs = gen12_emit_aux_table_inv(GEN12_GFX_CCS_AUX_NV, cs);
+
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
 	}
@@ -4213,6 +4689,56 @@ static int gen12_emit_flush_render(struct i915_request *request,
 	return 0;
 }
 
+static int gen12_emit_flush(struct i915_request *request, u32 mode)
+{
+	intel_engine_mask_t aux_inv = 0;
+	u32 cmd, *cs;
+
+	if (mode & EMIT_INVALIDATE)
+		aux_inv = request->engine->mask & ~BIT(BCS0);
+
+	cs = intel_ring_begin(request,
+			      4 + (aux_inv ? 2 * hweight8(aux_inv) + 2 : 0));
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	cmd = MI_FLUSH_DW + 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
+	if (mode & EMIT_INVALIDATE) {
+		cmd |= MI_INVALIDATE_TLB;
+		if (request->engine->class == VIDEO_DECODE_CLASS)
+			cmd |= MI_INVALIDATE_BSD;
+	}
+
+	*cs++ = cmd;
+	*cs++ = LRC_PPHWSP_SCRATCH_ADDR;
+	*cs++ = 0; /* upper addr */
+	*cs++ = 0; /* value */
+
+	if (aux_inv) { /* hsdes: 1809175790 */
+		struct intel_engine_cs *engine;
+		unsigned int tmp;
+
+		*cs++ = MI_LOAD_REGISTER_IMM(hweight8(aux_inv));
+		for_each_engine_masked(engine, request->engine->gt,
+				       aux_inv, tmp) {
+			*cs++ = i915_mmio_reg_offset(aux_inv_reg(engine));
+			*cs++ = AUX_INV;
+		}
+		*cs++ = MI_NOOP;
+	}
+	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
@@ -4242,8 +4768,7 @@ static u32 *emit_preempt_busywait(struct i915_request *request, u32 *cs)
 }
 
 static __always_inline u32*
-gen8_emit_fini_breadcrumb_footer(struct i915_request *request,
-				 u32 *cs)
+gen8_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs)
 {
 	*cs++ = MI_USER_INTERRUPT;
 
@@ -4257,14 +4782,16 @@ gen8_emit_fini_breadcrumb_footer(struct i915_request *request,
 	return gen8_emit_wa_tail(request, cs);
 }
 
-static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write(cs,
-				  request->fence.seqno,
-				  i915_request_active_timeline(request)->hwsp_offset,
-				  0);
+	u32 addr = i915_request_active_timeline(request)->hwsp_offset;
+
+	return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0);
+}
 
-	return gen8_emit_fini_breadcrumb_footer(request, cs);
+static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
+{
+	return gen8_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
 }
 
 static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
@@ -4282,7 +4809,7 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_CS_STALL);
 
-	return gen8_emit_fini_breadcrumb_footer(request, cs);
+	return gen8_emit_fini_breadcrumb_tail(request, cs);
 }
 
 static u32 *
@@ -4298,7 +4825,7 @@ gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_DC_FLUSH_ENABLE |
 				      PIPE_CONTROL_FLUSH_ENABLE);
 
-	return gen8_emit_fini_breadcrumb_footer(request, cs);
+	return gen8_emit_fini_breadcrumb_tail(request, cs);
 }
 
 /*
@@ -4336,7 +4863,7 @@ static u32 *gen12_emit_preempt_busywait(struct i915_request *request, u32 *cs)
 }
 
 static __always_inline u32*
-gen12_emit_fini_breadcrumb_footer(struct i915_request *request, u32 *cs)
+gen12_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs)
 {
 	*cs++ = MI_USER_INTERRUPT;
 
@@ -4350,33 +4877,29 @@ gen12_emit_fini_breadcrumb_footer(struct i915_request *request, u32 *cs)
 	return gen8_emit_wa_tail(request, cs);
 }
 
-static u32 *gen12_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write(cs,
-				  request->fence.seqno,
-				  i915_request_active_timeline(request)->hwsp_offset,
-				  0);
-
-	return gen12_emit_fini_breadcrumb_footer(request, cs);
+	return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
 }
 
 static u32 *
 gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write_rcs(cs,
-				      request->fence.seqno,
-				      i915_request_active_timeline(request)->hwsp_offset,
-				      PIPE_CONTROL_CS_STALL |
-				      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);
+	cs = gen12_emit_ggtt_write_rcs(cs,
+				       request->fence.seqno,
+				       i915_request_active_timeline(request)->hwsp_offset,
+				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
+				       PIPE_CONTROL_CS_STALL |
+				       PIPE_CONTROL_TILE_CACHE_FLUSH |
+				       PIPE_CONTROL_FLUSH_L3 |
+				       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);
 
-	return gen12_emit_fini_breadcrumb_footer(request, cs);
+	return gen12_emit_fini_breadcrumb_tail(request, cs);
 }
 
 static void execlists_park(struct intel_engine_cs *engine)
@@ -4428,6 +4951,8 @@ static void execlists_shutdown(struct intel_engine_cs *engine)
 
 static void execlists_release(struct intel_engine_cs *engine)
 {
+	engine->sanitize = NULL; /* no longer in control, nothing to sanitize */
+
 	execlists_shutdown(engine);
 
 	intel_engine_cleanup_common(engine);
@@ -4447,9 +4972,10 @@ 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)
+	if (INTEL_GEN(engine->i915) >= 12) {
 		engine->emit_fini_breadcrumb = gen12_emit_fini_breadcrumb;
-
+		engine->emit_flush = gen12_emit_flush;
+	}
 	engine->set_default_submission = intel_execlists_set_default_submission;
 
 	if (INTEL_GEN(engine->i915) < 11) {
@@ -4530,7 +5056,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 		 * because we only expect rare glitches but nothing
 		 * critical to prevent us from using GPU
 		 */
-		DRM_ERROR("WA batch buffer initialization failed\n");
+		drm_err(&i915->drm, "WA batch buffer initialization failed\n");
 
 	if (HAS_LOGICAL_RING_ELSQ(i915)) {
 		execlists->submit_reg = uncore->regs +
@@ -4558,48 +5084,13 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 		execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32);
 	}
 
-	reset_csb_pointers(engine);
-
 	/* Finally, take ownership and responsibility for cleanup! */
+	engine->sanitize = execlists_sanitize;
 	engine->release = execlists_release;
 
 	return 0;
 }
 
-static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
-{
-	u32 indirect_ctx_offset;
-
-	switch (INTEL_GEN(engine->i915)) {
-	default:
-		MISSING_CASE(INTEL_GEN(engine->i915));
-		/* fall through */
-	case 12:
-		indirect_ctx_offset =
-			GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-		break;
-	case 11:
-		indirect_ctx_offset =
-			GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-		break;
-	case 10:
-		indirect_ctx_offset =
-			GEN10_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-		break;
-	case 9:
-		indirect_ctx_offset =
-			GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-		break;
-	case 8:
-		indirect_ctx_offset =
-			GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
-		break;
-	}
-
-	return indirect_ctx_offset;
-}
-
-
 static void init_common_reg_state(u32 * const regs,
 				  const struct intel_engine_cs *engine,
 				  const struct intel_ring *ring,
@@ -4617,30 +5108,27 @@ static void init_common_reg_state(u32 * const regs,
 	regs[CTX_CONTEXT_CONTROL] = ctl;
 
 	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
+	regs[CTX_TIMESTAMP] = 0;
 }
 
 static void init_wa_bb_reg_state(u32 * const regs,
-				 const struct intel_engine_cs *engine,
-				 u32 pos_bb_per_ctx)
+				 const struct intel_engine_cs *engine)
 {
 	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] =
+		GEM_BUG_ON(lrc_ring_wa_bb_per_ctx(engine) == -1);
+		regs[lrc_ring_wa_bb_per_ctx(engine) + 1] =
 			(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
 	}
 
 	if (wa_ctx->indirect_ctx.size) {
-		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
-
-		regs[pos_bb_per_ctx + 2] =
-			(ggtt_offset + wa_ctx->indirect_ctx.offset) |
-			(wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
-
-		regs[pos_bb_per_ctx + 4] =
-			intel_lr_indirect_ctx_offset(engine) << 6;
+		lrc_ring_setup_indirect_ctx(regs, engine,
+					    i915_ggtt_offset(wa_ctx->vma) +
+					    wa_ctx->indirect_ctx.offset,
+					    wa_ctx->indirect_ctx.size);
 	}
 }
 
@@ -4689,10 +5177,7 @@ static void execlists_init_reg_state(u32 *regs,
 	init_common_reg_state(regs, engine, ring, inhibit);
 	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);
+	init_wa_bb_reg_state(regs, engine);
 
 	__reset_stop_ring(regs, engine);
 }
@@ -4705,29 +5190,18 @@ populate_lr_context(struct intel_context *ce,
 {
 	bool inhibit = true;
 	void *vaddr;
-	int ret;
 
 	vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB);
 	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		DRM_DEBUG_DRIVER("Could not map object pages! (%d)\n", ret);
-		return ret;
+		drm_dbg(&engine->i915->drm, "Could not map object pages!\n");
+		return PTR_ERR(vaddr);
 	}
 
 	set_redzone(vaddr, engine);
 
 	if (engine->default_state) {
-		void *defaults;
-
-		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
-		if (IS_ERR(defaults)) {
-			ret = PTR_ERR(defaults);
-			goto err_unpin_ctx;
-		}
-
-		memcpy(vaddr, defaults, engine->context_size);
-		i915_gem_object_unpin_map(engine->default_state);
+		shmem_read(engine->default_state, 0,
+			   vaddr, engine->context_size);
 		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
@@ -4739,14 +5213,12 @@ populate_lr_context(struct intel_context *ce,
 	 * The second page of the context object contains some registers which
 	 * must be set up prior to the first execution.
 	 */
-	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
+	execlists_init_reg_state(vaddr + LRC_STATE_OFFSET,
 				 ce, engine, ring, inhibit);
 
-	ret = 0;
-err_unpin_ctx:
 	__i915_gem_object_flush_map(ctx_obj, 0, engine->context_size);
 	i915_gem_object_unpin_map(ctx_obj);
-	return ret;
+	return 0;
 }
 
 static int __execlists_context_alloc(struct intel_context *ce,
@@ -4764,6 +5236,11 @@ static int __execlists_context_alloc(struct intel_context *ce,
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		context_size += I915_GTT_PAGE_SIZE; /* for redzone */
 
+	if (INTEL_GEN(engine->i915) == 12) {
+		ce->wa_bb_page = context_size / PAGE_SIZE;
+		context_size += PAGE_SIZE;
+	}
+
 	ctx_obj = i915_gem_object_create_shmem(engine->i915, context_size);
 	if (IS_ERR(ctx_obj))
 		return PTR_ERR(ctx_obj);
@@ -4803,7 +5280,8 @@ static int __execlists_context_alloc(struct intel_context *ce,
 
 	ret = populate_lr_context(ce, ctx_obj, engine, ring);
 	if (ret) {
-		DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
+		drm_dbg(&engine->i915->drm,
+			"Failed to populate LRC: %d\n", ret);
 		goto error_ring_free;
 	}
 
@@ -4856,6 +5334,8 @@ static void virtual_context_destroy(struct kref *kref)
 		__execlists_context_fini(&ve->context);
 	intel_context_fini(&ve->context);
 
+	intel_engine_free_request_pool(&ve->base);
+
 	kfree(ve->bonds);
 	kfree(ve);
 }
@@ -4980,12 +5460,15 @@ static void virtual_submission_tasklet(unsigned long data)
 		return;
 
 	local_irq_disable();
-	for (n = 0; READ_ONCE(ve->request) && n < ve->num_siblings; n++) {
-		struct intel_engine_cs *sibling = ve->siblings[n];
+	for (n = 0; n < ve->num_siblings; n++) {
+		struct intel_engine_cs *sibling = READ_ONCE(ve->siblings[n]);
 		struct ve_node * const node = &ve->nodes[sibling->id];
 		struct rb_node **parent, *rb;
 		bool first;
 
+		if (!READ_ONCE(ve->request))
+			break; /* already handled by a sibling's tasklet */
+
 		if (unlikely(!(mask & sibling->mask))) {
 			if (!RB_EMPTY_NODE(&node->rb)) {
 				spin_lock(&sibling->active.lock);
@@ -5036,10 +5519,8 @@ static void virtual_submission_tasklet(unsigned long data)
 submit_engine:
 		GEM_BUG_ON(RB_EMPTY_NODE(&node->rb));
 		node->prio = prio;
-		if (first && prio > sibling->execlists.queue_priority_hint) {
-			sibling->execlists.queue_priority_hint = prio;
+		if (first && prio > sibling->execlists.queue_priority_hint)
 			tasklet_hi_schedule(&sibling->execlists.tasklet);
-		}
 
 		spin_unlock(&sibling->active.lock);
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index dfbc214e14f5..91fd8e452d9b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -90,6 +90,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine);
 #define LRC_PPHWSP_SZ	(1)
 /* After the PPHWSP we have the logical state for the context */
 #define LRC_STATE_PN	(LRC_PPHWSP_PN + LRC_PPHWSP_SZ)
+#define LRC_STATE_OFFSET (LRC_STATE_PN * PAGE_SIZE)
 
 /* Space within PPHWSP reserved to be used as scratch */
 #define LRC_PPHWSP_SCRATCH		0x34
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index d39b72590e40..93cb6c460508 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -9,14 +9,13 @@
 
 #include <linux/types.h>
 
-/* GEN8 to GEN11 Reg State Context */
+/* GEN8 to GEN12 Reg State Context */
 #define CTX_CONTEXT_CONTROL		(0x02 + 1)
 #define CTX_RING_HEAD			(0x04 + 1)
 #define CTX_RING_TAIL			(0x06 + 1)
 #define CTX_RING_START			(0x08 + 1)
 #define CTX_RING_CTL			(0x0a + 1)
 #define CTX_BB_STATE			(0x10 + 1)
-#define CTX_BB_PER_CTX_PTR		(0x18 + 1)
 #define CTX_TIMESTAMP			(0x22 + 1)
 #define CTX_PDP3_UDW			(0x24 + 1)
 #define CTX_PDP3_LDW			(0x26 + 1)
@@ -30,9 +29,6 @@
 
 #define GEN9_CTX_RING_MI_MODE		0x54
 
-/* GEN12+ Reg State Context */
-#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)); \
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 3847ee44b181..ab675d35030d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -113,7 +113,6 @@ 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) {
@@ -165,16 +164,11 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	/* 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);
 
 	rc6->ctl_enable =
 		GEN6_RC_CTL_HW_ENABLE |
 		GEN6_RC_CTL_RC6_ENABLE |
-		rc6_mode;
+		GEN6_RC_CTL_EI_MODE(1);
 
 	/*
 	 * WaRsDisableCoarsePowerGating:skl,cnl
@@ -246,16 +240,18 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 	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");
+		drm_dbg(&i915->drm, "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);
+		drm_dbg(&i915->drm,
+			"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");
+			drm_err(&i915->drm,
+				"Couldn't fix incorrect rc6 voltage\n");
 	}
 }
 
@@ -263,14 +259,15 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 static int chv_rc6_init(struct intel_rc6 *rc6)
 {
 	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct drm_i915_private *i915 = rc6_to_i915(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;
+		drm_dbg(&i915->drm, "BIOS didn't set up PCBR, fixing up\n");
+		paddr = i915->dsm.end + 1 - pctx_size;
 		GEM_BUG_ON(paddr > U32_MAX);
 
 		pctx_paddr = (paddr & ~4095);
@@ -304,7 +301,7 @@ static int vlv_rc6_init(struct intel_rc6 *rc6)
 		goto out;
 	}
 
-	DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
+	drm_dbg(&i915->drm, "BIOS didn't set up PCBR, fixing up\n");
 
 	/*
 	 * From the Gunit register HAS:
@@ -316,7 +313,8 @@ static int vlv_rc6_init(struct intel_rc6 *rc6)
 	 */
 	pctx = i915_gem_object_create_stolen(i915, pctx_size);
 	if (IS_ERR(pctx)) {
-		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
+		drm_dbg(&i915->drm,
+			"not enough stolen space for PCTX, disabling\n");
 		return PTR_ERR(pctx);
 	}
 
@@ -398,14 +396,14 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
 	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: "
+	drm_dbg(&i915->drm, "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");
+		drm_dbg(&i915->drm, "RC6 Base location not set properly.\n");
 		enable_rc6 = false;
 	}
 
@@ -417,7 +415,7 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
 		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");
+		drm_dbg(&i915->drm, "RC6 Base address not as expected.\n");
 		enable_rc6 = false;
 	}
 
@@ -425,24 +423,25 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
 	      (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");
+		drm_dbg(&i915->drm,
+			"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");
+		drm_dbg(&i915->drm, "Pushbus not setup properly.\n");
 		enable_rc6 = false;
 	}
 
 	if (!intel_uncore_read(uncore, GEN6_GFXPAUSE)) {
-		DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
+		drm_dbg(&i915->drm, "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");
+		drm_dbg(&i915->drm, "GPM control not setup properly.\n");
 		enable_rc6 = false;
 	}
 
@@ -463,7 +462,7 @@ static bool rc6_supported(struct intel_rc6 *rc6)
 		return false;
 
 	if (IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(rc6)) {
-		dev_notice(i915->drm.dev,
+		drm_notice(&i915->drm,
 			   "RC6 and powersaving disabled by BIOS\n");
 		return false;
 	}
@@ -495,7 +494,7 @@ static bool pctx_corrupted(struct intel_rc6 *rc6)
 	if (intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO))
 		return false;
 
-	dev_notice(i915->drm.dev,
+	drm_notice(&i915->drm,
 		   "RC6 context corruption, disabling runtime power management\n");
 	return true;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index 5954ecc3207f..f59e7875cc5e 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -102,7 +102,7 @@ static int render_state_setup(struct intel_renderstate *so,
 	}
 
 	if (rodata->reloc[reloc_index] != -1) {
-		DRM_ERROR("only %d relocs resolved\n", reloc_index);
+		drm_err(&i915->drm, "only %d relocs resolved\n", reloc_index);
 		goto err;
 	}
 
@@ -194,7 +194,7 @@ int intel_renderstate_init(struct intel_renderstate *so,
 
 	err = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
-		goto err_vma;
+		goto err_obj;
 
 	err = render_state_setup(so, engine->i915);
 	if (err)
@@ -204,8 +204,6 @@ int intel_renderstate_init(struct intel_renderstate *so,
 
 err_unpin:
 	i915_vma_unpin(so->vma);
-err_vma:
-	i915_vma_close(so->vma);
 err_obj:
 	i915_gem_object_put(obj);
 	so->vma = NULL;
@@ -221,6 +219,14 @@ int intel_renderstate_emit(struct intel_renderstate *so,
 	if (!so->vma)
 		return 0;
 
+	i915_vma_lock(so->vma);
+	err = i915_request_await_object(rq, so->vma->obj, false);
+	if (err == 0)
+		err = i915_vma_move_to_active(so->vma, rq, 0);
+	i915_vma_unlock(so->vma);
+	if (err)
+		return err;
+
 	err = engine->emit_bb_start(rq,
 				    so->batch_offset, so->batch_size,
 				    I915_DISPATCH_SECURE);
@@ -235,13 +241,7 @@ int intel_renderstate_emit(struct intel_renderstate *so,
 			return err;
 	}
 
-	i915_vma_lock(so->vma);
-	err = i915_request_await_object(rq, so->vma->obj, false);
-	if (err == 0)
-		err = i915_vma_move_to_active(so->vma, rq, 0);
-	i915_vma_unlock(so->vma);
-
-	return err;
+	return 0;
 }
 
 void intel_renderstate_fini(struct intel_renderstate *so)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 80db3c9d785e..39070b514e65 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -109,7 +109,7 @@ static bool mark_guilty(struct i915_request *rq)
 		goto out;
 	}
 
-	dev_notice(ctx->i915->drm.dev,
+	drm_notice(&ctx->i915->drm,
 		   "%s context reset due to GPU hang\n",
 		   ctx->name);
 
@@ -755,7 +755,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 	for_each_engine(engine, gt, id)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
 
-	i915_gem_restore_fences(gt->ggtt);
+	intel_ggtt_restore_fences(gt->ggtt);
 
 	return err;
 }
@@ -1031,7 +1031,7 @@ void intel_gt_reset(struct intel_gt *gt,
 		goto unlock;
 
 	if (reason)
-		dev_notice(gt->i915->drm.dev,
+		drm_notice(&gt->i915->drm,
 			   "Resetting chip for %s\n", reason);
 	atomic_inc(&gt->i915->gpu_error.reset_count);
 
@@ -1039,7 +1039,7 @@ void intel_gt_reset(struct intel_gt *gt,
 
 	if (!intel_has_gpu_reset(gt)) {
 		if (i915_modparams.reset)
-			dev_err(gt->i915->drm.dev, "GPU reset not supported\n");
+			drm_err(&gt->i915->drm, "GPU reset not supported\n");
 		else
 			drm_dbg(&gt->i915->drm, "GPU reset disabled\n");
 		goto error;
@@ -1049,7 +1049,7 @@ void intel_gt_reset(struct intel_gt *gt,
 		intel_runtime_pm_disable_interrupts(gt->i915);
 
 	if (do_reset(gt, stalled_mask)) {
-		dev_err(gt->i915->drm.dev, "Failed to reset chip\n");
+		drm_err(&gt->i915->drm, "Failed to reset chip\n");
 		goto taint;
 	}
 
@@ -1111,7 +1111,7 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 /**
  * intel_engine_reset - reset GPU engine to recover from a hang
  * @engine: engine to reset
- * @msg: reason for GPU reset; or NULL for no dev_notice()
+ * @msg: reason for GPU reset; or NULL for no drm_notice()
  *
  * Reset a specific GPU engine. Useful if a hang is detected.
  * Returns zero on successful reset or otherwise an error code.
@@ -1136,7 +1136,7 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 	reset_prepare_engine(engine);
 
 	if (msg)
-		dev_notice(engine->i915->drm.dev,
+		drm_notice(&engine->i915->drm,
 			   "Resetting %s for %s\n", engine->name, msg);
 	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
@@ -1381,7 +1381,7 @@ static void intel_wedge_me(struct work_struct *work)
 {
 	struct intel_wedge_me *w = container_of(work, typeof(*w), work.work);
 
-	dev_err(w->gt->i915->drm.dev,
+	drm_err(&w->gt->i915->drm,
 		"%s timed out, cancelling all in-flight rendering.\n",
 		w->name);
 	intel_gt_set_wedged(w->gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index 5bdce24994aa..cc0ebca65167 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -88,6 +88,8 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 static inline void
 assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
 {
+	unsigned int head = READ_ONCE(ring->head);
+
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
 
 	/*
@@ -105,8 +107,7 @@ assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
 	 * into the same cacheline as ring->head.
 	 */
 #define cacheline(a) round_down(a, CACHELINE_BYTES)
-	GEM_BUG_ON(cacheline(tail) == cacheline(ring->head) &&
-		   tail < ring->head);
+	GEM_BUG_ON(cacheline(tail) == cacheline(head) && tail < head);
 #undef cacheline
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index fdc3f10e12aa..ca7286e58409 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -42,6 +42,7 @@
 #include "intel_reset.h"
 #include "intel_ring.h"
 #include "intel_workarounds.h"
+#include "shmem_utils.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -577,8 +578,9 @@ static void flush_cs_tlb(struct intel_engine_cs *engine)
 				    RING_INSTPM(engine->mmio_base),
 				    INSTPM_SYNC_FLUSH, 0,
 				    1000))
-		DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
-			  engine->name);
+		drm_err(&dev_priv->drm,
+			"%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
+			engine->name);
 }
 
 static void ring_setup_status_page(struct intel_engine_cs *engine)
@@ -601,8 +603,9 @@ static bool stop_ring(struct intel_engine_cs *engine)
 					    MODE_IDLE,
 					    MODE_IDLE,
 					    1000)) {
-			DRM_ERROR("%s : timed out trying to stop ring\n",
-				  engine->name);
+			drm_err(&dev_priv->drm,
+				"%s : timed out trying to stop ring\n",
+				engine->name);
 
 			/*
 			 * Sometimes we observe that the idle flag is not
@@ -661,22 +664,23 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	/* WaClearRingBufHeadRegAtInit:ctg,elk */
 	if (!stop_ring(engine)) {
 		/* G45 ring initialization often fails to reset head to zero */
-		DRM_DEBUG_DRIVER("%s head not reset to zero "
+		drm_dbg(&dev_priv->drm, "%s head not reset to zero "
+			"ctl %08x head %08x tail %08x start %08x\n",
+			engine->name,
+			ENGINE_READ(engine, RING_CTL),
+			ENGINE_READ(engine, RING_HEAD),
+			ENGINE_READ(engine, RING_TAIL),
+			ENGINE_READ(engine, RING_START));
+
+		if (!stop_ring(engine)) {
+			drm_err(&dev_priv->drm,
+				"failed to set %s head to zero "
 				"ctl %08x head %08x tail %08x start %08x\n",
 				engine->name,
 				ENGINE_READ(engine, RING_CTL),
 				ENGINE_READ(engine, RING_HEAD),
 				ENGINE_READ(engine, RING_TAIL),
 				ENGINE_READ(engine, RING_START));
-
-		if (!stop_ring(engine)) {
-			DRM_ERROR("failed to set %s head to zero "
-				  "ctl %08x head %08x tail %08x start %08x\n",
-				  engine->name,
-				  ENGINE_READ(engine, RING_CTL),
-				  ENGINE_READ(engine, RING_HEAD),
-				  ENGINE_READ(engine, RING_TAIL),
-				  ENGINE_READ(engine, RING_START));
 			ret = -EIO;
 			goto out;
 		}
@@ -719,7 +723,7 @@ static int xcs_resume(struct intel_engine_cs *engine)
 				    RING_CTL(engine->mmio_base),
 				    RING_VALID, RING_VALID,
 				    50)) {
-		DRM_ERROR("%s initialization failed "
+		drm_err(&dev_priv->drm, "%s initialization failed "
 			  "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
 			  engine->name,
 			  ENGINE_READ(engine, RING_CTL),
@@ -1238,7 +1242,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
 		i915_gem_object_set_cache_coherency(obj, I915_CACHE_L3_LLC);
 
 	if (engine->default_state) {
-		void *defaults, *vaddr;
+		void *vaddr;
 
 		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
 		if (IS_ERR(vaddr)) {
@@ -1246,15 +1250,8 @@ alloc_context_vma(struct intel_engine_cs *engine)
 			goto err_obj;
 		}
 
-		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
-		if (IS_ERR(defaults)) {
-			err = PTR_ERR(defaults);
-			goto err_map;
-		}
-
-		memcpy(vaddr, defaults, engine->context_size);
-		i915_gem_object_unpin_map(engine->default_state);
+		shmem_read(engine->default_state, 0,
+			   vaddr, engine->context_size);
 
 		i915_gem_object_flush_map(obj);
 		i915_gem_object_unpin_map(obj);
@@ -1268,8 +1265,6 @@ alloc_context_vma(struct intel_engine_cs *engine)
 
 	return vma;
 
-err_map:
-	i915_gem_object_unpin_map(obj);
 err_obj:
 	i915_gem_object_put(obj);
 	return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 19542fd9e207..2f59fc6df3c2 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -8,12 +8,15 @@
 
 #include "i915_drv.h"
 #include "intel_gt.h"
+#include "intel_gt_clock_utils.h"
 #include "intel_gt_irq.h"
 #include "intel_gt_pm_irq.h"
 #include "intel_rps.h"
 #include "intel_sideband.h"
 #include "../../../platform/x86/intel_ips.h"
 
+#define BUSY_MAX_EI	20u /* ms */
+
 /*
  * Lock protecting IPS related data structures
  */
@@ -44,6 +47,100 @@ static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
 	intel_uncore_write_fw(uncore, reg, val);
 }
 
+static void rps_timer(struct timer_list *t)
+{
+	struct intel_rps *rps = from_timer(rps, t, timer);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	s64 max_busy[3] = {};
+	ktime_t dt, last;
+
+	for_each_engine(engine, rps_to_gt(rps), id) {
+		s64 busy;
+		int i;
+
+		dt = intel_engine_get_busy_time(engine);
+		last = engine->stats.rps;
+		engine->stats.rps = dt;
+
+		busy = ktime_to_ns(ktime_sub(dt, last));
+		for (i = 0; i < ARRAY_SIZE(max_busy); i++) {
+			if (busy > max_busy[i])
+				swap(busy, max_busy[i]);
+		}
+	}
+
+	dt = ktime_get();
+	last = rps->pm_timestamp;
+	rps->pm_timestamp = dt;
+
+	if (intel_rps_is_active(rps)) {
+		s64 busy;
+		int i;
+
+		dt = ktime_sub(dt, last);
+
+		/*
+		 * Our goal is to evaluate each engine independently, so we run
+		 * at the lowest clocks required to sustain the heaviest
+		 * workload. However, a task may be split into sequential
+		 * dependent operations across a set of engines, such that
+		 * the independent contributions do not account for high load,
+		 * but overall the task is GPU bound. For example, consider
+		 * video decode on vcs followed by colour post-processing
+		 * on vecs, followed by general post-processing on rcs.
+		 * Since multi-engines being active does imply a single
+		 * continuous workload across all engines, we hedge our
+		 * bets by only contributing a factor of the distributed
+		 * load into our busyness calculation.
+		 */
+		busy = max_busy[0];
+		for (i = 1; i < ARRAY_SIZE(max_busy); i++) {
+			if (!max_busy[i])
+				break;
+
+			busy += div_u64(max_busy[i], 1 << i);
+		}
+		GT_TRACE(rps_to_gt(rps),
+			 "busy:%lld [%d%%], max:[%lld, %lld, %lld], interval:%d\n",
+			 busy, (int)div64_u64(100 * busy, dt),
+			 max_busy[0], max_busy[1], max_busy[2],
+			 rps->pm_interval);
+
+		if (100 * busy > rps->power.up_threshold * dt &&
+		    rps->cur_freq < rps->max_freq_softlimit) {
+			rps->pm_iir |= GEN6_PM_RP_UP_THRESHOLD;
+			rps->pm_interval = 1;
+			schedule_work(&rps->work);
+		} else if (100 * busy < rps->power.down_threshold * dt &&
+			   rps->cur_freq > rps->min_freq_softlimit) {
+			rps->pm_iir |= GEN6_PM_RP_DOWN_THRESHOLD;
+			rps->pm_interval = 1;
+			schedule_work(&rps->work);
+		} else {
+			rps->last_adj = 0;
+		}
+
+		mod_timer(&rps->timer,
+			  jiffies + msecs_to_jiffies(rps->pm_interval));
+		rps->pm_interval = min(rps->pm_interval * 2, BUSY_MAX_EI);
+	}
+}
+
+static void rps_start_timer(struct intel_rps *rps)
+{
+	rps->pm_timestamp = ktime_sub(ktime_get(), rps->pm_timestamp);
+	rps->pm_interval = 1;
+	mod_timer(&rps->timer, jiffies + 1);
+}
+
+static void rps_stop_timer(struct intel_rps *rps)
+{
+	del_timer_sync(&rps->timer);
+	rps->pm_timestamp = ktime_sub(ktime_get(), rps->pm_timestamp);
+	cancel_work_sync(&rps->work);
+}
+
 static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
 {
 	u32 mask = 0;
@@ -57,7 +154,7 @@ static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
 	if (val < rps->max_freq_softlimit)
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
 
-	mask &= READ_ONCE(rps->pm_events);
+	mask &= rps->pm_events;
 
 	return rps_pm_sanitize_mask(rps, ~mask);
 }
@@ -70,18 +167,11 @@ static void rps_reset_ei(struct intel_rps *rps)
 static void rps_enable_interrupts(struct intel_rps *rps)
 {
 	struct intel_gt *gt = rps_to_gt(rps);
-	u32 events;
 
-	rps_reset_ei(rps);
+	GT_TRACE(gt, "interrupts:on rps->pm_events: %x, rps_pm_mask:%x\n",
+		 rps->pm_events, rps_pm_mask(rps, rps->last_freq));
 
-	if (IS_VALLEYVIEW(gt->i915))
-		/* WaGsvRC0ResidencyMethod:vlv */
-		events = GEN6_PM_RP_UP_EI_EXPIRED;
-	else
-		events = (GEN6_PM_RP_UP_THRESHOLD |
-			  GEN6_PM_RP_DOWN_THRESHOLD |
-			  GEN6_PM_RP_DOWN_TIMEOUT);
-	WRITE_ONCE(rps->pm_events, events);
+	rps_reset_ei(rps);
 
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_enable_irq(gt, rps->pm_events);
@@ -120,8 +210,6 @@ static void rps_disable_interrupts(struct intel_rps *rps)
 {
 	struct intel_gt *gt = rps_to_gt(rps);
 
-	WRITE_ONCE(rps->pm_events, 0);
-
 	intel_uncore_write(gt->uncore,
 			   GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
 
@@ -140,6 +228,7 @@ static void rps_disable_interrupts(struct intel_rps *rps)
 	cancel_work_sync(&rps->work);
 
 	rps_reset_interrupts(rps);
+	GT_TRACE(gt, "interrupts:off\n");
 }
 
 static const struct cparams {
@@ -186,14 +275,12 @@ static void gen5_rps_init(struct intel_rps *rps)
 	fmin = (rgvmodectl & MEMMODE_FMIN_MASK);
 	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
 		MEMMODE_FSTART_SHIFT;
-	DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n",
-			 fmax, fmin, fstart);
+	drm_dbg(&i915->drm, "fmax: %d, fmin: %d, fstart: %d\n",
+		fmax, fmin, fstart);
 
 	rps->min_freq = fmax;
+	rps->efficient_freq = fstart;
 	rps->max_freq = fmin;
-
-	rps->idle_freq = rps->min_freq;
-	rps->cur_freq = rps->idle_freq;
 }
 
 static unsigned long
@@ -456,7 +543,8 @@ static bool gen5_rps_enable(struct intel_rps *rps)
 
 	if (wait_for_atomic((intel_uncore_read(uncore, MEMSWCTL) &
 			     MEMCTL_CMD_STS) == 0, 10))
-		DRM_ERROR("stuck trying to change perf mode\n");
+		drm_err(&uncore->i915->drm,
+			"stuck trying to change perf mode\n");
 	mdelay(1);
 
 	gen5_rps_set(rps, rps->cur_freq);
@@ -533,8 +621,8 @@ static u32 rps_limits(struct intel_rps *rps, u8 val)
 
 static void rps_set_power(struct intel_rps *rps, int new_power)
 {
-	struct intel_uncore *uncore = rps_to_uncore(rps);
-	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_gt *gt = rps_to_gt(rps);
+	struct intel_uncore *uncore = gt->uncore;
 	u32 threshold_up = 0, threshold_down = 0; /* in % */
 	u32 ei_up = 0, ei_down = 0;
 
@@ -543,55 +631,49 @@ static void rps_set_power(struct intel_rps *rps, int new_power)
 	if (new_power == rps->power.mode)
 		return;
 
+	threshold_up = 95;
+	threshold_down = 85;
+
 	/* Note the units here are not exactly 1us, but 1280ns. */
 	switch (new_power) {
 	case LOW_POWER:
-		/* Upclock if more than 95% busy over 16ms */
 		ei_up = 16000;
-		threshold_up = 95;
-
-		/* Downclock if less than 85% busy over 32ms */
 		ei_down = 32000;
-		threshold_down = 85;
 		break;
 
 	case BETWEEN:
-		/* Upclock if more than 90% busy over 13ms */
 		ei_up = 13000;
-		threshold_up = 90;
-
-		/* Downclock if less than 75% busy over 32ms */
 		ei_down = 32000;
-		threshold_down = 75;
 		break;
 
 	case HIGH_POWER:
-		/* Upclock if more than 85% busy over 10ms */
 		ei_up = 10000;
-		threshold_up = 85;
-
-		/* Downclock if less than 60% busy over 32ms */
 		ei_down = 32000;
-		threshold_down = 60;
 		break;
 	}
 
 	/* When byt can survive without system hang with dynamic
 	 * sw freq adjustments, this restriction can be lifted.
 	 */
-	if (IS_VALLEYVIEW(i915))
+	if (IS_VALLEYVIEW(gt->i915))
 		goto skip_hw_write;
 
-	set(uncore, GEN6_RP_UP_EI, GT_INTERVAL_FROM_US(i915, ei_up));
+	GT_TRACE(gt,
+		 "changing power mode [%d], up %d%% @ %dus, down %d%% @ %dus\n",
+		 new_power, threshold_up, ei_up, threshold_down, ei_down);
+
+	set(uncore, GEN6_RP_UP_EI,
+	    intel_gt_ns_to_pm_interval(gt, ei_up * 1000));
 	set(uncore, GEN6_RP_UP_THRESHOLD,
-	    GT_INTERVAL_FROM_US(i915, ei_up * threshold_up / 100));
+	    intel_gt_ns_to_pm_interval(gt, ei_up * threshold_up * 10));
 
-	set(uncore, GEN6_RP_DOWN_EI, GT_INTERVAL_FROM_US(i915, ei_down));
+	set(uncore, GEN6_RP_DOWN_EI,
+	    intel_gt_ns_to_pm_interval(gt, ei_down * 1000));
 	set(uncore, GEN6_RP_DOWN_THRESHOLD,
-	    GT_INTERVAL_FROM_US(i915, ei_down * threshold_down / 100));
+	    intel_gt_ns_to_pm_interval(gt, ei_down * threshold_down * 10));
 
 	set(uncore, GEN6_RP_CONTROL,
-	    (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
+	    (INTEL_GEN(gt->i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
 	    GEN6_RP_MEDIA_HW_NORMAL_MODE |
 	    GEN6_RP_MEDIA_IS_GFX |
 	    GEN6_RP_ENABLE |
@@ -646,9 +728,11 @@ static void gen6_rps_set_thresholds(struct intel_rps *rps, u8 val)
 
 void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive)
 {
+	GT_TRACE(rps_to_gt(rps), "mark interactive: %s\n", yesno(interactive));
+
 	mutex_lock(&rps->power.mutex);
 	if (interactive) {
-		if (!rps->power.interactive++ && READ_ONCE(rps->active))
+		if (!rps->power.interactive++ && intel_rps_is_active(rps))
 			rps_set_power(rps, HIGH_POWER);
 	} else {
 		GEM_BUG_ON(!rps->power.interactive);
@@ -673,6 +757,9 @@ static int gen6_rps_set(struct intel_rps *rps, u8 val)
 			 GEN6_AGGRESSIVE_TURBO);
 	set(uncore, GEN6_RPNSWREQ, swreq);
 
+	GT_TRACE(rps_to_gt(rps), "set val:%x, freq:%d, swreq:%x\n",
+		 val, intel_gpu_freq(rps, val), swreq);
+
 	return 0;
 }
 
@@ -685,6 +772,9 @@ static int vlv_rps_set(struct intel_rps *rps, u8 val)
 	err = vlv_punit_write(i915, PUNIT_REG_GPU_FREQ_REQ, val);
 	vlv_punit_put(i915);
 
+	GT_TRACE(rps_to_gt(rps), "set val:%x, freq:%d\n",
+		 val, intel_gpu_freq(rps, val));
+
 	return err;
 }
 
@@ -715,29 +805,30 @@ static int rps_set(struct intel_rps *rps, u8 val, bool update)
 
 void intel_rps_unpark(struct intel_rps *rps)
 {
-	u8 freq;
-
-	if (!rps->enabled)
+	if (!intel_rps_is_enabled(rps))
 		return;
 
+	GT_TRACE(rps_to_gt(rps), "unpark:%x\n", rps->cur_freq);
+
 	/*
 	 * Use the user's desired frequency as a guide, but for better
 	 * performance, jump directly to RPe as our starting frequency.
 	 */
 	mutex_lock(&rps->lock);
 
-	WRITE_ONCE(rps->active, true);
-
-	freq = max(rps->cur_freq, rps->efficient_freq),
-	freq = clamp(freq, rps->min_freq_softlimit, rps->max_freq_softlimit);
-	intel_rps_set(rps, freq);
-
-	rps->last_adj = 0;
+	intel_rps_set_active(rps);
+	intel_rps_set(rps,
+		      clamp(rps->cur_freq,
+			    rps->min_freq_softlimit,
+			    rps->max_freq_softlimit));
 
 	mutex_unlock(&rps->lock);
 
-	if (INTEL_GEN(rps_to_i915(rps)) >= 6)
+	rps->pm_iir = 0;
+	if (intel_rps_has_interrupts(rps))
 		rps_enable_interrupts(rps);
+	if (intel_rps_uses_timer(rps))
+		rps_start_timer(rps);
 
 	if (IS_GEN(rps_to_i915(rps), 5))
 		gen5_rps_update(rps);
@@ -745,15 +836,16 @@ void intel_rps_unpark(struct intel_rps *rps)
 
 void intel_rps_park(struct intel_rps *rps)
 {
-	struct drm_i915_private *i915 = rps_to_i915(rps);
+	int adj;
 
-	if (!rps->enabled)
+	if (!intel_rps_clear_active(rps))
 		return;
 
-	if (INTEL_GEN(i915) >= 6)
+	if (intel_rps_uses_timer(rps))
+		rps_stop_timer(rps);
+	if (intel_rps_has_interrupts(rps))
 		rps_disable_interrupts(rps);
 
-	WRITE_ONCE(rps->active, false);
 	if (rps->last_freq <= rps->idle_freq)
 		return;
 
@@ -784,8 +876,15 @@ void intel_rps_park(struct intel_rps *rps)
 	 * (Note we accommodate Cherryview's limitation of only using an
 	 * even bin by applying it to all.)
 	 */
-	rps->cur_freq =
-		max_t(int, round_down(rps->cur_freq - 1, 2), rps->min_freq);
+	adj = rps->last_adj;
+	if (adj < 0)
+		adj *= 2;
+	else /* CHV needs even encode values */
+		adj = -2;
+	rps->last_adj = adj;
+	rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq);
+
+	GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq);
 }
 
 void intel_rps_boost(struct i915_request *rq)
@@ -793,7 +892,7 @@ void intel_rps_boost(struct i915_request *rq)
 	struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
 	unsigned long flags;
 
-	if (i915_request_signaled(rq) || !READ_ONCE(rps->active))
+	if (i915_request_signaled(rq) || !intel_rps_is_active(rps))
 		return;
 
 	/* Serializes with i915_request_retire() */
@@ -802,6 +901,9 @@ void intel_rps_boost(struct i915_request *rq)
 	    !dma_fence_is_signaled_locked(&rq->fence)) {
 		set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
 
+		GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
+			 rq->fence.context, rq->fence.seqno);
+
 		if (!atomic_fetch_inc(&rps->num_waiters) &&
 		    READ_ONCE(rps->cur_freq) < rps->boost_freq)
 			schedule_work(&rps->work);
@@ -819,7 +921,7 @@ int intel_rps_set(struct intel_rps *rps, u8 val)
 	GEM_BUG_ON(val > rps->max_freq);
 	GEM_BUG_ON(val < rps->min_freq);
 
-	if (rps->active) {
+	if (intel_rps_is_active(rps)) {
 		err = rps_set(rps, val, true);
 		if (err)
 			return err;
@@ -828,7 +930,7 @@ int intel_rps_set(struct intel_rps *rps, u8 val)
 		 * Make sure we continue to get interrupts
 		 * until we hit the minimum or maximum frequencies.
 		 */
-		if (INTEL_GEN(rps_to_i915(rps)) >= 6) {
+		if (intel_rps_has_interrupts(rps)) {
 			struct intel_uncore *uncore = rps_to_uncore(rps);
 
 			set(uncore,
@@ -896,12 +998,14 @@ static void gen6_rps_init(struct intel_rps *rps)
 
 static bool rps_reset(struct intel_rps *rps)
 {
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
 	/* force a reset */
 	rps->power.mode = -1;
 	rps->last_freq = -1;
 
 	if (rps_set(rps, rps->min_freq, true)) {
-		DRM_ERROR("Failed to reset RPS to initial values\n");
+		drm_err(&i915->drm, "Failed to reset RPS to initial values\n");
 		return false;
 	}
 
@@ -912,20 +1016,18 @@ static bool rps_reset(struct intel_rps *rps)
 /* See the Gen9_GT_PM_Programming_Guide doc for the below */
 static bool gen9_rps_enable(struct intel_rps *rps)
 {
-	struct drm_i915_private *i915 = rps_to_i915(rps);
-	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct intel_gt *gt = rps_to_gt(rps);
+	struct intel_uncore *uncore = gt->uncore;
 
 	/* Program defaults and thresholds for RPS */
-	if (IS_GEN(i915, 9))
+	if (IS_GEN(gt->i915, 9))
 		intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
 				      GEN9_FREQUENCY(rps->rp1_freq));
 
-	/* 1 second timeout */
-	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT,
-			      GT_INTERVAL_FROM_US(i915, 1000000));
-
 	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 0xa);
 
+	rps->pm_events = GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD;
+
 	return rps_reset(rps);
 }
 
@@ -936,12 +1038,10 @@ static bool gen8_rps_enable(struct intel_rps *rps)
 	intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
 			      HSW_FREQUENCY(rps->rp1_freq));
 
-	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
-	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT,
-			      100000000 / 128); /* 1 second timeout */
-
 	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
 
+	rps->pm_events = GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD;
+
 	return rps_reset(rps);
 }
 
@@ -953,6 +1053,10 @@ static bool gen6_rps_enable(struct intel_rps *rps)
 	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 50000);
 	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
 
+	rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
+			  GEN6_PM_RP_DOWN_THRESHOLD |
+			  GEN6_PM_RP_DOWN_TIMEOUT);
+
 	return rps_reset(rps);
 }
 
@@ -1038,6 +1142,10 @@ static bool chv_rps_enable(struct intel_rps *rps)
 			      GEN6_RP_UP_BUSY_AVG |
 			      GEN6_RP_DOWN_IDLE_AVG);
 
+	rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
+			  GEN6_PM_RP_DOWN_THRESHOLD |
+			  GEN6_PM_RP_DOWN_TIMEOUT);
+
 	/* Setting Fixed Bias */
 	vlv_punit_get(i915);
 
@@ -1052,8 +1160,8 @@ static bool chv_rps_enable(struct intel_rps *rps)
 	drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0,
 		      "GPLL not enabled\n");
 
-	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
-	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+	drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE));
+	drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val);
 
 	return rps_reset(rps);
 }
@@ -1136,6 +1244,9 @@ static bool vlv_rps_enable(struct intel_rps *rps)
 			      GEN6_RP_UP_BUSY_AVG |
 			      GEN6_RP_DOWN_IDLE_CONT);
 
+	/* WaGsvRC0ResidencyMethod:vlv */
+	rps->pm_events = GEN6_PM_RP_UP_EI_EXPIRED;
+
 	vlv_punit_get(i915);
 
 	/* Setting Fixed Bias */
@@ -1150,8 +1261,8 @@ static bool vlv_rps_enable(struct intel_rps *rps)
 	drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0,
 		      "GPLL not enabled\n");
 
-	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
-	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+	drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE));
+	drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val);
 
 	return rps_reset(rps);
 }
@@ -1194,33 +1305,71 @@ static unsigned long __ips_gfx_val(struct intel_ips *ips)
 	return ips->gfx_power + state2;
 }
 
+static bool has_busy_stats(struct intel_rps *rps)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, rps_to_gt(rps), id) {
+		if (!intel_engine_supports_stats(engine))
+			return false;
+	}
+
+	return true;
+}
+
 void intel_rps_enable(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	struct intel_uncore *uncore = rps_to_uncore(rps);
+	bool enabled = false;
+
+	if (!HAS_RPS(i915))
+		return;
+
+	intel_gt_check_clock_frequency(rps_to_gt(rps));
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
-	if (IS_CHERRYVIEW(i915))
-		rps->enabled = chv_rps_enable(rps);
+	if (rps->max_freq <= rps->min_freq)
+		/* leave disabled, no room for dynamic reclocking */;
+	else if (IS_CHERRYVIEW(i915))
+		enabled = chv_rps_enable(rps);
 	else if (IS_VALLEYVIEW(i915))
-		rps->enabled = vlv_rps_enable(rps);
+		enabled = vlv_rps_enable(rps);
 	else if (INTEL_GEN(i915) >= 9)
-		rps->enabled = gen9_rps_enable(rps);
+		enabled = gen9_rps_enable(rps);
 	else if (INTEL_GEN(i915) >= 8)
-		rps->enabled = gen8_rps_enable(rps);
+		enabled = gen8_rps_enable(rps);
 	else if (INTEL_GEN(i915) >= 6)
-		rps->enabled = gen6_rps_enable(rps);
+		enabled = gen6_rps_enable(rps);
 	else if (IS_IRONLAKE_M(i915))
-		rps->enabled = gen5_rps_enable(rps);
+		enabled = gen5_rps_enable(rps);
+	else
+		MISSING_CASE(INTEL_GEN(i915));
 	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
-	if (!rps->enabled)
+	if (!enabled)
 		return;
 
-	drm_WARN_ON(&i915->drm, rps->max_freq < rps->min_freq);
-	drm_WARN_ON(&i915->drm, rps->idle_freq > rps->max_freq);
+	GT_TRACE(rps_to_gt(rps),
+		 "min:%x, max:%x, freq:[%d, %d]\n",
+		 rps->min_freq, rps->max_freq,
+		 intel_gpu_freq(rps, rps->min_freq),
+		 intel_gpu_freq(rps, rps->max_freq));
 
-	drm_WARN_ON(&i915->drm, rps->efficient_freq < rps->min_freq);
-	drm_WARN_ON(&i915->drm, rps->efficient_freq > rps->max_freq);
+	GEM_BUG_ON(rps->max_freq < rps->min_freq);
+	GEM_BUG_ON(rps->idle_freq > rps->max_freq);
+
+	GEM_BUG_ON(rps->efficient_freq < rps->min_freq);
+	GEM_BUG_ON(rps->efficient_freq > rps->max_freq);
+
+	if (has_busy_stats(rps))
+		intel_rps_set_timer(rps);
+	else if (INTEL_GEN(i915) >= 6)
+		intel_rps_set_interrupts(rps);
+	else
+		/* Ironlake currently uses intel_ips.ko */ {}
+
+	intel_rps_set_enabled(rps);
 }
 
 static void gen6_rps_disable(struct intel_rps *rps)
@@ -1232,7 +1381,9 @@ void intel_rps_disable(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 
-	rps->enabled = false;
+	intel_rps_clear_enabled(rps);
+	intel_rps_clear_interrupts(rps);
+	intel_rps_clear_timer(rps);
 
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_disable(rps);
@@ -1308,7 +1459,8 @@ static void vlv_init_gpll_ref_freq(struct intel_rps *rps)
 				  CCK_GPLL_CLOCK_CONTROL,
 				  i915->czclk_freq);
 
-	DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n", rps->gpll_ref_freq);
+	drm_dbg(&i915->drm, "GPLL reference freq: %d kHz\n",
+		rps->gpll_ref_freq);
 }
 
 static void vlv_rps_init(struct intel_rps *rps)
@@ -1336,28 +1488,24 @@ static void vlv_rps_init(struct intel_rps *rps)
 		i915->mem_freq = 1333;
 		break;
 	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq);
+	drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq);
 
 	rps->max_freq = vlv_rps_max_freq(rps);
 	rps->rp0_freq = rps->max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->max_freq),
-			 rps->max_freq);
+	drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->max_freq), rps->max_freq);
 
 	rps->efficient_freq = vlv_rps_rpe_freq(rps);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->efficient_freq),
-			 rps->efficient_freq);
+	drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq);
 
 	rps->rp1_freq = vlv_rps_guar_freq(rps);
-	DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->rp1_freq),
-			 rps->rp1_freq);
+	drm_dbg(&i915->drm, "RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq);
 
 	rps->min_freq = vlv_rps_min_freq(rps);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->min_freq),
-			 rps->min_freq);
+	drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->min_freq), rps->min_freq);
 
 	vlv_iosf_sb_put(i915,
 			BIT(VLV_IOSF_SB_PUNIT) |
@@ -1387,28 +1535,24 @@ static void chv_rps_init(struct intel_rps *rps)
 		i915->mem_freq = 1600;
 		break;
 	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq);
+	drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq);
 
 	rps->max_freq = chv_rps_max_freq(rps);
 	rps->rp0_freq = rps->max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->max_freq),
-			 rps->max_freq);
+	drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->max_freq), rps->max_freq);
 
 	rps->efficient_freq = chv_rps_rpe_freq(rps);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->efficient_freq),
-			 rps->efficient_freq);
+	drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq);
 
 	rps->rp1_freq = chv_rps_guar_freq(rps);
-	DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->rp1_freq),
-			 rps->rp1_freq);
+	drm_dbg(&i915->drm, "RP1(Guar) GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq);
 
 	rps->min_freq = chv_rps_min_freq(rps);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(rps, rps->min_freq),
-			 rps->min_freq);
+	drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n",
+		intel_gpu_freq(rps, rps->min_freq), rps->min_freq);
 
 	vlv_iosf_sb_put(i915,
 			BIT(VLV_IOSF_SB_PUNIT) |
@@ -1471,12 +1615,13 @@ static void rps_work(struct work_struct *work)
 {
 	struct intel_rps *rps = container_of(work, typeof(*rps), work);
 	struct intel_gt *gt = rps_to_gt(rps);
+	struct drm_i915_private *i915 = rps_to_i915(rps);
 	bool client_boost = false;
 	int new_freq, adj, min, max;
 	u32 pm_iir = 0;
 
 	spin_lock_irq(&gt->irq_lock);
-	pm_iir = fetch_and_zero(&rps->pm_iir) & READ_ONCE(rps->pm_events);
+	pm_iir = fetch_and_zero(&rps->pm_iir) & rps->pm_events;
 	client_boost = atomic_read(&rps->num_waiters);
 	spin_unlock_irq(&gt->irq_lock);
 
@@ -1485,6 +1630,10 @@ static void rps_work(struct work_struct *work)
 		goto out;
 
 	mutex_lock(&rps->lock);
+	if (!intel_rps_is_active(rps)) {
+		mutex_unlock(&rps->lock);
+		return;
+	}
 
 	pm_iir |= vlv_wa_c0_ei(rps, pm_iir);
 
@@ -1494,6 +1643,12 @@ static void rps_work(struct work_struct *work)
 	max = rps->max_freq_softlimit;
 	if (client_boost)
 		max = rps->max_freq;
+
+	GT_TRACE(gt,
+		 "pm_iir:%x, client_boost:%s, last:%d, cur:%x, min:%x, max:%x\n",
+		 pm_iir, yesno(client_boost),
+		 adj, new_freq, min, max);
+
 	if (client_boost && new_freq < rps->boost_freq) {
 		new_freq = rps->boost_freq;
 		adj = 0;
@@ -1525,30 +1680,18 @@ static void rps_work(struct work_struct *work)
 		adj = 0;
 	}
 
-	rps->last_adj = adj;
-
 	/*
-	 * Limit deboosting and boosting to keep ourselves at the extremes
-	 * when in the respective power modes (i.e. slowly decrease frequencies
-	 * while in the HIGH_POWER zone and slowly increase frequencies while
-	 * in the LOW_POWER zone). On idle, we will hit the timeout and drop
-	 * to the next level quickly, and conversely if busy we expect to
-	 * hit a waitboost and rapidly switch into max power.
-	 */
-	if ((adj < 0 && rps->power.mode == HIGH_POWER) ||
-	    (adj > 0 && rps->power.mode == LOW_POWER))
-		rps->last_adj = 0;
-
-	/* sysfs frequency interfaces may have snuck in while servicing the
-	 * interrupt
+	 * sysfs frequency limits may have snuck in while
+	 * servicing the interrupt
 	 */
 	new_freq += adj;
 	new_freq = clamp_t(int, new_freq, min, max);
 
 	if (intel_rps_set(rps, new_freq)) {
-		DRM_DEBUG_DRIVER("Failed to set new GPU frequency\n");
-		rps->last_adj = 0;
+		drm_dbg(&i915->drm, "Failed to set new GPU frequency\n");
+		adj = 0;
 	}
+	rps->last_adj = adj;
 
 	mutex_unlock(&rps->lock);
 
@@ -1568,6 +1711,8 @@ void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 	if (unlikely(!events))
 		return;
 
+	GT_TRACE(gt, "irq events:%x\n", events);
+
 	gen6_gt_pm_mask_irq(gt, events);
 
 	rps->pm_iir |= events;
@@ -1579,10 +1724,12 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 	struct intel_gt *gt = rps_to_gt(rps);
 	u32 events;
 
-	events = pm_iir & READ_ONCE(rps->pm_events);
+	events = pm_iir & rps->pm_events;
 	if (events) {
 		spin_lock(&gt->irq_lock);
 
+		GT_TRACE(gt, "irq events:%x\n", events);
+
 		gen6_gt_pm_mask_irq(gt, events);
 		rps->pm_iir |= events;
 
@@ -1640,6 +1787,7 @@ void intel_rps_init_early(struct intel_rps *rps)
 	mutex_init(&rps->power.mutex);
 
 	INIT_WORK(&rps->work, rps_work);
+	timer_setup(&rps->timer, rps_timer, 0);
 
 	atomic_set(&rps->num_waiters, 0);
 }
@@ -1668,9 +1816,10 @@ void intel_rps_init(struct intel_rps *rps)
 		sandybridge_pcode_read(i915, GEN6_READ_OC_PARAMS,
 				       &params, NULL);
 		if (params & BIT(31)) { /* OC supported */
-			DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n",
-					 (rps->max_freq & 0xff) * 50,
-					 (params & 0xff) * 50);
+			drm_dbg(&i915->drm,
+				"Overclocking supported, max: %dMHz, overclock: %dMHz\n",
+				(rps->max_freq & 0xff) * 50,
+				(params & 0xff) * 50);
 			rps->max_freq = params & 0xff;
 		}
 	}
@@ -1678,7 +1827,9 @@ void intel_rps_init(struct intel_rps *rps)
 	/* Finally allow us to boost to max by default */
 	rps->boost_freq = rps->max_freq;
 	rps->idle_freq = rps->min_freq;
-	rps->cur_freq = rps->idle_freq;
+
+	/* Start in the middle, from here we will autotune based on workload */
+	rps->cur_freq = rps->efficient_freq;
 
 	rps->pm_intrmsk_mbz = 0;
 
@@ -1695,6 +1846,12 @@ void intel_rps_init(struct intel_rps *rps)
 		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
 }
 
+void intel_rps_sanitize(struct intel_rps *rps)
+{
+	if (INTEL_GEN(rps_to_i915(rps)) >= 6)
+		rps_disable_interrupts(rps);
+}
+
 u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
@@ -1722,7 +1879,7 @@ static u32 read_cagf(struct intel_rps *rps)
 		freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
 		vlv_punit_put(i915);
 	} else {
-		freq = intel_uncore_read(rps_to_gt(rps)->uncore, GEN6_RPSTAT1);
+		freq = intel_uncore_read(rps_to_uncore(rps), GEN6_RPSTAT1);
 	}
 
 	return intel_rps_get_cagf(rps, freq);
@@ -1730,7 +1887,7 @@ static u32 read_cagf(struct intel_rps *rps)
 
 u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 {
-	struct intel_runtime_pm *rpm = rps_to_gt(rps)->uncore->rpm;
+	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
 	intel_wakeref_t wakeref;
 	u32 freq = 0;
 
@@ -1930,3 +2087,7 @@ bool i915_gpu_turbo_disable(void)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_rps.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index dfa98194f3b2..8d3c9d663662 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -13,6 +13,7 @@ struct i915_request;
 
 void intel_rps_init_early(struct intel_rps *rps);
 void intel_rps_init(struct intel_rps *rps);
+void intel_rps_sanitize(struct intel_rps *rps);
 
 void intel_rps_driver_register(struct intel_rps *rps);
 void intel_rps_driver_unregister(struct intel_rps *rps);
@@ -36,4 +37,64 @@ void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
 void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
 
+static inline bool intel_rps_is_enabled(const struct intel_rps *rps)
+{
+	return test_bit(INTEL_RPS_ENABLED, &rps->flags);
+}
+
+static inline void intel_rps_set_enabled(struct intel_rps *rps)
+{
+	set_bit(INTEL_RPS_ENABLED, &rps->flags);
+}
+
+static inline void intel_rps_clear_enabled(struct intel_rps *rps)
+{
+	clear_bit(INTEL_RPS_ENABLED, &rps->flags);
+}
+
+static inline bool intel_rps_is_active(const struct intel_rps *rps)
+{
+	return test_bit(INTEL_RPS_ACTIVE, &rps->flags);
+}
+
+static inline void intel_rps_set_active(struct intel_rps *rps)
+{
+	set_bit(INTEL_RPS_ACTIVE, &rps->flags);
+}
+
+static inline bool intel_rps_clear_active(struct intel_rps *rps)
+{
+	return test_and_clear_bit(INTEL_RPS_ACTIVE, &rps->flags);
+}
+
+static inline bool intel_rps_has_interrupts(const struct intel_rps *rps)
+{
+	return test_bit(INTEL_RPS_INTERRUPTS, &rps->flags);
+}
+
+static inline void intel_rps_set_interrupts(struct intel_rps *rps)
+{
+	set_bit(INTEL_RPS_INTERRUPTS, &rps->flags);
+}
+
+static inline void intel_rps_clear_interrupts(struct intel_rps *rps)
+{
+	clear_bit(INTEL_RPS_INTERRUPTS, &rps->flags);
+}
+
+static inline bool intel_rps_uses_timer(const struct intel_rps *rps)
+{
+	return test_bit(INTEL_RPS_TIMER, &rps->flags);
+}
+
+static inline void intel_rps_set_timer(struct intel_rps *rps)
+{
+	set_bit(INTEL_RPS_TIMER, &rps->flags);
+}
+
+static inline void intel_rps_clear_timer(struct intel_rps *rps)
+{
+	clear_bit(INTEL_RPS_TIMER, &rps->flags);
+}
+
 #endif /* INTEL_RPS_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rps_types.h b/drivers/gpu/drm/i915/gt/intel_rps_types.h
index c2e279154bd5..38083f0402d9 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps_types.h
@@ -31,6 +31,13 @@ struct intel_rps_ei {
 	u32 media_c0;
 };
 
+enum {
+	INTEL_RPS_ENABLED = 0,
+	INTEL_RPS_ACTIVE,
+	INTEL_RPS_INTERRUPTS,
+	INTEL_RPS_TIMER,
+};
+
 struct intel_rps {
 	struct mutex lock; /* protects enabling and the worker */
 
@@ -38,9 +45,12 @@ struct intel_rps {
 	 * work, interrupts_enabled and pm_iir are protected by
 	 * dev_priv->irq_lock
 	 */
+	struct timer_list timer;
 	struct work_struct work;
-	bool enabled;
-	bool active;
+	unsigned long flags;
+
+	ktime_t pm_timestamp;
+	u32 pm_interval;
 	u32 pm_iir;
 
 	/* PM interrupt bits that should never be masked */
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 74f793423231..d173271c7397 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -65,7 +65,6 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 {
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
 	bool subslice_pg = sseu->has_subslice_pg;
-	struct intel_sseu ctx_sseu;
 	u8 slices, subslices;
 	u32 rpcs = 0;
 
@@ -78,31 +77,13 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 
 	/*
 	 * If i915/perf is active, we want a stable powergating configuration
-	 * on the system.
-	 *
-	 * We could choose full enablement, but on ICL we know there are use
-	 * cases which disable slices for functional, apart for performance
-	 * reasons. So in this case we select a known stable subset.
+	 * on the system. Use the configuration pinned by i915/perf.
 	 */
-	if (!i915->perf.exclusive_stream) {
-		ctx_sseu = *req_sseu;
-	} else {
-		ctx_sseu = intel_sseu_from_device_info(sseu);
-
-		if (IS_GEN(i915, 11)) {
-			/*
-			 * We only need subslice count so it doesn't matter
-			 * which ones we select - just turn off low bits in the
-			 * amount of half of all available subslices per slice.
-			 */
-			ctx_sseu.subslice_mask =
-				~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2));
-			ctx_sseu.slice_mask = 0x1;
-		}
-	}
+	if (i915->perf.exclusive_stream)
+		req_sseu = &i915->perf.sseu;
 
-	slices = hweight8(ctx_sseu.slice_mask);
-	subslices = hweight8(ctx_sseu.subslice_mask);
+	slices = hweight8(req_sseu->slice_mask);
+	subslices = hweight8(req_sseu->subslice_mask);
 
 	/*
 	 * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
@@ -175,13 +156,13 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 	if (sseu->has_eu_pg) {
 		u32 val;
 
-		val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
+		val = req_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
 		val &= GEN8_RPCS_EU_MIN_MASK;
 
 		rpcs |= val;
 
-		val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
+		val = req_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
 		val &= GEN8_RPCS_EU_MAX_MASK;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 08b56d7ab4f4..4546284fede1 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -119,6 +119,15 @@ static void __idle_hwsp_free(struct intel_timeline_hwsp *hwsp, int cacheline)
 	spin_unlock_irqrestore(&gt->hwsp_lock, flags);
 }
 
+static void __rcu_cacheline_free(struct rcu_head *rcu)
+{
+	struct intel_timeline_cacheline *cl =
+		container_of(rcu, typeof(*cl), rcu);
+
+	i915_active_fini(&cl->active);
+	kfree(cl);
+}
+
 static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 {
 	GEM_BUG_ON(!i915_active_is_idle(&cl->active));
@@ -127,8 +136,7 @@ static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 	i915_vma_put(cl->hwsp->vma);
 	__idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS));
 
-	i915_active_fini(&cl->active);
-	kfree_rcu(cl, rcu);
+	call_rcu(&cl->rcu, __rcu_cacheline_free);
 }
 
 __i915_active_call
@@ -203,9 +211,9 @@ static void cacheline_free(struct intel_timeline_cacheline *cl)
 	i915_active_release(&cl->active);
 }
 
-int intel_timeline_init(struct intel_timeline *timeline,
-			struct intel_gt *gt,
-			struct i915_vma *hwsp)
+static int intel_timeline_init(struct intel_timeline *timeline,
+			       struct intel_gt *gt,
+			       struct i915_vma *hwsp)
 {
 	void *vaddr;
 
@@ -272,7 +280,7 @@ void intel_gt_init_timelines(struct intel_gt *gt)
 	INIT_LIST_HEAD(&timelines->hwsp_free_list);
 }
 
-void intel_timeline_fini(struct intel_timeline *timeline)
+static void intel_timeline_fini(struct intel_timeline *timeline)
 {
 	GEM_BUG_ON(atomic_read(&timeline->pin_count));
 	GEM_BUG_ON(!list_empty(&timeline->requests));
@@ -329,6 +337,13 @@ int intel_timeline_pin(struct intel_timeline *tl)
 	return 0;
 }
 
+void intel_timeline_reset_seqno(const struct intel_timeline *tl)
+{
+	/* Must be pinned to be writable, and no requests in flight. */
+	GEM_BUG_ON(!atomic_read(&tl->pin_count));
+	WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno);
+}
+
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
@@ -357,8 +372,16 @@ void intel_timeline_enter(struct intel_timeline *tl)
 		return;
 
 	spin_lock(&timelines->lock);
-	if (!atomic_fetch_inc(&tl->active_count))
+	if (!atomic_fetch_inc(&tl->active_count)) {
+		/*
+		 * The HWSP is volatile, and may have been lost while inactive,
+		 * e.g. across suspend/resume. Be paranoid, and ensure that
+		 * the HWSP value matches our seqno so we don't proclaim
+		 * the next request as already complete.
+		 */
+		intel_timeline_reset_seqno(tl);
 		list_add_tail(&tl->link, &timelines->active_list);
+	}
 	spin_unlock(&timelines->lock);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index f5b7eade3809..4298b9ac7327 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -31,11 +31,6 @@
 #include "i915_syncmap.h"
 #include "gt/intel_timeline_types.h"
 
-int intel_timeline_init(struct intel_timeline *tl,
-			struct intel_gt *gt,
-			struct i915_vma *hwsp);
-void intel_timeline_fini(struct intel_timeline *tl);
-
 struct intel_timeline *
 intel_timeline_create(struct intel_gt *gt, struct i915_vma *global_hwsp);
 
@@ -84,6 +79,8 @@ int intel_timeline_get_seqno(struct intel_timeline *tl,
 void intel_timeline_exit(struct intel_timeline *tl);
 void intel_timeline_unpin(struct intel_timeline *tl);
 
+void intel_timeline_reset_seqno(const struct intel_timeline *tl);
+
 int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *until,
 			     u32 *hwsp_offset);
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5176ad1a3976..90a2b9e399b0 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -485,25 +485,14 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void cnl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	struct drm_i915_private *i915 = engine->i915;
-
 	/* WaForceContextSaveRestoreNonCoherent:cnl */
 	WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0,
 			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
 
-	/* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */
-	if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0))
-		WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5);
-
 	/* WaDisableReplayBufferBankArbitrationOptimization:cnl */
 	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
-	/* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */
-	if (IS_CNL_REVID(i915, 0, CNL_REVID_B0))
-		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-				  GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
-
 	/* WaPushConstantDereferenceHoldDisable:cnl */
 	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
 
@@ -837,7 +826,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 			intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3) &
 			GEN10_L3BANK_MASK;
 
-		DRM_DEBUG_DRIVER("L3 fuse = %x\n", l3_fuse);
+		drm_dbg(&i915->drm, "L3 fuse = %x\n", l3_fuse);
 		l3_en = ~(l3_fuse << GEN10_L3BANK_PAIR_COUNT | l3_fuse);
 	} else {
 		l3_en = ~0;
@@ -846,7 +835,8 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	slice = fls(sseu->slice_mask) - 1;
 	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",
+		drm_warn(&i915->drm,
+			 "No common index found between subslice mask %x and L3 bank mask %x!\n",
 			 intel_sseu_get_subslices(sseu, slice), l3_en);
 		subslice = fls(l3_en);
 		drm_WARN_ON(&i915->drm, !subslice);
@@ -861,7 +851,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
 	}
 
-	DRM_DEBUG_DRIVER("MCR slice/subslice = %x\n", mcr);
+	drm_dbg(&i915->drm, "MCR slice/subslice = %x\n", mcr);
 
 	wa_write_masked_or(wal, GEN8_MCR_SELECTOR, mcr_mask, mcr);
 }
@@ -871,12 +861,6 @@ cnl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
 	wa_init_mcr(i915, wal);
 
-	/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
-	if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0))
-		wa_write_or(wal,
-			    GAMT_CHKN_BIT_REG,
-			    GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT);
-
 	/* WaInPlaceDecompressionHang:cnl */
 	wa_write_or(wal,
 		    GEN9_GAMT_ECO_REG_RW_IA,
@@ -933,15 +917,20 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *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);
+	/* Wa_1607087056:icl,ehl,jsl */
+	if (IS_ICELAKE(i915) ||
+	    IS_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0)) {
+		wa_write_or(wal,
+			    SLICE_UNIT_LEVEL_CLKGATE,
+			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
+	}
 }
 
 static void
 tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
+	wa_init_mcr(i915, wal);
+
 	/* Wa_1409420604:tgl */
 	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
 		wa_write_or(wal,
@@ -1379,12 +1368,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
 
-		/*
-		 * Wa_1409085225:tgl
-		 * Wa_14010229206:tgl
-		 */
-		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
-
 		/* Wa_1408615072:tgl */
 		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
 			    VSUNIT_CLKGATE_DIS_TGL);
@@ -1402,6 +1385,12 @@ 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_1409085225:tgl
+		 * Wa_14010229206:tgl
+		 */
+		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 	}
 
 	if (IS_GEN(i915, 11)) {
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 4a53ded7c2dd..b8dd3cbc8696 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -28,7 +28,6 @@
 #include "i915_drv.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
-#include "intel_engine_pool.h"
 
 #include "mock_engine.h"
 #include "selftests/mock_request.h"
@@ -328,7 +327,6 @@ int mock_engine_init(struct intel_engine_cs *engine)
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
-	intel_engine_pool_init(&engine->pool);
 
 	ce = create_kernel_context(engine);
 	if (IS_ERR(ce))
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index e874dfaa5316..52af1cee9a94 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -24,6 +24,7 @@ static int request_sync(struct i915_request *rq)
 
 	/* Opencode i915_request_add() so we can keep the timeline locked. */
 	__i915_request_commit(rq);
+	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 	__i915_request_queue(rq, NULL);
 
 	timeout = i915_request_wait(rq, 0, HZ / 10);
@@ -154,10 +155,7 @@ static int live_context_size(void *arg)
 	 */
 
 	for_each_engine(engine, gt, id) {
-		struct {
-			struct drm_i915_gem_object *state;
-			void *pinned;
-		} saved;
+		struct file *saved;
 
 		if (!engine->context_size)
 			continue;
@@ -171,8 +169,7 @@ static int live_context_size(void *arg)
 		 * active state is sufficient, we are only checking that we
 		 * don't use more than we planned.
 		 */
-		saved.state = fetch_and_zero(&engine->default_state);
-		saved.pinned = fetch_and_zero(&engine->pinned_default_state);
+		saved = fetch_and_zero(&engine->default_state);
 
 		/* Overlaps with the execlists redzone */
 		engine->context_size += I915_GTT_PAGE_SIZE;
@@ -181,8 +178,7 @@ static int live_context_size(void *arg)
 
 		engine->context_size -= I915_GTT_PAGE_SIZE;
 
-		engine->pinned_default_state = saved.pinned;
-		engine->default_state = saved.state;
+		engine->default_state = saved;
 
 		intel_engine_pm_put(engine);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index 09ff8e4f88af..242181a5214c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -7,6 +7,7 @@
 
 #include "selftest_llc.h"
 #include "selftest_rc6.h"
+#include "selftest_rps.h"
 
 static int live_gt_resume(void *arg)
 {
@@ -52,6 +53,13 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_rc6_manual),
+		SUBTEST(live_rps_clock_interval),
+		SUBTEST(live_rps_control),
+		SUBTEST(live_rps_frequency_cs),
+		SUBTEST(live_rps_frequency_srm),
+		SUBTEST(live_rps_power),
+		SUBTEST(live_rps_interrupt),
+		SUBTEST(live_rps_dynamic),
 		SUBTEST(live_gt_resume),
 	};
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index f95ae15ce865..824f99c4cc7c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -21,7 +21,8 @@
 #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 */
+#define NUM_GPR 16
+#define NUM_GPR_DW (NUM_GPR * 2) /* each GPR is 2 dwords */
 
 static struct i915_vma *create_scratch(struct intel_gt *gt)
 {
@@ -68,26 +69,41 @@ static void engine_heartbeat_enable(struct intel_engine_cs *engine,
 	engine->props.heartbeat_interval_ms = saved;
 }
 
+static bool is_active(struct i915_request *rq)
+{
+	if (i915_request_is_active(rq))
+		return true;
+
+	if (i915_request_on_hold(rq))
+		return true;
+
+	if (i915_request_started(rq))
+		return true;
+
+	return false;
+}
+
 static int wait_for_submit(struct intel_engine_cs *engine,
 			   struct i915_request *rq,
 			   unsigned long timeout)
 {
 	timeout += jiffies;
 	do {
-		cond_resched();
-		intel_engine_flush_submission(engine);
+		bool done = time_after(jiffies, timeout);
 
-		if (READ_ONCE(engine->execlists.pending[0]))
-			continue;
-
-		if (i915_request_is_active(rq))
+		if (i915_request_completed(rq)) /* that was quick! */
 			return 0;
 
-		if (i915_request_started(rq)) /* that was quick! */
+		/* Wait until the HW has acknowleged the submission (or err) */
+		intel_engine_flush_submission(engine);
+		if (!READ_ONCE(engine->execlists.pending[0]) && is_active(rq))
 			return 0;
-	} while (time_before(jiffies, timeout));
 
-	return -ETIME;
+		if (done)
+			return -ETIME;
+
+		cond_resched();
+	} while (1);
 }
 
 static int wait_for_reset(struct intel_engine_cs *engine,
@@ -634,9 +650,9 @@ static int live_error_interrupt(void *arg)
 						 error_repr(p->error[i]));
 
 				if (!i915_request_started(client[i])) {
-					pr_debug("%s: %s request not stated!\n",
-						 engine->name,
-						 error_repr(p->error[i]));
+					pr_err("%s: %s request not started!\n",
+					       engine->name,
+					       error_repr(p->error[i]));
 					err = -ETIME;
 					goto out;
 				}
@@ -644,9 +660,10 @@ static int live_error_interrupt(void *arg)
 				/* Kick the tasklet to process the error */
 				intel_engine_flush_submission(engine);
 				if (client[i]->fence.error != p->error[i]) {
-					pr_err("%s: %s request completed with wrong error code: %d\n",
+					pr_err("%s: %s request (%s) with wrong error code: %d\n",
 					       engine->name,
 					       error_repr(p->error[i]),
+					       i915_request_completed(client[i]) ? "completed" : "running",
 					       client[i]->fence.error);
 					err = -EINVAL;
 					goto out;
@@ -1057,7 +1074,6 @@ static int live_timeslice_rewind(void *arg)
 			       engine->name);
 			goto err;
 		}
-		GEM_BUG_ON(!timer_pending(&engine->execlists.timer));
 
 		/* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */
 		if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */
@@ -1230,8 +1246,14 @@ static int live_timeslice_queue(void *arg)
 		if (err)
 			goto err_rq;
 
-		intel_engine_flush_submission(engine);
+		/* Wait until we ack the release_queue and start timeslicing */
+		do {
+			cond_resched();
+			intel_engine_flush_submission(engine);
+		} while (READ_ONCE(engine->execlists.pending[0]));
+
 		if (!READ_ONCE(engine->execlists.timer.expires) &&
+		    execlists_active(&engine->execlists) == rq &&
 		    !i915_request_completed(rq)) {
 			struct drm_printer p =
 				drm_info_printer(gt->i915->drm.dev);
@@ -2032,6 +2054,9 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 	if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT))
 		return 0;
 
+	if (!intel_has_reset_engine(arg->engine->gt))
+		return 0;
+
 	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
 	rq = spinner_create_request(&arg->a.spin,
 				    arg->a.ctx, arg->engine,
@@ -2632,7 +2657,7 @@ static int create_gang(struct intel_engine_cs *engine,
 	if (IS_ERR(rq))
 		goto err_obj;
 
-	rq->batch = vma;
+	rq->batch = i915_vma_get(vma);
 	i915_request_get(rq);
 
 	i915_vma_lock(vma);
@@ -2656,6 +2681,7 @@ static int create_gang(struct intel_engine_cs *engine,
 	return 0;
 
 err_rq:
+	i915_vma_put(rq->batch);
 	i915_request_put(rq);
 err_obj:
 	i915_gem_object_put(obj);
@@ -2752,6 +2778,7 @@ static int live_preempt_gang(void *arg)
 				err = -ETIME;
 			}
 
+			i915_vma_put(rq->batch);
 			i915_request_put(rq);
 			rq = n;
 		}
@@ -2765,6 +2792,331 @@ static int live_preempt_gang(void *arg)
 	return 0;
 }
 
+static struct i915_vma *
+create_gpr_user(struct intel_engine_cs *engine,
+		struct i915_vma *result,
+		unsigned int offset)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+	int i;
+
+	obj = i915_gem_object_create_internal(engine->i915, 4096);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	vma = i915_vma_instance(obj, result->vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err) {
+		i915_vma_put(vma);
+		return ERR_PTR(err);
+	}
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(cs)) {
+		i915_vma_put(vma);
+		return ERR_CAST(cs);
+	}
+
+	/* All GPR are clear for new contexts. We use GPR(0) as a constant */
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = CS_GPR(engine, 0);
+	*cs++ = 1;
+
+	for (i = 1; i < NUM_GPR; i++) {
+		u64 addr;
+
+		/*
+		 * Perform: GPR[i]++
+		 *
+		 * As we read and write into the context saved GPR[i], if
+		 * we restart this batch buffer from an earlier point, we
+		 * will repeat the increment and store a value > 1.
+		 */
+		*cs++ = MI_MATH(4);
+		*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCA, MI_MATH_REG(i));
+		*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCB, MI_MATH_REG(0));
+		*cs++ = MI_MATH_ADD;
+		*cs++ = MI_MATH_STORE(MI_MATH_REG(i), MI_MATH_REG_ACCU);
+
+		addr = result->node.start + offset + i * sizeof(*cs);
+		*cs++ = MI_STORE_REGISTER_MEM_GEN8;
+		*cs++ = CS_GPR(engine, 2 * i);
+		*cs++ = lower_32_bits(addr);
+		*cs++ = upper_32_bits(addr);
+
+		*cs++ = MI_SEMAPHORE_WAIT |
+			MI_SEMAPHORE_POLL |
+			MI_SEMAPHORE_SAD_GTE_SDD;
+		*cs++ = i;
+		*cs++ = lower_32_bits(result->node.start);
+		*cs++ = upper_32_bits(result->node.start);
+	}
+
+	*cs++ = MI_BATCH_BUFFER_END;
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	return vma;
+}
+
+static struct i915_vma *create_global(struct intel_gt *gt, size_t sz)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
+
+	obj = i915_gem_object_create_internal(gt->i915, sz);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_ggtt_pin(vma, 0, 0);
+	if (err) {
+		i915_vma_put(vma);
+		return ERR_PTR(err);
+	}
+
+	return vma;
+}
+
+static struct i915_request *
+create_gpr_client(struct intel_engine_cs *engine,
+		  struct i915_vma *global,
+		  unsigned int offset)
+{
+	struct i915_vma *batch, *vma;
+	struct intel_context *ce;
+	struct i915_request *rq;
+	int err;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
+
+	vma = i915_vma_instance(global->obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_ce;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto out_ce;
+
+	batch = create_gpr_user(engine, vma, offset);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_vma;
+	}
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_batch;
+	}
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, false);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, 0);
+	i915_vma_unlock(vma);
+
+	i915_vma_lock(batch);
+	if (!err)
+		err = i915_request_await_object(rq, batch->obj, false);
+	if (!err)
+		err = i915_vma_move_to_active(batch, rq, 0);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						batch->node.start,
+						PAGE_SIZE, 0);
+	i915_vma_unlock(batch);
+	i915_vma_unpin(batch);
+
+	if (!err)
+		i915_request_get(rq);
+	i915_request_add(rq);
+
+out_batch:
+	i915_vma_put(batch);
+out_vma:
+	i915_vma_unpin(vma);
+out_ce:
+	intel_context_put(ce);
+	return err ? ERR_PTR(err) : rq;
+}
+
+static int preempt_user(struct intel_engine_cs *engine,
+			struct i915_vma *global,
+			int id)
+{
+	struct i915_sched_attr attr = {
+		.priority = I915_PRIORITY_MAX
+	};
+	struct i915_request *rq;
+	int err = 0;
+	u32 *cs;
+
+	rq = intel_engine_create_kernel_request(engine);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return PTR_ERR(cs);
+	}
+
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = i915_ggtt_offset(global);
+	*cs++ = 0;
+	*cs++ = id;
+
+	intel_ring_advance(rq, cs);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	engine->schedule(rq, &attr);
+
+	if (i915_request_wait(rq, 0, HZ / 2) < 0)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int live_preempt_user(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	struct i915_vma *global;
+	enum intel_engine_id id;
+	u32 *result;
+	int err = 0;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+		return 0;
+
+	/*
+	 * In our other tests, we look at preemption in carefully
+	 * controlled conditions in the ringbuffer. Since most of the
+	 * time is spent in user batches, most of our preemptions naturally
+	 * occur there. We want to verify that when we preempt inside a batch
+	 * we continue on from the current instruction and do not roll back
+	 * to the start, or another earlier arbitration point.
+	 *
+	 * To verify this, we create a batch which is a mixture of
+	 * MI_MATH (gpr++) MI_SRM (gpr) and preemption points. Then with
+	 * a few preempting contexts thrown into the mix, we look for any
+	 * repeated instructions (which show up as incorrect values).
+	 */
+
+	global = create_global(gt, 4096);
+	if (IS_ERR(global))
+		return PTR_ERR(global);
+
+	result = i915_gem_object_pin_map(global->obj, I915_MAP_WC);
+	if (IS_ERR(result)) {
+		i915_vma_unpin_and_release(&global, 0);
+		return PTR_ERR(result);
+	}
+
+	for_each_engine(engine, gt, id) {
+		struct i915_request *client[3] = {};
+		struct igt_live_test t;
+		int i;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		if (IS_GEN(gt->i915, 8) && engine->class != RENDER_CLASS)
+			continue; /* we need per-context GPR */
+
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
+			err = -EIO;
+			break;
+		}
+
+		memset(result, 0, 4096);
+
+		for (i = 0; i < ARRAY_SIZE(client); i++) {
+			struct i915_request *rq;
+
+			rq = create_gpr_client(engine, global,
+					       NUM_GPR * i * sizeof(u32));
+			if (IS_ERR(rq))
+				goto end_test;
+
+			client[i] = rq;
+		}
+
+		/* Continuously preempt the set of 3 running contexts */
+		for (i = 1; i <= NUM_GPR; i++) {
+			err = preempt_user(engine, global, i);
+			if (err)
+				goto end_test;
+		}
+
+		if (READ_ONCE(result[0]) != NUM_GPR) {
+			pr_err("%s: Failed to release semaphore\n",
+			       engine->name);
+			err = -EIO;
+			goto end_test;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(client); i++) {
+			int gpr;
+
+			if (i915_request_wait(client[i], 0, HZ / 2) < 0) {
+				err = -ETIME;
+				goto end_test;
+			}
+
+			for (gpr = 1; gpr < NUM_GPR; gpr++) {
+				if (result[NUM_GPR * i + gpr] != 1) {
+					pr_err("%s: Invalid result, client %d, gpr %d, result: %d\n",
+					       engine->name,
+					       i, gpr, result[NUM_GPR * i + gpr]);
+					err = -EINVAL;
+					goto end_test;
+				}
+			}
+		}
+
+end_test:
+		for (i = 0; i < ARRAY_SIZE(client); i++) {
+			if (!client[i])
+				break;
+
+			i915_request_put(client[i]);
+		}
+
+		/* Flush the semaphores on error */
+		smp_store_mb(result[0], -1);
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			break;
+	}
+
+	i915_vma_unpin_and_release(&global, I915_VMA_RELEASE_MAP);
+	return err;
+}
+
 static int live_preempt_timeout(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -3972,6 +4324,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_chain_preempt),
 		SUBTEST(live_preempt_gang),
 		SUBTEST(live_preempt_timeout),
+		SUBTEST(live_preempt_user),
 		SUBTEST(live_preempt_smoke),
 		SUBTEST(live_virtual_engine),
 		SUBTEST(live_virtual_mask),
@@ -3989,35 +4342,6 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 	return intel_gt_live_subtests(tests, &i915->gt);
 }
 
-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 emit_semaphore_signal(struct intel_context *ce, void *slot)
 {
 	const u32 offset =
@@ -4099,13 +4423,12 @@ static int live_lrc_layout(void *arg)
 		if (!engine->default_state)
 			continue;
 
-		hw = i915_gem_object_pin_map(engine->default_state,
-					     I915_MAP_WB);
+		hw = shmem_pin_map(engine->default_state);
 		if (IS_ERR(hw)) {
 			err = PTR_ERR(hw);
 			break;
 		}
-		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+		hw += LRC_STATE_OFFSET / sizeof(*hw);
 
 		execlists_init_reg_state(memset(lrc, POISON_INUSE, PAGE_SIZE),
 					 engine->kernel_context,
@@ -4166,13 +4489,13 @@ static int live_lrc_layout(void *arg)
 
 		if (err) {
 			pr_info("%s: HW register image:\n", engine->name);
-			hexdump(hw, PAGE_SIZE);
+			igt_hexdump(hw, PAGE_SIZE);
 
 			pr_info("%s: SW register image:\n", engine->name);
-			hexdump(lrc, PAGE_SIZE);
+			igt_hexdump(lrc, PAGE_SIZE);
 		}
 
-		i915_gem_object_unpin_map(engine->default_state);
+		shmem_unpin_map(engine->default_state, hw);
 		if (err)
 			break;
 	}
@@ -4241,10 +4564,35 @@ static int live_lrc_fixed(void *arg)
 				"BB_STATE"
 			},
 			{
+				i915_mmio_reg_offset(RING_BB_PER_CTX_PTR(engine->mmio_base)),
+				lrc_ring_wa_bb_per_ctx(engine),
+				"RING_BB_PER_CTX_PTR"
+			},
+			{
+				i915_mmio_reg_offset(RING_INDIRECT_CTX(engine->mmio_base)),
+				lrc_ring_indirect_ptr(engine),
+				"RING_INDIRECT_CTX_PTR"
+			},
+			{
+				i915_mmio_reg_offset(RING_INDIRECT_CTX_OFFSET(engine->mmio_base)),
+				lrc_ring_indirect_offset(engine),
+				"RING_INDIRECT_CTX_OFFSET"
+			},
+			{
 				i915_mmio_reg_offset(RING_CTX_TIMESTAMP(engine->mmio_base)),
 				CTX_TIMESTAMP - 1,
 				"RING_CTX_TIMESTAMP"
 			},
+			{
+				i915_mmio_reg_offset(GEN8_RING_CS_GPR(engine->mmio_base, 0)),
+				lrc_ring_gpr0(engine),
+				"RING_CS_GPR0"
+			},
+			{
+				i915_mmio_reg_offset(RING_CMD_BUF_CCTL(engine->mmio_base)),
+				lrc_ring_cmd_buf_cctl(engine),
+				"RING_CMD_BUF_CCTL"
+			},
 			{ },
 		}, *t;
 		u32 *hw;
@@ -4252,13 +4600,12 @@ static int live_lrc_fixed(void *arg)
 		if (!engine->default_state)
 			continue;
 
-		hw = i915_gem_object_pin_map(engine->default_state,
-					     I915_MAP_WB);
+		hw = shmem_pin_map(engine->default_state);
 		if (IS_ERR(hw)) {
 			err = PTR_ERR(hw);
 			break;
 		}
-		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+		hw += LRC_STATE_OFFSET / sizeof(*hw);
 
 		for (t = tbl; t->name; t++) {
 			int dw = find_offset(hw, t->reg);
@@ -4274,7 +4621,7 @@ static int live_lrc_fixed(void *arg)
 			}
 		}
 
-		i915_gem_object_unpin_map(engine->default_state);
+		shmem_unpin_map(engine->default_state, hw);
 	}
 
 	return err;
@@ -4830,6 +5177,7 @@ store_context(struct intel_context *ce, struct i915_vma *scratch)
 {
 	struct i915_vma *batch;
 	u32 dw, x, *cs, *hw;
+	u32 *defaults;
 
 	batch = create_user_vma(ce->vm, SZ_64K);
 	if (IS_ERR(batch))
@@ -4841,10 +5189,17 @@ store_context(struct intel_context *ce, struct i915_vma *scratch)
 		return ERR_CAST(cs);
 	}
 
+	defaults = shmem_pin_map(ce->engine->default_state);
+	if (!defaults) {
+		i915_gem_object_unpin_map(batch->obj);
+		i915_vma_put(batch);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	x = 0;
 	dw = 0;
-	hw = ce->engine->pinned_default_state;
-	hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+	hw = defaults;
+	hw += LRC_STATE_OFFSET / sizeof(*hw);
 	do {
 		u32 len = hw[dw] & 0x7f;
 
@@ -4874,6 +5229,8 @@ store_context(struct intel_context *ce, struct i915_vma *scratch)
 
 	*cs++ = MI_BATCH_BUFFER_END;
 
+	shmem_unpin_map(ce->engine->default_state, defaults);
+
 	i915_gem_object_flush_map(batch->obj);
 	i915_gem_object_unpin_map(batch->obj);
 
@@ -4984,6 +5341,7 @@ static struct i915_vma *load_context(struct intel_context *ce, u32 poison)
 {
 	struct i915_vma *batch;
 	u32 dw, *cs, *hw;
+	u32 *defaults;
 
 	batch = create_user_vma(ce->vm, SZ_64K);
 	if (IS_ERR(batch))
@@ -4995,9 +5353,16 @@ static struct i915_vma *load_context(struct intel_context *ce, u32 poison)
 		return ERR_CAST(cs);
 	}
 
+	defaults = shmem_pin_map(ce->engine->default_state);
+	if (!defaults) {
+		i915_gem_object_unpin_map(batch->obj);
+		i915_vma_put(batch);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	dw = 0;
-	hw = ce->engine->pinned_default_state;
-	hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+	hw = defaults;
+	hw += LRC_STATE_OFFSET / sizeof(*hw);
 	do {
 		u32 len = hw[dw] & 0x7f;
 
@@ -5024,6 +5389,8 @@ static struct i915_vma *load_context(struct intel_context *ce, u32 poison)
 
 	*cs++ = MI_BATCH_BUFFER_END;
 
+	shmem_unpin_map(ce->engine->default_state, defaults);
+
 	i915_gem_object_flush_map(batch->obj);
 	i915_gem_object_unpin_map(batch->obj);
 
@@ -5091,6 +5458,7 @@ static int compare_isolation(struct intel_engine_cs *engine,
 {
 	u32 x, dw, *hw, *lrc;
 	u32 *A[2], *B[2];
+	u32 *defaults;
 	int err = 0;
 
 	A[0] = i915_gem_object_pin_map(ref[0]->obj, I915_MAP_WC);
@@ -5121,12 +5489,18 @@ static int compare_isolation(struct intel_engine_cs *engine,
 		err = PTR_ERR(lrc);
 		goto err_B1;
 	}
-	lrc += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+	lrc += LRC_STATE_OFFSET / sizeof(*hw);
+
+	defaults = shmem_pin_map(ce->engine->default_state);
+	if (!defaults) {
+		err = -ENOMEM;
+		goto err_lrc;
+	}
 
 	x = 0;
 	dw = 0;
-	hw = engine->pinned_default_state;
-	hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+	hw = defaults;
+	hw += LRC_STATE_OFFSET / sizeof(*hw);
 	do {
 		u32 len = hw[dw] & 0x7f;
 
@@ -5157,7 +5531,6 @@ static int compare_isolation(struct intel_engine_cs *engine,
 					       A[0][x], B[0][x], B[1][x],
 					       poison, lrc[dw + 1]);
 					err = -EINVAL;
-					break;
 				}
 			}
 			dw += 2;
@@ -5166,6 +5539,8 @@ static int compare_isolation(struct intel_engine_cs *engine,
 	} while (dw < PAGE_SIZE / sizeof(u32) &&
 		 (hw[dw] & ~BIT(0)) != MI_BATCH_BUFFER_END);
 
+	shmem_unpin_map(ce->engine->default_state, defaults);
+err_lrc:
 	i915_gem_object_unpin_map(ce->state->obj);
 err_B1:
 	i915_gem_object_unpin_map(result[1]->obj);
@@ -5296,6 +5671,7 @@ static int live_lrc_isolation(void *arg)
 		0xffffffff,
 		0xffff0000,
 	};
+	int err = 0;
 
 	/*
 	 * Our goal is try and verify that per-context state cannot be
@@ -5306,7 +5682,6 @@ static int live_lrc_isolation(void *arg)
 	 */
 
 	for_each_engine(engine, gt, id) {
-		int err = 0;
 		int i;
 
 		/* Just don't even ask */
@@ -5315,25 +5690,180 @@ static int live_lrc_isolation(void *arg)
 			continue;
 
 		intel_engine_pm_get(engine);
-		if (engine->pinned_default_state) {
-			for (i = 0; i < ARRAY_SIZE(poison); i++) {
-				err = __lrc_isolation(engine, poison[i]);
-				if (err)
-					break;
+		for (i = 0; i < ARRAY_SIZE(poison); i++) {
+			int result;
 
-				err = __lrc_isolation(engine, ~poison[i]);
-				if (err)
-					break;
-			}
+			result = __lrc_isolation(engine, poison[i]);
+			if (result && !err)
+				err = result;
+
+			result = __lrc_isolation(engine, ~poison[i]);
+			if (result && !err)
+				err = result;
 		}
 		intel_engine_pm_put(engine);
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int indirect_ctx_submit_req(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	int err = 0;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -ETIME;
+
+	i915_request_put(rq);
+
+	return err;
+}
+
+#define CTX_BB_CANARY_OFFSET (3 * 1024)
+#define CTX_BB_CANARY_INDEX  (CTX_BB_CANARY_OFFSET / sizeof(u32))
+
+static u32 *
+emit_indirect_ctx_bb_canary(const struct intel_context *ce, u32 *cs)
+{
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(RING_START(0));
+	*cs++ = i915_ggtt_offset(ce->state) +
+		context_wa_bb_offset(ce) +
+		CTX_BB_CANARY_OFFSET;
+	*cs++ = 0;
+
+	return cs;
+}
+
+static void
+indirect_ctx_bb_setup(struct intel_context *ce)
+{
+	u32 *cs = context_indirect_bb(ce);
+
+	cs[CTX_BB_CANARY_INDEX] = 0xdeadf00d;
+
+	setup_indirect_ctx_bb(ce, ce->engine, emit_indirect_ctx_bb_canary);
+}
+
+static bool check_ring_start(struct intel_context *ce)
+{
+	const u32 * const ctx_bb = (void *)(ce->lrc_reg_state) -
+		LRC_STATE_OFFSET + context_wa_bb_offset(ce);
+
+	if (ctx_bb[CTX_BB_CANARY_INDEX] == ce->lrc_reg_state[CTX_RING_START])
+		return true;
+
+	pr_err("ring start mismatch: canary 0x%08x vs state 0x%08x\n",
+	       ctx_bb[CTX_BB_CANARY_INDEX],
+	       ce->lrc_reg_state[CTX_RING_START]);
+
+	return false;
+}
+
+static int indirect_ctx_bb_check(struct intel_context *ce)
+{
+	int err;
+
+	err = indirect_ctx_submit_req(ce);
+	if (err)
+		return err;
+
+	if (!check_ring_start(ce))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __live_lrc_indirect_ctx_bb(struct intel_engine_cs *engine)
+{
+	struct intel_context *a, *b;
+	int err;
+
+	a = intel_context_create(engine);
+	if (IS_ERR(a))
+		return PTR_ERR(a);
+	err = intel_context_pin(a);
+	if (err)
+		goto put_a;
+
+	b = intel_context_create(engine);
+	if (IS_ERR(b)) {
+		err = PTR_ERR(b);
+		goto unpin_a;
+	}
+	err = intel_context_pin(b);
+	if (err)
+		goto put_b;
+
+	/* We use the already reserved extra page in context state */
+	if (!a->wa_bb_page) {
+		GEM_BUG_ON(b->wa_bb_page);
+		GEM_BUG_ON(INTEL_GEN(engine->i915) == 12);
+		goto unpin_b;
+	}
+
+	/*
+	 * In order to test that our per context bb is truly per context,
+	 * and executes at the intended spot on context restoring process,
+	 * make the batch store the ring start value to memory.
+	 * As ring start is restored apriori of starting the indirect ctx bb and
+	 * as it will be different for each context, it fits to this purpose.
+	 */
+	indirect_ctx_bb_setup(a);
+	indirect_ctx_bb_setup(b);
+
+	err = indirect_ctx_bb_check(a);
+	if (err)
+		goto unpin_b;
+
+	err = indirect_ctx_bb_check(b);
+
+unpin_b:
+	intel_context_unpin(b);
+put_b:
+	intel_context_put(b);
+unpin_a:
+	intel_context_unpin(a);
+put_a:
+	intel_context_put(a);
+
+	return err;
+}
+
+static int live_lrc_indirect_ctx_bb(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	for_each_engine(engine, gt, id) {
+		intel_engine_pm_get(engine);
+		err = __live_lrc_indirect_ctx_bb(engine);
+		intel_engine_pm_put(engine);
+
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
+
 		if (err)
-			return err;
+			break;
 	}
 
-	return 0;
+	return err;
 }
 
 static void garbage_reset(struct intel_engine_cs *engine,
@@ -5367,7 +5897,7 @@ static struct i915_request *garbage(struct intel_context *ce,
 	prandom_bytes_state(prng,
 			    ce->lrc_reg_state,
 			    ce->engine->context_size -
-			    LRC_STATE_PN * PAGE_SIZE);
+			    LRC_STATE_OFFSET);
 
 	rq = intel_context_create_request(ce);
 	if (IS_ERR(rq)) {
@@ -5571,6 +6101,7 @@ int intel_lrc_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_lrc_timestamp),
 		SUBTEST(live_lrc_garbage),
 		SUBTEST(live_pphwsp_runtime),
+		SUBTEST(live_lrc_indirect_ctx_bb),
 	};
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
index 95b165faeba7..2dc460624bbc 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rc6.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -11,6 +11,7 @@
 #include "selftest_rc6.h"
 
 #include "selftests/i915_random.h"
+#include "selftests/librapl.h"
 
 static u64 rc6_residency(struct intel_rc6 *rc6)
 {
@@ -31,7 +32,9 @@ int live_rc6_manual(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_rc6 *rc6 = &gt->rc6;
+	u64 rc0_power, rc6_power;
 	intel_wakeref_t wakeref;
+	ktime_t dt;
 	u64 res[2];
 	int err = 0;
 
@@ -54,7 +57,12 @@ int live_rc6_manual(void *arg)
 	msleep(1); /* wakeup is not immediate, takes about 100us on icl */
 
 	res[0] = rc6_residency(rc6);
+
+	dt = ktime_get();
+	rc0_power = librapl_energy_uJ();
 	msleep(250);
+	rc0_power = librapl_energy_uJ() - rc0_power;
+	dt = ktime_sub(ktime_get(), dt);
 	res[1] = rc6_residency(rc6);
 	if ((res[1] - res[0]) >> 10) {
 		pr_err("RC6 residency increased by %lldus while disabled for 250ms!\n",
@@ -63,13 +71,24 @@ int live_rc6_manual(void *arg)
 		goto out_unlock;
 	}
 
+	rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, ktime_to_ns(dt));
+	if (!rc0_power) {
+		pr_err("No power measured while in RC0\n");
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* Manually enter RC6 */
 	intel_rc6_park(rc6);
 
 	res[0] = rc6_residency(rc6);
+	intel_uncore_forcewake_flush(rc6_to_uncore(rc6), FORCEWAKE_ALL);
+	dt = ktime_get();
+	rc6_power = librapl_energy_uJ();
 	msleep(100);
+	rc6_power = librapl_energy_uJ() - rc6_power;
+	dt = ktime_sub(ktime_get(), dt);
 	res[1] = rc6_residency(rc6);
-
 	if (res[1] == res[0]) {
 		pr_err("Did not enter RC6! RC6_STATE=%08x, RC6_CONTROL=%08x, residency=%lld\n",
 		       intel_uncore_read_fw(gt->uncore, GEN6_RC_STATE),
@@ -78,6 +97,15 @@ int live_rc6_manual(void *arg)
 		err = -EINVAL;
 	}
 
+	rc6_power = div64_u64(NSEC_PER_SEC * rc6_power, ktime_to_ns(dt));
+	pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n",
+		rc0_power, rc6_power);
+	if (2 * rc6_power > rc0_power) {
+		pr_err("GPU leaked energy while in RC6!\n");
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* Restore what should have been the original state! */
 	intel_rc6_unpark(rc6);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
index 9995faadd7e8..3350e7c995bc 100644
--- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
@@ -54,6 +54,8 @@ static struct i915_vma *create_wally(struct intel_engine_cs *engine)
 	*cs++ = STACK_MAGIC;
 
 	*cs++ = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	vma->private = intel_context_create(engine); /* dummy residuals */
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
new file mode 100644
index 000000000000..6275d69aa9cc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -0,0 +1,1331 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/pm_qos.h>
+#include <linux/sort.h>
+
+#include "intel_engine_heartbeat.h"
+#include "intel_engine_pm.h"
+#include "intel_gpu_commands.h"
+#include "intel_gt_clock_utils.h"
+#include "intel_gt_pm.h"
+#include "intel_rc6.h"
+#include "selftest_rps.h"
+#include "selftests/igt_flush_test.h"
+#include "selftests/igt_spinner.h"
+#include "selftests/librapl.h"
+
+/* Try to isolate the impact of cstates from determing frequency response */
+#define CPU_LATENCY 0 /* -1 to disable pm_qos, 0 to disable cstates */
+
+static unsigned long engine_heartbeat_disable(struct intel_engine_cs *engine)
+{
+	unsigned long old;
+
+	old = fetch_and_zero(&engine->props.heartbeat_interval_ms);
+
+	intel_engine_pm_get(engine);
+	intel_engine_park_heartbeat(engine);
+
+	return old;
+}
+
+static void engine_heartbeat_enable(struct intel_engine_cs *engine,
+				    unsigned long saved)
+{
+	intel_engine_pm_put(engine);
+
+	engine->props.heartbeat_interval_ms = saved;
+}
+
+static void dummy_rps_work(struct work_struct *wrk)
+{
+}
+
+static int cmp_u64(const void *A, const void *B)
+{
+	const u64 *a = A, *b = B;
+
+	if (a < b)
+		return -1;
+	else if (a > b)
+		return 1;
+	else
+		return 0;
+}
+
+static int cmp_u32(const void *A, const void *B)
+{
+	const u32 *a = A, *b = B;
+
+	if (a < b)
+		return -1;
+	else if (a > b)
+		return 1;
+	else
+		return 0;
+}
+
+static struct i915_vma *
+create_spin_counter(struct intel_engine_cs *engine,
+		    struct i915_address_space *vm,
+		    bool srm,
+		    u32 **cancel,
+		    u32 **counter)
+{
+	enum {
+		COUNT,
+		INC,
+		__NGPR__,
+	};
+#define CS_GPR(x) GEN8_RING_CS_GPR(engine->mmio_base, x)
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	unsigned long end;
+	u32 *base, *cs;
+	int loop, i;
+	int err;
+
+	obj = i915_gem_object_create_internal(vm->i915, 64 << 10);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	end = obj->base.size / sizeof(u32) - 1;
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err) {
+		i915_vma_put(vma);
+		return ERR_PTR(err);
+	}
+
+	base = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(base)) {
+		i915_gem_object_put(obj);
+		return ERR_CAST(base);
+	}
+	cs = base;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(__NGPR__ * 2);
+	for (i = 0; i < __NGPR__; i++) {
+		*cs++ = i915_mmio_reg_offset(CS_GPR(i));
+		*cs++ = 0;
+		*cs++ = i915_mmio_reg_offset(CS_GPR(i)) + 4;
+		*cs++ = 0;
+	}
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(INC));
+	*cs++ = 1;
+
+	loop = cs - base;
+
+	/* Unroll the loop to avoid MI_BB_START stalls impacting measurements */
+	for (i = 0; i < 1024; i++) {
+		*cs++ = MI_MATH(4);
+		*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCA, MI_MATH_REG(COUNT));
+		*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCB, MI_MATH_REG(INC));
+		*cs++ = MI_MATH_ADD;
+		*cs++ = MI_MATH_STORE(MI_MATH_REG(COUNT), MI_MATH_REG_ACCU);
+
+		if (srm) {
+			*cs++ = MI_STORE_REGISTER_MEM_GEN8;
+			*cs++ = i915_mmio_reg_offset(CS_GPR(COUNT));
+			*cs++ = lower_32_bits(vma->node.start + end * sizeof(*cs));
+			*cs++ = upper_32_bits(vma->node.start + end * sizeof(*cs));
+		}
+	}
+
+	*cs++ = MI_BATCH_BUFFER_START_GEN8;
+	*cs++ = lower_32_bits(vma->node.start + loop * sizeof(*cs));
+	*cs++ = upper_32_bits(vma->node.start + loop * sizeof(*cs));
+	GEM_BUG_ON(cs - base > end);
+
+	i915_gem_object_flush_map(obj);
+
+	*cancel = base + loop;
+	*counter = srm ? memset32(base + end, 0, 1) : NULL;
+	return vma;
+}
+
+static u8 wait_for_freq(struct intel_rps *rps, u8 freq, int timeout_ms)
+{
+	u8 history[64], i;
+	unsigned long end;
+	int sleep;
+
+	i = 0;
+	memset(history, freq, sizeof(history));
+	sleep = 20;
+
+	/* The PCU does not change instantly, but drifts towards the goal? */
+	end = jiffies + msecs_to_jiffies(timeout_ms);
+	do {
+		u8 act;
+
+		act = read_cagf(rps);
+		if (time_after(jiffies, end))
+			return act;
+
+		/* Target acquired */
+		if (act == freq)
+			return act;
+
+		/* Any change within the last N samples? */
+		if (!memchr_inv(history, act, sizeof(history)))
+			return act;
+
+		history[i] = act;
+		i = (i + 1) % ARRAY_SIZE(history);
+
+		usleep_range(sleep, 2 * sleep);
+		sleep *= 2;
+		if (sleep > timeout_ms * 20)
+			sleep = timeout_ms * 20;
+	} while (1);
+}
+
+static u8 rps_set_check(struct intel_rps *rps, u8 freq)
+{
+	mutex_lock(&rps->lock);
+	GEM_BUG_ON(!intel_rps_is_active(rps));
+	intel_rps_set(rps, freq);
+	GEM_BUG_ON(rps->last_freq != freq);
+	mutex_unlock(&rps->lock);
+
+	return wait_for_freq(rps, freq, 50);
+}
+
+static void show_pstate_limits(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (IS_BROXTON(i915)) {
+		pr_info("P_STATE_CAP[%x]: 0x%08x\n",
+			i915_mmio_reg_offset(BXT_RP_STATE_CAP),
+			intel_uncore_read(rps_to_uncore(rps),
+					  BXT_RP_STATE_CAP));
+	} else if (IS_GEN(i915, 9)) {
+		pr_info("P_STATE_LIMITS[%x]: 0x%08x\n",
+			i915_mmio_reg_offset(GEN9_RP_STATE_LIMITS),
+			intel_uncore_read(rps_to_uncore(rps),
+					  GEN9_RP_STATE_LIMITS));
+	}
+}
+
+int live_rps_clock_interval(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	intel_gt_pm_get(gt);
+	intel_rps_disable(&gt->rps);
+
+	intel_gt_check_clock_frequency(gt);
+
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_heartbeat;
+		struct i915_request *rq;
+		u32 cycles;
+		u64 dt;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		saved_heartbeat = engine_heartbeat_disable(engine);
+
+		rq = igt_spinner_create_request(&spin,
+						engine->kernel_context,
+						MI_NOOP);
+		if (IS_ERR(rq)) {
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			pr_err("%s: RPS spinner did not start\n",
+			       engine->name);
+			igt_spinner_end(&spin);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			intel_gt_set_wedged(engine->gt);
+			err = -EIO;
+			break;
+		}
+
+		intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+
+		intel_uncore_write_fw(gt->uncore, GEN6_RP_CUR_UP_EI, 0);
+
+		/* Set the evaluation interval to infinity! */
+		intel_uncore_write_fw(gt->uncore,
+				      GEN6_RP_UP_EI, 0xffffffff);
+		intel_uncore_write_fw(gt->uncore,
+				      GEN6_RP_UP_THRESHOLD, 0xffffffff);
+
+		intel_uncore_write_fw(gt->uncore, GEN6_RP_CONTROL,
+				      GEN6_RP_ENABLE | GEN6_RP_UP_BUSY_AVG);
+
+		if (wait_for(intel_uncore_read_fw(gt->uncore,
+						  GEN6_RP_CUR_UP_EI),
+			     10)) {
+			/* Just skip the test; assume lack of HW support */
+			pr_notice("%s: rps evaluation interval not ticking\n",
+				  engine->name);
+			err = -ENODEV;
+		} else {
+			ktime_t dt_[5];
+			u32 cycles_[5];
+			int i;
+
+			for (i = 0; i < 5; i++) {
+				preempt_disable();
+
+				dt_[i] = ktime_get();
+				cycles_[i] = -intel_uncore_read_fw(gt->uncore, GEN6_RP_CUR_UP_EI);
+
+				udelay(1000);
+
+				dt_[i] = ktime_sub(ktime_get(), dt_[i]);
+				cycles_[i] += intel_uncore_read_fw(gt->uncore, GEN6_RP_CUR_UP_EI);
+
+				preempt_enable();
+			}
+
+			/* Use the median of both cycle/dt; close enough */
+			sort(cycles_, 5, sizeof(*cycles_), cmp_u32, NULL);
+			cycles = (cycles_[1] + 2 * cycles_[2] + cycles_[3]) / 4;
+			sort(dt_, 5, sizeof(*dt_), cmp_u64, NULL);
+			dt = div_u64(dt_[1] + 2 * dt_[2] + dt_[3], 4);
+		}
+
+		intel_uncore_write_fw(gt->uncore, GEN6_RP_CONTROL, 0);
+		intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
+
+		igt_spinner_end(&spin);
+		engine_heartbeat_enable(engine, saved_heartbeat);
+
+		if (err == 0) {
+			u64 time = intel_gt_pm_interval_to_ns(gt, cycles);
+			u32 expected =
+				intel_gt_ns_to_pm_interval(gt, dt);
+
+			pr_info("%s: rps counted %d C0 cycles [%lldns] in %lldns [%d cycles], using GT clock frequency of %uKHz\n",
+				engine->name, cycles, time, dt, expected,
+				gt->clock_frequency / 1000);
+
+			if (10 * time < 8 * dt ||
+			    8 * time > 10 * dt) {
+				pr_err("%s: rps clock time does not match walltime!\n",
+				       engine->name);
+				err = -EINVAL;
+			}
+
+			if (10 * expected < 8 * cycles ||
+			    8 * expected > 10 * cycles) {
+				pr_err("%s: walltime does not match rps clock ticks!\n",
+				       engine->name);
+				err = -EINVAL;
+			}
+		}
+
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
+
+		break; /* once is enough */
+	}
+
+	intel_rps_enable(&gt->rps);
+	intel_gt_pm_put(gt);
+
+	igt_spinner_fini(&spin);
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	if (err == -ENODEV) /* skipped, don't report a fail */
+		err = 0;
+
+	return err;
+}
+
+int live_rps_control(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * Check that the actual frequency matches our requested frequency,
+	 * to verify our control mechanism. We have to be careful that the
+	 * PCU may throttle the GPU in which case the actual frequency used
+	 * will be lowered than requested.
+	 */
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (IS_CHERRYVIEW(gt->i915)) /* XXX fragile PCU */
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	intel_gt_pm_get(gt);
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_heartbeat;
+		struct i915_request *rq;
+		ktime_t min_dt, max_dt;
+		int f, limit;
+		int min, max;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		saved_heartbeat = engine_heartbeat_disable(engine);
+
+		rq = igt_spinner_create_request(&spin,
+						engine->kernel_context,
+						MI_NOOP);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			pr_err("%s: RPS spinner did not start\n",
+			       engine->name);
+			igt_spinner_end(&spin);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			intel_gt_set_wedged(engine->gt);
+			err = -EIO;
+			break;
+		}
+
+		if (rps_set_check(rps, rps->min_freq) != rps->min_freq) {
+			pr_err("%s: could not set minimum frequency [%x], only %x!\n",
+			       engine->name, rps->min_freq, read_cagf(rps));
+			igt_spinner_end(&spin);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			show_pstate_limits(rps);
+			err = -EINVAL;
+			break;
+		}
+
+		for (f = rps->min_freq + 1; f < rps->max_freq; f++) {
+			if (rps_set_check(rps, f) < f)
+				break;
+		}
+
+		limit = rps_set_check(rps, f);
+
+		if (rps_set_check(rps, rps->min_freq) != rps->min_freq) {
+			pr_err("%s: could not restore minimum frequency [%x], only %x!\n",
+			       engine->name, rps->min_freq, read_cagf(rps));
+			igt_spinner_end(&spin);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			show_pstate_limits(rps);
+			err = -EINVAL;
+			break;
+		}
+
+		max_dt = ktime_get();
+		max = rps_set_check(rps, limit);
+		max_dt = ktime_sub(ktime_get(), max_dt);
+
+		min_dt = ktime_get();
+		min = rps_set_check(rps, rps->min_freq);
+		min_dt = ktime_sub(ktime_get(), min_dt);
+
+		igt_spinner_end(&spin);
+		engine_heartbeat_enable(engine, saved_heartbeat);
+
+		pr_info("%s: range:[%x:%uMHz, %x:%uMHz] limit:[%x:%uMHz], %x:%x response %lluns:%lluns\n",
+			engine->name,
+			rps->min_freq, intel_gpu_freq(rps, rps->min_freq),
+			rps->max_freq, intel_gpu_freq(rps, rps->max_freq),
+			limit, intel_gpu_freq(rps, limit),
+			min, max, ktime_to_ns(min_dt), ktime_to_ns(max_dt));
+
+		if (limit == rps->min_freq) {
+			pr_err("%s: GPU throttled to minimum!\n",
+			       engine->name);
+			show_pstate_limits(rps);
+			err = -ENODEV;
+			break;
+		}
+
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+	}
+	intel_gt_pm_put(gt);
+
+	igt_spinner_fini(&spin);
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	return err;
+}
+
+static void show_pcu_config(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	unsigned int max_gpu_freq, min_gpu_freq;
+	intel_wakeref_t wakeref;
+	int gpu_freq;
+
+	if (!HAS_LLC(i915))
+		return;
+
+	min_gpu_freq = rps->min_freq;
+	max_gpu_freq = rps->max_freq;
+	if (INTEL_GEN(i915) >= 9) {
+		/* Convert GT frequency to 50 HZ units */
+		min_gpu_freq /= GEN9_FREQ_SCALER;
+		max_gpu_freq /= GEN9_FREQ_SCALER;
+	}
+
+	wakeref = intel_runtime_pm_get(rps_to_uncore(rps)->rpm);
+
+	pr_info("%5s  %5s  %5s\n", "GPU", "eCPU", "eRing");
+	for (gpu_freq = min_gpu_freq; gpu_freq <= max_gpu_freq; gpu_freq++) {
+		int ia_freq = gpu_freq;
+
+		sandybridge_pcode_read(i915,
+				       GEN6_PCODE_READ_MIN_FREQ_TABLE,
+				       &ia_freq, NULL);
+
+		pr_info("%5d  %5d  %5d\n",
+			gpu_freq * 50,
+			((ia_freq >> 0) & 0xff) * 100,
+			((ia_freq >> 8) & 0xff) * 100);
+	}
+
+	intel_runtime_pm_put(rps_to_uncore(rps)->rpm, wakeref);
+}
+
+static u64 __measure_frequency(u32 *cntr, int duration_ms)
+{
+	u64 dc, dt;
+
+	dt = ktime_get();
+	dc = READ_ONCE(*cntr);
+	usleep_range(1000 * duration_ms, 2000 * duration_ms);
+	dc = READ_ONCE(*cntr) - dc;
+	dt = ktime_get() - dt;
+
+	return div64_u64(1000 * 1000 * dc, dt);
+}
+
+static u64 measure_frequency_at(struct intel_rps *rps, u32 *cntr, int *freq)
+{
+	u64 x[5];
+	int i;
+
+	*freq = rps_set_check(rps, *freq);
+	for (i = 0; i < 5; i++)
+		x[i] = __measure_frequency(cntr, 2);
+	*freq = (*freq + read_cagf(rps)) / 2;
+
+	/* A simple triangle filter for better result stability */
+	sort(x, 5, sizeof(*x), cmp_u64, NULL);
+	return div_u64(x[1] + 2 * x[2] + x[3], 4);
+}
+
+static u64 __measure_cs_frequency(struct intel_engine_cs *engine,
+				  int duration_ms)
+{
+	u64 dc, dt;
+
+	dt = ktime_get();
+	dc = intel_uncore_read_fw(engine->uncore, CS_GPR(0));
+	usleep_range(1000 * duration_ms, 2000 * duration_ms);
+	dc = intel_uncore_read_fw(engine->uncore, CS_GPR(0)) - dc;
+	dt = ktime_get() - dt;
+
+	return div64_u64(1000 * 1000 * dc, dt);
+}
+
+static u64 measure_cs_frequency_at(struct intel_rps *rps,
+				   struct intel_engine_cs *engine,
+				   int *freq)
+{
+	u64 x[5];
+	int i;
+
+	*freq = rps_set_check(rps, *freq);
+	for (i = 0; i < 5; i++)
+		x[i] = __measure_cs_frequency(engine, 2);
+	*freq = (*freq + read_cagf(rps)) / 2;
+
+	/* A simple triangle filter for better result stability */
+	sort(x, 5, sizeof(*x), cmp_u64, NULL);
+	return div_u64(x[1] + 2 * x[2] + x[3], 4);
+}
+
+static bool scaled_within(u64 x, u64 y, u32 f_n, u32 f_d)
+{
+	return f_d * x > f_n * y && f_n * x < f_d * y;
+}
+
+int live_rps_frequency_cs(void *arg)
+{
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	struct intel_engine_cs *engine;
+	struct pm_qos_request qos;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * The premise is that the GPU does change freqency at our behest.
+	 * Let's check there is a correspondence between the requested
+	 * frequency, the actual frequency, and the observed clock rate.
+	 */
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (INTEL_GEN(gt->i915) < 8) /* for CS simplicity */
+		return 0;
+
+	if (CPU_LATENCY >= 0)
+		cpu_latency_qos_add_request(&qos, CPU_LATENCY);
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_heartbeat;
+		struct i915_request *rq;
+		struct i915_vma *vma;
+		u32 *cancel, *cntr;
+		struct {
+			u64 count;
+			int freq;
+		} min, max;
+
+		saved_heartbeat = engine_heartbeat_disable(engine);
+
+		vma = create_spin_counter(engine,
+					  engine->kernel_context->vm, false,
+					  &cancel, &cntr);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			break;
+		}
+
+		rq = intel_engine_create_kernel_request(engine);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_vma;
+		}
+
+		i915_vma_lock(vma);
+		err = i915_request_await_object(rq, vma->obj, false);
+		if (!err)
+			err = i915_vma_move_to_active(vma, rq, 0);
+		if (!err)
+			err = rq->engine->emit_bb_start(rq,
+							vma->node.start,
+							PAGE_SIZE, 0);
+		i915_vma_unlock(vma);
+		i915_request_add(rq);
+		if (err)
+			goto err_vma;
+
+		if (wait_for(intel_uncore_read(engine->uncore, CS_GPR(0)),
+			     10)) {
+			pr_err("%s: timed loop did not start\n",
+			       engine->name);
+			goto err_vma;
+		}
+
+		min.freq = rps->min_freq;
+		min.count = measure_cs_frequency_at(rps, engine, &min.freq);
+
+		max.freq = rps->max_freq;
+		max.count = measure_cs_frequency_at(rps, engine, &max.freq);
+
+		pr_info("%s: min:%lluKHz @ %uMHz, max:%lluKHz @ %uMHz [%d%%]\n",
+			engine->name,
+			min.count, intel_gpu_freq(rps, min.freq),
+			max.count, intel_gpu_freq(rps, max.freq),
+			(int)DIV64_U64_ROUND_CLOSEST(100 * min.freq * max.count,
+						     max.freq * min.count));
+
+		if (!scaled_within(max.freq * min.count,
+				   min.freq * max.count,
+				   2, 3)) {
+			int f;
+
+			pr_err("%s: CS did not scale with frequency! scaled min:%llu, max:%llu\n",
+			       engine->name,
+			       max.freq * min.count,
+			       min.freq * max.count);
+			show_pcu_config(rps);
+
+			for (f = min.freq + 1; f <= rps->max_freq; f++) {
+				int act = f;
+				u64 count;
+
+				count = measure_cs_frequency_at(rps, engine, &act);
+				if (act < f)
+					break;
+
+				pr_info("%s: %x:%uMHz: %lluKHz [%d%%]\n",
+					engine->name,
+					act, intel_gpu_freq(rps, act), count,
+					(int)DIV64_U64_ROUND_CLOSEST(100 * min.freq * count,
+								     act * min.count));
+
+				f = act; /* may skip ahead [pcu granularity] */
+			}
+
+			err = -EINVAL;
+		}
+
+err_vma:
+		*cancel = MI_BATCH_BUFFER_END;
+		i915_gem_object_flush_map(vma->obj);
+		i915_gem_object_unpin_map(vma->obj);
+		i915_vma_unpin(vma);
+		i915_vma_put(vma);
+
+		engine_heartbeat_enable(engine, saved_heartbeat);
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
+		if (err)
+			break;
+	}
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	if (CPU_LATENCY >= 0)
+		cpu_latency_qos_remove_request(&qos);
+
+	return err;
+}
+
+int live_rps_frequency_srm(void *arg)
+{
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	struct intel_engine_cs *engine;
+	struct pm_qos_request qos;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * The premise is that the GPU does change freqency at our behest.
+	 * Let's check there is a correspondence between the requested
+	 * frequency, the actual frequency, and the observed clock rate.
+	 */
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (INTEL_GEN(gt->i915) < 8) /* for CS simplicity */
+		return 0;
+
+	if (CPU_LATENCY >= 0)
+		cpu_latency_qos_add_request(&qos, CPU_LATENCY);
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_heartbeat;
+		struct i915_request *rq;
+		struct i915_vma *vma;
+		u32 *cancel, *cntr;
+		struct {
+			u64 count;
+			int freq;
+		} min, max;
+
+		saved_heartbeat = engine_heartbeat_disable(engine);
+
+		vma = create_spin_counter(engine,
+					  engine->kernel_context->vm, true,
+					  &cancel, &cntr);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			break;
+		}
+
+		rq = intel_engine_create_kernel_request(engine);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_vma;
+		}
+
+		i915_vma_lock(vma);
+		err = i915_request_await_object(rq, vma->obj, false);
+		if (!err)
+			err = i915_vma_move_to_active(vma, rq, 0);
+		if (!err)
+			err = rq->engine->emit_bb_start(rq,
+							vma->node.start,
+							PAGE_SIZE, 0);
+		i915_vma_unlock(vma);
+		i915_request_add(rq);
+		if (err)
+			goto err_vma;
+
+		if (wait_for(READ_ONCE(*cntr), 10)) {
+			pr_err("%s: timed loop did not start\n",
+			       engine->name);
+			goto err_vma;
+		}
+
+		min.freq = rps->min_freq;
+		min.count = measure_frequency_at(rps, cntr, &min.freq);
+
+		max.freq = rps->max_freq;
+		max.count = measure_frequency_at(rps, cntr, &max.freq);
+
+		pr_info("%s: min:%lluKHz @ %uMHz, max:%lluKHz @ %uMHz [%d%%]\n",
+			engine->name,
+			min.count, intel_gpu_freq(rps, min.freq),
+			max.count, intel_gpu_freq(rps, max.freq),
+			(int)DIV64_U64_ROUND_CLOSEST(100 * min.freq * max.count,
+						     max.freq * min.count));
+
+		if (!scaled_within(max.freq * min.count,
+				   min.freq * max.count,
+				   1, 2)) {
+			int f;
+
+			pr_err("%s: CS did not scale with frequency! scaled min:%llu, max:%llu\n",
+			       engine->name,
+			       max.freq * min.count,
+			       min.freq * max.count);
+			show_pcu_config(rps);
+
+			for (f = min.freq + 1; f <= rps->max_freq; f++) {
+				int act = f;
+				u64 count;
+
+				count = measure_frequency_at(rps, cntr, &act);
+				if (act < f)
+					break;
+
+				pr_info("%s: %x:%uMHz: %lluKHz [%d%%]\n",
+					engine->name,
+					act, intel_gpu_freq(rps, act), count,
+					(int)DIV64_U64_ROUND_CLOSEST(100 * min.freq * count,
+								     act * min.count));
+
+				f = act; /* may skip ahead [pcu granularity] */
+			}
+
+			err = -EINVAL;
+		}
+
+err_vma:
+		*cancel = MI_BATCH_BUFFER_END;
+		i915_gem_object_flush_map(vma->obj);
+		i915_gem_object_unpin_map(vma->obj);
+		i915_vma_unpin(vma);
+		i915_vma_put(vma);
+
+		engine_heartbeat_enable(engine, saved_heartbeat);
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
+		if (err)
+			break;
+	}
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	if (CPU_LATENCY >= 0)
+		cpu_latency_qos_remove_request(&qos);
+
+	return err;
+}
+
+static void sleep_for_ei(struct intel_rps *rps, int timeout_us)
+{
+	/* Flush any previous EI */
+	usleep_range(timeout_us, 2 * timeout_us);
+
+	/* Reset the interrupt status */
+	rps_disable_interrupts(rps);
+	GEM_BUG_ON(rps->pm_iir);
+	rps_enable_interrupts(rps);
+
+	/* And then wait for the timeout, for real this time */
+	usleep_range(2 * timeout_us, 3 * timeout_us);
+}
+
+static int __rps_up_interrupt(struct intel_rps *rps,
+			      struct intel_engine_cs *engine,
+			      struct igt_spinner *spin)
+{
+	struct intel_uncore *uncore = engine->uncore;
+	struct i915_request *rq;
+	u32 timeout;
+
+	if (!intel_engine_can_store_dword(engine))
+		return 0;
+
+	rps_set_check(rps, rps->min_freq);
+
+	rq = igt_spinner_create_request(spin, engine->kernel_context, MI_NOOP);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	if (!igt_wait_for_spinner(spin, rq)) {
+		pr_err("%s: RPS spinner did not start\n",
+		       engine->name);
+		i915_request_put(rq);
+		intel_gt_set_wedged(engine->gt);
+		return -EIO;
+	}
+
+	if (!intel_rps_is_active(rps)) {
+		pr_err("%s: RPS not enabled on starting spinner\n",
+		       engine->name);
+		igt_spinner_end(spin);
+		i915_request_put(rq);
+		return -EINVAL;
+	}
+
+	if (!(rps->pm_events & GEN6_PM_RP_UP_THRESHOLD)) {
+		pr_err("%s: RPS did not register UP interrupt\n",
+		       engine->name);
+		i915_request_put(rq);
+		return -EINVAL;
+	}
+
+	if (rps->last_freq != rps->min_freq) {
+		pr_err("%s: RPS did not program min frequency\n",
+		       engine->name);
+		i915_request_put(rq);
+		return -EINVAL;
+	}
+
+	timeout = intel_uncore_read(uncore, GEN6_RP_UP_EI);
+	timeout = intel_gt_pm_interval_to_ns(engine->gt, timeout);
+	timeout = DIV_ROUND_UP(timeout, 1000);
+
+	sleep_for_ei(rps, timeout);
+	GEM_BUG_ON(i915_request_completed(rq));
+
+	igt_spinner_end(spin);
+	i915_request_put(rq);
+
+	if (rps->cur_freq != rps->min_freq) {
+		pr_err("%s: Frequency unexpectedly changed [up], now %d!\n",
+		       engine->name, intel_rps_read_actual_frequency(rps));
+		return -EINVAL;
+	}
+
+	if (!(rps->pm_iir & GEN6_PM_RP_UP_THRESHOLD)) {
+		pr_err("%s: UP interrupt not recorded for spinner, pm_iir:%x, prev_up:%x, up_threshold:%x, up_ei:%x\n",
+		       engine->name, rps->pm_iir,
+		       intel_uncore_read(uncore, GEN6_RP_PREV_UP),
+		       intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD),
+		       intel_uncore_read(uncore, GEN6_RP_UP_EI));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __rps_down_interrupt(struct intel_rps *rps,
+				struct intel_engine_cs *engine)
+{
+	struct intel_uncore *uncore = engine->uncore;
+	u32 timeout;
+
+	rps_set_check(rps, rps->max_freq);
+
+	if (!(rps->pm_events & GEN6_PM_RP_DOWN_THRESHOLD)) {
+		pr_err("%s: RPS did not register DOWN interrupt\n",
+		       engine->name);
+		return -EINVAL;
+	}
+
+	if (rps->last_freq != rps->max_freq) {
+		pr_err("%s: RPS did not program max frequency\n",
+		       engine->name);
+		return -EINVAL;
+	}
+
+	timeout = intel_uncore_read(uncore, GEN6_RP_DOWN_EI);
+	timeout = intel_gt_pm_interval_to_ns(engine->gt, timeout);
+	timeout = DIV_ROUND_UP(timeout, 1000);
+
+	sleep_for_ei(rps, timeout);
+
+	if (rps->cur_freq != rps->max_freq) {
+		pr_err("%s: Frequency unexpectedly changed [down], now %d!\n",
+		       engine->name,
+		       intel_rps_read_actual_frequency(rps));
+		return -EINVAL;
+	}
+
+	if (!(rps->pm_iir & (GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT))) {
+		pr_err("%s: DOWN interrupt not recorded for idle, pm_iir:%x, prev_down:%x, down_threshold:%x, down_ei:%x [prev_up:%x, up_threshold:%x, up_ei:%x]\n",
+		       engine->name, rps->pm_iir,
+		       intel_uncore_read(uncore, GEN6_RP_PREV_DOWN),
+		       intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD),
+		       intel_uncore_read(uncore, GEN6_RP_DOWN_EI),
+		       intel_uncore_read(uncore, GEN6_RP_PREV_UP),
+		       intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD),
+		       intel_uncore_read(uncore, GEN6_RP_UP_EI));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int live_rps_interrupt(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	u32 pm_events;
+	int err = 0;
+
+	/*
+	 * First, let's check whether or not we are receiving interrupts.
+	 */
+
+	if (!intel_rps_has_interrupts(rps))
+		return 0;
+
+	intel_gt_pm_get(gt);
+	pm_events = rps->pm_events;
+	intel_gt_pm_put(gt);
+	if (!pm_events) {
+		pr_err("No RPS PM events registered, but RPS is enabled?\n");
+		return -ENODEV;
+	}
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	for_each_engine(engine, gt, id) {
+		/* Keep the engine busy with a spinner; expect an UP! */
+		if (pm_events & GEN6_PM_RP_UP_THRESHOLD) {
+			unsigned long saved_heartbeat;
+
+			intel_gt_pm_wait_for_idle(engine->gt);
+			GEM_BUG_ON(intel_rps_is_active(rps));
+
+			saved_heartbeat = engine_heartbeat_disable(engine);
+
+			err = __rps_up_interrupt(rps, engine, &spin);
+
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			if (err)
+				goto out;
+
+			intel_gt_pm_wait_for_idle(engine->gt);
+		}
+
+		/* Keep the engine awake but idle and check for DOWN */
+		if (pm_events & GEN6_PM_RP_DOWN_THRESHOLD) {
+			unsigned long saved_heartbeat;
+
+			saved_heartbeat = engine_heartbeat_disable(engine);
+			intel_rc6_disable(&gt->rc6);
+
+			err = __rps_down_interrupt(rps, engine);
+
+			intel_rc6_enable(&gt->rc6);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	if (igt_flush_test(gt->i915))
+		err = -EIO;
+
+	igt_spinner_fini(&spin);
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	return err;
+}
+
+static u64 __measure_power(int duration_ms)
+{
+	u64 dE, dt;
+
+	dt = ktime_get();
+	dE = librapl_energy_uJ();
+	usleep_range(1000 * duration_ms, 2000 * duration_ms);
+	dE = librapl_energy_uJ() - dE;
+	dt = ktime_get() - dt;
+
+	return div64_u64(1000 * 1000 * dE, dt);
+}
+
+static u64 measure_power_at(struct intel_rps *rps, int *freq)
+{
+	u64 x[5];
+	int i;
+
+	*freq = rps_set_check(rps, *freq);
+	for (i = 0; i < 5; i++)
+		x[i] = __measure_power(5);
+	*freq = (*freq + read_cagf(rps)) / 2;
+
+	/* A simple triangle filter for better result stability */
+	sort(x, 5, sizeof(*x), cmp_u64, NULL);
+	return div_u64(x[1] + 2 * x[2] + x[3], 4);
+}
+
+int live_rps_power(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	void (*saved_work)(struct work_struct *wrk);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * Our fundamental assumption is that running at lower frequency
+	 * actually saves power. Let's see if our RAPL measurement support
+	 * that theory.
+	 */
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (!librapl_energy_uJ())
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	intel_gt_pm_wait_for_idle(gt);
+	saved_work = rps->work.func;
+	rps->work.func = dummy_rps_work;
+
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_heartbeat;
+		struct i915_request *rq;
+		struct {
+			u64 power;
+			int freq;
+		} min, max;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		saved_heartbeat = engine_heartbeat_disable(engine);
+
+		rq = igt_spinner_create_request(&spin,
+						engine->kernel_context,
+						MI_NOOP);
+		if (IS_ERR(rq)) {
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			pr_err("%s: RPS spinner did not start\n",
+			       engine->name);
+			igt_spinner_end(&spin);
+			engine_heartbeat_enable(engine, saved_heartbeat);
+			intel_gt_set_wedged(engine->gt);
+			err = -EIO;
+			break;
+		}
+
+		max.freq = rps->max_freq;
+		max.power = measure_power_at(rps, &max.freq);
+
+		min.freq = rps->min_freq;
+		min.power = measure_power_at(rps, &min.freq);
+
+		igt_spinner_end(&spin);
+		engine_heartbeat_enable(engine, saved_heartbeat);
+
+		pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n",
+			engine->name,
+			min.power, intel_gpu_freq(rps, min.freq),
+			max.power, intel_gpu_freq(rps, max.freq));
+
+		if (10 * min.freq >= 9 * max.freq) {
+			pr_notice("Could not control frequency, ran at [%d:%uMHz, %d:%uMhz]\n",
+				  min.freq, intel_gpu_freq(rps, min.freq),
+				  max.freq, intel_gpu_freq(rps, max.freq));
+			continue;
+		}
+
+		if (11 * min.power > 10 * max.power) {
+			pr_err("%s: did not conserve power when setting lower frequency!\n",
+			       engine->name);
+			err = -EINVAL;
+			break;
+		}
+
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+	}
+
+	igt_spinner_fini(&spin);
+
+	intel_gt_pm_wait_for_idle(gt);
+	rps->work.func = saved_work;
+
+	return err;
+}
+
+int live_rps_dynamic(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rps *rps = &gt->rps;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * We've looked at the bascs, and have established that we
+	 * can change the clock frequency and that the HW will generate
+	 * interrupts based on load. Now we check how we integrate those
+	 * moving parts into dynamic reclocking based on load.
+	 */
+
+	if (!intel_rps_is_enabled(rps))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	for_each_engine(engine, gt, id) {
+		struct i915_request *rq;
+		struct {
+			ktime_t dt;
+			u8 freq;
+		} min, max;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		intel_gt_pm_wait_for_idle(gt);
+		GEM_BUG_ON(intel_rps_is_active(rps));
+		rps->cur_freq = rps->min_freq;
+
+		intel_engine_pm_get(engine);
+		intel_rc6_disable(&gt->rc6);
+		GEM_BUG_ON(rps->last_freq != rps->min_freq);
+
+		rq = igt_spinner_create_request(&spin,
+						engine->kernel_context,
+						MI_NOOP);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err;
+		}
+
+		i915_request_add(rq);
+
+		max.dt = ktime_get();
+		max.freq = wait_for_freq(rps, rps->max_freq, 500);
+		max.dt = ktime_sub(ktime_get(), max.dt);
+
+		igt_spinner_end(&spin);
+
+		min.dt = ktime_get();
+		min.freq = wait_for_freq(rps, rps->min_freq, 2000);
+		min.dt = ktime_sub(ktime_get(), min.dt);
+
+		pr_info("%s: dynamically reclocked to %u:%uMHz while busy in %lluns, and %u:%uMHz while idle in %lluns\n",
+			engine->name,
+			max.freq, intel_gpu_freq(rps, max.freq),
+			ktime_to_ns(max.dt),
+			min.freq, intel_gpu_freq(rps, min.freq),
+			ktime_to_ns(min.dt));
+		if (min.freq >= max.freq) {
+			pr_err("%s: dynamic reclocking of spinner failed\n!",
+			       engine->name);
+			err = -EINVAL;
+		}
+
+err:
+		intel_rc6_enable(&gt->rc6);
+		intel_engine_pm_put(engine);
+
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
+		if (err)
+			break;
+	}
+
+	igt_spinner_fini(&spin);
+
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.h b/drivers/gpu/drm/i915/gt/selftest_rps.h
new file mode 100644
index 000000000000..6e82a631cfa1
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef SELFTEST_RPS_H
+#define SELFTEST_RPS_H
+
+int live_rps_control(void *arg);
+int live_rps_clock_interval(void *arg);
+int live_rps_frequency_cs(void *arg);
+int live_rps_frequency_srm(void *arg);
+int live_rps_power(void *arg);
+int live_rps_interrupt(void *arg);
+int live_rps_dynamic(void *arg);
+
+#endif /* SELFTEST_RPS_H */
diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c
new file mode 100644
index 000000000000..43c7acbdc79d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shmem_utils.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/shmem_fs.h>
+
+#include "gem/i915_gem_object.h"
+#include "shmem_utils.h"
+
+struct file *shmem_create_from_data(const char *name, void *data, size_t len)
+{
+	struct file *file;
+	int err;
+
+	file = shmem_file_setup(name, PAGE_ALIGN(len), VM_NORESERVE);
+	if (IS_ERR(file))
+		return file;
+
+	err = shmem_write(file, 0, data, len);
+	if (err) {
+		fput(file);
+		return ERR_PTR(err);
+	}
+
+	return file;
+}
+
+struct file *shmem_create_from_object(struct drm_i915_gem_object *obj)
+{
+	struct file *file;
+	void *ptr;
+
+	if (obj->ops == &i915_gem_shmem_ops) {
+		file = obj->base.filp;
+		atomic_long_inc(&file->f_count);
+		return file;
+	}
+
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(ptr))
+		return ERR_CAST(ptr);
+
+	file = shmem_create_from_data("", ptr, obj->base.size);
+	i915_gem_object_unpin_map(obj);
+
+	return file;
+}
+
+static size_t shmem_npte(struct file *file)
+{
+	return file->f_mapping->host->i_size >> PAGE_SHIFT;
+}
+
+static void __shmem_unpin_map(struct file *file, void *ptr, size_t n_pte)
+{
+	unsigned long pfn;
+
+	vunmap(ptr);
+
+	for (pfn = 0; pfn < n_pte; pfn++) {
+		struct page *page;
+
+		page = shmem_read_mapping_page_gfp(file->f_mapping, pfn,
+						   GFP_KERNEL);
+		if (!WARN_ON(IS_ERR(page))) {
+			put_page(page);
+			put_page(page);
+		}
+	}
+}
+
+void *shmem_pin_map(struct file *file)
+{
+	const size_t n_pte = shmem_npte(file);
+	pte_t *stack[32], **ptes, **mem;
+	struct vm_struct *area;
+	unsigned long pfn;
+
+	mem = stack;
+	if (n_pte > ARRAY_SIZE(stack)) {
+		mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
+		if (!mem)
+			return NULL;
+	}
+
+	area = alloc_vm_area(n_pte << PAGE_SHIFT, mem);
+	if (!area) {
+		if (mem != stack)
+			kvfree(mem);
+		return NULL;
+	}
+
+	ptes = mem;
+	for (pfn = 0; pfn < n_pte; pfn++) {
+		struct page *page;
+
+		page = shmem_read_mapping_page_gfp(file->f_mapping, pfn,
+						   GFP_KERNEL);
+		if (IS_ERR(page))
+			goto err_page;
+
+		**ptes++ = mk_pte(page,  PAGE_KERNEL);
+	}
+
+	if (mem != stack)
+		kvfree(mem);
+
+	mapping_set_unevictable(file->f_mapping);
+	return area->addr;
+
+err_page:
+	if (mem != stack)
+		kvfree(mem);
+
+	__shmem_unpin_map(file, area->addr, pfn);
+	return NULL;
+}
+
+void shmem_unpin_map(struct file *file, void *ptr)
+{
+	mapping_clear_unevictable(file->f_mapping);
+	__shmem_unpin_map(file, ptr, shmem_npte(file));
+}
+
+static int __shmem_rw(struct file *file, loff_t off,
+		      void *ptr, size_t len,
+		      bool write)
+{
+	unsigned long pfn;
+
+	for (pfn = off >> PAGE_SHIFT; len; pfn++) {
+		unsigned int this =
+			min_t(size_t, PAGE_SIZE - offset_in_page(off), len);
+		struct page *page;
+		void *vaddr;
+
+		page = shmem_read_mapping_page_gfp(file->f_mapping, pfn,
+						   GFP_KERNEL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+
+		vaddr = kmap(page);
+		if (write)
+			memcpy(vaddr + offset_in_page(off), ptr, this);
+		else
+			memcpy(ptr, vaddr + offset_in_page(off), this);
+		kunmap(page);
+		put_page(page);
+
+		len -= this;
+		ptr += this;
+		off = 0;
+	}
+
+	return 0;
+}
+
+int shmem_read(struct file *file, loff_t off, void *dst, size_t len)
+{
+	return __shmem_rw(file, off, dst, len, false);
+}
+
+int shmem_write(struct file *file, loff_t off, void *src, size_t len)
+{
+	return __shmem_rw(file, off, src, len, true);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "st_shmem_utils.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.h b/drivers/gpu/drm/i915/gt/shmem_utils.h
new file mode 100644
index 000000000000..c1669170c351
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shmem_utils.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef SHMEM_UTILS_H
+#define SHMEM_UTILS_H
+
+#include <linux/types.h>
+
+struct drm_i915_gem_object;
+struct file;
+
+struct file *shmem_create_from_data(const char *name, void *data, size_t len);
+struct file *shmem_create_from_object(struct drm_i915_gem_object *obj);
+
+void *shmem_pin_map(struct file *file);
+void shmem_unpin_map(struct file *file, void *ptr);
+
+int shmem_read(struct file *file, loff_t off, void *dst, size_t len);
+int shmem_write(struct file *file, loff_t off, void *src, size_t len);
+
+#endif /* SHMEM_UTILS_H */
diff --git a/drivers/gpu/drm/i915/gt/st_shmem_utils.c b/drivers/gpu/drm/i915/gt/st_shmem_utils.c
new file mode 100644
index 000000000000..b279fe88b70e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/st_shmem_utils.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+/* Just a quick and causal check of the shmem_utils API */
+
+static int igt_shmem_basic(void *ignored)
+{
+	u32 datum = 0xdeadbeef, result;
+	struct file *file;
+	u32 *map;
+	int err;
+
+	file = shmem_create_from_data("mock", &datum, sizeof(datum));
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	result = 0;
+	err = shmem_read(file, 0, &result, sizeof(result));
+	if (err)
+		goto out_file;
+
+	if (result != datum) {
+		pr_err("Incorrect read back from shmemfs: %x != %x\n",
+		       result, datum);
+		err = -EINVAL;
+		goto out_file;
+	}
+
+	result = 0xc0ffee;
+	err = shmem_write(file, 0, &result, sizeof(result));
+	if (err)
+		goto out_file;
+
+	map = shmem_pin_map(file);
+	if (!map) {
+		err = -ENOMEM;
+		goto out_file;
+	}
+
+	if (*map != result) {
+		pr_err("Incorrect read back via mmap of last write: %x != %x\n",
+		       *map, result);
+		err = -EINVAL;
+		goto out_map;
+	}
+
+out_map:
+	shmem_unpin_map(file, map);
+out_file:
+	fput(file);
+	return err;
+}
+
+int shmem_utils_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_shmem_basic),
+	};
+
+	return i915_subtests(tests, NULL);
+}
diff --git a/drivers/gpu/drm/i915/gt/sysfs_engines.c b/drivers/gpu/drm/i915/gt/sysfs_engines.c
index 8f9b2f33dbaf..535cc1169e54 100644
--- a/drivers/gpu/drm/i915/gt/sysfs_engines.c
+++ b/drivers/gpu/drm/i915/gt/sysfs_engines.c
@@ -192,6 +192,17 @@ static struct kobj_attribute max_spin_attr =
 __ATTR(max_busywait_duration_ns, 0644, max_spin_show, max_spin_store);
 
 static ssize_t
+max_spin_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->defaults.max_busywait_duration_ns);
+}
+
+static struct kobj_attribute max_spin_def =
+__ATTR(max_busywait_duration_ns, 0444, max_spin_default, NULL);
+
+static ssize_t
 timeslice_store(struct kobject *kobj, struct kobj_attribute *attr,
 		const char *buf, size_t count)
 {
@@ -234,6 +245,17 @@ static struct kobj_attribute timeslice_duration_attr =
 __ATTR(timeslice_duration_ms, 0644, timeslice_show, timeslice_store);
 
 static ssize_t
+timeslice_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->defaults.timeslice_duration_ms);
+}
+
+static struct kobj_attribute timeslice_duration_def =
+__ATTR(timeslice_duration_ms, 0444, timeslice_default, NULL);
+
+static ssize_t
 stop_store(struct kobject *kobj, struct kobj_attribute *attr,
 	   const char *buf, size_t count)
 {
@@ -273,6 +295,17 @@ static struct kobj_attribute stop_timeout_attr =
 __ATTR(stop_timeout_ms, 0644, stop_show, stop_store);
 
 static ssize_t
+stop_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->defaults.stop_timeout_ms);
+}
+
+static struct kobj_attribute stop_timeout_def =
+__ATTR(stop_timeout_ms, 0444, stop_default, NULL);
+
+static ssize_t
 preempt_timeout_store(struct kobject *kobj, struct kobj_attribute *attr,
 		      const char *buf, size_t count)
 {
@@ -317,6 +350,18 @@ static struct kobj_attribute preempt_timeout_attr =
 __ATTR(preempt_timeout_ms, 0644, preempt_timeout_show, preempt_timeout_store);
 
 static ssize_t
+preempt_timeout_default(struct kobject *kobj, struct kobj_attribute *attr,
+			char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->defaults.preempt_timeout_ms);
+}
+
+static struct kobj_attribute preempt_timeout_def =
+__ATTR(preempt_timeout_ms, 0444, preempt_timeout_default, NULL);
+
+static ssize_t
 heartbeat_store(struct kobject *kobj, struct kobj_attribute *attr,
 		const char *buf, size_t count)
 {
@@ -359,6 +404,17 @@ heartbeat_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 static struct kobj_attribute heartbeat_interval_attr =
 __ATTR(heartbeat_interval_ms, 0644, heartbeat_show, heartbeat_store);
 
+static ssize_t
+heartbeat_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_engine_cs *engine = kobj_to_engine(kobj);
+
+	return sprintf(buf, "%lu\n", engine->defaults.heartbeat_interval_ms);
+}
+
+static struct kobj_attribute heartbeat_interval_def =
+__ATTR(heartbeat_interval_ms, 0444, heartbeat_default, NULL);
+
 static void kobj_engine_release(struct kobject *kobj)
 {
 	kfree(kobj);
@@ -390,6 +446,42 @@ kobj_engine(struct kobject *dir, struct intel_engine_cs *engine)
 	return &ke->base;
 }
 
+static void add_defaults(struct kobj_engine *parent)
+{
+	static const struct attribute *files[] = {
+		&max_spin_def.attr,
+		&stop_timeout_def.attr,
+#if CONFIG_DRM_I915_HEARTBEAT_INTERVAL
+		&heartbeat_interval_def.attr,
+#endif
+		NULL
+	};
+	struct kobj_engine *ke;
+
+	ke = kzalloc(sizeof(*ke), GFP_KERNEL);
+	if (!ke)
+		return;
+
+	kobject_init(&ke->base, &kobj_engine_type);
+	ke->engine = parent->engine;
+
+	if (kobject_add(&ke->base, &parent->base, "%s", ".defaults")) {
+		kobject_put(&ke->base);
+		return;
+	}
+
+	if (sysfs_create_files(&ke->base, files))
+		return;
+
+	if (intel_engine_has_timeslices(ke->engine) &&
+	    sysfs_create_file(&ke->base, &timeslice_duration_def.attr))
+		return;
+
+	if (intel_engine_has_preempt_reset(ke->engine) &&
+	    sysfs_create_file(&ke->base, &preempt_timeout_def.attr))
+		return;
+}
+
 void intel_engines_add_sysfs(struct drm_i915_private *i915)
 {
 	static const struct attribute *files[] = {
@@ -433,6 +525,8 @@ void intel_engines_add_sysfs(struct drm_i915_private *i915)
 		    sysfs_create_file(kobj, &preempt_timeout_attr.attr))
 			goto err_engine;
 
+		add_defaults(container_of(kobj, struct kobj_engine, base));
+
 		if (0) {
 err_object:
 			kobject_put(kobj);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 819f09ef51fc..861657897c0f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -169,7 +169,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 
-	intel_guc_fw_init_early(guc);
+	intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC);
 	intel_guc_ct_init_early(&guc->ct);
 	intel_guc_log_init_early(&guc->log);
 	intel_guc_submission_init_early(guc);
@@ -723,3 +723,47 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
 
 	return 0;
 }
+
+/**
+ * intel_guc_load_status - dump information about GuC load status
+ * @guc: the GuC
+ * @p: the &drm_printer
+ *
+ * Pretty printer for GuC load status.
+ */
+void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct intel_uncore *uncore = gt->uncore;
+	intel_wakeref_t wakeref;
+
+	if (!intel_guc_is_supported(guc)) {
+		drm_printf(p, "GuC not supported\n");
+		return;
+	}
+
+	if (!intel_guc_is_wanted(guc)) {
+		drm_printf(p, "GuC disabled\n");
+		return;
+	}
+
+	intel_uc_fw_dump(&guc->fw, p);
+
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		u32 status = intel_uncore_read(uncore, GUC_STATUS);
+		u32 i;
+
+		drm_printf(p, "\nGuC status 0x%08x:\n", status);
+		drm_printf(p, "\tBootrom status = 0x%x\n",
+			   (status & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT);
+		drm_printf(p, "\tuKernel status = 0x%x\n",
+			   (status & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT);
+		drm_printf(p, "\tMIA Core status = 0x%x\n",
+			   (status & GS_MIA_MASK) >> GS_MIA_SHIFT);
+		drm_puts(p, "\nScratch registers:\n");
+		for (i = 0; i < 16; i++) {
+			drm_printf(p, "\t%2d: \t0x%x\n",
+				   i, intel_uncore_read(uncore, SOFT_SCRATCH(i)));
+		}
+	}
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 4594ccbeaa34..e84ab67b317d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -74,6 +74,11 @@ struct intel_guc {
 	struct mutex send_mutex;
 };
 
+static inline struct intel_guc *log_to_guc(struct intel_guc_log *log)
+{
+	return container_of(log, struct intel_guc, log);
+}
+
 static
 inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len)
 {
@@ -190,4 +195,6 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask)
 int intel_guc_reset_engine(struct intel_guc *guc,
 			   struct intel_engine_cs *engine);
 
+void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
new file mode 100644
index 000000000000..fe7cb7b29a1e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <drm/drm_print.h>
+
+#include "gt/debugfs_gt.h"
+#include "intel_guc.h"
+#include "intel_guc_debugfs.h"
+#include "intel_guc_log_debugfs.h"
+
+static int guc_info_show(struct seq_file *m, void *data)
+{
+	struct intel_guc *guc = m->private;
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	if (!intel_guc_is_supported(guc))
+		return -ENODEV;
+
+	intel_guc_load_status(guc, &p);
+	drm_puts(&p, "\n");
+	intel_guc_log_info(&guc->log, &p);
+
+	/* Add more as required ... */
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info);
+
+void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "guc_info", &guc_info_fops, NULL },
+	};
+
+	if (!intel_guc_is_supported(guc))
+		return;
+
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), guc);
+	intel_guc_log_debugfs_register(&guc->log, root);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h
new file mode 100644
index 000000000000..424c26665cf1
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GUC_H
+#define DEBUGFS_GUC_H
+
+struct intel_guc;
+struct dentry;
+
+void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root);
+
+#endif /* DEBUGFS_GUC_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index 3a1c47d600ea..d4a87f4c9421 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -13,20 +13,6 @@
 #include "intel_guc_fw.h"
 #include "i915_drv.h"
 
-/**
- * intel_guc_fw_init_early() - initializes GuC firmware struct
- * @guc: intel_guc struct
- *
- * On platforms with GuC selects firmware for uploading
- */
-void intel_guc_fw_init_early(struct intel_guc *guc)
-{
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
-
-	intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC, HAS_GT_UC(i915),
-			       INTEL_INFO(i915)->platform, INTEL_REVID(i915));
-}
-
 static void guc_prepare_xfer(struct intel_uncore *uncore)
 {
 	u32 shim_flags = GUC_DISABLE_SRAM_INIT_TO_ZEROES |
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h
index b5ab639d7259..0b4d2a9c9435 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h
@@ -8,7 +8,6 @@
 
 struct intel_guc;
 
-void intel_guc_fw_init_early(struct intel_guc *guc);
 int intel_guc_fw_upload(struct intel_guc *guc);
 
 #endif
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 caed0d57e704..fb10f3597ea5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -55,11 +55,6 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable,
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static inline struct intel_guc *log_to_guc(struct intel_guc_log *log)
-{
-	return container_of(log, struct intel_guc, log);
-}
-
 static void guc_log_enable_flush_events(struct intel_guc_log *log)
 {
 	intel_guc_enable_msg(log_to_guc(log),
@@ -672,3 +667,95 @@ void intel_guc_log_handle_flush_event(struct intel_guc_log *log)
 {
 	queue_work(system_highpri_wq, &log->relay.flush_work);
 }
+
+static const char *
+stringify_guc_log_type(enum guc_log_buffer_type type)
+{
+	switch (type) {
+	case GUC_ISR_LOG_BUFFER:
+		return "ISR";
+	case GUC_DPC_LOG_BUFFER:
+		return "DPC";
+	case GUC_CRASH_DUMP_LOG_BUFFER:
+		return "CRASH";
+	default:
+		MISSING_CASE(type);
+	}
+
+	return "";
+}
+
+/**
+ * intel_guc_log_info - dump information about GuC log relay
+ * @log: the GuC log
+ * @p: the &drm_printer
+ *
+ * Pretty printer for GuC log info
+ */
+void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p)
+{
+	enum guc_log_buffer_type type;
+
+	if (!intel_guc_log_relay_created(log)) {
+		drm_puts(p, "GuC log relay not created\n");
+		return;
+	}
+
+	drm_puts(p, "GuC logging stats:\n");
+
+	drm_printf(p, "\tRelay full count: %u\n", log->relay.full_count);
+
+	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
+		drm_printf(p, "\t%s:\tflush count %10u, overflow count %10u\n",
+			   stringify_guc_log_type(type),
+			   log->stats[type].flush,
+			   log->stats[type].sampled_overflow);
+	}
+}
+
+/**
+ * intel_guc_log_dump - dump the contents of the GuC log
+ * @log: the GuC log
+ * @p: the &drm_printer
+ * @dump_load_err: dump the log saved on GuC load error
+ *
+ * Pretty printer for the GuC log
+ */
+int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
+		       bool dump_load_err)
+{
+	struct intel_guc *guc = log_to_guc(log);
+	struct intel_uc *uc = container_of(guc, struct intel_uc, guc);
+	struct drm_i915_gem_object *obj = NULL;
+	u32 *map;
+	int i = 0;
+
+	if (!intel_guc_is_supported(guc))
+		return -ENODEV;
+
+	if (dump_load_err)
+		obj = uc->load_err_log;
+	else if (guc->log.vma)
+		obj = guc->log.vma->obj;
+
+	if (!obj)
+		return 0;
+
+	map = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(map)) {
+		DRM_DEBUG("Failed to pin object\n");
+		drm_puts(p, "(log data unaccessible)\n");
+		return PTR_ERR(map);
+	}
+
+	for (i = 0; i < obj->base.size / sizeof(u32); i += 4)
+		drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   *(map + i), *(map + i + 1),
+			   *(map + i + 2), *(map + i + 3));
+
+	drm_puts(p, "\n");
+
+	i915_gem_object_unpin_map(obj);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
index c252c022c5fc..11fccd0b2294 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
@@ -79,4 +79,8 @@ static inline u32 intel_guc_log_get_level(struct intel_guc_log *log)
 	return log->level;
 }
 
+void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p);
+int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
+		       bool dump_load_err);
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c
new file mode 100644
index 000000000000..129e0cf7dfe2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/fs.h>
+#include <drm/drm_print.h>
+
+#include "gt/debugfs_gt.h"
+#include "intel_guc.h"
+#include "intel_guc_log.h"
+#include "intel_guc_log_debugfs.h"
+
+static int guc_log_dump_show(struct seq_file *m, void *data)
+{
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	return intel_guc_log_dump(m->private, &p, false);
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_log_dump);
+
+static int guc_load_err_log_dump_show(struct seq_file *m, void *data)
+{
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	return intel_guc_log_dump(m->private, &p, true);
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_load_err_log_dump);
+
+static int guc_log_level_get(void *data, u64 *val)
+{
+	struct intel_guc_log *log = data;
+
+	if (!intel_guc_is_used(log_to_guc(log)))
+		return -ENODEV;
+
+	*val = intel_guc_log_get_level(log);
+
+	return 0;
+}
+
+static int guc_log_level_set(void *data, u64 val)
+{
+	struct intel_guc_log *log = data;
+
+	if (!intel_guc_is_used(log_to_guc(log)))
+		return -ENODEV;
+
+	return intel_guc_log_set_level(log, val);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(guc_log_level_fops,
+			guc_log_level_get, guc_log_level_set,
+			"%lld\n");
+
+static int guc_log_relay_open(struct inode *inode, struct file *file)
+{
+	struct intel_guc_log *log = inode->i_private;
+
+	if (!intel_guc_is_ready(log_to_guc(log)))
+		return -ENODEV;
+
+	file->private_data = log;
+
+	return intel_guc_log_relay_open(log);
+}
+
+static ssize_t
+guc_log_relay_write(struct file *filp,
+		    const char __user *ubuf,
+		    size_t cnt,
+		    loff_t *ppos)
+{
+	struct intel_guc_log *log = filp->private_data;
+	int val;
+	int ret;
+
+	ret = kstrtoint_from_user(ubuf, cnt, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Enable and start the guc log relay on value of 1.
+	 * Flush log relay for any other value.
+	 */
+	if (val == 1)
+		ret = intel_guc_log_relay_start(log);
+	else
+		intel_guc_log_relay_flush(log);
+
+	return ret ?: cnt;
+}
+
+static int guc_log_relay_release(struct inode *inode, struct file *file)
+{
+	struct intel_guc_log *log = inode->i_private;
+
+	intel_guc_log_relay_close(log);
+	return 0;
+}
+
+static const struct file_operations guc_log_relay_fops = {
+	.owner = THIS_MODULE,
+	.open = guc_log_relay_open,
+	.write = guc_log_relay_write,
+	.release = guc_log_relay_release,
+};
+
+void intel_guc_log_debugfs_register(struct intel_guc_log *log,
+				    struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "guc_log_dump", &guc_log_dump_fops, NULL },
+		{ "guc_load_err_log_dump", &guc_load_err_log_dump_fops, NULL },
+		{ "guc_log_level", &guc_log_level_fops, NULL },
+		{ "guc_log_relay", &guc_log_relay_fops, NULL },
+	};
+
+	if (!intel_guc_is_supported(log_to_guc(log)))
+		return;
+
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), log);
+}
+
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h
new file mode 100644
index 000000000000..e8900e3d74ea
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GUC_LOG_H
+#define DEBUGFS_GUC_LOG_H
+
+struct intel_guc_log;
+struct dentry;
+
+void intel_guc_log_debugfs_register(struct intel_guc_log *log,
+				    struct dentry *root);
+
+#endif /* DEBUGFS_GUC_LOG_H */
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 aa6d56e25a10..94eb63f309ce 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -258,7 +258,7 @@ static void guc_submit(struct intel_engine_cs *engine,
 
 static inline int rq_prio(const struct i915_request *rq)
 {
-	return rq->sched.attr.priority | __NO_PREEMPTION;
+	return rq->sched.attr.priority;
 }
 
 static struct i915_request *schedule_in(struct i915_request *rq, int idx)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index a74b65694512..65eeb44b397d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -41,7 +41,7 @@ void intel_huc_init_early(struct intel_huc *huc)
 {
 	struct drm_i915_private *i915 = huc_to_gt(huc)->i915;
 
-	intel_huc_fw_init_early(huc);
+	intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC);
 
 	if (INTEL_GEN(i915) >= 11) {
 		huc->status.reg = GEN11_HUC_KERNEL_LOAD_INFO;
@@ -200,9 +200,13 @@ fail:
  * This function reads status register to verify if HuC
  * firmware was successfully loaded.
  *
- * Returns: 1 if HuC firmware is loaded and verified,
- * 0 if HuC firmware is not loaded and -ENODEV if HuC
- * is not present on this platform.
+ * Returns:
+ *  * -ENODEV if HuC is not present on this platform,
+ *  * -EOPNOTSUPP if HuC firmware is disabled,
+ *  * -ENOPKG if HuC firmware was not installed,
+ *  * -ENOEXEC if HuC firmware is invalid or mismatched,
+ *  * 0 if HuC firmware is not running,
+ *  * 1 if HuC firmware is authenticated and running.
  */
 int intel_huc_check_status(struct intel_huc *huc)
 {
@@ -210,11 +214,50 @@ int intel_huc_check_status(struct intel_huc *huc)
 	intel_wakeref_t wakeref;
 	u32 status = 0;
 
-	if (!intel_huc_is_supported(huc))
+	switch (__intel_uc_fw_status(&huc->fw)) {
+	case INTEL_UC_FIRMWARE_NOT_SUPPORTED:
 		return -ENODEV;
+	case INTEL_UC_FIRMWARE_DISABLED:
+		return -EOPNOTSUPP;
+	case INTEL_UC_FIRMWARE_MISSING:
+		return -ENOPKG;
+	case INTEL_UC_FIRMWARE_ERROR:
+		return -ENOEXEC;
+	default:
+		break;
+	}
 
 	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;
 }
+
+/**
+ * intel_huc_load_status - dump information about HuC load status
+ * @huc: the HuC
+ * @p: the &drm_printer
+ *
+ * Pretty printer for HuC load status.
+ */
+void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p)
+{
+	struct intel_gt *gt = huc_to_gt(huc);
+	intel_wakeref_t wakeref;
+
+	if (!intel_huc_is_supported(huc)) {
+		drm_printf(p, "HuC not supported\n");
+		return;
+	}
+
+	if (!intel_huc_is_wanted(huc)) {
+		drm_printf(p, "HuC disabled\n");
+		return;
+	}
+
+	intel_uc_fw_dump(&huc->fw, p);
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		drm_printf(p, "HuC status: 0x%08x\n",
+			   intel_uncore_read(gt->uncore, huc->status.reg));
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index a40b9cfc6c22..daee43b661d4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -57,4 +57,6 @@ static inline bool intel_huc_is_authenticated(struct intel_huc *huc)
 	return intel_uc_fw_is_running(&huc->fw);
 }
 
+void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p);
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c
new file mode 100644
index 000000000000..5733c15fd123
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <drm/drm_print.h>
+
+#include "gt/debugfs_gt.h"
+#include "intel_huc.h"
+#include "intel_huc_debugfs.h"
+
+static int huc_info_show(struct seq_file *m, void *data)
+{
+	struct intel_huc *huc = m->private;
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	if (!intel_huc_is_supported(huc))
+		return -ENODEV;
+
+	intel_huc_load_status(huc, &p);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(huc_info);
+
+void intel_huc_debugfs_register(struct intel_huc *huc, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "huc_info", &huc_info_fops, NULL },
+	};
+
+	if (!intel_huc_is_supported(huc))
+		return;
+
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), huc);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h
new file mode 100644
index 000000000000..be79e992f976
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef DEBUGFS_HUC_H
+#define DEBUGFS_HUC_H
+
+struct intel_huc;
+struct dentry;
+
+void intel_huc_debugfs_register(struct intel_huc *huc, struct dentry *root);
+
+#endif /* DEBUGFS_HUC_H */
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 9cdf4cbe691c..e5ef509c70e8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -8,23 +8,6 @@
 #include "i915_drv.h"
 
 /**
- * intel_huc_fw_init_early() - initializes HuC firmware struct
- * @huc: intel_huc struct
- *
- * On platforms with HuC selects firmware for uploading
- */
-void intel_huc_fw_init_early(struct intel_huc *huc)
-{
-	struct intel_gt *gt = huc_to_gt(huc);
-	struct intel_uc *uc = &gt->uc;
-	struct drm_i915_private *i915 = gt->i915;
-
-	intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC,
-			       intel_uc_wants_guc(uc),
-			       INTEL_INFO(i915)->platform, INTEL_REVID(i915));
-}
-
-/**
  * intel_huc_fw_upload() - load HuC uCode to device
  * @huc: intel_huc structure
  *
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
index b791269ce923..12f264ee3e0b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h
@@ -8,7 +8,6 @@
 
 struct intel_huc;
 
-void intel_huc_fw_init_early(struct intel_huc *huc);
 int intel_huc_fw_upload(struct intel_huc *huc);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index a4cbe06e06bd..f518fe05c6f9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -45,12 +45,12 @@ static void __confirm_options(struct intel_uc *uc)
 {
 	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
 
-	DRM_DEV_DEBUG_DRIVER(i915->drm.dev,
-			     "enable_guc=%d (guc:%s submission:%s huc:%s)\n",
-			     i915_modparams.enable_guc,
-			     yesno(intel_uc_wants_guc(uc)),
-			     yesno(intel_uc_wants_guc_submission(uc)),
-			     yesno(intel_uc_wants_huc(uc)));
+	drm_dbg(&i915->drm,
+		"enable_guc=%d (guc:%s submission:%s huc:%s)\n",
+		i915_modparams.enable_guc,
+		yesno(intel_uc_wants_guc(uc)),
+		yesno(intel_uc_wants_guc_submission(uc)),
+		yesno(intel_uc_wants_huc(uc)));
 
 	if (i915_modparams.enable_guc == -1)
 		return;
@@ -63,25 +63,25 @@ static void __confirm_options(struct intel_uc *uc)
 	}
 
 	if (!intel_uc_supports_guc(uc))
-		dev_info(i915->drm.dev,
+		drm_info(&i915->drm,
 			 "Incompatible option enable_guc=%d - %s\n",
 			 i915_modparams.enable_guc, "GuC is not supported!");
 
 	if (i915_modparams.enable_guc & ENABLE_GUC_LOAD_HUC &&
 	    !intel_uc_supports_huc(uc))
-		dev_info(i915->drm.dev,
+		drm_info(&i915->drm,
 			 "Incompatible option enable_guc=%d - %s\n",
 			 i915_modparams.enable_guc, "HuC is not supported!");
 
 	if (i915_modparams.enable_guc & ENABLE_GUC_SUBMISSION &&
 	    !intel_uc_supports_guc_submission(uc))
-		dev_info(i915->drm.dev,
+		drm_info(&i915->drm,
 			 "Incompatible option enable_guc=%d - %s\n",
 			 i915_modparams.enable_guc, "GuC submission is N/A");
 
 	if (i915_modparams.enable_guc & ~(ENABLE_GUC_SUBMISSION |
 					  ENABLE_GUC_LOAD_HUC))
-		dev_info(i915->drm.dev,
+		drm_info(&i915->drm,
 			 "Incompatible option enable_guc=%d - %s\n",
 			 i915_modparams.enable_guc, "undocumented flag");
 }
@@ -131,6 +131,13 @@ static void __uc_free_load_err_log(struct intel_uc *uc)
 		i915_gem_object_put(log);
 }
 
+void intel_uc_driver_remove(struct intel_uc *uc)
+{
+	intel_uc_fini_hw(uc);
+	intel_uc_fini(uc);
+	__uc_free_load_err_log(uc);
+}
+
 static inline bool guc_communication_enabled(struct intel_guc *guc)
 {
 	return intel_guc_ct_enabled(&guc->ct);
@@ -311,8 +318,6 @@ static void __uc_fini(struct intel_uc *uc)
 {
 	intel_huc_fini(&uc->huc);
 	intel_guc_fini(&uc->guc);
-
-	__uc_free_load_err_log(uc);
 }
 
 static int __uc_sanitize(struct intel_uc *uc)
@@ -475,14 +480,14 @@ static int __uc_init_hw(struct intel_uc *uc)
 	if (intel_uc_uses_guc_submission(uc))
 		intel_guc_submission_enable(guc);
 
-	dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n",
+	drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
 		 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path,
 		 guc->fw.major_ver_found, guc->fw.minor_ver_found,
 		 "submission",
 		 enableddisabled(intel_uc_uses_guc_submission(uc)));
 
 	if (intel_uc_uses_huc(uc)) {
-		dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n",
+		drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
 			 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC),
 			 huc->fw.path,
 			 huc->fw.major_ver_found, huc->fw.minor_ver_found,
@@ -503,7 +508,7 @@ err_out:
 	__uc_sanitize(uc);
 
 	if (!ret) {
-		dev_notice(i915->drm.dev, "GuC is uninitialized\n");
+		drm_notice(&i915->drm, "GuC is uninitialized\n");
 		/* We want to run without GuC submission */
 		return 0;
 	}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
index 5ae7b50b7dc1..9c954c589edf 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
@@ -34,6 +34,7 @@ struct intel_uc {
 
 void intel_uc_init_early(struct intel_uc *uc);
 void intel_uc_driver_late_release(struct intel_uc *uc);
+void intel_uc_driver_remove(struct intel_uc *uc);
 void intel_uc_init_mmio(struct intel_uc *uc);
 void intel_uc_reset_prepare(struct intel_uc *uc);
 void intel_uc_suspend(struct intel_uc *uc);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c
new file mode 100644
index 000000000000..9d16b784aa0d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/debugfs.h>
+
+#include "intel_guc_debugfs.h"
+#include "intel_huc_debugfs.h"
+#include "intel_uc.h"
+#include "intel_uc_debugfs.h"
+
+void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root)
+{
+	struct dentry *root;
+
+	if (!gt_root)
+		return;
+
+	/* GuC and HuC go always in pair, no need to check both */
+	if (!intel_uc_supports_guc(uc))
+		return;
+
+	root = debugfs_create_dir("uc", gt_root);
+	if (IS_ERR(root))
+		return;
+
+	intel_guc_debugfs_register(&uc->guc, root);
+	intel_huc_debugfs_register(&uc->huc, root);
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h
new file mode 100644
index 000000000000..010ce250d223
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef DEBUGFS_UC_H
+#define DEBUGFS_UC_H
+
+struct intel_uc;
+struct dentry;
+
+void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root);
+
+#endif /* DEBUGFS_UC_H */
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 18c755203688..e1caae93996d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -11,26 +11,32 @@
 #include "intel_uc_fw_abi.h"
 #include "i915_drv.h"
 
-static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
+static inline struct intel_gt *
+____uc_fw_to_gt(struct intel_uc_fw *uc_fw, enum intel_uc_fw_type type)
 {
-	GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED);
-	if (uc_fw->type == INTEL_UC_FW_TYPE_GUC)
+	if (type == INTEL_UC_FW_TYPE_GUC)
 		return container_of(uc_fw, struct intel_gt, uc.guc.fw);
 
-	GEM_BUG_ON(uc_fw->type != INTEL_UC_FW_TYPE_HUC);
+	GEM_BUG_ON(type != INTEL_UC_FW_TYPE_HUC);
 	return container_of(uc_fw, struct intel_gt, uc.huc.fw);
 }
 
+static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
+{
+	GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED);
+	return ____uc_fw_to_gt(uc_fw, uc_fw->type);
+}
+
 #ifdef CONFIG_DRM_I915_DEBUG_GUC
 void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 			       enum intel_uc_fw_status status)
 {
 	uc_fw->__status =  status;
-	DRM_DEV_DEBUG_DRIVER(__uc_fw_to_gt(uc_fw)->i915->drm.dev,
-			     "%s firmware -> %s\n",
-			     intel_uc_fw_type_repr(uc_fw->type),
-			     status == INTEL_UC_FIRMWARE_SELECTED ?
-			     uc_fw->path : intel_uc_fw_status_repr(status));
+	drm_dbg(&__uc_fw_to_gt(uc_fw)->i915->drm,
+		"%s firmware -> %s\n",
+		intel_uc_fw_type_repr(uc_fw->type),
+		status == INTEL_UC_FIRMWARE_SELECTED ?
+		uc_fw->path : intel_uc_fw_status_repr(status));
 }
 #endif
 
@@ -187,17 +193,15 @@ static void __uc_fw_user_override(struct intel_uc_fw *uc_fw)
  * intel_uc_fw_init_early - initialize the uC object and select the firmware
  * @uc_fw: uC firmware
  * @type: type of uC
- * @supported: is uC support possible
- * @platform: platform identifier
- * @rev: hardware revision
  *
  * Initialize the state of our uC object and relevant tracking and select the
  * firmware to fetch and load.
  */
 void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
-			    enum intel_uc_fw_type type, bool supported,
-			    enum intel_platform platform, u8 rev)
+			    enum intel_uc_fw_type type)
 {
+	struct drm_i915_private *i915 = ____uc_fw_to_gt(uc_fw, type)->i915;
+
 	/*
 	 * we use FIRMWARE_UNINITIALIZED to detect checks against uc_fw->status
 	 * before we're looked at the HW caps to see if we have uc support
@@ -208,8 +212,10 @@ void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
 
 	uc_fw->type = type;
 
-	if (supported) {
-		__uc_fw_auto_select(uc_fw, platform, rev);
+	if (HAS_GT_UC(i915)) {
+		__uc_fw_auto_select(uc_fw,
+				    INTEL_INFO(i915)->platform,
+				    INTEL_REVID(i915));
 		__uc_fw_user_override(uc_fw);
 	}
 
@@ -290,7 +296,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 
 	/* Check the size of the blob before examining buffer contents */
 	if (unlikely(fw->size < sizeof(struct uc_css_header))) {
-		dev_warn(dev, "%s firmware %s: invalid size: %zu < %zu\n",
+		drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 fw->size, sizeof(struct uc_css_header));
 		err = -ENODATA;
@@ -303,7 +309,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 	size = (css->header_size_dw - css->key_size_dw - css->modulus_size_dw -
 		css->exponent_size_dw) * sizeof(u32);
 	if (unlikely(size != sizeof(struct uc_css_header))) {
-		dev_warn(dev,
+		drm_warn(&i915->drm,
 			 "%s firmware %s: unexpected header size: %zu != %zu\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 fw->size, sizeof(struct uc_css_header));
@@ -316,7 +322,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 
 	/* now RSA */
 	if (unlikely(css->key_size_dw != UOS_RSA_SCRATCH_COUNT)) {
-		dev_warn(dev, "%s firmware %s: unexpected key size: %u != %u\n",
+		drm_warn(&i915->drm, "%s firmware %s: unexpected key size: %u != %u\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 css->key_size_dw, UOS_RSA_SCRATCH_COUNT);
 		err = -EPROTO;
@@ -327,7 +333,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 	/* At least, it should have header, uCode and RSA. Size of all three. */
 	size = sizeof(struct uc_css_header) + uc_fw->ucode_size + uc_fw->rsa_size;
 	if (unlikely(fw->size < size)) {
-		dev_warn(dev, "%s firmware %s: invalid size: %zu < %zu\n",
+		drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 fw->size, size);
 		err = -ENOEXEC;
@@ -337,7 +343,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 	/* Sanity check whether this fw is not larger than whole WOPCM memory */
 	size = __intel_uc_fw_get_upload_size(uc_fw);
 	if (unlikely(size >= i915->wopcm.size)) {
-		dev_warn(dev, "%s firmware %s: invalid size: %zu > %zu\n",
+		drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 size, (size_t)i915->wopcm.size);
 		err = -E2BIG;
@@ -352,7 +358,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 
 	if (uc_fw->major_ver_found != uc_fw->major_ver_wanted ||
 	    uc_fw->minor_ver_found < uc_fw->minor_ver_wanted) {
-		dev_notice(dev, "%s firmware %s: unexpected version: %u.%u != %u.%u\n",
+		drm_notice(&i915->drm, "%s firmware %s: unexpected version: %u.%u != %u.%u\n",
 			   intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			   uc_fw->major_ver_found, uc_fw->minor_ver_found,
 			   uc_fw->major_ver_wanted, uc_fw->minor_ver_wanted);
@@ -380,9 +386,9 @@ fail:
 				  INTEL_UC_FIRMWARE_MISSING :
 				  INTEL_UC_FIRMWARE_ERROR);
 
-	dev_notice(dev, "%s firmware %s: fetch failed with error %d\n",
+	drm_notice(&i915->drm, "%s firmware %s: fetch failed with error %d\n",
 		   intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err);
-	dev_info(dev, "%s firmware(s) can be downloaded from %s\n",
+	drm_info(&i915->drm, "%s firmware(s) can be downloaded from %s\n",
 		 intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL);
 
 	release_firmware(fw);		/* OK even if fw is NULL */
@@ -467,7 +473,7 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags)
 	/* Wait for DMA to finish */
 	ret = intel_wait_for_register_fw(uncore, DMA_CTRL, START_DMA, 0, 100);
 	if (ret)
-		dev_err(gt->i915->drm.dev, "DMA for %s fw failed, DMA_CTRL=%u\n",
+		drm_err(&gt->i915->drm, "DMA for %s fw failed, DMA_CTRL=%u\n",
 			intel_uc_fw_type_repr(uc_fw->type),
 			intel_uncore_read_fw(uncore, DMA_CTRL));
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 888ff0de0244..23d3a423ac0f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -239,8 +239,7 @@ static inline u32 intel_uc_fw_get_upload_size(struct intel_uc_fw *uc_fw)
 }
 
 void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
-			    enum intel_uc_fw_type type, bool supported,
-			    enum intel_platform platform, u8 rev);
+			    enum intel_uc_fw_type type);
 int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw);
 void intel_uc_fw_cleanup_fetch(struct intel_uc_fw *uc_fw);
 int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 offset, u32 dma_flags);
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 8b13f091cee2..0d6d59871308 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -35,7 +35,7 @@
  */
 
 #include "i915_drv.h"
-#include "i915_gem_fence_reg.h"
+#include "gt/intel_ggtt_fencing.h"
 #include "gvt.h"
 
 static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index a3cc080a46c6..8b87f130f7f1 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -882,6 +882,47 @@ static int mocs_cmd_reg_handler(struct parser_exec_state *s,
 	return 0;
 }
 
+static int is_cmd_update_pdps(unsigned int offset,
+			      struct parser_exec_state *s)
+{
+	u32 base = s->workload->engine->mmio_base;
+	return i915_mmio_reg_equal(_MMIO(offset), GEN8_RING_PDP_UDW(base, 0));
+}
+
+static int cmd_pdp_mmio_update_handler(struct parser_exec_state *s,
+				       unsigned int offset, unsigned int index)
+{
+	struct intel_vgpu *vgpu = s->vgpu;
+	struct intel_vgpu_mm *shadow_mm = s->workload->shadow_mm;
+	struct intel_vgpu_mm *mm;
+	u64 pdps[GEN8_3LVL_PDPES];
+
+	if (shadow_mm->ppgtt_mm.root_entry_type ==
+	    GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
+		pdps[0] = (u64)cmd_val(s, 2) << 32;
+		pdps[0] |= cmd_val(s, 4);
+
+		mm = intel_vgpu_find_ppgtt_mm(vgpu, pdps);
+		if (!mm) {
+			gvt_vgpu_err("failed to get the 4-level shadow vm\n");
+			return -EINVAL;
+		}
+		intel_vgpu_mm_get(mm);
+		list_add_tail(&mm->ppgtt_mm.link,
+			      &s->workload->lri_shadow_mm);
+		*cmd_ptr(s, 2) = upper_32_bits(mm->ppgtt_mm.shadow_pdps[0]);
+		*cmd_ptr(s, 4) = lower_32_bits(mm->ppgtt_mm.shadow_pdps[0]);
+	} else {
+		/* Currently all guests use PML4 table and now can't
+		 * have a guest with 3-level table but uses LRI for
+		 * PPGTT update. So this is simply un-testable. */
+		GEM_BUG_ON(1);
+		gvt_vgpu_err("invalid shared shadow vm type\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int cmd_reg_handler(struct parser_exec_state *s,
 	unsigned int offset, unsigned int index, char *cmd)
 {
@@ -920,6 +961,10 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 		patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE);
 	}
 
+	if (is_cmd_update_pdps(offset, s) &&
+	    cmd_pdp_mmio_update_handler(s, offset, index))
+		return -EINVAL;
+
 	/* TODO
 	 * In order to let workload with inhibit context to generate
 	 * correct image data into memory, vregs values will be loaded to
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index dd25c3024370..158873f269b1 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -424,8 +424,6 @@ static int complete_execlist_workload(struct intel_vgpu_workload *workload)
 
 	ret = emulate_execlist_ctx_schedule_out(execlist, &workload->ctx_desc);
 out:
-	intel_vgpu_unpin_mm(workload->shadow_mm);
-	intel_vgpu_destroy_workload(workload);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 2a4b23f8aa74..210016192ce7 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1900,6 +1900,7 @@ struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
 
 	INIT_LIST_HEAD(&mm->ppgtt_mm.list);
 	INIT_LIST_HEAD(&mm->ppgtt_mm.lru_list);
+	INIT_LIST_HEAD(&mm->ppgtt_mm.link);
 
 	if (root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY)
 		mm->ppgtt_mm.guest_pdps[0] = pdps[0];
@@ -2341,12 +2342,27 @@ int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu,
 {
 	const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
 	int ret;
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_engine_cs *engine;
+	int i;
 
 	if (bytes != 4 && bytes != 8)
 		return -EINVAL;
 
 	off -= info->gtt_start_offset;
 	ret = emulate_ggtt_mmio_write(vgpu, off, p_data, bytes);
+
+	/* if ggtt of last submitted context is written,
+	 * that context is probably got unpinned.
+	 * Set last shadowed ctx to invalid.
+	 */
+	for_each_engine(engine, vgpu->gvt->gt, i) {
+		if (!s->last_ctx[i].valid)
+			continue;
+
+		if (s->last_ctx[i].lrca == (off >> info->gtt_entry_size_shift))
+			s->last_ctx[i].valid = false;
+	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 88789316807d..320b8d6ad92f 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -160,6 +160,7 @@ struct intel_vgpu_mm {
 
 			struct list_head list;
 			struct list_head lru_list;
+			struct list_head link; /* possible LRI shadow mm list */
 		} ppgtt_mm;
 		struct {
 			void *virtual_ggtt;
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 9e1787867894..c7c561237883 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -31,7 +31,6 @@
  */
 
 #include <linux/types.h>
-#include <xen/xen.h>
 #include <linux/kthread.h>
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 58c2c7932e3f..a4a6db6b7f90 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -163,6 +163,11 @@ struct intel_vgpu_submission {
 	const struct intel_vgpu_submission_ops *ops;
 	int virtual_submission_interface;
 	bool active;
+	struct {
+		u32 lrca;
+		bool valid;
+		u64 ring_context_gpa;
+	} last_ctx[I915_NUM_ENGINES];
 };
 
 struct intel_vgpu {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 2faf50e1b051..3e88e3b5c43a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2812,7 +2812,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GAMTARBMODE, D_BDW_PLUS);
 
 #define RING_REG(base) _MMIO((base) + 0x270)
-	MMIO_RING_F(RING_REG, 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
+	MMIO_RING_F(RING_REG, 32, F_CMD_ACCESS, 0, 0, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
 	MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, hws_pga_write);
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index b17c4a1599cd..b79da5124f83 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -79,6 +79,4 @@ struct intel_gvt_mpt {
 	bool (*is_valid_gfn)(unsigned long handle, unsigned long gfn);
 };
 
-extern struct intel_gvt_mpt xengt_mpt;
-
 #endif /* _GVT_HYPERCALL_H_ */
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index e92ed96c9b23..0fb1df71c637 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -58,10 +58,8 @@ static void set_context_pdp_root_pointer(
 
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
-	struct drm_i915_gem_object *ctx_obj =
-		workload->req->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
+	struct intel_context *ctx = workload->req->context;
 
 	if (WARN_ON(!workload->shadow_mm))
 		return;
@@ -69,11 +67,9 @@ static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 	if (WARN_ON(!atomic_read(&workload->shadow_mm->pincount)))
 		return;
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap(page);
+	shadow_ring_context = (struct execlist_ring_context *)ctx->lrc_reg_state;
 	set_context_pdp_root_pointer(shadow_ring_context,
 			(void *)workload->shadow_mm->ppgtt_mm.shadow_pdps);
-	kunmap(page);
 }
 
 /*
@@ -128,16 +124,24 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct drm_i915_gem_object *ctx_obj =
-		workload->req->context->state->obj;
+	struct intel_context *ctx = workload->req->context;
 	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
 	void *dst;
+	void *context_base;
 	unsigned long context_gpa, context_page_num;
+	unsigned long gpa_base; /* first gpa of consecutive GPAs */
+	unsigned long gpa_size; /* size of consecutive GPAs */
+	struct intel_vgpu_submission *s = &vgpu->submission;
 	int i;
+	bool skip = false;
+	int ring_id = workload->engine->id;
+
+	GEM_BUG_ON(!intel_context_is_pinned(ctx));
+
+	context_base = (void *) ctx->lrc_reg_state -
+				(LRC_STATE_PN << I915_GTT_PAGE_SHIFT);
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap(page);
+	shadow_ring_context = (void *) ctx->lrc_reg_state;
 
 	sr_oa_regs(workload, (u32 *)shadow_ring_context, true);
 #define COPY_REG(name) \
@@ -169,23 +173,43 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 			I915_GTT_PAGE_SIZE - sizeof(*shadow_ring_context));
 
 	sr_oa_regs(workload, (u32 *)shadow_ring_context, false);
-	kunmap(page);
 
-	if (IS_RESTORE_INHIBIT(shadow_ring_context->ctx_ctrl.val))
-		return 0;
+	gvt_dbg_sched("ring %s workload lrca %x, ctx_id %x, ctx gpa %llx",
+			workload->engine->name, workload->ctx_desc.lrca,
+			workload->ctx_desc.context_id,
+			workload->ring_context_gpa);
 
-	gvt_dbg_sched("ring %s workload lrca %x",
-		      workload->engine->name,
-		      workload->ctx_desc.lrca);
+	/* only need to ensure this context is not pinned/unpinned during the
+	 * period from last submission to this this submission.
+	 * Upon reaching this function, the currently submitted context is not
+	 * supposed to get unpinned. If a misbehaving guest driver ever does
+	 * this, it would corrupt itself.
+	 */
+	if (s->last_ctx[ring_id].valid &&
+			(s->last_ctx[ring_id].lrca ==
+				workload->ctx_desc.lrca) &&
+			(s->last_ctx[ring_id].ring_context_gpa ==
+				workload->ring_context_gpa))
+		skip = true;
+
+	s->last_ctx[ring_id].lrca = workload->ctx_desc.lrca;
+	s->last_ctx[ring_id].ring_context_gpa = workload->ring_context_gpa;
 
+	if (IS_RESTORE_INHIBIT(shadow_ring_context->ctx_ctrl.val) || skip)
+		return 0;
+
+	s->last_ctx[ring_id].valid = false;
 	context_page_num = workload->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
 
 	if (IS_BROADWELL(gvt->gt->i915) && workload->engine->id == RCS0)
 		context_page_num = 19;
 
-	i = 2;
-	while (i < context_page_num) {
+	/* find consecutive GPAs from gma until the first inconsecutive GPA.
+	 * read from the continuous GPAs into dst virtual address
+	 */
+	gpa_size = 0;
+	for (i = 2; i < context_page_num; i++) {
 		context_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm,
 				(u32)((workload->ctx_desc.lrca + i) <<
 				I915_GTT_PAGE_SHIFT));
@@ -194,13 +218,26 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 			return -EFAULT;
 		}
 
-		page = i915_gem_object_get_page(ctx_obj, i);
-		dst = kmap(page);
-		intel_gvt_hypervisor_read_gpa(vgpu, context_gpa, dst,
-				I915_GTT_PAGE_SIZE);
-		kunmap(page);
-		i++;
+		if (gpa_size == 0) {
+			gpa_base = context_gpa;
+			dst = context_base + (i << I915_GTT_PAGE_SHIFT);
+		} else if (context_gpa != gpa_base + gpa_size)
+			goto read;
+
+		gpa_size += I915_GTT_PAGE_SIZE;
+
+		if (i == context_page_num - 1)
+			goto read;
+
+		continue;
+
+read:
+		intel_gvt_hypervisor_read_gpa(vgpu, gpa_base, dst, gpa_size);
+		gpa_base = context_gpa;
+		gpa_size = I915_GTT_PAGE_SIZE;
+		dst = context_base + (i << I915_GTT_PAGE_SHIFT);
 	}
+	s->last_ctx[ring_id].valid = true;
 	return 0;
 }
 
@@ -599,10 +636,9 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			if (bb->va && !IS_ERR(bb->va))
 				i915_gem_object_unpin_map(bb->obj);
 
-			if (bb->vma && !IS_ERR(bb->vma)) {
+			if (bb->vma && !IS_ERR(bb->vma))
 				i915_vma_unpin(bb->vma);
-				i915_vma_close(bb->vma);
-			}
+
 			i915_gem_object_put(bb->obj);
 		}
 		list_del(&bb->list);
@@ -610,10 +646,11 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 	}
 }
 
-static int prepare_workload(struct intel_vgpu_workload *workload)
+static int
+intel_vgpu_shadow_mm_pin(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_vgpu_mm *m;
 	int ret = 0;
 
 	ret = intel_vgpu_pin_mm(workload->shadow_mm);
@@ -628,6 +665,52 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 		return -EINVAL;
 	}
 
+	if (!list_empty(&workload->lri_shadow_mm)) {
+		list_for_each_entry(m, &workload->lri_shadow_mm,
+				    ppgtt_mm.link) {
+			ret = intel_vgpu_pin_mm(m);
+			if (ret) {
+				list_for_each_entry_from_reverse(m,
+								 &workload->lri_shadow_mm,
+								 ppgtt_mm.link)
+					intel_vgpu_unpin_mm(m);
+				gvt_vgpu_err("LRI shadow ppgtt fail to pin\n");
+				break;
+			}
+		}
+	}
+
+	if (ret)
+		intel_vgpu_unpin_mm(workload->shadow_mm);
+
+	return ret;
+}
+
+static void
+intel_vgpu_shadow_mm_unpin(struct intel_vgpu_workload *workload)
+{
+	struct intel_vgpu_mm *m;
+
+	if (!list_empty(&workload->lri_shadow_mm)) {
+		list_for_each_entry(m, &workload->lri_shadow_mm,
+				    ppgtt_mm.link)
+			intel_vgpu_unpin_mm(m);
+	}
+	intel_vgpu_unpin_mm(workload->shadow_mm);
+}
+
+static int prepare_workload(struct intel_vgpu_workload *workload)
+{
+	struct intel_vgpu *vgpu = workload->vgpu;
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	int ret = 0;
+
+	ret = intel_vgpu_shadow_mm_pin(workload);
+	if (ret) {
+		gvt_vgpu_err("fail to pin shadow mm\n");
+		return ret;
+	}
+
 	update_shadow_pdps(workload);
 
 	set_context_ppgtt_from_shadow(workload, s->shadow[workload->engine->id]);
@@ -674,7 +757,7 @@ err_shadow_wa_ctx:
 err_shadow_batch:
 	release_shadow_batch_buffer(workload);
 err_unpin_mm:
-	intel_vgpu_unpin_mm(workload->shadow_mm);
+	intel_vgpu_shadow_mm_unpin(workload);
 	return ret;
 }
 
@@ -784,15 +867,48 @@ out:
 	return workload;
 }
 
+static void update_guest_pdps(struct intel_vgpu *vgpu,
+			      u64 ring_context_gpa, u32 pdp[8])
+{
+	u64 gpa;
+	int i;
+
+	gpa = ring_context_gpa + RING_CTX_OFF(pdps[0].val);
+
+	for (i = 0; i < 8; i++)
+		intel_gvt_hypervisor_write_gpa(vgpu,
+				gpa + i * 8, &pdp[7 - i], 4);
+}
+
+static __maybe_unused bool
+check_shadow_context_ppgtt(struct execlist_ring_context *c, struct intel_vgpu_mm *m)
+{
+	if (m->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
+		u64 shadow_pdp = c->pdps[7].val | (u64) c->pdps[6].val << 32;
+
+		if (shadow_pdp != m->ppgtt_mm.shadow_pdps[0]) {
+			gvt_dbg_mm("4-level context ppgtt not match LRI command\n");
+			return false;
+		}
+		return true;
+	} else {
+		/* see comment in LRI handler in cmd_parser.c */
+		gvt_dbg_mm("invalid shadow mm type\n");
+		return false;
+	}
+}
+
 static void update_guest_context(struct intel_vgpu_workload *workload)
 {
 	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct drm_i915_gem_object *ctx_obj = rq->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
+	struct intel_context *ctx = workload->req->context;
+	void *context_base;
 	void *src;
 	unsigned long context_gpa, context_page_num;
+	unsigned long gpa_base; /* first gpa of consecutive GPAs */
+	unsigned long gpa_size; /* size of consecutive GPAs*/
 	int i;
 	u32 ring_base;
 	u32 head, tail;
@@ -801,6 +917,8 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id,
 		      workload->ctx_desc.lrca);
 
+	GEM_BUG_ON(!intel_context_is_pinned(ctx));
+
 	head = workload->rb_head;
 	tail = workload->rb_tail;
 	wrap_count = workload->guest_rb_head >> RB_HEAD_WRAP_CNT_OFF;
@@ -824,9 +942,14 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	if (IS_BROADWELL(rq->i915) && rq->engine->id == RCS0)
 		context_page_num = 19;
 
-	i = 2;
+	context_base = (void *) ctx->lrc_reg_state -
+			(LRC_STATE_PN << I915_GTT_PAGE_SHIFT);
 
-	while (i < context_page_num) {
+	/* find consecutive GPAs from gma until the first inconsecutive GPA.
+	 * write to the consecutive GPAs from src virtual address
+	 */
+	gpa_size = 0;
+	for (i = 2; i < context_page_num; i++) {
 		context_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm,
 				(u32)((workload->ctx_desc.lrca + i) <<
 					I915_GTT_PAGE_SHIFT));
@@ -835,19 +958,39 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 			return;
 		}
 
-		page = i915_gem_object_get_page(ctx_obj, i);
-		src = kmap(page);
-		intel_gvt_hypervisor_write_gpa(vgpu, context_gpa, src,
-				I915_GTT_PAGE_SIZE);
-		kunmap(page);
-		i++;
+		if (gpa_size == 0) {
+			gpa_base = context_gpa;
+			src = context_base + (i << I915_GTT_PAGE_SHIFT);
+		} else if (context_gpa != gpa_base + gpa_size)
+			goto write;
+
+		gpa_size += I915_GTT_PAGE_SIZE;
+
+		if (i == context_page_num - 1)
+			goto write;
+
+		continue;
+
+write:
+		intel_gvt_hypervisor_write_gpa(vgpu, gpa_base, src, gpa_size);
+		gpa_base = context_gpa;
+		gpa_size = I915_GTT_PAGE_SIZE;
+		src = context_base + (i << I915_GTT_PAGE_SHIFT);
 	}
 
 	intel_gvt_hypervisor_write_gpa(vgpu, workload->ring_context_gpa +
 		RING_CTX_OFF(ring_header.val), &workload->rb_tail, 4);
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap(page);
+	shadow_ring_context = (void *) ctx->lrc_reg_state;
+
+	if (!list_empty(&workload->lri_shadow_mm)) {
+		struct intel_vgpu_mm *m = list_last_entry(&workload->lri_shadow_mm,
+							  struct intel_vgpu_mm,
+							  ppgtt_mm.link);
+		GEM_BUG_ON(!check_shadow_context_ppgtt(shadow_ring_context, m));
+		update_guest_pdps(vgpu, workload->ring_context_gpa,
+				  (void *)m->ppgtt_mm.guest_pdps);
+	}
 
 #define COPY_REG(name) \
 	intel_gvt_hypervisor_write_gpa(vgpu, workload->ring_context_gpa + \
@@ -864,8 +1007,6 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 			(void *)shadow_ring_context +
 			sizeof(*shadow_ring_context),
 			I915_GTT_PAGE_SIZE - sizeof(*shadow_ring_context));
-
-	kunmap(page);
 }
 
 void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
@@ -959,6 +1100,9 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 
 	workload->complete(workload);
 
+	intel_vgpu_shadow_mm_unpin(workload);
+	intel_vgpu_destroy_workload(workload);
+
 	atomic_dec(&s->running_workload_num);
 	wake_up(&scheduler->workload_complete_wq);
 
@@ -1264,6 +1408,8 @@ 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);
 
+	memset(s->last_ctx, 0, sizeof(s->last_ctx));
+
 	i915_vm_put(&ppgtt->vm);
 	return 0;
 
@@ -1350,6 +1496,16 @@ void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload)
 	release_shadow_batch_buffer(workload);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 
+	if (!list_empty(&workload->lri_shadow_mm)) {
+		struct intel_vgpu_mm *m, *mm;
+		list_for_each_entry_safe(m, mm, &workload->lri_shadow_mm,
+					 ppgtt_mm.link) {
+			list_del(&m->ppgtt_mm.link);
+			intel_vgpu_mm_put(m);
+		}
+	}
+
+	GEM_BUG_ON(!list_empty(&workload->lri_shadow_mm));
 	if (workload->shadow_mm)
 		intel_vgpu_mm_put(workload->shadow_mm);
 
@@ -1368,6 +1524,7 @@ alloc_workload(struct intel_vgpu *vgpu)
 
 	INIT_LIST_HEAD(&workload->list);
 	INIT_LIST_HEAD(&workload->shadow_bb);
+	INIT_LIST_HEAD(&workload->lri_shadow_mm);
 
 	init_waitqueue_head(&workload->shadow_ctx_status_wq);
 	atomic_set(&workload->shadow_ctx_active, 0);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index bf7fc0ca4cb1..15d317f2a4a4 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -87,6 +87,7 @@ struct intel_vgpu_workload {
 	int status;
 
 	struct intel_vgpu_mm *shadow_mm;
+	struct list_head lri_shadow_mm; /* For PPGTT load cmd */
 
 	/* different submission model may need different handler */
 	int (*prepare)(struct intel_vgpu_workload *);
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index c4048628188a..d960d0be5bd2 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -496,7 +496,7 @@ static int flush_lazy_signals(struct i915_active *ref)
 	return err;
 }
 
-int i915_active_wait(struct i915_active *ref)
+int __i915_active_wait(struct i915_active *ref, int state)
 {
 	int err;
 
@@ -511,7 +511,9 @@ int i915_active_wait(struct i915_active *ref)
 	if (err)
 		return err;
 
-	if (wait_var_event_interruptible(ref, i915_active_is_idle(ref)))
+	if (!i915_active_is_idle(ref) &&
+	    ___wait_var_event(ref, i915_active_is_idle(ref),
+			      state, 0, 0, schedule()))
 		return -EINTR;
 
 	flush_work(&ref->work);
@@ -540,34 +542,88 @@ static int __await_active(struct i915_active_fence *active,
 	return 0;
 }
 
+struct wait_barrier {
+	struct wait_queue_entry base;
+	struct i915_active *ref;
+};
+
+static int
+barrier_wake(wait_queue_entry_t *wq, unsigned int mode, int flags, void *key)
+{
+	struct wait_barrier *wb = container_of(wq, typeof(*wb), base);
+
+	if (i915_active_is_idle(wb->ref)) {
+		list_del(&wq->entry);
+		i915_sw_fence_complete(wq->private);
+		kfree(wq);
+	}
+
+	return 0;
+}
+
+static int __await_barrier(struct i915_active *ref, struct i915_sw_fence *fence)
+{
+	struct wait_barrier *wb;
+
+	wb = kmalloc(sizeof(*wb), GFP_KERNEL);
+	if (unlikely(!wb))
+		return -ENOMEM;
+
+	GEM_BUG_ON(i915_active_is_idle(ref));
+	if (!i915_sw_fence_await(fence)) {
+		kfree(wb);
+		return -EINVAL;
+	}
+
+	wb->base.flags = 0;
+	wb->base.func = barrier_wake;
+	wb->base.private = fence;
+	wb->ref = ref;
+
+	add_wait_queue(__var_waitqueue(ref), &wb->base);
+	return 0;
+}
+
 static int await_active(struct i915_active *ref,
 			unsigned int flags,
 			int (*fn)(void *arg, struct dma_fence *fence),
-			void *arg)
+			void *arg, struct i915_sw_fence *barrier)
 {
 	int err = 0;
 
-	/* We must always wait for the exclusive fence! */
-	if (rcu_access_pointer(ref->excl.fence)) {
+	if (!i915_active_acquire_if_busy(ref))
+		return 0;
+
+	if (flags & I915_ACTIVE_AWAIT_EXCL &&
+	    rcu_access_pointer(ref->excl.fence)) {
 		err = __await_active(&ref->excl, fn, arg);
 		if (err)
-			return err;
+			goto out;
 	}
 
-	if (flags & I915_ACTIVE_AWAIT_ALL && i915_active_acquire_if_busy(ref)) {
+	if (flags & I915_ACTIVE_AWAIT_ACTIVE) {
 		struct active_node *it, *n;
 
 		rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
 			err = __await_active(&it->base, fn, arg);
 			if (err)
-				break;
+				goto out;
 		}
-		i915_active_release(ref);
+	}
+
+	if (flags & I915_ACTIVE_AWAIT_BARRIER) {
+		err = flush_lazy_signals(ref);
 		if (err)
-			return err;
+			goto out;
+
+		err = __await_barrier(ref, barrier);
+		if (err)
+			goto out;
 	}
 
-	return 0;
+out:
+	i915_active_release(ref);
+	return err;
 }
 
 static int rq_await_fence(void *arg, struct dma_fence *fence)
@@ -579,7 +635,7 @@ int i915_request_await_active(struct i915_request *rq,
 			      struct i915_active *ref,
 			      unsigned int flags)
 {
-	return await_active(ref, flags, rq_await_fence, rq);
+	return await_active(ref, flags, rq_await_fence, rq, &rq->submit);
 }
 
 static int sw_await_fence(void *arg, struct dma_fence *fence)
@@ -592,7 +648,7 @@ int i915_sw_fence_await_active(struct i915_sw_fence *fence,
 			       struct i915_active *ref,
 			       unsigned int flags)
 {
-	return await_active(ref, flags, sw_await_fence, fence);
+	return await_active(ref, flags, sw_await_fence, fence, fence);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
@@ -818,7 +874,7 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 
 		GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 		llist_add(barrier_to_ll(node), &engine->barrier_tasks);
-		intel_engine_pm_put(engine);
+		intel_engine_pm_put_delay(engine, 1);
 	}
 }
 
@@ -937,6 +993,59 @@ void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb)
 	active_fence_cb(fence, cb);
 }
 
+struct auto_active {
+	struct i915_active base;
+	struct kref ref;
+};
+
+struct i915_active *i915_active_get(struct i915_active *ref)
+{
+	struct auto_active *aa = container_of(ref, typeof(*aa), base);
+
+	kref_get(&aa->ref);
+	return &aa->base;
+}
+
+static void auto_release(struct kref *ref)
+{
+	struct auto_active *aa = container_of(ref, typeof(*aa), ref);
+
+	i915_active_fini(&aa->base);
+	kfree(aa);
+}
+
+void i915_active_put(struct i915_active *ref)
+{
+	struct auto_active *aa = container_of(ref, typeof(*aa), base);
+
+	kref_put(&aa->ref, auto_release);
+}
+
+static int auto_active(struct i915_active *ref)
+{
+	i915_active_get(ref);
+	return 0;
+}
+
+static void auto_retire(struct i915_active *ref)
+{
+	i915_active_put(ref);
+}
+
+struct i915_active *i915_active_create(void)
+{
+	struct auto_active *aa;
+
+	aa = kmalloc(sizeof(*aa), GFP_KERNEL);
+	if (!aa)
+		return NULL;
+
+	kref_init(&aa->ref);
+	i915_active_init(&aa->base, auto_active, auto_retire);
+
+	return &aa->base;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/i915_active.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index b3282ae7913c..cf4058150966 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -181,7 +181,11 @@ static inline bool i915_active_has_exclusive(struct i915_active *ref)
 	return rcu_access_pointer(ref->excl.fence);
 }
 
-int i915_active_wait(struct i915_active *ref);
+int __i915_active_wait(struct i915_active *ref, int state);
+static inline int i915_active_wait(struct i915_active *ref)
+{
+	return __i915_active_wait(ref, TASK_INTERRUPTIBLE);
+}
 
 int i915_sw_fence_await_active(struct i915_sw_fence *fence,
 			       struct i915_active *ref,
@@ -189,7 +193,9 @@ int i915_sw_fence_await_active(struct i915_sw_fence *fence,
 int i915_request_await_active(struct i915_request *rq,
 			      struct i915_active *ref,
 			      unsigned int flags);
-#define I915_ACTIVE_AWAIT_ALL BIT(0)
+#define I915_ACTIVE_AWAIT_EXCL BIT(0)
+#define I915_ACTIVE_AWAIT_ACTIVE BIT(1)
+#define I915_ACTIVE_AWAIT_BARRIER BIT(2)
 
 int i915_active_acquire(struct i915_active *ref);
 bool i915_active_acquire_if_busy(struct i915_active *ref);
@@ -221,4 +227,8 @@ void i915_request_add_active_barriers(struct i915_request *rq);
 void i915_active_print(struct i915_active *ref, struct drm_printer *m);
 void i915_active_unlock_wait(struct i915_active *ref);
 
+struct i915_active *i915_active_create(void);
+struct i915_active *i915_active_get(struct i915_active *ref);
+void i915_active_put(struct i915_active *ref);
+
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_config.c b/drivers/gpu/drm/i915/i915_config.c
new file mode 100644
index 000000000000..b79b5f6d2cfa
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_config.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_drv.h"
+
+unsigned long
+i915_fence_context_timeout(const struct drm_i915_private *i915, u64 context)
+{
+	if (context && IS_ACTIVE(CONFIG_DRM_I915_FENCE_TIMEOUT))
+		return msecs_to_jiffies_timeout(CONFIG_DRM_I915_FENCE_TIMEOUT);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6ca797128aa1..bca036ac6621 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -32,12 +32,13 @@
 #include <drm/drm_debugfs.h>
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_gt_buffer_pool.h"
+#include "gt/intel_gt_clock_utils.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/intel_rps.h"
-#include "gt/uc/intel_guc_submission.h"
 
 #include "i915_debugfs.h"
 #include "i915_debugfs_params.h"
@@ -218,7 +219,7 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 struct file_stats {
 	struct i915_address_space *vm;
 	unsigned long count;
-	u64 total, unbound;
+	u64 total;
 	u64 active, inactive;
 	u64 closed;
 };
@@ -234,8 +235,6 @@ static int per_file_stats(int id, void *ptr, void *data)
 
 	stats->count++;
 	stats->total += obj->base.size;
-	if (!atomic_read(&obj->bind_count))
-		stats->unbound += obj->base.size;
 
 	spin_lock(&obj->vma.lock);
 	if (!stats->vm) {
@@ -285,13 +284,12 @@ static int per_file_stats(int id, void *ptr, void *data)
 
 #define print_file_stats(m, name, stats) do { \
 	if (stats.count) \
-		seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu unbound, %llu closed)\n", \
+		seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu closed)\n", \
 			   name, \
 			   stats.count, \
 			   stats.total, \
 			   stats.active, \
 			   stats.inactive, \
-			   stats.unbound, \
 			   stats.closed); \
 } while (0)
 
@@ -745,7 +743,7 @@ i915_error_state_write(struct file *filp,
 	if (!error)
 		return 0;
 
-	DRM_DEBUG_DRIVER("Resetting error state\n");
+	drm_dbg(&error->i915->drm, "Resetting error state\n");
 	i915_reset_error_state(error->i915);
 
 	return cnt;
@@ -930,21 +928,30 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
-		seq_printf(m, "RP CUR UP EI: %d (%dus)\n",
-			   rpupei, GT_PM_INTERVAL_TO_US(dev_priv, rpupei));
-		seq_printf(m, "RP CUR UP: %d (%dus)\n",
-			   rpcurup, GT_PM_INTERVAL_TO_US(dev_priv, rpcurup));
-		seq_printf(m, "RP PREV UP: %d (%dus)\n",
-			   rpprevup, GT_PM_INTERVAL_TO_US(dev_priv, rpprevup));
+		seq_printf(m, "RP CUR UP EI: %d (%dns)\n",
+			   rpupei,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpupei));
+		seq_printf(m, "RP CUR UP: %d (%dun)\n",
+			   rpcurup,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpcurup));
+		seq_printf(m, "RP PREV UP: %d (%dns)\n",
+			   rpprevup,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpprevup));
 		seq_printf(m, "Up threshold: %d%%\n",
 			   rps->power.up_threshold);
 
-		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
-			   rpdownei, GT_PM_INTERVAL_TO_US(dev_priv, rpdownei));
-		seq_printf(m, "RP CUR DOWN: %d (%dus)\n",
-			   rpcurdown, GT_PM_INTERVAL_TO_US(dev_priv, rpcurdown));
-		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
-			   rpprevdown, GT_PM_INTERVAL_TO_US(dev_priv, rpprevdown));
+		seq_printf(m, "RP CUR DOWN EI: %d (%dns)\n",
+			   rpdownei,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
+						      rpdownei));
+		seq_printf(m, "RP CUR DOWN: %d (%dns)\n",
+			   rpcurdown,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
+						      rpcurdown));
+		seq_printf(m, "RP PREV DOWN: %d (%dns)\n",
+			   rpprevdown,
+			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
+						      rpprevdown));
 		seq_printf(m, "Down threshold: %d%%\n",
 			   rps->power.down_threshold);
 
@@ -1193,7 +1200,8 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt.rps;
 
-	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
+	seq_printf(m, "RPS enabled? %s\n", yesno(intel_rps_is_enabled(rps)));
+	seq_printf(m, "RPS active? %s\n", yesno(intel_rps_is_active(rps)));
 	seq_printf(m, "GPU busy? %s\n", yesno(dev_priv->gt.awake));
 	seq_printf(m, "Boosts outstanding? %d\n",
 		   atomic_read(&rps->num_waiters));
@@ -1213,7 +1221,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 
 	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
 
-	if (INTEL_GEN(dev_priv) >= 6 && rps->enabled && dev_priv->gt.awake) {
+	if (INTEL_GEN(dev_priv) >= 6 && intel_rps_is_active(rps)) {
 		u32 rpup, rpupei;
 		u32 rpdown, rpdownei;
 
@@ -1251,286 +1259,6 @@ static int i915_llc(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int i915_huc_load_status_info(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	intel_wakeref_t wakeref;
-	struct drm_printer p;
-
-	if (!HAS_GT_UC(dev_priv))
-		return -ENODEV;
-
-	p = drm_seq_file_printer(m);
-	intel_uc_fw_dump(&dev_priv->gt.uc.huc.fw, &p);
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref)
-		seq_printf(m, "\nHuC status 0x%08x:\n", I915_READ(HUC_STATUS2));
-
-	return 0;
-}
-
-static int i915_guc_load_status_info(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	intel_wakeref_t wakeref;
-	struct drm_printer p;
-
-	if (!HAS_GT_UC(dev_priv))
-		return -ENODEV;
-
-	p = drm_seq_file_printer(m);
-	intel_uc_fw_dump(&dev_priv->gt.uc.guc.fw, &p);
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		u32 tmp = I915_READ(GUC_STATUS);
-		u32 i;
-
-		seq_printf(m, "\nGuC status 0x%08x:\n", tmp);
-		seq_printf(m, "\tBootrom status = 0x%x\n",
-			   (tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT);
-		seq_printf(m, "\tuKernel status = 0x%x\n",
-			   (tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT);
-		seq_printf(m, "\tMIA Core status = 0x%x\n",
-			   (tmp & GS_MIA_MASK) >> GS_MIA_SHIFT);
-		seq_puts(m, "\nScratch registers:\n");
-		for (i = 0; i < 16; i++) {
-			seq_printf(m, "\t%2d: \t0x%x\n",
-				   i, I915_READ(SOFT_SCRATCH(i)));
-		}
-	}
-
-	return 0;
-}
-
-static const char *
-stringify_guc_log_type(enum guc_log_buffer_type type)
-{
-	switch (type) {
-	case GUC_ISR_LOG_BUFFER:
-		return "ISR";
-	case GUC_DPC_LOG_BUFFER:
-		return "DPC";
-	case GUC_CRASH_DUMP_LOG_BUFFER:
-		return "CRASH";
-	default:
-		MISSING_CASE(type);
-	}
-
-	return "";
-}
-
-static void i915_guc_log_info(struct seq_file *m, struct intel_guc_log *log)
-{
-	enum guc_log_buffer_type type;
-
-	if (!intel_guc_log_relay_created(log)) {
-		seq_puts(m, "GuC log relay not created\n");
-		return;
-	}
-
-	seq_puts(m, "GuC logging stats:\n");
-
-	seq_printf(m, "\tRelay full count: %u\n",
-		   log->relay.full_count);
-
-	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
-		seq_printf(m, "\t%s:\tflush count %10u, overflow count %10u\n",
-			   stringify_guc_log_type(type),
-			   log->stats[type].flush,
-			   log->stats[type].sampled_overflow);
-	}
-}
-
-static int i915_guc_info(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct intel_uc *uc = &dev_priv->gt.uc;
-
-	if (!intel_uc_uses_guc(uc))
-		return -ENODEV;
-
-	i915_guc_log_info(m, &uc->guc.log);
-
-	/* Add more as required ... */
-
-	return 0;
-}
-
-static int i915_guc_stage_pool(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct intel_uc *uc = &dev_priv->gt.uc;
-	struct guc_stage_desc *desc = uc->guc.stage_desc_pool_vaddr;
-	int index;
-
-	if (!intel_uc_uses_guc_submission(uc))
-		return -ENODEV;
-
-	for (index = 0; index < GUC_MAX_STAGE_DESCRIPTORS; index++, desc++) {
-		struct intel_engine_cs *engine;
-
-		if (!(desc->attribute & GUC_STAGE_DESC_ATTR_ACTIVE))
-			continue;
-
-		seq_printf(m, "GuC stage descriptor %u:\n", index);
-		seq_printf(m, "\tIndex: %u\n", desc->stage_id);
-		seq_printf(m, "\tAttribute: 0x%x\n", desc->attribute);
-		seq_printf(m, "\tPriority: %d\n", desc->priority);
-		seq_printf(m, "\tDoorbell id: %d\n", desc->db_id);
-		seq_printf(m, "\tEngines used: 0x%x\n",
-			   desc->engines_used);
-		seq_printf(m, "\tDoorbell trigger phy: 0x%llx, cpu: 0x%llx, uK: 0x%x\n",
-			   desc->db_trigger_phy,
-			   desc->db_trigger_cpu,
-			   desc->db_trigger_uk);
-		seq_printf(m, "\tProcess descriptor: 0x%x\n",
-			   desc->process_desc);
-		seq_printf(m, "\tWorkqueue address: 0x%x, size: 0x%x\n",
-			   desc->wq_addr, desc->wq_size);
-		seq_putc(m, '\n');
-
-		for_each_uabi_engine(engine, dev_priv) {
-			u32 guc_engine_id = engine->guc_id;
-			struct guc_execlist_context *lrc =
-						&desc->lrc[guc_engine_id];
-
-			seq_printf(m, "\t%s LRC:\n", engine->name);
-			seq_printf(m, "\t\tContext desc: 0x%x\n",
-				   lrc->context_desc);
-			seq_printf(m, "\t\tContext id: 0x%x\n", lrc->context_id);
-			seq_printf(m, "\t\tLRCA: 0x%x\n", lrc->ring_lrca);
-			seq_printf(m, "\t\tRing begin: 0x%x\n", lrc->ring_begin);
-			seq_printf(m, "\t\tRing end: 0x%x\n", lrc->ring_end);
-			seq_putc(m, '\n');
-		}
-	}
-
-	return 0;
-}
-
-static int i915_guc_log_dump(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = m->private;
-	struct drm_i915_private *dev_priv = node_to_i915(node);
-	bool dump_load_err = !!node->info_ent->data;
-	struct drm_i915_gem_object *obj = NULL;
-	u32 *log;
-	int i = 0;
-
-	if (!HAS_GT_UC(dev_priv))
-		return -ENODEV;
-
-	if (dump_load_err)
-		obj = dev_priv->gt.uc.load_err_log;
-	else if (dev_priv->gt.uc.guc.log.vma)
-		obj = dev_priv->gt.uc.guc.log.vma->obj;
-
-	if (!obj)
-		return 0;
-
-	log = i915_gem_object_pin_map(obj, I915_MAP_WC);
-	if (IS_ERR(log)) {
-		DRM_DEBUG("Failed to pin object\n");
-		seq_puts(m, "(log data unaccessible)\n");
-		return PTR_ERR(log);
-	}
-
-	for (i = 0; i < obj->base.size / sizeof(u32); i += 4)
-		seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   *(log + i), *(log + i + 1),
-			   *(log + i + 2), *(log + i + 3));
-
-	seq_putc(m, '\n');
-
-	i915_gem_object_unpin_map(obj);
-
-	return 0;
-}
-
-static int i915_guc_log_level_get(void *data, u64 *val)
-{
-	struct drm_i915_private *dev_priv = data;
-	struct intel_uc *uc = &dev_priv->gt.uc;
-
-	if (!intel_uc_uses_guc(uc))
-		return -ENODEV;
-
-	*val = intel_guc_log_get_level(&uc->guc.log);
-
-	return 0;
-}
-
-static int i915_guc_log_level_set(void *data, u64 val)
-{
-	struct drm_i915_private *dev_priv = data;
-	struct intel_uc *uc = &dev_priv->gt.uc;
-
-	if (!intel_uc_uses_guc(uc))
-		return -ENODEV;
-
-	return intel_guc_log_set_level(&uc->guc.log, val);
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_level_fops,
-			i915_guc_log_level_get, i915_guc_log_level_set,
-			"%lld\n");
-
-static int i915_guc_log_relay_open(struct inode *inode, struct file *file)
-{
-	struct drm_i915_private *i915 = inode->i_private;
-	struct intel_guc *guc = &i915->gt.uc.guc;
-	struct intel_guc_log *log = &guc->log;
-
-	if (!intel_guc_is_ready(guc))
-		return -ENODEV;
-
-	file->private_data = log;
-
-	return intel_guc_log_relay_open(log);
-}
-
-static ssize_t
-i915_guc_log_relay_write(struct file *filp,
-			 const char __user *ubuf,
-			 size_t cnt,
-			 loff_t *ppos)
-{
-	struct intel_guc_log *log = filp->private_data;
-	int val;
-	int ret;
-
-	ret = kstrtoint_from_user(ubuf, cnt, 0, &val);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * Enable and start the guc log relay on value of 1.
-	 * Flush log relay for any other value.
-	 */
-	if (val == 1)
-		ret = intel_guc_log_relay_start(log);
-	else
-		intel_guc_log_relay_flush(log);
-
-	return ret ?: cnt;
-}
-
-static int i915_guc_log_relay_release(struct inode *inode, struct file *file)
-{
-	struct drm_i915_private *i915 = inode->i_private;
-	struct intel_guc *guc = &i915->gt.uc.guc;
-
-	intel_guc_log_relay_close(&guc->log);
-	return 0;
-}
-
-static const struct file_operations i915_guc_log_relay_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_guc_log_relay_open,
-	.write = i915_guc_log_relay_write,
-	.release = i915_guc_log_relay_release,
-};
-
 static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -1576,8 +1304,8 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 	seq_printf(m, "GT awake? %s [%d]\n",
 		   yesno(dev_priv->gt.awake),
 		   atomic_read(&dev_priv->gt.wakeref.count));
-	seq_printf(m, "CS timestamp frequency: %u kHz\n",
-		   RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz);
+	seq_printf(m, "CS timestamp frequency: %u Hz\n",
+		   RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_hz);
 
 	p = drm_seq_file_printer(m);
 	for_each_uabi_engine(engine, dev_priv)
@@ -1676,13 +1404,12 @@ 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))
+	if (i915_cs_timestamp_ns_to_ticks(i915, val) > U32_MAX)
 		return -EINVAL;
 
 	atomic64_set(&i915->perf.noa_programming_delay, val);
@@ -1757,6 +1484,9 @@ gt_drop_caches(struct intel_gt *gt, u64 val)
 	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(gt))
 		intel_gt_handle_error(gt, ALL_ENGINES, 0, NULL);
 
+	if (val & DROP_FREED)
+		intel_gt_flush_buffer_pool(gt);
+
 	return 0;
 }
 
@@ -2139,12 +1869,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_objects", i915_gem_object_info, 0},
 	{"i915_gem_fence_regs", i915_gem_fence_regs_info, 0},
 	{"i915_gem_interrupt", i915_interrupt_info, 0},
-	{"i915_guc_info", i915_guc_info, 0},
-	{"i915_guc_load_status", i915_guc_load_status_info, 0},
-	{"i915_guc_log_dump", i915_guc_log_dump, 0},
-	{"i915_guc_load_err_log_dump", i915_guc_log_dump, 0, (void *)1},
-	{"i915_guc_stage_pool", i915_guc_stage_pool, 0},
-	{"i915_huc_load_status", i915_huc_load_status_info, 0},
 	{"i915_frequency_info", i915_frequency_info, 0},
 	{"i915_ring_freq_table", i915_ring_freq_table, 0},
 	{"i915_context_status", i915_context_status, 0},
@@ -2172,11 +1896,9 @@ static const struct i915_debugfs_files {
 	{"i915_error_state", &i915_error_state_fops},
 	{"i915_gpu_info", &i915_gpu_info_fops},
 #endif
-	{"i915_guc_log_level", &i915_guc_log_level_fops},
-	{"i915_guc_log_relay", &i915_guc_log_relay_fops},
 };
 
-int i915_debugfs_register(struct drm_i915_private *dev_priv)
+void i915_debugfs_register(struct drm_i915_private *dev_priv)
 {
 	struct drm_minor *minor = dev_priv->drm.primary;
 	int i;
@@ -2193,7 +1915,7 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 				    i915_debugfs_files[i].fops);
 	}
 
-	return drm_debugfs_create_files(i915_debugfs_list,
-					I915_DEBUGFS_ENTRIES,
-					minor->debugfs_root, minor);
+	drm_debugfs_create_files(i915_debugfs_list,
+				 I915_DEBUGFS_ENTRIES,
+				 minor->debugfs_root, minor);
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.h b/drivers/gpu/drm/i915/i915_debugfs.h
index 6da39c76ab5e..1de2736f1248 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.h
+++ b/drivers/gpu/drm/i915/i915_debugfs.h
@@ -12,10 +12,10 @@ struct drm_i915_private;
 struct seq_file;
 
 #ifdef CONFIG_DEBUG_FS
-int i915_debugfs_register(struct drm_i915_private *dev_priv);
+void i915_debugfs_register(struct drm_i915_private *dev_priv);
 void i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj);
 #else
-static inline int i915_debugfs_register(struct drm_i915_private *dev_priv) { return 0; }
+static inline void i915_debugfs_register(struct drm_i915_private *dev_priv) {}
 static inline void i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) {}
 #endif
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 81a4621853db..34ee12f3f02d 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -43,6 +43,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
+#include <drm/drm_managed.h>
 #include <drm/drm_probe_helper.h>
 
 #include "display/intel_acpi.h"
@@ -227,14 +228,14 @@ static int i915_driver_modeset_probe_noirq(struct drm_i915_private *i915)
 		ret = drm_vblank_init(&i915->drm,
 				      INTEL_NUM_PIPES(i915));
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	intel_bios_init(i915);
 
 	ret = intel_vga_register(i915);
 	if (ret)
-		goto out;
+		goto cleanup_bios;
 
 	intel_power_domains_init_hw(i915, false);
 
@@ -242,13 +243,16 @@ static int i915_driver_modeset_probe_noirq(struct drm_i915_private *i915)
 
 	ret = intel_modeset_init_noirq(i915);
 	if (ret)
-		goto cleanup_vga_client;
+		goto cleanup_vga_client_pw_domain_csr;
 
 	return 0;
 
-cleanup_vga_client:
+cleanup_vga_client_pw_domain_csr:
+	intel_csr_ucode_fini(i915);
+	intel_power_domains_driver_remove(i915);
 	intel_vga_unregister(i915);
-out:
+cleanup_bios:
+	intel_bios_driver_remove(i915);
 	return ret;
 }
 
@@ -307,13 +311,13 @@ static void i915_driver_modeset_remove(struct drm_i915_private *i915)
 /* part #2: call after irq uninstall */
 static void i915_driver_modeset_remove_noirq(struct drm_i915_private *i915)
 {
-	intel_modeset_driver_remove_noirq(i915);
+	intel_csr_ucode_fini(i915);
 
-	intel_bios_driver_remove(i915);
+	intel_power_domains_driver_remove(i915);
 
 	intel_vga_unregister(i915);
 
-	intel_csr_ucode_fini(i915);
+	intel_bios_driver_remove(i915);
 }
 
 static void intel_init_dpio(struct drm_i915_private *dev_priv)
@@ -566,6 +570,62 @@ static void intel_sanitize_options(struct drm_i915_private *dev_priv)
 }
 
 /**
+ * i915_set_dma_info - set all relevant PCI dma info as configured for the
+ * platform
+ * @i915: valid i915 instance
+ *
+ * Set the dma max segment size, device and coherent masks.  The dma mask set
+ * needs to occur before i915_ggtt_probe_hw.
+ *
+ * A couple of platforms have special needs.  Address them as well.
+ *
+ */
+static int i915_set_dma_info(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+	unsigned int mask_size = INTEL_INFO(i915)->dma_mask_size;
+	int ret;
+
+	GEM_BUG_ON(!mask_size);
+
+	/*
+	 * 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);
+
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(mask_size));
+	if (ret)
+		goto mask_err;
+
+	/* overlay on gen2 is broken and can't address above 1G */
+	if (IS_GEN(i915, 2))
+		mask_size = 30;
+
+	/*
+	 * 965GM sometimes incorrectly writes to hardware status page (HWS)
+	 * using 32bit addressing, overwriting memory if HWS is located
+	 * above 4GB.
+	 *
+	 * The documentation also mentions an issue with undefined
+	 * behaviour if any general state is accessed within a page above 4GB,
+	 * which also needs to be handled carefully.
+	 */
+	if (IS_I965G(i915) || IS_I965GM(i915))
+		mask_size = 32;
+
+	ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(mask_size));
+	if (ret)
+		goto mask_err;
+
+	return 0;
+
+mask_err:
+	drm_err(&i915->drm, "Can't set DMA mask/consistent mask (%d)\n", ret);
+	return ret;
+}
+
+/**
  * i915_driver_hw_probe - setup state requiring device access
  * @dev_priv: device private
  *
@@ -610,6 +670,10 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	/* needs to be done before ggtt probe */
 	intel_dram_edram_detect(dev_priv);
 
+	ret = i915_set_dma_info(dev_priv);
+	if (ret)
+		return ret;
+
 	i915_perf_init(dev_priv);
 
 	ret = i915_ggtt_probe_hw(dev_priv);
@@ -638,40 +702,6 @@ 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));
-		if (ret) {
-			drm_err(&dev_priv->drm, "failed to set DMA mask\n");
-
-			goto err_mem_regions;
-		}
-	}
-
-	/* 965GM sometimes incorrectly writes to hardware status page (HWS)
-	 * using 32bit addressing, overwriting memory if HWS is located
-	 * above 4GB.
-	 *
-	 * The documentation also mentions an issue with undefined
-	 * behaviour if any general state is accessed within a page above 4GB,
-	 * which also needs to be handled carefully.
-	 */
-	if (IS_I965G(dev_priv) || IS_I965GM(dev_priv)) {
-		ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
-
-		if (ret) {
-			drm_err(&dev_priv->drm, "failed to set DMA mask\n");
-
-			goto err_mem_regions;
-		}
-	}
-
 	cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	intel_gt_init_workarounds(dev_priv);
@@ -876,17 +906,11 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent)
 		(struct intel_device_info *)ent->driver_data;
 	struct intel_device_info *device_info;
 	struct drm_i915_private *i915;
-	int err;
-
-	i915 = kzalloc(sizeof(*i915), GFP_KERNEL);
-	if (!i915)
-		return ERR_PTR(-ENOMEM);
 
-	err = drm_dev_init(&i915->drm, &driver, &pdev->dev);
-	if (err) {
-		kfree(i915);
-		return ERR_PTR(err);
-	}
+	i915 = devm_drm_dev_alloc(&pdev->dev, &driver,
+				  struct drm_i915_private, drm);
+	if (IS_ERR(i915))
+		return i915;
 
 	i915->drm.pdev = pdev;
 	pci_set_drvdata(pdev, i915);
@@ -901,17 +925,6 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return i915;
 }
 
-static void i915_driver_destroy(struct drm_i915_private *i915)
-{
-	struct pci_dev *pdev = i915->drm.pdev;
-
-	drm_dev_fini(&i915->drm);
-	kfree(i915);
-
-	/* And make sure we never chase our dangling pointer from pci_dev */
-	pci_set_drvdata(pdev, NULL);
-}
-
 /**
  * i915_driver_probe - setup chip and create an initial config
  * @pdev: PCI device
@@ -993,12 +1006,14 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	i915_welcome_messages(i915);
 
+	i915->do_release = true;
+
 	return 0;
 
 out_cleanup_irq:
 	intel_irq_uninstall(i915);
 out_cleanup_modeset:
-	/* FIXME */
+	i915_driver_modeset_remove_noirq(i915);
 out_cleanup_hw:
 	i915_driver_hw_remove(i915);
 	intel_memory_regions_driver_release(i915);
@@ -1012,7 +1027,6 @@ out_pci_disable:
 	pci_disable_device(pdev);
 out_fini:
 	i915_probe_error(i915, "Device initialization failed (%d)\n", ret);
-	i915_driver_destroy(i915);
 	return ret;
 }
 
@@ -1035,12 +1049,12 @@ void i915_driver_remove(struct drm_i915_private *i915)
 
 	intel_irq_uninstall(i915);
 
-	i915_driver_modeset_remove_noirq(i915);
+	intel_modeset_driver_remove_noirq(i915);
 
 	i915_reset_error_state(i915);
 	i915_gem_driver_remove(i915);
 
-	intel_power_domains_driver_remove(i915);
+	i915_driver_modeset_remove_noirq(i915);
 
 	i915_driver_hw_remove(i915);
 
@@ -1052,6 +1066,9 @@ static void i915_driver_release(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_runtime_pm *rpm = &dev_priv->runtime_pm;
 
+	if (!dev_priv->do_release)
+		return;
+
 	disable_rpm_wakeref_asserts(rpm);
 
 	i915_gem_driver_release(dev_priv);
@@ -1065,7 +1082,6 @@ static void i915_driver_release(struct drm_device *dev)
 	intel_runtime_pm_driver_release(rpm);
 
 	i915_driver_late_release(dev_priv);
-	i915_driver_destroy(dev_priv);
 }
 
 static int i915_driver_open(struct drm_device *dev, struct drm_file *file)
@@ -1286,7 +1302,6 @@ static int i915_drm_resume(struct drm_device *dev)
 		drm_err(&dev_priv->drm, "failed to re-enable GGTT\n");
 
 	i915_ggtt_resume(&dev_priv->ggtt);
-	i915_gem_restore_fences(&dev_priv->ggtt);
 
 	intel_csr_ucode_resume(dev_priv);
 
@@ -1604,8 +1619,6 @@ static int intel_runtime_suspend(struct device *kdev)
 
 		intel_gt_runtime_resume(&dev_priv->gt);
 
-		i915_gem_restore_fences(&dev_priv->ggtt);
-
 		enable_rpm_wakeref_asserts(rpm);
 
 		return ret;
@@ -1685,7 +1698,6 @@ 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->ggtt);
 
 	/*
 	 * On VLV/CHV display interrupts are part of the display
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 62b901ffabf9..adb9bf34cf97 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -92,7 +92,6 @@
 #include "intel_wopcm.h"
 
 #include "i915_gem.h"
-#include "i915_gem_fence_reg.h"
 #include "i915_gem_gtt.h"
 #include "i915_gpu_error.h"
 #include "i915_perf_types.h"
@@ -109,8 +108,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20200313"
-#define DRIVER_TIMESTAMP	1584144591
+#define DRIVER_DATE		"20200515"
+#define DRIVER_TIMESTAMP	1589543364
 
 struct drm_i915_gem_object;
 
@@ -149,6 +148,8 @@ enum hpd_pin {
 struct i915_hotplug {
 	struct delayed_work hotplug_work;
 
+	const u32 *hpd, *pch_hpd;
+
 	struct {
 		unsigned long last_jiffies;
 		int count;
@@ -417,6 +418,7 @@ struct intel_fbc {
 		struct {
 			const struct drm_format_info *format;
 			unsigned int stride;
+			u64 modifier;
 		} fb;
 		u16 gen9_wa_cfb_stride;
 		s8 fence_id;
@@ -510,6 +512,7 @@ struct i915_psr {
 	u32 dc3co_exit_delay;
 	struct delayed_work dc3co_work;
 	bool force_mode_changed;
+	struct drm_dp_vsc_sdp vsc;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
@@ -540,7 +543,6 @@ struct i915_suspend_saved_registers {
 	u32 saveSWF0[16];
 	u32 saveSWF1[16];
 	u32 saveSWF3[3];
-	u64 saveFENCE[I915_MAX_NUM_FENCES];
 	u32 savePCH_PORT_HOTPLUG;
 	u16 saveGCDGMBUS;
 };
@@ -615,13 +617,14 @@ struct i915_gem_mm {
 
 #define I915_IDLE_ENGINES_TIMEOUT (200) /* in ms */
 
-#define I915_RESET_TIMEOUT (10 * HZ) /* 10s */
-#define I915_FENCE_TIMEOUT (10 * HZ) /* 10s */
-
-#define I915_ENGINE_DEAD_TIMEOUT  (4 * HZ)  /* Seqno, head and subunits dead */
-#define I915_SEQNO_DEAD_TIMEOUT   (12 * HZ) /* Seqno dead with active head */
+unsigned long i915_fence_context_timeout(const struct drm_i915_private *i915,
+					 u64 context);
 
-#define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
+static inline unsigned long
+i915_fence_timeout(const struct drm_i915_private *i915)
+{
+	return i915_fence_context_timeout(i915, U64_MAX);
+}
 
 /* Amount of SAGV/QGV points, BSpec precisely defines this */
 #define I915_NUM_QGV_POINTS 8
@@ -823,6 +826,9 @@ struct i915_selftest_stash {
 struct drm_i915_private {
 	struct drm_device drm;
 
+	/* FIXME: Device release actions should all be moved to drmm_ */
+	bool do_release;
+
 	const struct intel_device_info __info; /* Use INTEL_INFO() to access. */
 	struct intel_runtime_info __runtime; /* Use RUNTIME_INFO() to access. */
 	struct intel_driver_caps caps;
@@ -885,7 +891,6 @@ struct drm_i915_private {
 
 	struct pci_dev *bridge_dev;
 
-	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct rb_root uabi_engines;
 
 	struct resource mch_res;
@@ -1506,6 +1511,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_ICL_REVID(p, since, until) \
 	(IS_ICELAKE(p) && IS_REVID(p, since, until))
 
+#define EHL_REVID_A0            0x0
+
+#define IS_EHL_REVID(p, since, until) \
+	(IS_ELKHARTLAKE(p) && IS_REVID(p, since, until))
+
 #define TGL_REVID_A0		0x0
 #define TGL_REVID_B0		0x1
 #define TGL_REVID_C0		0x2
@@ -1606,7 +1616,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_DDI(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ddi)
 #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->has_fpga_dbg)
 #define HAS_PSR(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_psr)
-#define HAS_TRANSCODER_EDP(dev_priv)	 (INTEL_INFO(dev_priv)->trans_offsets[TRANSCODER_EDP] != 0)
+#define HAS_TRANSCODER(dev_priv, trans)	 ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0)
 
 #define HAS_RC6(dev_priv)		 (INTEL_INFO(dev_priv)->has_rc6)
 #define HAS_RC6p(dev_priv)		 (INTEL_INFO(dev_priv)->has_rc6p)
@@ -1740,6 +1750,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
 #define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1)
+#define I915_GEM_OBJECT_UNBIND_TEST BIT(2)
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
@@ -1913,4 +1924,16 @@ i915_coherent_map_type(struct drm_i915_private *i915)
 	return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
 }
 
+static inline u64 i915_cs_timestamp_ns_to_ticks(struct drm_i915_private *i915, u64 val)
+{
+	return DIV_ROUND_UP_ULL(val * RUNTIME_INFO(i915)->cs_timestamp_frequency_hz,
+				1000000000);
+}
+
+static inline u64 i915_cs_timestamp_ticks_to_ns(struct drm_i915_private *i915, u64 val)
+{
+	return div_u64(val * 1000000000,
+		       RUNTIME_INFO(i915)->cs_timestamp_frequency_hz);
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ca5420012a22..0cbcb9f54e7d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -118,7 +118,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 	struct i915_vma *vma;
 	int ret;
 
-	if (!atomic_read(&obj->bind_count))
+	if (list_empty(&obj->vma.list))
 		return 0;
 
 	/*
@@ -141,6 +141,11 @@ try_again:
 		if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
 			continue;
 
+		if (flags & I915_GEM_OBJECT_UNBIND_TEST) {
+			ret = -EBUSY;
+			break;
+		}
+
 		ret = -EAGAIN;
 		if (!i915_vm_tryopen(vm))
 			break;
@@ -993,18 +998,16 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
+	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	if (ret)
+		return ERR_PTR(ret);
+
 	if (vma->fence && !i915_gem_object_is_tiled(obj)) {
 		mutex_lock(&ggtt->vm.mutex);
-		ret = i915_vma_revoke_fence(vma);
+		i915_vma_revoke_fence(vma);
 		mutex_unlock(&ggtt->vm.mutex);
-		if (ret)
-			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
-	if (ret)
-		return ERR_PTR(ret);
-
 	ret = i915_vma_wait_for_bind(vma);
 	if (ret) {
 		i915_vma_unpin(vma);
@@ -1156,7 +1159,6 @@ err_unlock:
 		/* Minimal basic recovery for KMS */
 		ret = i915_ggtt_enable_hw(dev_priv);
 		i915_ggtt_resume(&dev_priv->ggtt);
-		i915_gem_restore_fences(&dev_priv->ggtt);
 		intel_init_clock_gating(dev_priv);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 02ad1acd117c..6501939929d5 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -226,7 +226,12 @@ found:
 
 	while (ret == 0 && (node = drm_mm_scan_color_evict(&scan))) {
 		vma = container_of(node, struct i915_vma, node);
-		ret = __i915_vma_unbind(vma);
+
+		/* If we find any non-objects (!vma), we cannot evict them */
+		if (vma->node.color != I915_COLOR_UNEVICTABLE)
+			ret = __i915_vma_unbind(vma);
+		else
+			ret = -ENOSPC; /* XXX search failed, try again? */
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 54fce81d5724..d042644b9cd2 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -153,7 +153,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			return -ENODEV;
 		break;
 	case I915_PARAM_CS_TIMESTAMP_FREQUENCY:
-		value = 1000 * RUNTIME_INFO(i915)->cs_timestamp_frequency_khz;
+		value = RUNTIME_INFO(i915)->cs_timestamp_frequency_hz;
 		break;
 	case I915_PARAM_MMAP_GTT_COHERENT:
 		value = INTEL_INFO(i915)->has_coherent_ggtt;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 5c8e51d2ba5b..eec292d06f11 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -467,14 +467,14 @@ static void error_print_request(struct drm_i915_error_state_buf *m,
 	if (!erq->seqno)
 		return;
 
-	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, start %08x, head %08x, tail %08x\n",
+	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, head %08x, tail %08x\n",
 		   prefix, erq->pid, erq->context, erq->seqno,
 		   test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 			    &erq->flags) ? "!" : "",
 		   test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			    &erq->flags) ? "+" : "",
 		   erq->sched_attr.priority,
-		   erq->start, erq->head, erq->tail);
+		   erq->head, erq->tail);
 }
 
 static void error_print_context(struct drm_i915_error_state_buf *m,
@@ -1211,7 +1211,6 @@ static void record_request(const struct i915_request *request,
 	erq->context = request->fence.context;
 	erq->seqno = request->fence.seqno;
 	erq->sched_attr = request->sched.attr;
-	erq->start = i915_ggtt_offset(request->ring->vma);
 	erq->head = request->head;
 	erq->tail = request->tail;
 
@@ -1321,26 +1320,6 @@ capture_user(struct intel_engine_capture_vma *capture,
 	return capture;
 }
 
-static struct i915_vma_coredump *
-capture_object(const struct intel_gt *gt,
-	       struct drm_i915_gem_object *obj,
-	       const char *name,
-	       struct i915_vma_compress *compress)
-{
-	if (obj && i915_gem_object_has_pages(obj)) {
-		struct i915_vma fake = {
-			.node = { .start = U64_MAX, .size = obj->base.size },
-			.size = obj->base.size,
-			.pages = obj->mm.pages,
-			.obj = obj,
-		};
-
-		return i915_vma_coredump_create(gt, &fake, name, compress);
-	} else {
-		return NULL;
-	}
-}
-
 static void add_vma(struct intel_engine_coredump *ee,
 		    struct i915_vma_coredump *vma)
 {
@@ -1429,12 +1408,6 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
 					 engine->wa_ctx.vma,
 					 "WA context",
 					 compress));
-
-	add_vma(ee,
-		capture_object(engine->gt,
-			       engine->default_state,
-			       "NULL context",
-			       compress));
 }
 
 static struct intel_engine_coredump *
@@ -1860,7 +1833,7 @@ void i915_error_state_store(struct i915_gpu_coredump *error)
 		return;
 
 	i915 = error->i915;
-	dev_info(i915->drm.dev, "%s\n", error_msg(error));
+	drm_info(&i915->drm, "%s\n", error_msg(error));
 
 	if (error->simulated ||
 	    cmpxchg(&i915->gpu_error.first_error, NULL, error))
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 0d1f6c8ff355..76b80fbfb7e9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -42,7 +42,7 @@ struct i915_vma_coredump {
 	int num_pages;
 	int page_count;
 	int unused;
-	u32 *pages[0];
+	u32 *pages[];
 };
 
 struct i915_request_coredump {
@@ -50,7 +50,6 @@ struct i915_request_coredump {
 	pid_t pid;
 	u32 context;
 	u32 seqno;
-	u32 start;
 	u32 head;
 	u32 tail;
 	struct i915_sched_attr sched_attr;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8a2b83807ffc..4dc601dffc08 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -124,7 +124,6 @@ static const u32 hpd_status_i915[HPD_NUM_PINS] = {
 	[HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS,
 };
 
-/* BXT hpd list */
 static const u32 hpd_bxt[HPD_NUM_PINS] = {
 	[HPD_PORT_A] = BXT_DE_PORT_HP_DDIA,
 	[HPD_PORT_B] = BXT_DE_PORT_HP_DDIB,
@@ -168,6 +167,49 @@ static const u32 hpd_tgp[HPD_NUM_PINS] = {
 	[HPD_PORT_I] = SDE_TC_HOTPLUG_ICP(PORT_TC6),
 };
 
+static void intel_hpd_init_pins(struct drm_i915_private *dev_priv)
+{
+	struct i915_hotplug *hpd = &dev_priv->hotplug;
+
+	if (HAS_GMCH(dev_priv)) {
+		if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) ||
+		    IS_CHERRYVIEW(dev_priv))
+			hpd->hpd = hpd_status_g4x;
+		else
+			hpd->hpd = hpd_status_i915;
+		return;
+	}
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		hpd->hpd = hpd_gen12;
+	else if (INTEL_GEN(dev_priv) >= 11)
+		hpd->hpd = hpd_gen11;
+	else if (IS_GEN9_LP(dev_priv))
+		hpd->hpd = hpd_bxt;
+	else if (INTEL_GEN(dev_priv) >= 8)
+		hpd->hpd = hpd_bdw;
+	else if (INTEL_GEN(dev_priv) >= 7)
+		hpd->hpd = hpd_ivb;
+	else
+		hpd->hpd = hpd_ilk;
+
+	if (!HAS_PCH_SPLIT(dev_priv) || HAS_PCH_NOP(dev_priv))
+		return;
+
+	if (HAS_PCH_TGP(dev_priv) || HAS_PCH_JSP(dev_priv))
+		hpd->pch_hpd = hpd_tgp;
+	else if (HAS_PCH_ICP(dev_priv) || HAS_PCH_MCC(dev_priv))
+		hpd->pch_hpd = hpd_icp;
+	else if (HAS_PCH_CNP(dev_priv) || HAS_PCH_SPT(dev_priv))
+		hpd->pch_hpd = hpd_spt;
+	else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_CPT(dev_priv))
+		hpd->pch_hpd = hpd_cpt;
+	else if (HAS_PCH_IBX(dev_priv))
+		hpd->pch_hpd = hpd_ibx;
+	else
+		MISSING_CASE(INTEL_PCH_TYPE(dev_priv));
+}
+
 static void
 intel_handle_vblank(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
@@ -1504,33 +1546,27 @@ static void i9xx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 				 u32 hotplug_status)
 {
 	u32 pin_mask = 0, long_mask = 0;
+	u32 hotplug_trigger;
 
-	if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) ||
-	    IS_CHERRYVIEW(dev_priv)) {
-		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
-
-		if (hotplug_trigger) {
-			intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-					   hotplug_trigger, hotplug_trigger,
-					   hpd_status_g4x,
-					   i9xx_port_hotplug_long_detect);
+	if (IS_G4X(dev_priv) ||
+	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
+	else
+		hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
 
-			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
-		}
+	if (hotplug_trigger) {
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   hotplug_trigger, hotplug_trigger,
+				   dev_priv->hotplug.hpd,
+				   i9xx_port_hotplug_long_detect);
 
-		if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
-			dp_aux_irq_handler(dev_priv);
-	} else {
-		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
-
-		if (hotplug_trigger) {
-			intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-					   hotplug_trigger, hotplug_trigger,
-					   hpd_status_i915,
-					   i9xx_port_hotplug_long_detect);
-			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
-		}
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 	}
+
+	if ((IS_G4X(dev_priv) ||
+	     IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
+		dp_aux_irq_handler(dev_priv);
 }
 
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
@@ -1696,8 +1732,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 }
 
 static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv,
-				u32 hotplug_trigger,
-				const u32 hpd[HPD_NUM_PINS])
+				u32 hotplug_trigger)
 {
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
@@ -1720,8 +1755,9 @@ static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	if (!hotplug_trigger)
 		return;
 
-	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
-			   dig_hotplug_reg, hpd,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+			   hotplug_trigger, dig_hotplug_reg,
+			   dev_priv->hotplug.pch_hpd,
 			   pch_port_hotplug_long_detect);
 
 	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
@@ -1732,7 +1768,7 @@ static void ibx_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	enum pipe pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK;
 
-	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ibx);
+	ibx_hpd_irq_handler(dev_priv, hotplug_trigger);
 
 	if (pch_iir & SDE_AUDIO_POWER_MASK) {
 		int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK) >>
@@ -1820,7 +1856,7 @@ static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	enum pipe pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
 
-	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_cpt);
+	ibx_hpd_irq_handler(dev_priv, hotplug_trigger);
 
 	if (pch_iir & SDE_AUDIO_POWER_MASK_CPT) {
 		int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
@@ -1857,22 +1893,18 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	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_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_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 {
 		drm_WARN(&dev_priv->drm, !HAS_PCH_ICP(dev_priv),
 			 "Unrecognized PCH type 0x%x\n",
@@ -1881,7 +1913,6 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		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) {
@@ -1891,8 +1922,8 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		I915_WRITE(SHOTPLUG_CTL_DDI, dig_hotplug_reg);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   ddi_hotplug_trigger,
-				   dig_hotplug_reg, pins,
+				   ddi_hotplug_trigger, dig_hotplug_reg,
+				   dev_priv->hotplug.pch_hpd,
 				   icp_ddi_port_hotplug_long_detect);
 	}
 
@@ -1903,8 +1934,8 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		I915_WRITE(SHOTPLUG_CTL_TC, dig_hotplug_reg);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   tc_hotplug_trigger,
-				   dig_hotplug_reg, pins,
+				   tc_hotplug_trigger, dig_hotplug_reg,
+				   dev_priv->hotplug.pch_hpd,
 				   tc_port_hotplug_long_detect);
 	}
 
@@ -1929,7 +1960,8 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   hotplug_trigger, dig_hotplug_reg, hpd_spt,
+				   hotplug_trigger, dig_hotplug_reg,
+				   dev_priv->hotplug.pch_hpd,
 				   spt_port_hotplug_long_detect);
 	}
 
@@ -1940,7 +1972,8 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		I915_WRITE(PCH_PORT_HOTPLUG2, dig_hotplug_reg);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   hotplug2_trigger, dig_hotplug_reg, hpd_spt,
+				   hotplug2_trigger, dig_hotplug_reg,
+				   dev_priv->hotplug.pch_hpd,
 				   spt_port_hotplug2_long_detect);
 	}
 
@@ -1952,16 +1985,16 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 }
 
 static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv,
-				u32 hotplug_trigger,
-				const u32 hpd[HPD_NUM_PINS])
+				u32 hotplug_trigger)
 {
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
 	dig_hotplug_reg = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL);
 	I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg);
 
-	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
-			   dig_hotplug_reg, hpd,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+			   hotplug_trigger, dig_hotplug_reg,
+			   dev_priv->hotplug.hpd,
 			   ilk_port_hotplug_long_detect);
 
 	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
@@ -1974,7 +2007,7 @@ static void ilk_display_irq_handler(struct drm_i915_private *dev_priv,
 	u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG;
 
 	if (hotplug_trigger)
-		ilk_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ilk);
+		ilk_hpd_irq_handler(dev_priv, hotplug_trigger);
 
 	if (de_iir & DE_AUX_CHANNEL_A)
 		dp_aux_irq_handler(dev_priv);
@@ -2020,7 +2053,7 @@ static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
 	u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG_IVB;
 
 	if (hotplug_trigger)
-		ilk_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ivb);
+		ilk_hpd_irq_handler(dev_priv, hotplug_trigger);
 
 	if (de_iir & DE_ERR_INT_IVB)
 		ivb_err_int_handler(dev_priv);
@@ -2130,16 +2163,16 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 }
 
 static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
-				u32 hotplug_trigger,
-				const u32 hpd[HPD_NUM_PINS])
+				u32 hotplug_trigger)
 {
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
 	dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
 	I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
 
-	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
-			   dig_hotplug_reg, hpd,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+			   hotplug_trigger, dig_hotplug_reg,
+			   dev_priv->hotplug.hpd,
 			   bxt_port_hotplug_long_detect);
 
 	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
@@ -2151,15 +2184,11 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 	u32 trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK;
 	u32 trigger_tbt = iir & GEN11_DE_TBT_HOTPLUG_MASK;
 	long_pulse_detect_func long_pulse_detect;
-	const u32 *hpd;
 
-	if (INTEL_GEN(dev_priv) >= 12) {
+	if (INTEL_GEN(dev_priv) >= 12)
 		long_pulse_detect = gen12_port_hotplug_long_detect;
-		hpd = hpd_gen12;
-	} else {
+	else
 		long_pulse_detect = gen11_port_hotplug_long_detect;
-		hpd = hpd_gen11;
-	}
 
 	if (trigger_tc) {
 		u32 dig_hotplug_reg;
@@ -2167,8 +2196,10 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 		dig_hotplug_reg = I915_READ(GEN11_TC_HOTPLUG_CTL);
 		I915_WRITE(GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg);
 
-		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc,
-				   dig_hotplug_reg, hpd, long_pulse_detect);
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   trigger_tc, dig_hotplug_reg,
+				   dev_priv->hotplug.hpd,
+				   long_pulse_detect);
 	}
 
 	if (trigger_tbt) {
@@ -2177,8 +2208,10 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 		dig_hotplug_reg = I915_READ(GEN11_TBT_HOTPLUG_CTL);
 		I915_WRITE(GEN11_TBT_HOTPLUG_CTL, dig_hotplug_reg);
 
-		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt,
-				   dig_hotplug_reg, hpd, long_pulse_detect);
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   trigger_tbt, dig_hotplug_reg,
+				   dev_priv->hotplug.hpd,
+				   long_pulse_detect);
 	}
 
 	if (pin_mask)
@@ -2309,15 +2342,13 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			if (IS_GEN9_LP(dev_priv)) {
 				tmp_mask = iir & BXT_DE_PORT_HOTPLUG_MASK;
 				if (tmp_mask) {
-					bxt_hpd_irq_handler(dev_priv, tmp_mask,
-							    hpd_bxt);
+					bxt_hpd_irq_handler(dev_priv, tmp_mask);
 					found = true;
 				}
 			} else if (IS_BROADWELL(dev_priv)) {
 				tmp_mask = iir & GEN8_PORT_DP_A_HOTPLUG;
 				if (tmp_mask) {
-					ilk_hpd_irq_handler(dev_priv,
-							    tmp_mask, hpd_bdw);
+					ilk_hpd_irq_handler(dev_priv, tmp_mask);
 					found = true;
 				}
 			}
@@ -2870,6 +2901,14 @@ static void gen11_display_irq_reset(struct drm_i915_private *dev_priv)
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		GEN3_IRQ_RESET(uncore, SDE);
+
+	/* Wa_14010685332:icl */
+	if (INTEL_PCH_TYPE(dev_priv) == PCH_ICP) {
+		intel_uncore_rmw(uncore, SOUTH_CHICKEN1,
+				 SBCLK_RUN_REFCLK_DIS, SBCLK_RUN_REFCLK_DIS);
+		intel_uncore_rmw(uncore, SOUTH_CHICKEN1,
+				 SBCLK_RUN_REFCLK_DIS, 0);
+	}
 }
 
 static void gen11_irq_reset(struct drm_i915_private *dev_priv)
@@ -2989,13 +3028,12 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
-	if (HAS_PCH_IBX(dev_priv)) {
+	if (HAS_PCH_IBX(dev_priv))
 		hotplug_irqs = SDE_HOTPLUG_MASK;
-		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ibx);
-	} else {
+	else
 		hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
-		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_cpt);
-	}
+
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd);
 
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
@@ -3021,13 +3059,12 @@ static void icp_hpd_detection_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 ddi_enable_mask, u32 tc_enable_mask)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
 	hotplug_irqs = sde_ddi_mask | sde_tc_mask;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, pins);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd);
 
 	I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
 
@@ -3044,8 +3081,7 @@ static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	icp_hpd_irq_setup(dev_priv,
 			  SDE_DDI_MASK_ICP, SDE_TC_HOTPLUG_ICP(PORT_TC1),
-			  ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE(PORT_TC1),
-			  hpd_icp);
+			  ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE(PORT_TC1));
 }
 
 /*
@@ -3057,8 +3093,7 @@ 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);
+			  TGP_DDI_HPD_ENABLE_MASK, 0);
 }
 
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -3083,11 +3118,9 @@ static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
 static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
-	const u32 *hpd;
 	u32 val;
 
-	hpd = INTEL_GEN(dev_priv) >= 12 ? hpd_gen12 : hpd_gen11;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd);
 	hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK | GEN11_DE_TBT_HOTPLUG_MASK;
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
@@ -3099,12 +3132,10 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_TGP)
 		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);
+				  TGP_DDI_HPD_ENABLE_MASK, TGP_TC_HPD_ENABLE_MASK);
 	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		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);
+				  ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE_MASK);
 }
 
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -3140,7 +3171,7 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 		I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
 
 	hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd);
 
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
@@ -3169,17 +3200,17 @@ static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv)
 
 	if (INTEL_GEN(dev_priv) >= 8) {
 		hotplug_irqs = GEN8_PORT_DP_A_HOTPLUG;
-		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bdw);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd);
 
 		bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
 	} else if (INTEL_GEN(dev_priv) >= 7) {
 		hotplug_irqs = DE_DP_A_HOTPLUG_IVB;
-		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ivb);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd);
 
 		ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
 	} else {
 		hotplug_irqs = DE_DP_A_HOTPLUG;
-		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ilk);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd);
 
 		ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
 	}
@@ -3230,7 +3261,7 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd);
 	hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK;
 
 	bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
@@ -3646,7 +3677,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3751,7 +3782,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3893,10 +3924,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_BSD_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->engine[VCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[VCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3924,6 +3955,8 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 	int i;
 
+	intel_hpd_init_pins(dev_priv);
+
 	intel_hpd_init_work(dev_priv);
 
 	INIT_WORK(&dev_priv->l3_parity.error_work, ivb_parity_work);
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 2c80a0194c80..eb0b5be7c35d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -160,6 +160,7 @@
 	GEN(2), \
 	.is_mobile = 1, \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
 	.display.has_overlay = 1, \
 	.display.cursor_needs_physical = 1, \
 	.display.overlay_needs_physical = 1, \
@@ -170,6 +171,7 @@
 	.engine_mask = BIT(RCS0), \
 	.has_snoop = true, \
 	.has_coherent_ggtt = false, \
+	.dma_mask_size = 32, \
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
@@ -179,6 +181,7 @@
 #define I845_FEATURES \
 	GEN(2), \
 	.pipe_mask = BIT(PIPE_A), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A), \
 	.display.has_overlay = 1, \
 	.display.overlay_needs_physical = 1, \
 	.display.has_gmch = 1, \
@@ -188,6 +191,7 @@
 	.engine_mask = BIT(RCS0), \
 	.has_snoop = true, \
 	.has_coherent_ggtt = false, \
+	.dma_mask_size = 32, \
 	I845_PIPE_OFFSETS, \
 	I845_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
@@ -218,11 +222,13 @@ static const struct intel_device_info i865g_info = {
 #define GEN3_FEATURES \
 	GEN(3), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
 	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.engine_mask = BIT(RCS0), \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
+	.dma_mask_size = 32, \
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
@@ -283,6 +289,7 @@ static const struct intel_device_info g33_info = {
 	PLATFORM(INTEL_G33),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
+	.dma_mask_size = 36,
 };
 
 static const struct intel_device_info pnv_g_info = {
@@ -290,6 +297,7 @@ static const struct intel_device_info pnv_g_info = {
 	PLATFORM(INTEL_PINEVIEW),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
+	.dma_mask_size = 36,
 };
 
 static const struct intel_device_info pnv_m_info = {
@@ -298,17 +306,20 @@ static const struct intel_device_info pnv_m_info = {
 	.is_mobile = 1,
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
+	.dma_mask_size = 36,
 };
 
 #define GEN4_FEATURES \
 	GEN(4), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
 	.display.has_hotplug = 1, \
 	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.engine_mask = BIT(RCS0), \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
+	.dma_mask_size = 36, \
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I965_COLORS, \
@@ -354,12 +365,14 @@ static const struct intel_device_info gm45_info = {
 #define GEN5_FEATURES \
 	GEN(5), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
 	.display.has_hotplug = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0), \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
 	/* ilk does support rc6, but we do not implement [power] contexts */ \
 	.has_rc6 = 0, \
+	.dma_mask_size = 36, \
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	ILK_COLORS, \
@@ -381,6 +394,7 @@ static const struct intel_device_info ilk_m_info = {
 #define GEN6_FEATURES \
 	GEN(6), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
 	.display.has_hotplug = 1, \
 	.display.has_fbc = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
@@ -389,6 +403,7 @@ static const struct intel_device_info ilk_m_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
+	.dma_mask_size = 40, \
 	.ppgtt_type = INTEL_PPGTT_ALIASING, \
 	.ppgtt_size = 31, \
 	I9XX_PIPE_OFFSETS, \
@@ -430,6 +445,7 @@ static const struct intel_device_info snb_m_gt2_info = {
 #define GEN7_FEATURES  \
 	GEN(7), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \
 	.display.has_hotplug = 1, \
 	.display.has_fbc = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
@@ -438,6 +454,7 @@ static const struct intel_device_info snb_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
+	.dma_mask_size = 40, \
 	.ppgtt_type = INTEL_PPGTT_ALIASING, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
@@ -482,6 +499,7 @@ static const struct intel_device_info ivb_q_info = {
 	PLATFORM(INTEL_IVYBRIDGE),
 	.gt = 2,
 	.pipe_mask = 0, /* legal, last one wins */
+	.cpu_transcoder_mask = 0,
 	.has_l3_dpf = 1,
 };
 
@@ -490,11 +508,13 @@ static const struct intel_device_info vlv_info = {
 	GEN(7),
 	.is_lp = 1,
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B),
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B),
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
+	.dma_mask_size = 40,
 	.ppgtt_type = INTEL_PPGTT_ALIASING,
 	.ppgtt_size = 31,
 	.has_snoop = true,
@@ -511,6 +531,8 @@ static const struct intel_device_info vlv_info = {
 #define G75_FEATURES  \
 	GEN7_FEATURES, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP), \
 	.display.has_ddi = 1, \
 	.has_fpga_dbg = 1, \
 	.display.has_psr = 1, \
@@ -543,6 +565,7 @@ static const struct intel_device_info hsw_gt3_info = {
 	G75_FEATURES, \
 	GEN(8), \
 	.has_logical_ring_contexts = 1, \
+	.dma_mask_size = 39, \
 	.ppgtt_type = INTEL_PPGTT_FULL, \
 	.ppgtt_size = 48, \
 	.has_64bit_reloc = 1, \
@@ -581,6 +604,7 @@ static const struct intel_device_info chv_info = {
 	PLATFORM(INTEL_CHERRYVIEW),
 	GEN(8),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C),
 	.display.has_hotplug = 1,
 	.is_lp = 1,
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0),
@@ -590,7 +614,8 @@ static const struct intel_device_info chv_info = {
 	.has_rps = true,
 	.has_logical_ring_contexts = 1,
 	.display.has_gmch = 1,
-	.ppgtt_type = INTEL_PPGTT_ALIASING,
+	.dma_mask_size = 39,
+	.ppgtt_type = INTEL_PPGTT_FULL,
 	.ppgtt_size = 32,
 	.has_reset_engine = 1,
 	.has_snoop = true,
@@ -656,6 +681,9 @@ static const struct intel_device_info skl_gt4_info = {
 	.display.has_hotplug = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \
+		BIT(TRANSCODER_DSI_A) | BIT(TRANSCODER_DSI_C), \
 	.has_64bit_reloc = 1, \
 	.display.has_ddi = 1, \
 	.has_fpga_dbg = 1, \
@@ -670,6 +698,7 @@ static const struct intel_device_info skl_gt4_info = {
 	.has_logical_ring_contexts = 1, \
 	.has_logical_ring_preemption = 1, \
 	.has_gt_uc = 1, \
+	.dma_mask_size = 39, \
 	.ppgtt_type = INTEL_PPGTT_FULL, \
 	.ppgtt_size = 48, \
 	.has_reset_engine = 1, \
@@ -759,6 +788,9 @@ static const struct intel_device_info cnl_info = {
 #define GEN11_FEATURES \
 	GEN10_FEATURES, \
 	GEN11_DEFAULT_PAGE_SIZES, \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \
+		BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \
 	.pipe_offsets = { \
 		[TRANSCODER_A] = PIPE_A_OFFSET, \
 		[TRANSCODER_B] = PIPE_B_OFFSET, \
@@ -799,6 +831,10 @@ static const struct intel_device_info ehl_info = {
 #define GEN12_FEATURES \
 	GEN11_FEATURES, \
 	GEN(12), \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \
+	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
+		BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | \
+		BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \
 	.pipe_offsets = { \
 		[TRANSCODER_A] = PIPE_A_OFFSET, \
 		[TRANSCODER_B] = PIPE_B_OFFSET, \
@@ -822,7 +858,6 @@ static const struct intel_device_info ehl_info = {
 static const struct intel_device_info tgl_info = {
 	GEN12_FEATURES,
 	PLATFORM(INTEL_TIGERLAKE),
-	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
 	.display.has_modular_fia = 1,
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
@@ -920,8 +955,6 @@ static void i915_pci_remove(struct pci_dev *pdev)
 
 	i915_driver_remove(i915);
 	pci_set_drvdata(pdev, NULL);
-
-	drm_dev_put(&i915->drm);
 }
 
 /* is device_id present in comma separated list of ids */
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 60da28d412d6..75c60c2afb7e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -204,21 +204,6 @@
 
 #include "i915_drv.h"
 #include "i915_perf.h"
-#include "oa/i915_oa_hsw.h"
-#include "oa/i915_oa_bdw.h"
-#include "oa/i915_oa_chv.h"
-#include "oa/i915_oa_sklgt2.h"
-#include "oa/i915_oa_sklgt3.h"
-#include "oa/i915_oa_sklgt4.h"
-#include "oa/i915_oa_bxt.h"
-#include "oa/i915_oa_kblgt2.h"
-#include "oa/i915_oa_kblgt3.h"
-#include "oa/i915_oa_glk.h"
-#include "oa/i915_oa_cflgt2.h"
-#include "oa/i915_oa_cflgt3.h"
-#include "oa/i915_oa_cnl.h"
-#include "oa/i915_oa_icl.h"
-#include "oa/i915_oa_tgl.h"
 
 /* HW requires this to be a power of two, between 128k and 16M, though driver
  * is currently generally designed assuming the largest 16M size is used such
@@ -238,26 +223,17 @@
  *
  * Although this can be observed explicitly while copying reports to userspace
  * by checking for a zeroed report-id field in tail reports, we want to account
- * for this earlier, as part of the oa_buffer_check to avoid lots of redundant
- * read() attempts.
- *
- * In effect we define a tail pointer for reading that lags the real tail
- * pointer by at least %OA_TAIL_MARGIN_NSEC nanoseconds, which gives enough
- * time for the corresponding reports to become visible to the CPU.
- *
- * To manage this we actually track two tail pointers:
- *  1) An 'aging' tail with an associated timestamp that is tracked until we
- *     can trust the corresponding data is visible to the CPU; at which point
- *     it is considered 'aged'.
- *  2) An 'aged' tail that can be used for read()ing.
- *
- * The two separate pointers let us decouple read()s from tail pointer aging.
- *
- * The tail pointers are checked and updated at a limited rate within a hrtimer
- * callback (the same callback that is used for delivering EPOLLIN events)
- *
- * Initially the tails are marked invalid with %INVALID_TAIL_PTR which
- * indicates that an updated tail pointer is needed.
+ * for this earlier, as part of the oa_buffer_check_unlocked to avoid lots of
+ * redundant read() attempts.
+ *
+ * We workaround this issue in oa_buffer_check_unlocked() by reading the reports
+ * in the OA buffer, starting from the tail reported by the HW until we find a
+ * report with its first 2 dwords not 0 meaning its previous report is
+ * completely in memory and ready to be read. Those dwords are also set to 0
+ * once read and the whole buffer is cleared upon OA buffer initialization. The
+ * first dword is the reason for this report while the second is the timestamp,
+ * making the chances of having those 2 fields at 0 fairly unlikely. A more
+ * detailed explanation is available in oa_buffer_check_unlocked().
  *
  * Most of the implementation details for this workaround are in
  * oa_buffer_check_unlocked() and _append_oa_reports()
@@ -272,11 +248,11 @@
 #define OA_TAIL_MARGIN_NSEC	100000ULL
 #define INVALID_TAIL_PTR	0xffffffff
 
-/* frequency for checking whether the OA unit has written new reports to the
- * circular OA buffer...
+/* The default frequency for checking whether the OA unit has written new
+ * reports to the circular OA buffer...
  */
-#define POLL_FREQUENCY 200
-#define POLL_PERIOD (NSEC_PER_SEC / POLL_FREQUENCY)
+#define DEFAULT_POLL_FREQUENCY_HZ 200
+#define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ)
 
 /* for sysctl proc_dointvec_minmax of dev.i915.perf_stream_paranoid */
 static u32 i915_perf_stream_paranoid = true;
@@ -359,6 +335,12 @@ static const struct i915_oa_format gen12_oa_formats[I915_OA_FORMAT_MAX] = {
  * @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
+ * @has_sseu: Whether @sseu was specified by userspace
+ * @sseu: internal SSEU configuration computed either from the userspace
+ *        specified configuration in the opening parameters or a default value
+ *        (see get_default_sseu_config())
+ * @poll_oa_period: The period in nanoseconds at which the CPU will check for OA
+ * data availability
  *
  * As read_properties_unlocked() enumerates and validates the properties given
  * to open a stream of metrics the configuration is built up in the structure
@@ -378,6 +360,11 @@ struct perf_open_properties {
 	int oa_period_exponent;
 
 	struct intel_engine_cs *engine;
+
+	bool has_sseu;
+	struct intel_sseu sseu;
+
+	u64 poll_oa_period;
 };
 
 struct i915_oa_config_bo {
@@ -409,10 +396,7 @@ i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set)
 	struct i915_oa_config *oa_config;
 
 	rcu_read_lock();
-	if (metrics_set == 1)
-		oa_config = &perf->test_config;
-	else
-		oa_config = idr_find(&perf->metrics_idr, metrics_set);
+	oa_config = idr_find(&perf->metrics_idr, metrics_set);
 	if (oa_config)
 		oa_config = i915_oa_config_get(oa_config);
 	rcu_read_unlock();
@@ -465,8 +449,8 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
  * (See description of OA_TAIL_MARGIN_NSEC above for further details.)
  *
  * Besides returning true when there is data available to read() this function
- * also has the side effect of updating the oa_buffer.tails[], .aging_timestamp
- * and .aged_tail_idx state used for reading.
+ * also updates the tail, aging_tail and aging_timestamp in the oa_buffer
+ * object.
  *
  * Note: It's safe to read OA config state here unlocked, assuming that this is
  * only called while the stream is enabled, while the global OA configuration
@@ -476,28 +460,19 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
  */
 static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 {
+	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	int report_size = stream->oa_buffer.format_size;
 	unsigned long flags;
-	unsigned int aged_idx;
-	u32 head, hw_tail, aged_tail, aging_tail;
+	bool pollin;
+	u32 hw_tail;
 	u64 now;
 
 	/* We have to consider the (unlikely) possibility that read() errors
-	 * could result in an OA buffer reset which might reset the head,
-	 * tails[] and aged_tail state.
+	 * could result in an OA buffer reset which might reset the head and
+	 * tail state.
 	 */
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
-	/* NB: The head we observe here might effectively be a little out of
-	 * date (between head and tails[aged_idx].offset if there is currently
-	 * a read() in progress.
-	 */
-	head = stream->oa_buffer.head;
-
-	aged_idx = stream->oa_buffer.aged_tail_idx;
-	aged_tail = stream->oa_buffer.tails[aged_idx].offset;
-	aging_tail = stream->oa_buffer.tails[!aged_idx].offset;
-
 	hw_tail = stream->perf->ops.oa_hw_tail_read(stream);
 
 	/* The tail pointer increases in 64 byte increments,
@@ -507,64 +482,63 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 
 	now = ktime_get_mono_fast_ns();
 
-	/* Update the aged tail
-	 *
-	 * Flip the tail pointer available for read()s once the aging tail is
-	 * old enough to trust that the corresponding data will be visible to
-	 * the CPU...
-	 *
-	 * Do this before updating the aging pointer in case we may be able to
-	 * immediately start aging a new pointer too (if new data has become
-	 * available) without needing to wait for a later hrtimer callback.
-	 */
-	if (aging_tail != INVALID_TAIL_PTR &&
-	    ((now - stream->oa_buffer.aging_timestamp) >
-	     OA_TAIL_MARGIN_NSEC)) {
-
-		aged_idx ^= 1;
-		stream->oa_buffer.aged_tail_idx = aged_idx;
+	if (hw_tail == stream->oa_buffer.aging_tail &&
+	    (now - stream->oa_buffer.aging_timestamp) > OA_TAIL_MARGIN_NSEC) {
+		/* If the HW tail hasn't move since the last check and the HW
+		 * tail has been aging for long enough, declare it the new
+		 * tail.
+		 */
+		stream->oa_buffer.tail = stream->oa_buffer.aging_tail;
+	} else {
+		u32 head, tail, aged_tail;
 
-		aged_tail = aging_tail;
+		/* NB: The head we observe here might effectively be a little
+		 * out of date. If a read() is in progress, the head could be
+		 * anywhere between this head and stream->oa_buffer.tail.
+		 */
+		head = stream->oa_buffer.head - gtt_offset;
+		aged_tail = stream->oa_buffer.tail - gtt_offset;
+
+		hw_tail -= gtt_offset;
+		tail = hw_tail;
+
+		/* Walk the stream backward until we find a report with dword 0
+		 * & 1 not at 0. Since the circular buffer pointers progress by
+		 * increments of 64 bytes and that reports can be up to 256
+		 * bytes long, we can't tell whether a report has fully landed
+		 * in memory before the first 2 dwords of the following report
+		 * have effectively landed.
+		 *
+		 * This is assuming that the writes of the OA unit land in
+		 * memory in the order they were written to.
+		 * If not : (╯°□°）╯︵ ┻━┻
+		 */
+		while (OA_TAKEN(tail, aged_tail) >= report_size) {
+			u32 *report32 = (void *)(stream->oa_buffer.vaddr + tail);
 
-		/* Mark that we need a new pointer to start aging... */
-		stream->oa_buffer.tails[!aged_idx].offset = INVALID_TAIL_PTR;
-		aging_tail = INVALID_TAIL_PTR;
-	}
+			if (report32[0] != 0 || report32[1] != 0)
+				break;
 
-	/* Update the aging tail
-	 *
-	 * We throttle aging tail updates until we have a new tail that
-	 * represents >= one report more data than is already available for
-	 * reading. This ensures there will be enough data for a successful
-	 * read once this new pointer has aged and ensures we will give the new
-	 * pointer time to age.
-	 */
-	if (aging_tail == INVALID_TAIL_PTR &&
-	    (aged_tail == INVALID_TAIL_PTR ||
-	     OA_TAKEN(hw_tail, aged_tail) >= report_size)) {
-		struct i915_vma *vma = stream->oa_buffer.vma;
-		u32 gtt_offset = i915_ggtt_offset(vma);
-
-		/* Be paranoid and do a bounds check on the pointer read back
-		 * from hardware, just in case some spurious hardware condition
-		 * could put the tail out of bounds...
-		 */
-		if (hw_tail >= gtt_offset &&
-		    hw_tail < (gtt_offset + OA_BUFFER_SIZE)) {
-			stream->oa_buffer.tails[!aged_idx].offset =
-				aging_tail = hw_tail;
-			stream->oa_buffer.aging_timestamp = now;
-		} else {
-			drm_err(&stream->perf->i915->drm,
-				"Ignoring spurious out of range OA buffer tail pointer = %x\n",
-				hw_tail);
+			tail = (tail - report_size) & (OA_BUFFER_SIZE - 1);
 		}
+
+		if (OA_TAKEN(hw_tail, tail) > report_size &&
+		    __ratelimit(&stream->perf->tail_pointer_race))
+			DRM_NOTE("unlanded report(s) head=0x%x "
+				 "tail=0x%x hw_tail=0x%x\n",
+				 head, tail, hw_tail);
+
+		stream->oa_buffer.tail = gtt_offset + tail;
+		stream->oa_buffer.aging_tail = gtt_offset + hw_tail;
+		stream->oa_buffer.aging_timestamp = now;
 	}
 
+	pollin = OA_TAKEN(stream->oa_buffer.tail - gtt_offset,
+			  stream->oa_buffer.head - gtt_offset) >= report_size;
+
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
-	return aged_tail == INVALID_TAIL_PTR ?
-		false : OA_TAKEN(aged_tail, head) >= report_size;
+	return pollin;
 }
 
 /**
@@ -682,7 +656,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	u32 mask = (OA_BUFFER_SIZE - 1);
 	size_t start_offset = *offset;
 	unsigned long flags;
-	unsigned int aged_tail_idx;
 	u32 head, tail;
 	u32 taken;
 	int ret = 0;
@@ -693,19 +666,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
 	head = stream->oa_buffer.head;
-	aged_tail_idx = stream->oa_buffer.aged_tail_idx;
-	tail = stream->oa_buffer.tails[aged_tail_idx].offset;
+	tail = stream->oa_buffer.tail;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
 	/*
-	 * An invalid tail pointer here means we're still waiting for the poll
-	 * hrtimer callback to give us a pointer
-	 */
-	if (tail == INVALID_TAIL_PTR)
-		return -EAGAIN;
-
-	/*
 	 * NB: oa_buffer.head/tail include the gtt_offset which we don't want
 	 * while indexing relative to oa_buf_base.
 	 */
@@ -838,13 +803,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		}
 
 		/*
-		 * The above reason field sanity check is based on
-		 * the assumption that the OA buffer is initially
-		 * zeroed and we reset the field after copying so the
-		 * check is still meaningful once old reports start
-		 * being overwritten.
+		 * Clear out the first 2 dword as a mean to detect unlanded
+		 * reports.
 		 */
 		report32[0] = 0;
+		report32[1] = 0;
 	}
 
 	if (start_offset != *offset) {
@@ -985,7 +948,6 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	u32 mask = (OA_BUFFER_SIZE - 1);
 	size_t start_offset = *offset;
 	unsigned long flags;
-	unsigned int aged_tail_idx;
 	u32 head, tail;
 	u32 taken;
 	int ret = 0;
@@ -996,17 +958,10 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
 	head = stream->oa_buffer.head;
-	aged_tail_idx = stream->oa_buffer.aged_tail_idx;
-	tail = stream->oa_buffer.tails[aged_tail_idx].offset;
+	tail = stream->oa_buffer.tail;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
-	/* An invalid tail pointer here means we're still waiting for the poll
-	 * hrtimer callback to give us a pointer
-	 */
-	if (tail == INVALID_TAIL_PTR)
-		return -EAGAIN;
-
 	/* NB: oa_buffer.head/tail include the gtt_offset which we don't want
 	 * while indexing relative to oa_buf_base.
 	 */
@@ -1064,13 +1019,11 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 		if (ret)
 			break;
 
-		/* The above report-id field sanity check is based on
-		 * the assumption that the OA buffer is initially
-		 * zeroed and we reset the field after copying so the
-		 * check is still meaningful once old reports start
-		 * being overwritten.
+		/* Clear out the first 2 dwords as a mean to detect unlanded
+		 * reports.
 		 */
 		report32[0] = 0;
+		report32[1] = 0;
 	}
 
 	if (start_offset != *offset) {
@@ -1447,8 +1400,8 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 			   gtt_offset | OABUFFER_SIZE_16M);
 
 	/* Mark that we need updated tail pointers to read from... */
-	stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR;
-	stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR;
+	stream->oa_buffer.aging_tail = INVALID_TAIL_PTR;
+	stream->oa_buffer.tail = gtt_offset;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
@@ -1470,8 +1423,6 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 	 * memory...
 	 */
 	memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE);
-
-	stream->pollin = false;
 }
 
 static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
@@ -1501,8 +1452,8 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	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;
-	stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR;
+	stream->oa_buffer.aging_tail = INVALID_TAIL_PTR;
+	stream->oa_buffer.tail = gtt_offset;
 
 	/*
 	 * Reset state used to recognise context switches, affecting which
@@ -1526,8 +1477,6 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	 * memory...
 	 */
 	memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE);
-
-	stream->pollin = false;
 }
 
 static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
@@ -1557,8 +1506,8 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 			   gtt_offset & GEN12_OAG_OATAILPTR_MASK);
 
 	/* Mark that we need updated tail pointers to read from... */
-	stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR;
-	stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR;
+	stream->oa_buffer.aging_tail = INVALID_TAIL_PTR;
+	stream->oa_buffer.tail = gtt_offset;
 
 	/*
 	 * Reset state used to recognise context switches, affecting which
@@ -1583,8 +1532,6 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 	 */
 	memset(stream->oa_buffer.vaddr, 0,
 	       stream->oa_buffer.vma->size);
-
-	stream->pollin = false;
 }
 
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
@@ -1665,10 +1612,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	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);
+		i915_cs_timestamp_ns_to_ticks(i915, atomic64_read(&stream->perf->noa_programming_delay));
 	const u32 base = stream->engine->mmio_base;
 #define CS_GPR(x) GEN8_RING_CS_GPR(base, x)
 	u32 *batch, *ts0, *cs, *jump;
@@ -1970,10 +1914,11 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static struct i915_request *
+static int
 emit_oa_config(struct i915_perf_stream *stream,
 	       struct i915_oa_config *oa_config,
-	       struct intel_context *ce)
+	       struct intel_context *ce,
+	       struct i915_active *active)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1981,7 +1926,7 @@ emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return ERR_CAST(vma);
+		return PTR_ERR(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
@@ -1995,6 +1940,18 @@ emit_oa_config(struct i915_perf_stream *stream,
 		goto err_vma_unpin;
 	}
 
+	if (!IS_ERR_OR_NULL(active)) {
+		/* After all individual context modifications */
+		err = i915_request_await_active(rq, active,
+						I915_ACTIVE_AWAIT_ACTIVE);
+		if (err)
+			goto err_add_request;
+
+		err = i915_active_add_request(active, rq);
+		if (err)
+			goto err_add_request;
+	}
+
 	i915_vma_lock(vma);
 	err = i915_request_await_object(rq, vma->obj, 0);
 	if (!err)
@@ -2009,14 +1966,13 @@ emit_oa_config(struct i915_perf_stream *stream,
 	if (err)
 		goto err_add_request;
 
-	i915_request_get(rq);
 err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
 err_vma_put:
 	i915_vma_put(vma);
-	return err ? ERR_PTR(err) : rq;
+	return err;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -2024,8 +1980,9 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static struct i915_request *
-hsw_enable_metric_set(struct i915_perf_stream *stream)
+static int
+hsw_enable_metric_set(struct i915_perf_stream *stream,
+		      struct i915_active *active)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2044,7 +2001,9 @@ 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->oa_config, oa_context(stream));
+	return emit_oa_config(stream,
+			      stream->oa_config, oa_context(stream),
+			      active);
 }
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
@@ -2114,9 +2073,6 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,
 	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]);
-
-	reg_state[CTX_R_PWR_CLK_STATE] =
-		intel_sseu_make_rpcs(ce->engine->i915, &ce->sseu);
 }
 
 struct flex {
@@ -2137,7 +2093,7 @@ gen8_store_flex(struct i915_request *rq,
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
-	offset = i915_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
+	offset = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET;
 	do {
 		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*cs++ = offset + flex->offset * sizeof(u32);
@@ -2194,8 +2150,10 @@ static int gen8_modify_context(struct intel_context *ce,
 	return err;
 }
 
-static int gen8_modify_self(struct intel_context *ce,
-			    const struct flex *flex, unsigned int count)
+static int
+gen8_modify_self(struct intel_context *ce,
+		 const struct flex *flex, unsigned int count,
+		 struct i915_active *active)
 {
 	struct i915_request *rq;
 	int err;
@@ -2206,8 +2164,17 @@ static int gen8_modify_self(struct intel_context *ce,
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	if (!IS_ERR_OR_NULL(active)) {
+		err = i915_active_add_request(active, rq);
+		if (err)
+			goto err_add_request;
+	}
+
 	err = gen8_load_flex(rq, ce, flex, count);
+	if (err)
+		goto err_add_request;
 
+err_add_request:
 	i915_request_add(rq);
 	return err;
 }
@@ -2241,7 +2208,8 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 	return err;
 }
 
-static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable)
+static int gen12_configure_oar_context(struct i915_perf_stream *stream,
+				       struct i915_active *active)
 {
 	int err;
 	struct intel_context *ce = stream->pinned_ctx;
@@ -2250,7 +2218,7 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena
 		{
 			GEN8_OACTXCONTROL,
 			stream->perf->ctx_oactxctrl_offset + 1,
-			enable ? GEN8_OA_COUNTER_RESUME : 0,
+			active ? GEN8_OA_COUNTER_RESUME : 0,
 		},
 	};
 	/* Offsets in regs_lri are not used since this configuration is only
@@ -2262,13 +2230,13 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena
 			GEN12_OAR_OACONTROL,
 			GEN12_OAR_OACONTROL_OFFSET + 1,
 			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
-			(enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0)
+			(active ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0)
 		},
 		{
 			RING_CONTEXT_CONTROL(ce->engine->mmio_base),
 			CTX_CONTEXT_CONTROL,
 			_MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
-				      enable ?
+				      active ?
 				      GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :
 				      0)
 		},
@@ -2285,7 +2253,7 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena
 		return err;
 
 	/* Apply regs_lri using LRI with pinned context */
-	return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri));
+	return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri), active);
 }
 
 /*
@@ -2313,9 +2281,11 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena
  * Note: it's only the RCS/Render context that has any OA state.
  * Note: the first flex register passed must always be R_PWR_CLK_STATE
  */
-static int oa_configure_all_contexts(struct i915_perf_stream *stream,
-				     struct flex *regs,
-				     size_t num_regs)
+static int
+oa_configure_all_contexts(struct i915_perf_stream *stream,
+			  struct flex *regs,
+			  size_t num_regs,
+			  struct i915_active *active)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_engine_cs *engine;
@@ -2372,7 +2342,7 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream,
 
 		regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu);
 
-		err = gen8_modify_self(ce, regs, num_regs);
+		err = gen8_modify_self(ce, regs, num_regs, active);
 		if (err)
 			return err;
 	}
@@ -2380,8 +2350,10 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream,
 	return 0;
 }
 
-static int gen12_configure_all_contexts(struct i915_perf_stream *stream,
-					const struct i915_oa_config *oa_config)
+static int
+gen12_configure_all_contexts(struct i915_perf_stream *stream,
+			     const struct i915_oa_config *oa_config,
+			     struct i915_active *active)
 {
 	struct flex regs[] = {
 		{
@@ -2390,11 +2362,15 @@ static int gen12_configure_all_contexts(struct i915_perf_stream *stream,
 		},
 	};
 
-	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+	return oa_configure_all_contexts(stream,
+					 regs, ARRAY_SIZE(regs),
+					 active);
 }
 
-static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
-				      const struct i915_oa_config *oa_config)
+static int
+lrc_configure_all_contexts(struct i915_perf_stream *stream,
+			   const struct i915_oa_config *oa_config,
+			   struct i915_active *active)
 {
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
 	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
@@ -2427,11 +2403,14 @@ static int lrc_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);
 
-	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+	return oa_configure_all_contexts(stream,
+					 regs, ARRAY_SIZE(regs),
+					 active);
 }
 
-static struct i915_request *
-gen8_enable_metric_set(struct i915_perf_stream *stream)
+static int
+gen8_enable_metric_set(struct i915_perf_stream *stream,
+		       struct i915_active *active)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2471,11 +2450,13 @@ gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 * to make sure all slices/subslices are ON before writing to NOA
 	 * registers.
 	 */
-	ret = lrc_configure_all_contexts(stream, oa_config);
+	ret = lrc_configure_all_contexts(stream, oa_config, active);
 	if (ret)
-		return ERR_PTR(ret);
+		return ret;
 
-	return emit_oa_config(stream, oa_config, oa_context(stream));
+	return emit_oa_config(stream,
+			      stream->oa_config, oa_context(stream),
+			      active);
 }
 
 static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
@@ -2485,8 +2466,9 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static struct i915_request *
-gen12_enable_metric_set(struct i915_perf_stream *stream)
+static int
+gen12_enable_metric_set(struct i915_perf_stream *stream,
+			struct i915_active *active)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2515,9 +2497,9 @@ gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 * to make sure all slices/subslices are ON before writing to NOA
 	 * registers.
 	 */
-	ret = gen12_configure_all_contexts(stream, oa_config);
+	ret = gen12_configure_all_contexts(stream, oa_config, active);
 	if (ret)
-		return ERR_PTR(ret);
+		return ret;
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2525,12 +2507,14 @@ gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 * requested this.
 	 */
 	if (stream->ctx) {
-		ret = gen12_configure_oar_context(stream, true);
+		ret = gen12_configure_oar_context(stream, active);
 		if (ret)
-			return ERR_PTR(ret);
+			return ret;
 	}
 
-	return emit_oa_config(stream, oa_config, oa_context(stream));
+	return emit_oa_config(stream,
+			      stream->oa_config, oa_context(stream),
+			      active);
 }
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
@@ -2538,7 +2522,7 @@ static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	lrc_configure_all_contexts(stream, NULL);
+	lrc_configure_all_contexts(stream, NULL, NULL);
 
 	intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0);
 }
@@ -2548,7 +2532,7 @@ static void gen10_disable_metric_set(struct i915_perf_stream *stream)
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	lrc_configure_all_contexts(stream, NULL);
+	lrc_configure_all_contexts(stream, NULL, NULL);
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
@@ -2559,11 +2543,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	gen12_configure_all_contexts(stream, NULL);
+	gen12_configure_all_contexts(stream, NULL, NULL);
 
 	/* disable the context save/restore or OAR counters */
 	if (stream->ctx)
-		gen12_configure_oar_context(stream, false);
+		gen12_configure_oar_context(stream, NULL);
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
@@ -2655,11 +2639,13 @@ static void gen12_oa_enable(struct i915_perf_stream *stream)
  */
 static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 {
+	stream->pollin = false;
+
 	stream->perf->ops.oa_enable(stream);
 
 	if (stream->periodic)
 		hrtimer_start(&stream->poll_check_timer,
-			      ns_to_ktime(POLL_PERIOD),
+			      ns_to_ktime(stream->poll_oa_period),
 			      HRTIMER_MODE_REL_PINNED);
 }
 
@@ -2735,16 +2721,52 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 
 static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
 {
-	struct i915_request *rq;
+	struct i915_active *active;
+	int err;
 
-	rq = stream->perf->ops.enable_metric_set(stream);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
+	active = i915_active_create();
+	if (!active)
+		return -ENOMEM;
 
-	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
-	i915_request_put(rq);
+	err = stream->perf->ops.enable_metric_set(stream, active);
+	if (err == 0)
+		__i915_active_wait(active, TASK_UNINTERRUPTIBLE);
 
-	return 0;
+	i915_active_put(active);
+	return err;
+}
+
+static void
+get_default_sseu_config(struct intel_sseu *out_sseu,
+			struct intel_engine_cs *engine)
+{
+	const struct sseu_dev_info *devinfo_sseu =
+		&RUNTIME_INFO(engine->i915)->sseu;
+
+	*out_sseu = intel_sseu_from_device_info(devinfo_sseu);
+
+	if (IS_GEN(engine->i915, 11)) {
+		/*
+		 * We only need subslice count so it doesn't matter which ones
+		 * we select - just turn off low bits in the amount of half of
+		 * all available subslices per slice.
+		 */
+		out_sseu->subslice_mask =
+			~(~0 << (hweight8(out_sseu->subslice_mask) / 2));
+		out_sseu->slice_mask = 0x1;
+	}
+}
+
+static int
+get_sseu_config(struct intel_sseu *out_sseu,
+		struct intel_engine_cs *engine,
+		const struct drm_i915_gem_context_param_sseu *drm_sseu)
+{
+	if (drm_sseu->engine.engine_class != engine->uabi_class ||
+	    drm_sseu->engine.engine_instance != engine->uabi_instance)
+		return -EINVAL;
+
+	return i915_gem_user_to_context_sseu(engine->i915, drm_sseu, out_sseu);
 }
 
 /**
@@ -2879,6 +2901,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_oa_buf_alloc;
 
 	stream->ops = &i915_oa_stream_ops;
+
+	perf->sseu = props->sseu;
 	WRITE_ONCE(perf->exclusive_stream, stream);
 
 	ret = i915_perf_stream_enable_sync(stream);
@@ -2930,10 +2954,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 
 	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
 	stream = READ_ONCE(engine->i915->perf.exclusive_stream);
-	/*
-	 * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller
-	 * is already doing that, so nothing to be done for gen12 here.
-	 */
 	if (stream && INTEL_GEN(stream->perf->i915) < 12)
 		gen8_update_reg_state_unlocked(ce, stream);
 }
@@ -3024,7 +3044,8 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
 		wake_up(&stream->poll_wq);
 	}
 
-	hrtimer_forward_now(hrtimer, ns_to_ktime(POLL_PERIOD));
+	hrtimer_forward_now(hrtimer,
+			    ns_to_ktime(stream->poll_oa_period));
 
 	return HRTIMER_RESTART;
 }
@@ -3155,7 +3176,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		struct i915_request *rq;
+		int err;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3166,13 +3187,11 @@ 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.
 		 */
-		rq = emit_oa_config(stream, config, oa_context(stream));
-		if (!IS_ERR(rq)) {
+		err = emit_oa_config(stream, config, oa_context(stream), NULL);
+		if (!err)
 			config = xchg(&stream->oa_config, config);
-			i915_request_put(rq);
-		} else {
-			ret = PTR_ERR(rq);
-		}
+		else
+			ret = err;
 	}
 
 	i915_oa_config_put(config);
@@ -3385,6 +3404,14 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		privileged_op = true;
 	}
 
+	/*
+	 * Asking for SSEU configuration is a priviliged operation.
+	 */
+	if (props->has_sseu)
+		privileged_op = true;
+	else
+		get_default_sseu_config(&props->sseu, props->engine);
+
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
 	 * we check a dev.i915.perf_stream_paranoid sysctl option
 	 * to determine if it's ok to access system wide OA counters
@@ -3405,6 +3432,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 
 	stream->perf = perf;
 	stream->ctx = specific_ctx;
+	stream->poll_oa_period = props->poll_oa_period;
 
 	ret = i915_oa_stream_init(stream, param, props);
 	if (ret)
@@ -3454,8 +3482,7 @@ err:
 
 static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
 {
-	return div64_u64(1000000000ULL * (2ULL << exponent),
-			 1000ULL * RUNTIME_INFO(perf->i915)->cs_timestamp_frequency_khz);
+	return i915_cs_timestamp_ticks_to_ns(perf->i915, 2ULL << exponent);
 }
 
 /**
@@ -3480,8 +3507,10 @@ static int read_properties_unlocked(struct i915_perf *perf,
 {
 	u64 __user *uprop = uprops;
 	u32 i;
+	int ret;
 
 	memset(props, 0, sizeof(struct perf_open_properties));
+	props->poll_oa_period = DEFAULT_POLL_PERIOD_NS;
 
 	if (!n_props) {
 		DRM_DEBUG("No i915 perf properties given\n");
@@ -3511,7 +3540,6 @@ static int read_properties_unlocked(struct i915_perf *perf,
 	for (i = 0; i < n_props; i++) {
 		u64 oa_period, oa_freq_hz;
 		u64 id, value;
-		int ret;
 
 		ret = get_user(id, uprop);
 		if (ret)
@@ -3596,6 +3624,32 @@ static int read_properties_unlocked(struct i915_perf *perf,
 		case DRM_I915_PERF_PROP_HOLD_PREEMPTION:
 			props->hold_preemption = !!value;
 			break;
+		case DRM_I915_PERF_PROP_GLOBAL_SSEU: {
+			struct drm_i915_gem_context_param_sseu user_sseu;
+
+			if (copy_from_user(&user_sseu,
+					   u64_to_user_ptr(value),
+					   sizeof(user_sseu))) {
+				DRM_DEBUG("Unable to copy global sseu parameter\n");
+				return -EFAULT;
+			}
+
+			ret = get_sseu_config(&props->sseu, props->engine, &user_sseu);
+			if (ret) {
+				DRM_DEBUG("Invalid SSEU configuration\n");
+				return ret;
+			}
+			props->has_sseu = true;
+			break;
+		}
+		case DRM_I915_PERF_PROP_POLL_OA_PERIOD:
+			if (value < 100000 /* 100us */) {
+				DRM_DEBUG("OA availability timer too small (%lluns < 100us)\n",
+					  value);
+				return -EINVAL;
+			}
+			props->poll_oa_period = value;
+			break;
 		case DRM_I915_PERF_PROP_MAX:
 			MISSING_CASE(id);
 			return -EINVAL;
@@ -3678,7 +3732,6 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 void i915_perf_register(struct drm_i915_private *i915)
 {
 	struct i915_perf *perf = &i915->perf;
-	int ret;
 
 	if (!perf->i915)
 		return;
@@ -3692,64 +3745,7 @@ void i915_perf_register(struct drm_i915_private *i915)
 	perf->metrics_kobj =
 		kobject_create_and_add("metrics",
 				       &i915->drm.primary->kdev->kobj);
-	if (!perf->metrics_kobj)
-		goto exit;
-
-	sysfs_attr_init(&perf->test_config.sysfs_metric_id.attr);
-
-	if (IS_TIGERLAKE(i915)) {
-		i915_perf_load_test_config_tgl(i915);
-	} else 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(perf->metrics_kobj,
-				 &perf->test_config.sysfs_metric);
-	if (ret)
-		goto sysfs_error;
-
-	perf->test_config.perf = perf;
-	kref_init(&perf->test_config.ref);
-
-	goto exit;
 
-sysfs_error:
-	kobject_put(perf->metrics_kobj);
-	perf->metrics_kobj = NULL;
-
-exit:
 	mutex_unlock(&perf->lock);
 }
 
@@ -3769,9 +3765,6 @@ void i915_perf_unregister(struct drm_i915_private *i915)
 	if (!perf->metrics_kobj)
 		return;
 
-	sysfs_remove_group(perf->metrics_kobj,
-			   &perf->test_config.sysfs_metric);
-
 	kobject_put(perf->metrics_kobj);
 	perf->metrics_kobj = NULL;
 }
@@ -4346,8 +4339,8 @@ void i915_perf_init(struct drm_i915_private *i915)
 	if (perf->ops.enable_metric_set) {
 		mutex_init(&perf->lock);
 
-		oa_sample_rate_hard_limit = 1000 *
-			(RUNTIME_INFO(i915)->cs_timestamp_frequency_khz / 2);
+		oa_sample_rate_hard_limit =
+			RUNTIME_INFO(i915)->cs_timestamp_frequency_hz / 2;
 
 		mutex_init(&perf->metrics_lock);
 		idr_init(&perf->metrics_idr);
@@ -4370,6 +4363,11 @@ void i915_perf_init(struct drm_i915_private *i915)
 		ratelimit_set_flags(&perf->spurious_report_rs,
 				    RATELIMIT_MSG_ON_RELEASE);
 
+		ratelimit_state_init(&perf->tail_pointer_race,
+				     5 * HZ, 10);
+		ratelimit_set_flags(&perf->tail_pointer_race,
+				    RATELIMIT_MSG_ON_RELEASE);
+
 		atomic64_set(&perf->noa_programming_delay,
 			     500 * 1000 /* 500us */);
 
@@ -4430,8 +4428,15 @@ int i915_perf_ioctl_version(void)
 	 *    preemption on a particular context so that performance data is
 	 *    accessible from a delta of MI_RPC reports without looking at the
 	 *    OA buffer.
+	 *
+	 * 4: Add DRM_I915_PERF_PROP_ALLOWED_SSEU to limit what contexts can
+	 *    be run for the duration of the performance recording based on
+	 *    their SSEU configuration.
+	 *
+	 * 5: Add DRM_I915_PERF_PROP_POLL_OA_PERIOD parameter that controls the
+	 *    interval for the hrtimer used to check for OA data.
 	 */
-	return 3;
+	return 5;
 }
 
 #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 a0e22f00f6cf..a36a455ae336 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -16,11 +16,13 @@
 #include <linux/uuid.h>
 #include <linux/wait.h>
 
+#include "gt/intel_sseu.h"
 #include "i915_reg.h"
 #include "intel_wakeref.h"
 
 struct drm_i915_private;
 struct file;
+struct i915_active;
 struct i915_gem_context;
 struct i915_perf;
 struct i915_vma;
@@ -272,21 +274,10 @@ struct i915_perf_stream {
 		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.
+		 * @aging_tail: The last HW tail reported by HW. The data
+		 * might not have made it to memory yet though.
 		 */
-		unsigned int aged_tail_idx;
+		u32 aging_tail;
 
 		/**
 		 * @aging_timestamp: A monotonic timestamp for when the current aging tail pointer
@@ -302,6 +293,11 @@ struct i915_perf_stream {
 		 * OA buffer data to userspace.
 		 */
 		u32 head;
+
+		/**
+		 * @tail: The last verified tail that can be read by userspace.
+		 */
+		u32 tail;
 	} oa_buffer;
 
 	/**
@@ -309,6 +305,12 @@ struct i915_perf_stream {
 	 * reprogrammed.
 	 */
 	struct i915_vma *noa_wait;
+
+	/**
+	 * @poll_oa_period: The period in nanoseconds at which the OA
+	 * buffer should be checked for available data.
+	 */
+	u64 poll_oa_period;
 };
 
 /**
@@ -339,8 +341,8 @@ struct i915_oa_ops {
 	 * counter reports being sampled. May apply system constraints such as
 	 * disabling EU clock gating as required.
 	 */
-	struct i915_request *
-		(*enable_metric_set)(struct i915_perf_stream *stream);
+	int (*enable_metric_set)(struct i915_perf_stream *stream,
+				 struct i915_active *active);
 
 	/**
 	 * @disable_metric_set: Remove system constraints associated with using
@@ -408,12 +410,22 @@ struct i915_perf {
 	struct i915_perf_stream *exclusive_stream;
 
 	/**
+	 * @sseu: sseu configuration selected to run while perf is active,
+	 * applies to all contexts.
+	 */
+	struct intel_sseu sseu;
+
+	/**
 	 * For rate limiting any notifications of spurious
 	 * invalid OA reports
 	 */
 	struct ratelimit_state spurious_report_rs;
 
-	struct i915_oa_config test_config;
+	/**
+	 * For rate limiting any notifications of tail pointer
+	 * race.
+	 */
+	struct ratelimit_state tail_pointer_race;
 
 	u32 gen7_latched_oastatus1;
 	u32 ctx_oactxctrl_offset;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 2c062534eac1..e991a707bdb7 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -439,29 +439,10 @@ static u64 count_interrupts(struct drm_i915_private *i915)
 	return sum;
 }
 
-static void engine_event_destroy(struct perf_event *event)
-{
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
-	struct intel_engine_cs *engine;
-
-	engine = intel_engine_lookup_user(i915,
-					  engine_event_class(event),
-					  engine_event_instance(event));
-	if (drm_WARN_ON_ONCE(&i915->drm, !engine))
-		return;
-
-	if (engine_event_sample(event) == I915_SAMPLE_BUSY &&
-	    intel_engine_supports_stats(engine))
-		intel_disable_engine_stats(engine);
-}
-
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
 	WARN_ON(event->parent);
-
-	if (is_engine_event(event))
-		engine_event_destroy(event);
+	module_put(THIS_MODULE);
 }
 
 static int
@@ -514,23 +495,13 @@ static int engine_event_init(struct perf_event *event)
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
 	struct intel_engine_cs *engine;
-	u8 sample;
-	int ret;
 
 	engine = intel_engine_lookup_user(i915, engine_event_class(event),
 					  engine_event_instance(event));
 	if (!engine)
 		return -ENODEV;
 
-	sample = engine_event_sample(event);
-	ret = engine_event_status(engine, sample);
-	if (ret)
-		return ret;
-
-	if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine))
-		ret = intel_enable_engine_stats(engine);
-
-	return ret;
+	return engine_event_status(engine, engine_event_sample(event));
 }
 
 static int i915_pmu_event_init(struct perf_event *event)
@@ -563,8 +534,10 @@ static int i915_pmu_event_init(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (!event->parent)
+	if (!event->parent) {
+		__module_get(THIS_MODULE);
 		event->destroy = i915_pmu_event_destroy;
+	}
 
 	return 0;
 }
@@ -1115,7 +1088,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	int ret = -ENOMEM;
 
 	if (INTEL_GEN(i915) <= 2) {
-		dev_info(i915->drm.dev, "PMU not supported for this GPU.");
+		drm_info(&i915->drm, "PMU not supported for this GPU.");
 		return;
 	}
 
@@ -1178,7 +1151,7 @@ err_name:
 	if (!is_igp(i915))
 		kfree(pmu->name);
 err:
-	dev_notice(i915->drm.dev, "Failed to register PMU!\n");
+	drm_notice(&i915->drm, "Failed to register PMU!\n");
 }
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 732aad148881..5003a71113cb 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -24,15 +24,12 @@ enum {
 	I915_PRIORITY_DISPLAY,
 };
 
-#define I915_USER_PRIORITY_SHIFT 2
+#define I915_USER_PRIORITY_SHIFT 0
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
 #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
 #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
 
-#define I915_PRIORITY_WAIT		((u8)BIT(0))
-#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(1))
-
 /* Smallest priority value that cannot be bumped. */
 #define I915_PRIORITY_INVALID (INT_MIN | (u8)I915_PRIORITY_MASK)
 
@@ -47,8 +44,6 @@ enum {
 #define I915_PRIORITY_UNPREEMPTABLE INT_MAX
 #define I915_PRIORITY_BARRIER INT_MAX
 
-#define __NO_PREEMPTION (I915_PRIORITY_WAIT)
-
 struct i915_priolist {
 	struct list_head requests[I915_PRIORITY_COUNT];
 	struct rb_node node;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6e12000c4b6b..6c076a24eb82 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -561,6 +561,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  * Registers used only by the command parser
  */
 #define BCS_SWCTRL _MMIO(0x22200)
+#define   BCS_SRC_Y REG_BIT(0)
+#define   BCS_DST_Y REG_BIT(1)
 
 /* There are 16 GPR registers */
 #define BCS_GPR(n)	_MMIO(0x22600 + (n) * 8)
@@ -2555,6 +2557,14 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
 #define GEN12_PAT_INDEX(index)	_MMIO(0x4800 + (index) * 4)
 #define BSD_HWS_PGA_GEN7	_MMIO(0x04180)
+#define GEN12_GFX_CCS_AUX_NV	_MMIO(0x4208)
+#define GEN12_VD0_AUX_NV	_MMIO(0x4218)
+#define GEN12_VD1_AUX_NV	_MMIO(0x4228)
+#define GEN12_VD2_AUX_NV	_MMIO(0x4298)
+#define GEN12_VD3_AUX_NV	_MMIO(0x42A8)
+#define GEN12_VE0_AUX_NV	_MMIO(0x4238)
+#define GEN12_VE1_AUX_NV	_MMIO(0x42B8)
+#define   AUX_INV		REG_BIT(0)
 #define BLT_HWS_PGA_GEN7	_MMIO(0x04280)
 #define VEBOX_HWS_PGA_GEN7	_MMIO(0x04380)
 #define RING_ACTHD(base)	_MMIO((base) + 0x74)
@@ -2657,6 +2667,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
 #define RING_INSTPM(base)	_MMIO((base) + 0xc0)
 #define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
+#define RING_CMD_BUF_CCTL(base) _MMIO((base) + 0x84)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)
@@ -4013,31 +4024,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN6_RP_STATE_LIMITS	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
 #define GEN6_RP_STATE_CAP	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
 #define BXT_RP_STATE_CAP        _MMIO(0x138170)
-
-/*
- * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
- * 8300) freezing up around GPU hangs. Looks as if even
- * scheduling/timer interrupts start misbehaving if the RPS
- * EI/thresholds are "bad", leading to a very sluggish or even
- * frozen machine.
- */
-#define INTERVAL_1_28_US(us)	roundup(((us) * 100) >> 7, 25)
-#define INTERVAL_1_33_US(us)	(((us) * 3)   >> 2)
-#define INTERVAL_0_833_US(us)	(((us) * 6) / 5)
-#define GT_INTERVAL_FROM_US(dev_priv, us) (INTEL_GEN(dev_priv) >= 9 ? \
-				(IS_GEN9_LP(dev_priv) ? \
-				INTERVAL_0_833_US(us) : \
-				INTERVAL_1_33_US(us)) : \
-				INTERVAL_1_28_US(us))
-
-#define INTERVAL_1_28_TO_US(interval)  (((interval) << 7) / 100)
-#define INTERVAL_1_33_TO_US(interval)  (((interval) << 2) / 3)
-#define INTERVAL_0_833_TO_US(interval) (((interval) * 5)  / 6)
-#define GT_PM_INTERVAL_TO_US(dev_priv, interval) (INTEL_GEN(dev_priv) >= 9 ? \
-                           (IS_GEN9_LP(dev_priv) ? \
-                           INTERVAL_0_833_TO_US(interval) : \
-                           INTERVAL_1_33_TO_US(interval)) : \
-                           INTERVAL_1_28_TO_US(interval))
+#define GEN9_RP_STATE_LIMITS	_MMIO(0x138148)
 
 /*
  * Logical Context regs
@@ -4325,6 +4312,96 @@ enum {
 #define   EXITLINE_MASK		REG_GENMASK(12, 0)
 #define   EXITLINE_SHIFT	0
 
+/* VRR registers */
+#define _TRANS_VRR_CTL_A		0x60420
+#define _TRANS_VRR_CTL_B		0x61420
+#define _TRANS_VRR_CTL_C		0x62420
+#define _TRANS_VRR_CTL_D		0x63420
+#define TRANS_VRR_CTL(trans)		_MMIO_TRANS2(trans, _TRANS_VRR_CTL_A)
+#define   VRR_CTL_VRR_ENABLE		REG_BIT(31)
+#define   VRR_CTL_IGN_MAX_SHIFT		REG_BIT(30)
+#define   VRR_CTL_FLIP_LINE_EN		REG_BIT(29)
+#define   VRR_CTL_LINE_COUNT_MASK	REG_GENMASK(10, 3)
+#define   VRR_CTL_SW_FULLLINE_COUNT	REG_BIT(0)
+
+#define _TRANS_VRR_VMAX_A		0x60424
+#define _TRANS_VRR_VMAX_B		0x61424
+#define _TRANS_VRR_VMAX_C		0x62424
+#define _TRANS_VRR_VMAX_D		0x63424
+#define TRANS_VRR_VMAX(trans)		_MMIO_TRANS2(trans, _TRANS_VRR_VMAX_A)
+#define   VRR_VMAX_MASK			REG_GENMASK(19, 0)
+
+#define _TRANS_VRR_VMIN_A		0x60434
+#define _TRANS_VRR_VMIN_B		0x61434
+#define _TRANS_VRR_VMIN_C		0x62434
+#define _TRANS_VRR_VMIN_D		0x63434
+#define TRANS_VRR_VMIN(trans)		_MMIO_TRANS2(trans, _TRANS_VRR_VMIN_A)
+#define   VRR_VMIN_MASK			REG_GENMASK(15, 0)
+
+#define _TRANS_VRR_VMAXSHIFT_A		0x60428
+#define _TRANS_VRR_VMAXSHIFT_B		0x61428
+#define _TRANS_VRR_VMAXSHIFT_C		0x62428
+#define _TRANS_VRR_VMAXSHIFT_D		0x63428
+#define TRANS_VRR_VMAXSHIFT(trans)	_MMIO_TRANS2(trans, \
+					_TRANS_VRR_VMAXSHIFT_A)
+#define   VRR_VMAXSHIFT_DEC_MASK	REG_GENMASK(29, 16)
+#define   VRR_VMAXSHIFT_DEC		REG_BIT(16)
+#define   VRR_VMAXSHIFT_INC_MASK	REG_GENMASK(12, 0)
+
+#define _TRANS_VRR_STATUS_A		0x6042C
+#define _TRANS_VRR_STATUS_B		0x6142C
+#define _TRANS_VRR_STATUS_C		0x6242C
+#define _TRANS_VRR_STATUS_D		0x6342C
+#define TRANS_VRR_STATUS(trans)		_MMIO_TRANS2(trans, _TRANS_VRR_STATUS_A)
+#define   VRR_STATUS_VMAX_REACHED	REG_BIT(31)
+#define   VRR_STATUS_NOFLIP_TILL_BNDR	REG_BIT(30)
+#define   VRR_STATUS_FLIP_BEF_BNDR	REG_BIT(29)
+#define   VRR_STATUS_NO_FLIP_FRAME	REG_BIT(28)
+#define   VRR_STATUS_VRR_EN_LIVE	REG_BIT(27)
+#define   VRR_STATUS_FLIPS_SERVICED	REG_BIT(26)
+#define   VRR_STATUS_VBLANK_MASK	REG_GENMASK(22, 20)
+#define   STATUS_FSM_IDLE		REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 0)
+#define   STATUS_FSM_WAIT_TILL_FDB	REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 1)
+#define   STATUS_FSM_WAIT_TILL_FS	REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 2)
+#define   STATUS_FSM_WAIT_TILL_FLIP	REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 3)
+#define   STATUS_FSM_PIPELINE_FILL	REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 4)
+#define   STATUS_FSM_ACTIVE		REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 5)
+#define   STATUS_FSM_LEGACY_VBLANK	REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 6)
+
+#define _TRANS_VRR_VTOTAL_PREV_A	0x60480
+#define _TRANS_VRR_VTOTAL_PREV_B	0x61480
+#define _TRANS_VRR_VTOTAL_PREV_C	0x62480
+#define _TRANS_VRR_VTOTAL_PREV_D	0x63480
+#define TRANS_VRR_VTOTAL_PREV(trans)	_MMIO_TRANS2(trans, \
+					_TRANS_VRR_VTOTAL_PREV_A)
+#define   VRR_VTOTAL_FLIP_BEFR_BNDR	REG_BIT(31)
+#define   VRR_VTOTAL_FLIP_AFTER_BNDR	REG_BIT(30)
+#define   VRR_VTOTAL_FLIP_AFTER_DBLBUF	REG_BIT(29)
+#define   VRR_VTOTAL_PREV_FRAME_MASK	REG_GENMASK(19, 0)
+
+#define _TRANS_VRR_FLIPLINE_A		0x60438
+#define _TRANS_VRR_FLIPLINE_B		0x61438
+#define _TRANS_VRR_FLIPLINE_C		0x62438
+#define _TRANS_VRR_FLIPLINE_D		0x63438
+#define TRANS_VRR_FLIPLINE(trans)	_MMIO_TRANS2(trans, \
+					_TRANS_VRR_FLIPLINE_A)
+#define   VRR_FLIPLINE_MASK		REG_GENMASK(19, 0)
+
+#define _TRANS_VRR_STATUS2_A		0x6043C
+#define _TRANS_VRR_STATUS2_B		0x6143C
+#define _TRANS_VRR_STATUS2_C		0x6243C
+#define _TRANS_VRR_STATUS2_D		0x6343C
+#define TRANS_VRR_STATUS2(trans)	_MMIO_TRANS2(trans, _TRANS_VRR_STATUS2_A)
+#define   VRR_STATUS2_VERT_LN_CNT_MASK	REG_GENMASK(19, 0)
+
+#define _TRANS_PUSH_A			0x60A70
+#define _TRANS_PUSH_B			0x61A70
+#define _TRANS_PUSH_C			0x62A70
+#define _TRANS_PUSH_D			0x63A70
+#define TRANS_PUSH(trans)		_MMIO_TRANS2(trans, _TRANS_PUSH_A)
+#define   TRANS_PUSH_EN			REG_BIT(31)
+#define   TRANS_PUSH_SEND		REG_BIT(30)
+
 /*
  * HSW+ eDP PSR registers
  *
@@ -6765,7 +6842,7 @@ enum {
 #define   PLANE_CTL_FORMAT_P012			(5 << 24)
 #define   PLANE_CTL_FORMAT_XRGB_16161616F	(6 << 24)
 #define   PLANE_CTL_FORMAT_P016			(7 << 24)
-#define   PLANE_CTL_FORMAT_AYUV			(8 << 24)
+#define   PLANE_CTL_FORMAT_XYUV			(8 << 24)
 #define   PLANE_CTL_FORMAT_INDEXED		(12 << 24)
 #define   PLANE_CTL_FORMAT_RGB_565		(14 << 24)
 #define   ICL_PLANE_CTL_FORMAT_MASK		(0x1f << 23)
@@ -8504,6 +8581,7 @@ enum {
 #define  FDI_BC_BIFURCATION_SELECT	(1 << 12)
 #define  CHASSIS_CLK_REQ_DURATION_MASK	(0xf << 8)
 #define  CHASSIS_CLK_REQ_DURATION(x)	((x) << 8)
+#define  SBCLK_RUN_REFCLK_DIS		(1 << 7)
 #define  SPT_PWM_GRANULARITY		(1 << 0)
 #define SOUTH_CHICKEN2		_MMIO(0xc2004)
 #define  FDI_MPHY_IOSFSB_RESET_STATUS	(1 << 13)
@@ -8995,6 +9073,7 @@ enum {
 #define     GEN7_PCODE_ILLEGAL_DATA		0x3
 #define     GEN11_PCODE_ILLEGAL_SUBCOMMAND	0x4
 #define     GEN11_PCODE_LOCKED			0x6
+#define     GEN11_PCODE_REJECTED		0x11
 #define     GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10
 #define   GEN6_PCODE_WRITE_RC6VIDS		0x4
 #define   GEN6_PCODE_READ_RC6VIDS		0x5
@@ -9016,10 +9095,18 @@ enum {
 #define   ICL_PCODE_MEM_SUBSYSYSTEM_INFO	0xd
 #define     ICL_PCODE_MEM_SS_READ_GLOBAL_INFO	(0x0 << 8)
 #define     ICL_PCODE_MEM_SS_READ_QGV_POINT_INFO(point)	(((point) << 16) | (0x1 << 8))
+#define   ICL_PCODE_SAGV_DE_MEM_SS_CONFIG	0xe
+#define     ICL_PCODE_POINTS_RESTRICTED		0x0
+#define     ICL_PCODE_POINTS_RESTRICTED_MASK	0x1
 #define   GEN6_PCODE_READ_D_COMP		0x10
 #define   GEN6_PCODE_WRITE_D_COMP		0x11
+#define   ICL_PCODE_EXIT_TCCOLD			0x12
 #define   HSW_PCODE_DE_WRITE_FREQ_REQ		0x17
 #define   DISPLAY_IPS_CONTROL			0x19
+#define   TGL_PCODE_TCCOLD			0x26
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_L_EXIT_FAILED	REG_BIT(0)
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ	0
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ	REG_BIT(0)
             /* See also IPS_CTL */
 #define     IPS_PCODE_CONTROL			(1 << 30)
 #define   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL	0x1A
@@ -9306,6 +9393,22 @@ enum {
 #define AUD_PIN_BUF_CTL		_MMIO(0x48414)
 #define   AUD_PIN_BUF_ENABLE		REG_BIT(31)
 
+/* Display Audio Config Reg */
+#define AUD_CONFIG_BE			_MMIO(0x65ef0)
+#define HBLANK_EARLY_ENABLE_ICL(pipe)		(0x1 << (20 - (pipe)))
+#define HBLANK_EARLY_ENABLE_TGL(pipe)		(0x1 << (24 + (pipe)))
+#define HBLANK_START_COUNT_MASK(pipe)		(0x7 << (3 + ((pipe) * 6)))
+#define HBLANK_START_COUNT(pipe, val)		(((val) & 0x7) << (3 + ((pipe)) * 6))
+#define NUMBER_SAMPLES_PER_LINE_MASK(pipe)	(0x3 << ((pipe) * 6))
+#define NUMBER_SAMPLES_PER_LINE(pipe, val)	(((val) & 0x3) << ((pipe) * 6))
+
+#define HBLANK_START_COUNT_8	0
+#define HBLANK_START_COUNT_16	1
+#define HBLANK_START_COUNT_32	2
+#define HBLANK_START_COUNT_64	3
+#define HBLANK_START_COUNT_96	4
+#define HBLANK_START_COUNT_128	5
+
 /*
  * HSW - ICL power wells
  *
@@ -9701,8 +9804,11 @@ enum skl_power_gate {
 #define  TRANS_DDI_BPC_10		(1 << 20)
 #define  TRANS_DDI_BPC_6		(2 << 20)
 #define  TRANS_DDI_BPC_12		(3 << 20)
+#define  TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK	REG_GENMASK(19, 18) /* bdw-cnl */
+#define  TRANS_DDI_PORT_SYNC_MASTER_SELECT(x)	REG_FIELD_PREP(TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK, (x))
 #define  TRANS_DDI_PVSYNC		(1 << 17)
 #define  TRANS_DDI_PHSYNC		(1 << 16)
+#define  TRANS_DDI_PORT_SYNC_ENABLE	REG_BIT(15) /* bdw-cnl */
 #define  TRANS_DDI_EDP_INPUT_MASK	(7 << 12)
 #define  TRANS_DDI_EDP_INPUT_A_ON	(0 << 12)
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
@@ -9729,12 +9835,10 @@ enum skl_power_gate {
 #define _TRANS_DDI_FUNC_CTL2_EDP	0x6f404
 #define _TRANS_DDI_FUNC_CTL2_DSI0	0x6b404
 #define _TRANS_DDI_FUNC_CTL2_DSI1	0x6bc04
-#define TRANS_DDI_FUNC_CTL2(tran)	_MMIO_TRANS2(tran, \
-						     _TRANS_DDI_FUNC_CTL2_A)
-#define  PORT_SYNC_MODE_ENABLE			(1 << 4)
-#define  PORT_SYNC_MODE_MASTER_SELECT(x)	((x) << 0)
-#define  PORT_SYNC_MODE_MASTER_SELECT_MASK	(0x7 << 0)
-#define  PORT_SYNC_MODE_MASTER_SELECT_SHIFT	0
+#define TRANS_DDI_FUNC_CTL2(tran)	_MMIO_TRANS2(tran, _TRANS_DDI_FUNC_CTL2_A)
+#define  PORT_SYNC_MODE_ENABLE			REG_BIT(4)
+#define  PORT_SYNC_MODE_MASTER_SELECT_MASK	REG_GENMASK(2, 0)
+#define  PORT_SYNC_MODE_MASTER_SELECT(x)	REG_FIELD_PREP(PORT_SYNC_MODE_MASTER_SELECT_MASK, (x))
 
 /* DisplayPort Transport Control */
 #define _DP_TP_CTL_A			0x64040
@@ -9795,6 +9899,24 @@ enum skl_power_gate {
 #define  DDI_BUF_BALANCE_LEG_ENABLE	(1 << 31)
 #define DDI_BUF_TRANS_HI(port, i)	_MMIO(_PORT(port, _DDI_BUF_TRANS_A, _DDI_BUF_TRANS_B) + (i) * 8 + 4)
 
+/* DDI DP Compliance Control */
+#define _DDI_DP_COMP_CTL_A			0x605F0
+#define _DDI_DP_COMP_CTL_B			0x615F0
+#define DDI_DP_COMP_CTL(pipe)			_MMIO_PIPE(pipe, _DDI_DP_COMP_CTL_A, _DDI_DP_COMP_CTL_B)
+#define   DDI_DP_COMP_CTL_ENABLE		(1 << 31)
+#define   DDI_DP_COMP_CTL_D10_2			(0 << 28)
+#define   DDI_DP_COMP_CTL_SCRAMBLED_0		(1 << 28)
+#define   DDI_DP_COMP_CTL_PRBS7			(2 << 28)
+#define   DDI_DP_COMP_CTL_CUSTOM80		(3 << 28)
+#define   DDI_DP_COMP_CTL_HBR2			(4 << 28)
+#define   DDI_DP_COMP_CTL_SCRAMBLED_1		(5 << 28)
+#define   DDI_DP_COMP_CTL_HBR2_RESET		(0xFC << 0)
+
+/* DDI DP Compliance Pattern */
+#define _DDI_DP_COMP_PAT_A			0x605F4
+#define _DDI_DP_COMP_PAT_B			0x615F4
+#define DDI_DP_COMP_PAT(pipe, i)		_MMIO(_PIPE(pipe, _DDI_DP_COMP_PAT_A, _DDI_DP_COMP_PAT_B) + (i) * 4)
+
 /* Sideband Interface (SBI) is programmed indirectly, via
  * SBI_ADDR, which contains the register offset; and SBI_DATA,
  * which contains the payload */
@@ -10742,6 +10864,12 @@ 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, \
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e2b78db685ea..526c1e9acbd5 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/dma-fence-array.h>
+#include <linux/dma-fence-chain.h>
 #include <linux/irq_work.h>
 #include <linux/prefetch.h>
 #include <linux/sched.h>
@@ -101,6 +102,11 @@ static signed long i915_fence_wait(struct dma_fence *fence,
 				 timeout);
 }
 
+struct kmem_cache *i915_request_slab_cache(void)
+{
+	return global.slab_requests;
+}
+
 static void i915_fence_release(struct dma_fence *fence)
 {
 	struct i915_request *rq = to_request(fence);
@@ -115,6 +121,10 @@ static void i915_fence_release(struct dma_fence *fence)
 	i915_sw_fence_fini(&rq->submit);
 	i915_sw_fence_fini(&rq->semaphore);
 
+	/* Keep one request on each engine for reserved use under mempressure */
+	if (!cmpxchg(&rq->engine->request_pool, NULL, rq))
+		return;
+
 	kmem_cache_free(global.slab_requests, rq);
 }
 
@@ -358,8 +368,6 @@ __await_execution(struct i915_request *rq,
 	}
 	spin_unlock_irq(&signal->lock);
 
-	/* Copy across semaphore status as we need the same behaviour */
-	rq->sched.flags |= signal->sched.flags;
 	return 0;
 }
 
@@ -527,10 +535,8 @@ void __i915_request_unsubmit(struct i915_request *request)
 	spin_unlock(&request->lock);
 
 	/* We've already spun, don't charge on resubmitting. */
-	if (request->sched.semaphores && i915_request_started(request)) {
-		request->sched.attr.priority |= I915_PRIORITY_NOSEMAPHORE;
+	if (request->sched.semaphores && i915_request_started(request))
 		request->sched.semaphores = 0;
-	}
 
 	/*
 	 * We don't need to wake_up any waiters on request->execute, they
@@ -588,15 +594,6 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 	return NOTIFY_DONE;
 }
 
-static void irq_semaphore_cb(struct irq_work *wrk)
-{
-	struct i915_request *rq =
-		container_of(wrk, typeof(*rq), semaphore_work);
-
-	i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE);
-	i915_request_put(rq);
-}
-
 static int __i915_sw_fence_call
 semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
@@ -604,11 +601,6 @@ semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) {
-			i915_request_get(rq);
-			init_irq_work(&rq->semaphore_work, irq_semaphore_cb);
-			irq_work_queue(&rq->semaphore_work);
-		}
 		break;
 
 	case FENCE_FREE:
@@ -629,14 +621,22 @@ static void retire_requests(struct intel_timeline *tl)
 }
 
 static noinline struct i915_request *
-request_alloc_slow(struct intel_timeline *tl, gfp_t gfp)
+request_alloc_slow(struct intel_timeline *tl,
+		   struct i915_request **rsvd,
+		   gfp_t gfp)
 {
 	struct i915_request *rq;
 
-	if (list_empty(&tl->requests))
-		goto out;
+	/* If we cannot wait, dip into our reserves */
+	if (!gfpflags_allow_blocking(gfp)) {
+		rq = xchg(rsvd, NULL);
+		if (!rq) /* Use the normal failure path for one final WARN */
+			goto out;
 
-	if (!gfpflags_allow_blocking(gfp))
+		return rq;
+	}
+
+	if (list_empty(&tl->requests))
 		goto out;
 
 	/* Move our oldest request to the slab-cache (if not in use!) */
@@ -721,7 +721,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq = kmem_cache_alloc(global.slab_requests,
 			      gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (unlikely(!rq)) {
-		rq = request_alloc_slow(tl, gfp);
+		rq = request_alloc_slow(tl, &ce->engine->request_pool, gfp);
 		if (!rq) {
 			ret = -ENOMEM;
 			goto err_unreserve;
@@ -933,6 +933,7 @@ __emit_semaphore_wait(struct i915_request *to,
 	u32 *cs;
 
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
+	GEM_BUG_ON(i915_request_has_initial_breadcrumb(to));
 
 	/* We need to pin the signaler's HWSP until we are finished reading. */
 	err = intel_timeline_read_hwsp(from, to, &hwsp_offset);
@@ -978,13 +979,26 @@ emit_semaphore_wait(struct i915_request *to,
 		    gfp_t gfp)
 {
 	const intel_engine_mask_t mask = READ_ONCE(from->engine)->mask;
+	struct i915_sw_fence *wait = &to->submit;
 
 	if (!intel_context_use_semaphores(to->context))
 		goto await_fence;
 
+	if (i915_request_has_initial_breadcrumb(to))
+		goto await_fence;
+
 	if (!rcu_access_pointer(from->hwsp_cacheline))
 		goto await_fence;
 
+	/*
+	 * If this or its dependents are waiting on an external fence
+	 * that may fail catastrophically, then we want to avoid using
+	 * sempahores as they bypass the fence signaling metadata, and we
+	 * lose the fence->error propagation.
+	 */
+	if (from->sched.flags & I915_SCHED_HAS_EXTERNAL_CHAIN)
+		goto await_fence;
+
 	/* Just emit the first semaphore we see as request space is limited. */
 	if (already_busywaiting(to) & mask)
 		goto await_fence;
@@ -1000,11 +1014,10 @@ emit_semaphore_wait(struct i915_request *to,
 		goto await_fence;
 
 	to->sched.semaphores |= mask;
-	to->sched.flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
-	return 0;
+	wait = &to->semaphore;
 
 await_fence:
-	return i915_sw_fence_await_dma_fence(&to->submit,
+	return i915_sw_fence_await_dma_fence(wait,
 					     &from->fence, 0,
 					     I915_FENCE_GFP);
 }
@@ -1039,15 +1052,56 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 	if (ret < 0)
 		return ret;
 
-	if (to->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN) {
-		ret = i915_sw_fence_await_dma_fence(&to->semaphore,
-						    &from->fence, 0,
-						    I915_FENCE_GFP);
-		if (ret < 0)
-			return ret;
+	return 0;
+}
+
+static void mark_external(struct i915_request *rq)
+{
+	/*
+	 * The downside of using semaphores is that we lose metadata passing
+	 * along the signaling chain. This is particularly nasty when we
+	 * need to pass along a fatal error such as EFAULT or EDEADLK. For
+	 * fatal errors we want to scrub the request before it is executed,
+	 * which means that we cannot preload the request onto HW and have
+	 * it wait upon a semaphore.
+	 */
+	rq->sched.flags |= I915_SCHED_HAS_EXTERNAL_CHAIN;
+}
+
+static int
+__i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
+{
+	mark_external(rq);
+	return i915_sw_fence_await_dma_fence(&rq->submit, fence,
+					     i915_fence_context_timeout(rq->i915,
+									fence->context),
+					     I915_FENCE_GFP);
+}
+
+static int
+i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
+{
+	struct dma_fence *iter;
+	int err = 0;
+
+	if (!to_dma_fence_chain(fence))
+		return __i915_request_await_external(rq, fence);
+
+	dma_fence_chain_for_each(iter, fence) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(iter);
+
+		if (!dma_fence_is_i915(chain->fence)) {
+			err = __i915_request_await_external(rq, iter);
+			break;
+		}
+
+		err = i915_request_await_dma_fence(rq, chain->fence);
+		if (err < 0)
+			break;
 	}
 
-	return 0;
+	dma_fence_put(iter);
+	return err;
 }
 
 int
@@ -1097,9 +1151,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 		if (dma_fence_is_i915(fence))
 			ret = i915_request_await_request(rq, to_request(fence));
 		else
-			ret = i915_sw_fence_await_dma_fence(&rq->submit, fence,
-							    fence->context ? I915_FENCE_TIMEOUT : 0,
-							    I915_FENCE_GFP);
+			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
 			return ret;
 
@@ -1179,7 +1231,8 @@ __i915_request_await_execution(struct i915_request *to,
 	 * immediate execution, and so we must wait until it reaches the
 	 * active slot.
 	 */
-	if (intel_engine_has_semaphores(to->engine)) {
+	if (intel_engine_has_semaphores(to->engine) &&
+	    !i915_request_has_initial_breadcrumb(to)) {
 		err = __emit_semaphore_wait(to, from, from->fence.seqno - 1);
 		if (err < 0)
 			return err;
@@ -1225,6 +1278,9 @@ i915_request_await_execution(struct i915_request *rq,
 			continue;
 		}
 
+		if (fence->context == rq->fence.context)
+			continue;
+
 		/*
 		 * We don't squash repeated fence dependencies here as we
 		 * want to run our callback in all cases.
@@ -1235,9 +1291,7 @@ i915_request_await_execution(struct i915_request *rq,
 							     to_request(fence),
 							     hook);
 		else
-			ret = i915_sw_fence_await_dma_fence(&rq->submit, fence,
-							    I915_FENCE_TIMEOUT,
-							    GFP_KERNEL);
+			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
 			return ret;
 	} while (--nchild);
@@ -1445,14 +1499,7 @@ void i915_request_add(struct i915_request *rq)
 		attr = ctx->sched;
 	rcu_read_unlock();
 
-	if (!(rq->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN))
-		attr.priority |= I915_PRIORITY_NOSEMAPHORE;
-	if (list_empty(&rq->sched.signalers_list))
-		attr.priority |= I915_PRIORITY_WAIT;
-
-	local_bh_disable();
 	__i915_request_queue(rq, &attr);
-	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
 
 	mutex_unlock(&tl->mutex);
 }
@@ -1636,7 +1683,6 @@ long i915_request_wait(struct i915_request *rq,
 	if (flags & I915_WAIT_PRIORITY) {
 		if (!i915_request_started(rq) && INTEL_GEN(rq->i915) >= 6)
 			intel_rps_boost(rq);
-		i915_schedule_bump_priority(rq, I915_PRIORITY_WAIT);
 	}
 
 	wait.tsk = current;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 3c552bfea67a..8ec7ee4dbadc 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -84,19 +84,26 @@ enum {
 	I915_FENCE_FLAG_PQUEUE,
 
 	/*
-	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
+	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
 	 *
-	 * Internal bookkeeping used by the breadcrumb code to track when
-	 * a request is on the various signal_list.
+	 * This request has been suspended, pending an ongoing investigation.
 	 */
-	I915_FENCE_FLAG_SIGNAL,
+	I915_FENCE_FLAG_HOLD,
 
 	/*
-	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
+	 * I915_FENCE_FLAG_INITIAL_BREADCRUMB - this request has the initial
+	 * breadcrumb that marks the end of semaphore waits and start of the
+	 * user payload.
+	 */
+	I915_FENCE_FLAG_INITIAL_BREADCRUMB,
+
+	/*
+	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
 	 *
-	 * This request has been suspended, pending an ongoing investigation.
+	 * Internal bookkeeping used by the breadcrumb code to track when
+	 * a request is on the various signal_list.
 	 */
-	I915_FENCE_FLAG_HOLD,
+	I915_FENCE_FLAG_SIGNAL,
 
 	/*
 	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
@@ -209,7 +216,6 @@ struct i915_request {
 	};
 	struct list_head execute_cb;
 	struct i915_sw_fence semaphore;
-	struct irq_work semaphore_work;
 
 	/*
 	 * A list of everyone we wait upon, and everyone who waits upon us.
@@ -300,6 +306,8 @@ static inline bool dma_fence_is_i915(const struct dma_fence *fence)
 	return fence->ops == &i915_fence_ops;
 }
 
+struct kmem_cache *i915_request_slab_cache(void);
+
 struct i915_request * __must_check
 __i915_request_create(struct intel_context *ce, gfp_t gfp);
 struct i915_request * __must_check
@@ -388,6 +396,12 @@ static inline bool i915_request_in_priority_queue(const struct i915_request *rq)
 	return test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
+static inline bool
+i915_request_has_initial_breadcrumb(const struct i915_request *rq)
+{
+	return test_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
+}
+
 /**
  * Returns true if seq1 is later than seq2.
  */
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index f0a9e8958ca0..f4ea318781f0 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -51,11 +51,11 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 	GEM_BUG_ON(rb_first_cached(&execlists->queue) !=
 		   rb_first(&execlists->queue.rb_root));
 
-	last_prio = (INT_MAX >> I915_USER_PRIORITY_SHIFT) + 1;
+	last_prio = INT_MAX;
 	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		const struct i915_priolist *p = to_priolist(rb);
 
-		GEM_BUG_ON(p->priority >= last_prio);
+		GEM_BUG_ON(p->priority > last_prio);
 		last_prio = p->priority;
 
 		GEM_BUG_ON(!p->used);
@@ -174,7 +174,7 @@ sched_lock_engine(const struct i915_sched_node *node,
 
 static inline int rq_prio(const struct i915_request *rq)
 {
-	return rq->sched.attr.priority | __NO_PREEMPTION;
+	return rq->sched.attr.priority;
 }
 
 static inline bool need_preempt(int prio, int active)
@@ -209,6 +209,12 @@ static void kick_submission(struct intel_engine_cs *engine,
 	if (!inflight)
 		goto unlock;
 
+	ENGINE_TRACE(engine,
+		     "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
+		     prio,
+		     rq->fence.context, rq->fence.seqno,
+		     inflight->fence.context, inflight->fence.seqno,
+		     inflight->sched.attr.priority);
 	engine->execlists.queue_priority_hint = prio;
 
 	/*
@@ -428,25 +434,12 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 		dep->waiter = node;
 		dep->flags = flags;
 
-		/* Keep track of whether anyone on this chain has a semaphore */
-		if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN &&
-		    !node_started(signal))
-			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
-
 		/* All set, now publish. Beware the lockless walkers. */
 		list_add_rcu(&dep->signal_link, &node->signalers_list);
 		list_add_rcu(&dep->wait_link, &signal->waiters_list);
 
-		/*
-		 * As we do not allow WAIT to preempt inflight requests,
-		 * once we have executed a request, along with triggering
-		 * any execution callbacks, we must preserve its ordering
-		 * within the non-preemptible FIFO.
-		 */
-		BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK);
-		if (flags & I915_DEPENDENCY_EXTERNAL)
-			__bump_priority(signal, __NO_PREEMPTION);
-
+		/* Propagate the chains */
+		node->flags |= signal->flags;
 		ret = true;
 	}
 
@@ -465,10 +458,14 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 	if (!dep)
 		return -ENOMEM;
 
+	local_bh_disable();
+
 	if (!__i915_sched_node_add_dependency(node, signal, dep,
 					      flags | I915_DEPENDENCY_ALLOC))
 		i915_dependency_free(dep);
 
+	local_bh_enable(); /* kick submission tasklet */
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 7186875088a0..f72e6c397b08 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -65,7 +65,7 @@ struct i915_sched_node {
 	struct list_head link;
 	struct i915_sched_attr attr;
 	unsigned int flags;
-#define I915_SCHED_HAS_SEMAPHORE_CHAIN	BIT(0)
+#define I915_SCHED_HAS_EXTERNAL_CHAIN	BIT(0)
 	intel_engine_mask_t semaphores;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 98bcb6fa0ab4..d53d207ab6eb 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -133,4 +133,6 @@ bool __igt_timeout(unsigned long timeout, const char *fmt, ...);
 #define igt_timeout(t, fmt, ...) \
 	__igt_timeout((t), KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 
+void igt_hexdump(const void *buf, size_t len);
+
 #endif /* !__I915_SELFTEST_H__ */
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index a3d38e089b6e..295b9829e2da 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -421,7 +421,7 @@ static void timer_i915_sw_fence_wake(struct timer_list *t)
 	if (!fence)
 		return;
 
-	pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%pS)\n",
+	pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%ps)\n",
 		  cb->dma->ops->get_driver_name(cb->dma),
 		  cb->dma->ops->get_timeline_name(cb->dma),
 		  cb->dma->seqno,
@@ -546,13 +546,11 @@ int __i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 	cb->fence = fence;
 	i915_sw_fence_await(fence);
 
-	ret = dma_fence_add_callback(dma, &cb->base, __dma_i915_sw_fence_wake);
-	if (ret == 0) {
-		ret = 1;
-	} else {
+	ret = 1;
+	if (dma_fence_add_callback(dma, &cb->base, __dma_i915_sw_fence_wake)) {
+		/* fence already signaled */
 		__dma_i915_sw_fence_wake(dma, &cb->base);
-		if (ret == -ENOENT) /* fence already signaled */
-			ret = 0;
+		ret = 0;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c
index 997b2998f1f2..a3a81bb8f2c3 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c
@@ -38,7 +38,10 @@ fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 		if (!f->dma.error) {
 			dma_fence_get(&f->dma);
-			queue_work(system_unbound_wq, &f->work);
+			if (test_bit(DMA_FENCE_WORK_IMM, &f->dma.flags))
+				fence_work(&f->work);
+			else
+				queue_work(system_unbound_wq, &f->work);
 		} else {
 			fence_complete(f);
 		}
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.h b/drivers/gpu/drm/i915/i915_sw_fence_work.h
index 3a22b287e201..2c409f11c5c5 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.h
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.h
@@ -32,6 +32,10 @@ struct dma_fence_work {
 	const struct dma_fence_work_ops *ops;
 };
 
+enum {
+	DMA_FENCE_WORK_IMM = DMA_FENCE_FLAG_USER_BITS,
+};
+
 void dma_fence_work_init(struct dma_fence_work *f,
 			 const struct dma_fence_work_ops *ops);
 int dma_fence_work_chain(struct dma_fence_work *f, struct dma_fence *signal);
@@ -41,4 +45,23 @@ static inline void dma_fence_work_commit(struct dma_fence_work *f)
 	i915_sw_fence_commit(&f->chain);
 }
 
+/**
+ * dma_fence_work_commit_imm: Commit the fence, and if possible execute locally.
+ * @f: the fenced worker
+ *
+ * Instead of always scheduling a worker to execute the callback (see
+ * dma_fence_work_commit()), we try to execute the callback immediately in
+ * the local context. It is required that the fence be committed before it
+ * is published, and that no other threads try to tamper with the number
+ * of asynchronous waits on the fence (or else the callback will be
+ * executed in the wrong context, i.e. not the callers).
+ */
+static inline void dma_fence_work_commit_imm(struct dma_fence_work *f)
+{
+	if (atomic_read(&f->chain.pending) <= 1)
+		__set_bit(DMA_FENCE_WORK_IMM, &f->dma.flags);
+
+	dma_fence_work_commit(f);
+}
+
 #endif /* I915_SW_FENCE_WORK_H */
diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c
index ed69b5d4a375..b3a24eac21f1 100644
--- a/drivers/gpu/drm/i915/i915_switcheroo.c
+++ b/drivers/gpu/drm/i915/i915_switcheroo.c
@@ -20,14 +20,14 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
 	}
 
 	if (state == VGA_SWITCHEROO_ON) {
-		pr_info("switched on\n");
+		drm_info(&i915->drm, "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");
+		drm_info(&i915->drm, "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;
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index 029854ae65fc..e28eae4a8f70 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -101,5 +101,6 @@ void set_timer_ms(struct timer_list *t, unsigned long timeout)
 	 */
 	barrier();
 
-	mod_timer(t, jiffies + timeout);
+	/* Keep t->expires = 0 reserved to indicate a canceled timer. */
+	mod_timer(t, jiffies + timeout ?: 1);
 }
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 2cd7a7e87c0a..fc14ebf9a0b7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -522,7 +522,6 @@ void i915_vma_unpin_and_release(struct i915_vma **p_vma, unsigned int flags)
 	GEM_BUG_ON(!obj);
 
 	i915_vma_unpin(vma);
-	i915_vma_close(vma);
 
 	if (flags & I915_VMA_RELEASE_MAP)
 		i915_gem_object_unpin_map(obj);
@@ -610,18 +609,6 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color)
 	return true;
 }
 
-static void assert_bind_count(const struct drm_i915_gem_object *obj)
-{
-	/*
-	 * Combine the assertion that the object is bound and that we have
-	 * pinned its pages. But we should never have bound the object
-	 * more than we have pinned its pages. (For complete accuracy, we
-	 * assume that no else is pinning the pages, but as a rough assertion
-	 * that we will not run into problems later, this will do!)
-	 */
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < atomic_read(&obj->bind_count));
-}
-
 /**
  * i915_vma_insert - finds a slot for the vma in its address space
  * @vma: the vma
@@ -740,12 +727,6 @@ 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));
 
-	if (vma->obj) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		atomic_inc(&obj->bind_count);
-		assert_bind_count(obj);
-	}
 	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
 
 	return 0;
@@ -763,12 +744,6 @@ i915_vma_detach(struct i915_vma *vma)
 	 * it to be reaped by the shrinker.
 	 */
 	list_del(&vma->vm_link);
-	if (vma->obj) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		assert_bind_count(obj);
-		atomic_dec(&obj->bind_count);
-	}
 }
 
 static bool try_qad_pin(struct i915_vma *vma, unsigned int flags)
@@ -915,11 +890,30 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	if (flags & PIN_GLOBAL)
 		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
 
-	/* No more allocations allowed once we hold vm->mutex */
-	err = mutex_lock_interruptible(&vma->vm->mutex);
+	/*
+	 * Differentiate between user/kernel vma inside the aliasing-ppgtt.
+	 *
+	 * We conflate the Global GTT with the user's vma when using the
+	 * aliasing-ppgtt, but it is still vitally important to try and
+	 * keep the use cases distinct. For example, userptr objects are
+	 * not allowed inside the Global GTT as that will cause lock
+	 * inversions when we have to evict them the mmu_notifier callbacks -
+	 * but they are allowed to be part of the user ppGTT which can never
+	 * be mapped. As such we try to give the distinct users of the same
+	 * mutex, distinct lockclasses [equivalent to how we keep i915_ggtt
+	 * and i915_ppgtt separate].
+	 *
+	 * NB this may cause us to mask real lock inversions -- while the
+	 * code is safe today, lockdep may not be able to spot future
+	 * transgressions.
+	 */
+	err = mutex_lock_interruptible_nested(&vma->vm->mutex,
+					      !(flags & PIN_GLOBAL));
 	if (err)
 		goto err_fence;
 
+	/* No more allocations allowed now we hold vm->mutex */
+
 	if (unlikely(i915_vma_is_closed(vma))) {
 		err = -ENOENT;
 		goto err_unlock;
@@ -982,7 +976,7 @@ err_unlock:
 	mutex_unlock(&vma->vm->mutex);
 err_fence:
 	if (work)
-		dma_fence_work_commit(&work->base);
+		dma_fence_work_commit_imm(&work->base);
 	if (wakeref)
 		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 err_pages:
@@ -1028,13 +1022,8 @@ int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags)
 	} while (1);
 }
 
-void i915_vma_close(struct i915_vma *vma)
+static void __vma_close(struct i915_vma *vma, struct intel_gt *gt)
 {
-	struct intel_gt *gt = vma->vm->gt;
-	unsigned long flags;
-
-	GEM_BUG_ON(i915_vma_is_closed(vma));
-
 	/*
 	 * We defer actually closing, unbinding and destroying the VMA until
 	 * the next idle point, or if the object is freed in the meantime. By
@@ -1047,9 +1036,25 @@ void i915_vma_close(struct i915_vma *vma)
 	 * causing us to rebind the VMA once more. This ends up being a lot
 	 * of wasted work for the steady state.
 	 */
-	spin_lock_irqsave(&gt->closed_lock, flags);
+	GEM_BUG_ON(i915_vma_is_closed(vma));
 	list_add(&vma->closed_link, &gt->closed_vma);
-	spin_unlock_irqrestore(&gt->closed_lock, flags);
+}
+
+void i915_vma_close(struct i915_vma *vma)
+{
+	struct intel_gt *gt = vma->vm->gt;
+	unsigned long flags;
+
+	if (i915_vma_is_ggtt(vma))
+		return;
+
+	GEM_BUG_ON(!atomic_read(&vma->open_count));
+	if (atomic_dec_and_lock_irqsave(&vma->open_count,
+					&gt->closed_lock,
+					flags)) {
+		__vma_close(vma, gt);
+		spin_unlock_irqrestore(&gt->closed_lock, flags);
+	}
 }
 
 static void __i915_vma_remove_closed(struct i915_vma *vma)
@@ -1174,7 +1179,8 @@ int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq)
 	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, 0);
+	err = i915_request_await_active(rq, &vma->active,
+					I915_ACTIVE_AWAIT_EXCL);
 	if (err)
 		return err;
 
@@ -1215,6 +1221,10 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 		dma_resv_add_shared_fence(vma->resv, &rq->fence);
 		obj->write_domain = 0;
 	}
+
+	if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence)
+		i915_active_add_request(&vma->fence->active, rq);
+
 	obj->read_domains |= I915_GEM_GPU_DOMAINS;
 	obj->mm.dirty = true;
 
@@ -1249,6 +1259,9 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
 	if (i915_vma_is_map_and_fenceable(vma)) {
+		/* Force a pagefault for domain tracking on next user access */
+		i915_vma_revoke_mmap(vma);
+
 		/*
 		 * Check that we have flushed all writes through the GGTT
 		 * before the unbind, other due to non-strict nature of those
@@ -1265,12 +1278,7 @@ int __i915_vma_unbind(struct i915_vma *vma)
 		i915_vma_flush_writes(vma);
 
 		/* release the fence reg _after_ flushing */
-		ret = i915_vma_revoke_fence(vma);
-		if (ret)
-			return ret;
-
-		/* Force a pagefault for domain tracking on next user access */
-		i915_vma_revoke_mmap(vma);
+		i915_vma_revoke_fence(vma);
 
 		__i915_vma_iounmap(vma);
 		clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
@@ -1315,7 +1323,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 		/* XXX not always required: nop_clear_range */
 		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
 
-	err = mutex_lock_interruptible(&vm->mutex);
+	err = mutex_lock_interruptible_nested(&vma->vm->mutex, !wakeref);
 	if (err)
 		goto out_rpm;
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index e1ced1df13e1..8ad1daabcd58 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -30,10 +30,10 @@
 
 #include <drm/drm_mm.h>
 
+#include "gt/intel_ggtt_fencing.h"
 #include "gem/i915_gem_object.h"
 
 #include "i915_gem_gtt.h"
-#include "i915_gem_fence_reg.h"
 
 #include "i915_active.h"
 #include "i915_request.h"
@@ -326,7 +326,7 @@ static inline struct page *i915_vma_first_page(struct i915_vma *vma)
  * True if the vma has a fence, false otherwise.
  */
 int __must_check i915_vma_pin_fence(struct i915_vma *vma);
-int __must_check i915_vma_revoke_fence(struct i915_vma *vma);
+void i915_vma_revoke_fence(struct i915_vma *vma);
 
 int __i915_vma_pin_fence(struct i915_vma *vma);
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index d7fe12734db8..8a635bd4d5d8 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -98,6 +98,7 @@ void intel_device_info_print_static(const struct intel_device_info *info,
 	drm_printf(p, "platform: %s\n", intel_platform_name(info->platform));
 	drm_printf(p, "ppgtt-size: %d\n", info->ppgtt_size);
 	drm_printf(p, "ppgtt-type: %d\n", info->ppgtt_type);
+	drm_printf(p, "dma_mask_size: %u\n", info->dma_mask_size);
 
 #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->name));
 	DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG);
@@ -135,8 +136,8 @@ void intel_device_info_print_runtime(const struct intel_runtime_info *info,
 	sseu_dump(&info->sseu, p);
 
 	drm_printf(p, "rawclk rate: %u kHz\n", info->rawclk_freq);
-	drm_printf(p, "CS timestamp frequency: %u kHz\n",
-		   info->cs_timestamp_frequency_khz);
+	drm_printf(p, "CS timestamp frequency: %u Hz\n",
+		   info->cs_timestamp_frequency_hz);
 }
 
 static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
@@ -677,12 +678,12 @@ static u32 read_reference_ts_freq(struct drm_i915_private *dev_priv)
 
 	base_freq = ((ts_override & GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK) >>
 		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_SHIFT) + 1;
-	base_freq *= 1000;
+	base_freq *= 1000000;
 
 	frac_freq = ((ts_override &
 		      GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK) >>
 		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_SHIFT);
-	frac_freq = 1000 / (frac_freq + 1);
+	frac_freq = 1000000 / (frac_freq + 1);
 
 	return base_freq + frac_freq;
 }
@@ -690,8 +691,8 @@ static u32 read_reference_ts_freq(struct drm_i915_private *dev_priv)
 static u32 gen10_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
 					u32 rpm_config_reg)
 {
-	u32 f19_2_mhz = 19200;
-	u32 f24_mhz = 24000;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
 	u32 crystal_clock = (rpm_config_reg &
 			     GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
 			    GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
@@ -710,10 +711,10 @@ static u32 gen10_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
 static u32 gen11_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
 					u32 rpm_config_reg)
 {
-	u32 f19_2_mhz = 19200;
-	u32 f24_mhz = 24000;
-	u32 f25_mhz = 25000;
-	u32 f38_4_mhz = 38400;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+	u32 f25_mhz = 25000000;
+	u32 f38_4_mhz = 38400000;
 	u32 crystal_clock = (rpm_config_reg &
 			     GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
 			    GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
@@ -735,9 +736,9 @@ static u32 gen11_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
 
 static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
 {
-	u32 f12_5_mhz = 12500;
-	u32 f19_2_mhz = 19200;
-	u32 f24_mhz = 24000;
+	u32 f12_5_mhz = 12500000;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
 
 	if (INTEL_GEN(dev_priv) <= 4) {
 		/* PRMs say:
@@ -746,7 +747,7 @@ static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
 		 *      hclks." (through the “Clocking Configuration”
 		 *      (“CLKCFG”) MCHBAR register)
 		 */
-		return RUNTIME_INFO(dev_priv)->rawclk_freq / 16;
+		return RUNTIME_INFO(dev_priv)->rawclk_freq * 1000 / 16;
 	} else if (INTEL_GEN(dev_priv) <= 8) {
 		/* PRMs say:
 		 *
@@ -980,35 +981,32 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			drm_info(&dev_priv->drm,
 				 "Display fused off, disabling\n");
 			info->pipe_mask = 0;
+			info->cpu_transcoder_mask = 0;
 		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
 			drm_info(&dev_priv->drm, "PipeC fused off\n");
 			info->pipe_mask &= ~BIT(PIPE_C);
+			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
 		}
 	} else if (HAS_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 9) {
 		u32 dfsm = I915_READ(SKL_DFSM);
-		u8 enabled_mask = info->pipe_mask;
-
-		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
-			enabled_mask &= ~BIT(PIPE_A);
-		if (dfsm & SKL_DFSM_PIPE_B_DISABLE)
-			enabled_mask &= ~BIT(PIPE_B);
-		if (dfsm & SKL_DFSM_PIPE_C_DISABLE)
-			enabled_mask &= ~BIT(PIPE_C);
-		if (INTEL_GEN(dev_priv) >= 12 &&
-		    (dfsm & TGL_DFSM_PIPE_D_DISABLE))
-			enabled_mask &= ~BIT(PIPE_D);
 
-		/*
-		 * At least one pipe should be enabled and if there are
-		 * disabled pipes, they should be the last ones, with no holes
-		 * in the mask.
-		 */
-		if (enabled_mask == 0 || !is_power_of_2(enabled_mask + 1))
-			drm_err(&dev_priv->drm,
-				"invalid pipe fuse configuration: enabled_mask=0x%x\n",
-				enabled_mask);
-		else
-			info->pipe_mask = enabled_mask;
+		if (dfsm & SKL_DFSM_PIPE_A_DISABLE) {
+			info->pipe_mask &= ~BIT(PIPE_A);
+			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_A);
+		}
+		if (dfsm & SKL_DFSM_PIPE_B_DISABLE) {
+			info->pipe_mask &= ~BIT(PIPE_B);
+			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_B);
+		}
+		if (dfsm & SKL_DFSM_PIPE_C_DISABLE) {
+			info->pipe_mask &= ~BIT(PIPE_C);
+			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
+		}
+		if (INTEL_GEN(dev_priv) >= 12 &&
+		    (dfsm & TGL_DFSM_PIPE_D_DISABLE)) {
+			info->pipe_mask &= ~BIT(PIPE_D);
+			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D);
+		}
 
 		if (dfsm & SKL_DFSM_DISPLAY_HDCP_DISABLE)
 			info->display.has_hdcp = 0;
@@ -1050,11 +1048,11 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 	drm_dbg(&dev_priv->drm, "rawclk rate: %d kHz\n", runtime->rawclk_freq);
 
 	/* Initialize command stream timestamp frequency */
-	runtime->cs_timestamp_frequency_khz =
+	runtime->cs_timestamp_frequency_hz =
 		read_timestamp_frequency(dev_priv);
-	if (runtime->cs_timestamp_frequency_khz) {
+	if (runtime->cs_timestamp_frequency_hz) {
 		runtime->cs_timestamp_period_ns =
-			div_u64(1e6, runtime->cs_timestamp_frequency_khz);
+			i915_cs_timestamp_ticks_to_ns(dev_priv, 1);
 		drm_dbg(&dev_priv->drm,
 			"CS timestamp wraparound in %lldms\n",
 			div_u64(mul_u32_u32(runtime->cs_timestamp_period_ns,
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 1ecb9df2de91..62e03ffa377e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -158,6 +158,8 @@ struct intel_device_info {
 
 	enum intel_platform platform;
 
+	unsigned int dma_mask_size; /* available DMA address bits */
+
 	enum intel_ppgtt_type ppgtt_type;
 	unsigned int ppgtt_size; /* log2, e.g. 31/32/48 bits */
 
@@ -168,6 +170,7 @@ struct intel_device_info {
 	u32 display_mmio_offset;
 
 	u8 pipe_mask;
+	u8 cpu_transcoder_mask;
 
 #define DEFINE_FLAG(name) u8 name:1
 	DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG);
@@ -218,7 +221,7 @@ struct intel_runtime_info {
 
 	u32 rawclk_freq;
 
-	u32 cs_timestamp_frequency_khz;
+	u32 cs_timestamp_frequency_hz;
 	u32 cs_timestamp_period_ns;
 
 	/* Media engine access to SFC per instance */
diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c
index 6b922efb1d7c..8aa12cad93ce 100644
--- a/drivers/gpu/drm/i915/intel_dram.c
+++ b/drivers/gpu/drm/i915/intel_dram.c
@@ -495,6 +495,5 @@ void intel_dram_edram_detect(struct drm_i915_private *i915)
 	else
 		i915->edram_size_mb = gen9_edram_size_mb(i915, edram_cap);
 
-	dev_info(i915->drm.dev,
-		 "Found %uMB of eDRAM\n", i915->edram_size_mb);
+	drm_info(&i915->drm, "Found %uMB of eDRAM\n", i915->edram_size_mb);
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a52986a9e7a6..696491d71a1d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -43,6 +43,7 @@
 #include "i915_fixed.h"
 #include "i915_irq.h"
 #include "i915_trace.h"
+#include "display/intel_bw.h"
 #include "intel_pm.h"
 #include "intel_sideband.h"
 #include "../../../platform/x86/intel_ips.h"
@@ -3637,10 +3638,6 @@ 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;
 }
@@ -3757,42 +3754,120 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-bool intel_can_enable_sagv(struct intel_atomic_state *state)
+void intel_sagv_pre_plane_update(struct intel_atomic_state *state)
 {
-	struct drm_device *dev = state->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc;
-	struct intel_plane *plane;
-	struct intel_crtc_state *crtc_state;
-	enum pipe pipe;
-	int level, latency;
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	const struct intel_bw_state *new_bw_state;
+	const struct intel_bw_state *old_bw_state;
+	u32 new_mask = 0;
 
+	/*
+	 * Just return if we can't control SAGV or don't have it.
+	 * This is different from situation when we have SAGV but just can't
+	 * afford it due to DBuf limitation - in case if SAGV is completely
+	 * disabled in a BIOS, we are not even allowed to send a PCode request,
+	 * as it will throw an error. So have to check it here.
+	 */
 	if (!intel_has_sagv(dev_priv))
-		return false;
+		return;
+
+	new_bw_state = intel_atomic_get_new_bw_state(state);
+	if (!new_bw_state)
+		return;
 
+	if (INTEL_GEN(dev_priv) < 11 && !intel_can_enable_sagv(dev_priv, new_bw_state)) {
+		intel_disable_sagv(dev_priv);
+		return;
+	}
+
+	old_bw_state = intel_atomic_get_old_bw_state(state);
 	/*
-	 * If there are no active CRTCs, no additional checks need be performed
+	 * Nothing to mask
 	 */
-	if (hweight8(state->active_pipes) == 0)
-		return true;
+	if (new_bw_state->qgv_points_mask == old_bw_state->qgv_points_mask)
+		return;
+
+	new_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask;
+
+	/*
+	 * If new mask is zero - means there is nothing to mask,
+	 * we can only unmask, which should be done in unmask.
+	 */
+	if (!new_mask)
+		return;
+
+	/*
+	 * Restrict required qgv points before updating the configuration.
+	 * According to BSpec we can't mask and unmask qgv points at the same
+	 * time. Also masking should be done before updating the configuration
+	 * and unmasking afterwards.
+	 */
+	icl_pcode_restrict_qgv_points(dev_priv, new_mask);
+}
+
+void intel_sagv_post_plane_update(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	const struct intel_bw_state *new_bw_state;
+	const struct intel_bw_state *old_bw_state;
+	u32 new_mask = 0;
+
+	/*
+	 * Just return if we can't control SAGV or don't have it.
+	 * This is different from situation when we have SAGV but just can't
+	 * afford it due to DBuf limitation - in case if SAGV is completely
+	 * disabled in a BIOS, we are not even allowed to send a PCode request,
+	 * as it will throw an error. So have to check it here.
+	 */
+	if (!intel_has_sagv(dev_priv))
+		return;
+
+	new_bw_state = intel_atomic_get_new_bw_state(state);
+	if (!new_bw_state)
+		return;
+
+	if (INTEL_GEN(dev_priv) < 11 && intel_can_enable_sagv(dev_priv, new_bw_state)) {
+		intel_enable_sagv(dev_priv);
+		return;
+	}
+
+	old_bw_state = intel_atomic_get_old_bw_state(state);
+	/*
+	 * Nothing to unmask
+	 */
+	if (new_bw_state->qgv_points_mask == old_bw_state->qgv_points_mask)
+		return;
+
+	new_mask = new_bw_state->qgv_points_mask;
 
 	/*
-	 * SKL+ workaround: bspec recommends we disable SAGV when we have
-	 * more then one pipe enabled
+	 * Allow required qgv points after updating the configuration.
+	 * According to BSpec we can't mask and unmask qgv points at the same
+	 * time. Also masking should be done before updating the configuration
+	 * and unmasking afterwards.
 	 */
-	if (hweight8(state->active_pipes) > 1)
+	icl_pcode_restrict_qgv_points(dev_priv, new_mask);
+}
+
+static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_plane *plane;
+	const struct intel_plane_state *plane_state;
+	int level, latency;
+
+	if (!intel_has_sagv(dev_priv))
 		return false;
 
-	/* Since we're now guaranteed to only have one active CRTC... */
-	pipe = ffs(state->active_pipes) - 1;
-	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-	crtc_state = to_intel_crtc_state(crtc->base.state);
+	if (!crtc_state->hw.active)
+		return true;
 
 	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
-	for_each_intel_plane_on_crtc(dev, crtc, plane) {
-		struct skl_plane_wm *wm =
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+		const struct skl_plane_wm *wm =
 			&crtc_state->wm.skl.optimal.planes[plane->id];
 
 		/* Skip this plane if it's not enabled */
@@ -3807,7 +3882,7 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 		latency = dev_priv->wm.skl_latency[level];
 
 		if (skl_needs_memory_bw_wa(dev_priv) &&
-		    plane->base.state->fb->modifier ==
+		    plane_state->uapi.fb->modifier ==
 		    I915_FORMAT_MOD_X_TILED)
 			latency += 15;
 
@@ -3823,6 +3898,112 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	return true;
 }
 
+static bool tgl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	enum plane_id plane_id;
+
+	if (!crtc_state->hw.active)
+		return true;
+
+	for_each_plane_id_on_crtc(crtc, plane_id) {
+		const struct skl_ddb_entry *plane_alloc =
+			&crtc_state->wm.skl.plane_ddb_y[plane_id];
+		const struct skl_plane_wm *wm =
+			&crtc_state->wm.skl.optimal.planes[plane_id];
+
+		if (skl_ddb_entry_size(plane_alloc) < wm->sagv_wm0.min_ddb_alloc)
+			return false;
+	}
+
+	return true;
+}
+
+static bool intel_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		return tgl_crtc_can_enable_sagv(crtc_state);
+	else
+		return skl_crtc_can_enable_sagv(crtc_state);
+}
+
+bool intel_can_enable_sagv(struct drm_i915_private *dev_priv,
+			   const struct intel_bw_state *bw_state)
+{
+	if (INTEL_GEN(dev_priv) < 11 &&
+	    bw_state->active_pipes && !is_power_of_2(bw_state->active_pipes))
+		return false;
+
+	return bw_state->pipe_sagv_reject == 0;
+}
+
+static int intel_compute_sagv_mask(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	int ret;
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_bw_state *new_bw_state = NULL;
+	const struct intel_bw_state *old_bw_state = NULL;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc,
+					 new_crtc_state, i) {
+		new_bw_state = intel_atomic_get_bw_state(state);
+		if (IS_ERR(new_bw_state))
+			return PTR_ERR(new_bw_state);
+
+		old_bw_state = intel_atomic_get_old_bw_state(state);
+
+		if (intel_crtc_can_enable_sagv(new_crtc_state))
+			new_bw_state->pipe_sagv_reject &= ~BIT(crtc->pipe);
+		else
+			new_bw_state->pipe_sagv_reject |= BIT(crtc->pipe);
+	}
+
+	if (!new_bw_state)
+		return 0;
+
+	new_bw_state->active_pipes =
+		intel_calc_active_pipes(state, old_bw_state->active_pipes);
+
+	if (new_bw_state->active_pipes != old_bw_state->active_pipes) {
+		ret = intel_atomic_lock_global_state(&new_bw_state->base);
+		if (ret)
+			return ret;
+	}
+
+	for_each_new_intel_crtc_in_state(state, crtc,
+					 new_crtc_state, i) {
+		struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal;
+
+		/*
+		 * We store use_sagv_wm in the crtc state rather than relying on
+		 * that bw state since we have no convenient way to get at the
+		 * latter from the plane commit hooks (especially in the legacy
+		 * cursor case)
+		 */
+		pipe_wm->use_sagv_wm = INTEL_GEN(dev_priv) >= 12 &&
+				       intel_can_enable_sagv(dev_priv, new_bw_state);
+	}
+
+	if (intel_can_enable_sagv(dev_priv, new_bw_state) !=
+	    intel_can_enable_sagv(dev_priv, old_bw_state)) {
+		ret = intel_atomic_serialize_global_state(&new_bw_state->base);
+		if (ret)
+			return ret;
+	} else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) {
+		ret = intel_atomic_lock_global_state(&new_bw_state->base);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /*
  * Calculate initial DBuf slice offset, based on slice size
  * and mask(i.e if slice size is 1024 and second slice is enabled
@@ -4016,6 +4197,7 @@ static int skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 				 int color_plane);
 static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 				 int level,
+				 unsigned int latency,
 				 const struct skl_wm_params *wp,
 				 const struct skl_wm_level *result_prev,
 				 struct skl_wm_level *result /* out */);
@@ -4038,7 +4220,9 @@ skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
 	drm_WARN_ON(&dev_priv->drm, ret);
 
 	for (level = 0; level <= max_level; level++) {
-		skl_compute_plane_wm(crtc_state, level, &wp, &wm, &wm);
+		unsigned int latency = dev_priv->wm.skl_latency[level];
+
+		skl_compute_plane_wm(crtc_state, level, latency, &wp, &wm, &wm);
 		if (wm.min_ddb_alloc == U16_MAX)
 			break;
 
@@ -4544,6 +4728,20 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 	return total_data_rate;
 }
 
+static const struct skl_wm_level *
+skl_plane_wm_level(const struct intel_crtc_state *crtc_state,
+		   enum plane_id plane_id,
+		   int level)
+{
+	const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
+	const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id];
+
+	if (level == 0 && pipe_wm->use_sagv_wm)
+		return &wm->sagv_wm0;
+
+	return &wm->wm[level];
+}
+
 static int
 skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 {
@@ -4580,7 +4778,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 							 plane_data_rate,
 							 uv_plane_data_rate);
 
-
 	skl_ddb_get_pipe_allocation_limits(dev_priv, crtc_state, total_data_rate,
 					   alloc, &num_active);
 	alloc_size = skl_ddb_entry_size(alloc);
@@ -4780,7 +4977,7 @@ skl_wm_method1(const struct drm_i915_private *dev_priv, u32 pixel_rate,
 	wm_intermediate_val = latency * pixel_rate * cpp;
 	ret = div_fixed16(wm_intermediate_val, 1000 * dbuf_block_size);
 
-	if (INTEL_GEN(dev_priv) >= 10)
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		ret = add_fixed16_u32(ret, 1);
 
 	return ret;
@@ -4915,18 +5112,19 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 					   wp->y_min_scanlines,
 					   wp->dbuf_block_size);
 
-		if (INTEL_GEN(dev_priv) >= 10)
+		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 			interm_pbpl++;
 
 		wp->plane_blocks_per_line = div_fixed16(interm_pbpl,
 							wp->y_min_scanlines);
-	} else if (wp->x_tiled && IS_GEN(dev_priv, 9)) {
-		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
-					   wp->dbuf_block_size);
-		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	} else {
 		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
-					   wp->dbuf_block_size) + 1;
+					   wp->dbuf_block_size);
+
+		if (!wp->x_tiled ||
+		    INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+			interm_pbpl++;
+
 		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	}
 
@@ -4972,12 +5170,12 @@ static bool skl_wm_has_lines(struct drm_i915_private *dev_priv, int level)
 
 static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 				 int level,
+				 unsigned int latency,
 				 const struct skl_wm_params *wp,
 				 const struct skl_wm_level *result_prev,
 				 struct skl_wm_level *result /* out */)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
-	u32 latency = dev_priv->wm.skl_latency[level];
 	uint_fixed_16_16_t method1, method2;
 	uint_fixed_16_16_t selected_result;
 	u32 res_blocks, res_lines, min_ddb_alloc = 0;
@@ -5106,14 +5304,29 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 
 	for (level = 0; level <= max_level; level++) {
 		struct skl_wm_level *result = &levels[level];
+		unsigned int latency = dev_priv->wm.skl_latency[level];
 
-		skl_compute_plane_wm(crtc_state, level, wm_params,
-				     result_prev, result);
+		skl_compute_plane_wm(crtc_state, level, latency,
+				     wm_params, result_prev, result);
 
 		result_prev = result;
 	}
 }
 
+static void tgl_compute_sagv_wm(const struct intel_crtc_state *crtc_state,
+				const struct skl_wm_params *wm_params,
+				struct skl_plane_wm *plane_wm)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct skl_wm_level *sagv_wm = &plane_wm->sagv_wm0;
+	struct skl_wm_level *levels = plane_wm->wm;
+	unsigned int latency = dev_priv->wm.skl_latency[0] + dev_priv->sagv_block_time_us;
+
+	skl_compute_plane_wm(crtc_state, 0, latency,
+			     wm_params, &levels[0],
+			     sagv_wm);
+}
+
 static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
 				      const struct skl_wm_params *wp,
 				      struct skl_plane_wm *wm)
@@ -5166,10 +5379,6 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
 				trans_offset_b;
 	} else {
 		res_blocks = wm0_sel_res_b + trans_offset_b;
-
-		/* WA BUG:1938466 add one block for non y-tile planes */
-		if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_A0))
-			res_blocks += 1;
 	}
 
 	/*
@@ -5185,6 +5394,8 @@ static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state,
 				     const struct intel_plane_state *plane_state,
 				     enum plane_id plane_id, int color_plane)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id];
 	struct skl_wm_params wm_params;
 	int ret;
@@ -5195,6 +5406,10 @@ static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	skl_compute_wm_levels(crtc_state, &wm_params, wm->wm);
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_compute_sagv_wm(crtc_state, &wm_params, wm);
+
 	skl_compute_transition_wm(crtc_state, &wm_params, wm);
 
 	return 0;
@@ -5354,8 +5569,12 @@ void skl_write_plane_wm(struct intel_plane *plane,
 		&crtc_state->wm.skl.plane_ddb_uv[plane_id];
 
 	for (level = 0; level <= max_level; level++) {
+		const struct skl_wm_level *wm_level;
+
+		wm_level = skl_plane_wm_level(crtc_state, plane_id, level);
+
 		skl_write_wm_level(dev_priv, PLANE_WM(pipe, plane_id, level),
-				   &wm->wm[level]);
+				   wm_level);
 	}
 	skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id),
 			   &wm->trans_wm);
@@ -5388,8 +5607,12 @@ void skl_write_cursor_wm(struct intel_plane *plane,
 		&crtc_state->wm.skl.plane_ddb_y[plane_id];
 
 	for (level = 0; level <= max_level; level++) {
+		const struct skl_wm_level *wm_level;
+
+		wm_level = skl_plane_wm_level(crtc_state, plane_id, level);
+
 		skl_write_wm_level(dev_priv, CUR_WM(pipe, level),
-				   &wm->wm[level]);
+				   wm_level);
 	}
 	skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), &wm->trans_wm);
 
@@ -5424,8 +5647,8 @@ static bool skl_plane_wm_equals(struct drm_i915_private *dev_priv,
 	return skl_wm_level_equals(&wm1->trans_wm, &wm2->trans_wm);
 }
 
-static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
-					   const struct skl_ddb_entry *b)
+static bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
+				    const struct skl_ddb_entry *b)
 {
 	return a->start < b->end && b->start < a->end;
 }
@@ -5553,23 +5776,25 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				continue;
 
 			drm_dbg_kms(&dev_priv->drm,
-				    "[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm"
-				    " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm\n",
+				    "[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm"
+				    " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm\n",
 				    plane->base.base.id, plane->base.name,
 				    enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
 				    enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
 				    enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
 				    enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
 				    enast(old_wm->trans_wm.plane_en),
+				    enast(old_wm->sagv_wm0.plane_en),
 				    enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
 				    enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
 				    enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
 				    enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
-				    enast(new_wm->trans_wm.plane_en));
+				    enast(new_wm->trans_wm.plane_en),
+				    enast(new_wm->sagv_wm0.plane_en));
 
 			drm_dbg_kms(&dev_priv->drm,
-				    "[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
-				      " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
+				    "[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
+				      " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
 				    plane->base.base.id, plane->base.name,
 				    enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
 				    enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
@@ -5580,6 +5805,7 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
 				    enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
 				    enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
+				    enast(old_wm->sagv_wm0.ignore_lines), old_wm->sagv_wm0.plane_res_l,
 
 				    enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
 				    enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
@@ -5589,37 +5815,42 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
 				    enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
 				    enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
-				    enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l);
+				    enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l,
+				    enast(new_wm->sagv_wm0.ignore_lines), new_wm->sagv_wm0.plane_res_l);
 
 			drm_dbg_kms(&dev_priv->drm,
-				    "[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    "[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
 				    plane->base.base.id, plane->base.name,
 				    old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
 				    old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
 				    old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
 				    old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
 				    old_wm->trans_wm.plane_res_b,
+				    old_wm->sagv_wm0.plane_res_b,
 				    new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
 				    new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
 				    new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
 				    new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
-				    new_wm->trans_wm.plane_res_b);
+				    new_wm->trans_wm.plane_res_b,
+				    new_wm->sagv_wm0.plane_res_b);
 
 			drm_dbg_kms(&dev_priv->drm,
-				    "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
 				    plane->base.base.id, plane->base.name,
 				    old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
 				    old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
 				    old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
 				    old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
 				    old_wm->trans_wm.min_ddb_alloc,
+				    old_wm->sagv_wm0.min_ddb_alloc,
 				    new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
 				    new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
 				    new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
 				    new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
-				    new_wm->trans_wm.min_ddb_alloc);
+				    new_wm->trans_wm.min_ddb_alloc,
+				    new_wm->sagv_wm0.min_ddb_alloc);
 		}
 	}
 }
@@ -5780,6 +6011,10 @@ skl_compute_wm(struct intel_atomic_state *state)
 	if (ret)
 		return ret;
 
+	ret = intel_compute_sagv_mask(state);
+	if (ret)
+		return ret;
+
 	/*
 	 * skl_compute_ddb() will have adjusted the final watermarks
 	 * based on how much ddb is available. Now we can actually
@@ -5876,8 +6111,7 @@ static void ilk_optimize_watermarks(struct intel_atomic_state *state,
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
 
-static inline void skl_wm_level_from_reg_val(u32 val,
-					     struct skl_wm_level *level)
+static void skl_wm_level_from_reg_val(u32 val, struct skl_wm_level *level)
 {
 	level->plane_en = val & PLANE_WM_EN;
 	level->ignore_lines = val & PLANE_WM_IGNORE_LINES;
@@ -5909,6 +6143,9 @@ void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc,
 			skl_wm_level_from_reg_val(val, &wm->wm[level]);
 		}
 
+		if (INTEL_GEN(dev_priv) >= 12)
+			wm->sagv_wm0 = wm->wm[0];
+
 		if (plane_id != PLANE_CURSOR)
 			val = I915_READ(PLANE_WM_TRANS(pipe, plane_id));
 		else
@@ -6850,6 +7087,10 @@ static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
 	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0))
 		I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) |
 			   TGL_VRH_GATING_DIS);
+
+	/* Wa_14011059788:tgl */
+	intel_uncore_rmw(&dev_priv->uncore, GEN10_DFR_RATIO_EN_AND_CHICKEN,
+			 0, DFR_DISABLE);
 }
 
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -6882,9 +7123,6 @@ static void cnl_init_clock_gating(struct drm_i915_private *dev_priv)
 	val = I915_READ(SLICE_UNIT_LEVEL_CLKGATE);
 	/* ReadHitWriteOnlyDisable:cnl */
 	val |= RCCUNIT_CLKGATE_DIS;
-	/* WaSarbUnitClockGatingDisable:cnl (pre-prod) */
-	if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_B0))
-		val |= SARBUNIT_CLKGATE_DIS;
 	I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, val);
 
 	/* Wa_2201832410:cnl */
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index d60a85421c5a..614ac7f8d4cc 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 
 #include "i915_reg.h"
+#include "display/intel_bw.h"
 
 struct drm_device;
 struct drm_i915_private;
@@ -41,9 +42,12 @@ void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc,
 			      struct skl_pipe_wm *out);
 void g4x_wm_sanitize(struct drm_i915_private *dev_priv);
 void vlv_wm_sanitize(struct drm_i915_private *dev_priv);
-bool intel_can_enable_sagv(struct intel_atomic_state *state);
+bool intel_can_enable_sagv(struct drm_i915_private *dev_priv,
+			   const struct intel_bw_state *bw_state);
 int intel_enable_sagv(struct drm_i915_private *dev_priv);
 int intel_disable_sagv(struct drm_i915_private *dev_priv);
+void intel_sagv_pre_plane_update(struct intel_atomic_state *state);
+void intel_sagv_post_plane_update(struct intel_atomic_state *state);
 bool skl_wm_level_equals(const struct skl_wm_level *l1,
 			 const struct skl_wm_level *l2);
 bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb,
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 3f13baaef058..916ccd1c0e96 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -336,7 +336,7 @@ void intel_sbi_write(struct drm_i915_private *i915, u16 reg, u32 value,
 	intel_sbi_rw(i915, reg, destination, &value, false);
 }
 
-static inline int gen6_check_mailbox_status(u32 mbox)
+static int gen6_check_mailbox_status(u32 mbox)
 {
 	switch (mbox & GEN6_PCODE_ERROR_MASK) {
 	case GEN6_PCODE_SUCCESS:
@@ -356,7 +356,7 @@ static inline int gen6_check_mailbox_status(u32 mbox)
 	}
 }
 
-static inline int gen7_check_mailbox_status(u32 mbox)
+static int gen7_check_mailbox_status(u32 mbox)
 {
 	switch (mbox & GEN6_PCODE_ERROR_MASK) {
 	case GEN6_PCODE_SUCCESS:
@@ -371,6 +371,8 @@ static inline int gen7_check_mailbox_status(u32 mbox)
 		return -ENXIO;
 	case GEN11_PCODE_LOCKED:
 		return -EBUSY;
+	case GEN11_PCODE_REJECTED:
+		return -EACCES;
 	case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
 		return -EOVERFLOW;
 	default:
@@ -429,7 +431,7 @@ int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox,
 
 	mutex_lock(&i915->sb_lock);
 	err = __sandybridge_pcode_rw(i915, mbox, val, val1,
-				     500, 0,
+				     500, 20,
 				     true);
 	mutex_unlock(&i915->sb_lock);
 
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index abb18b90d7c3..a61cb8ca4d50 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -665,7 +665,7 @@ void intel_uncore_forcewake_user_put(struct intel_uncore *uncore)
 		mmio_debug_resume(uncore->debug);
 
 		if (check_for_unclaimed_mmio(uncore))
-			dev_info(uncore->i915->drm.dev,
+			drm_info(&uncore->i915->drm,
 				 "Invalid mmio detected during user access\n");
 		spin_unlock(&uncore->debug->lock);
 
@@ -735,6 +735,28 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore,
 }
 
 /**
+ * intel_uncore_forcewake_flush - flush the delayed release
+ * @uncore: the intel_uncore structure
+ * @fw_domains: forcewake domains to flush
+ */
+void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
+				  enum forcewake_domains fw_domains)
+{
+	struct intel_uncore_forcewake_domain *domain;
+	unsigned int tmp;
+
+	if (!uncore->funcs.force_wake_put)
+		return;
+
+	fw_domains &= uncore->fw_domains;
+	for_each_fw_domain_masked(domain, fw_domains, uncore, tmp) {
+		WRITE_ONCE(domain->active, false);
+		if (hrtimer_cancel(&domain->timer))
+			intel_uncore_fw_release_timer(&domain->timer);
+	}
+}
+
+/**
  * intel_uncore_forcewake_put__locked - grab forcewake domain references
  * @uncore: the intel_uncore structure
  * @fw_domains: forcewake domains to get reference on
@@ -877,11 +899,6 @@ find_fw_domain(struct intel_uncore *uncore, u32 offset)
 #define GEN_FW_RANGE(s, e, d) \
 	{ .start = (s), .end = (e), .domains = (d) }
 
-#define HAS_FWTABLE(dev_priv) \
-	(INTEL_GEN(dev_priv) >= 9 || \
-	 IS_CHERRYVIEW(dev_priv) || \
-	 IS_VALLEYVIEW(dev_priv))
-
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
 static const struct intel_forcewake_range __vlv_fw_ranges[] = {
 	GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER),
@@ -1070,8 +1087,7 @@ static const struct intel_forcewake_range __gen9_fw_ranges[] = {
 
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
 static const struct intel_forcewake_range __gen11_fw_ranges[] = {
-	GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_BLITTER),
-	GEN_FW_RANGE(0xb00, 0x1fff, 0), /* uncore range */
+	GEN_FW_RANGE(0x0, 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),
@@ -1081,27 +1097,31 @@ static const struct intel_forcewake_range __gen11_fw_ranges[] = {
 	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(0x8500, 0x87ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x8800, 0x8bff, 0),
 	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(0x8d00, 0x94cf, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x94d0, 0x955f, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x9560, 0x95ff, 0),
+	GEN_FW_RANGE(0x9600, 0xafff, FORCEWAKE_BLITTER),
 	GEN_FW_RANGE(0xb000, 0xb47f, FORCEWAKE_RENDER),
 	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(0x1a000, 0x23fff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x24000, 0x2407f, 0),
+	GEN_FW_RANGE(0x24080, 0x2417f, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x24180, 0x242ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x24300, 0x243ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x24400, 0x24fff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x25000, 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(0x1c4000, 0x1c7fff, 0),
+	GEN_FW_RANGE(0x1c8000, 0x1cffff, FORCEWAKE_MEDIA_VEBOX0),
 	GEN_FW_RANGE(0x1d0000, 0x1d3fff, FORCEWAKE_MEDIA_VDBOX2),
-	GEN_FW_RANGE(0x1d4000, 0x1d7fff, FORCEWAKE_MEDIA_VDBOX3),
-	GEN_FW_RANGE(0x1d8000, 0x1dbfff, FORCEWAKE_MEDIA_VEBOX1)
+	GEN_FW_RANGE(0x1d4000, 0x1dbfff, 0)
 };
 
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index dcfa243892c6..8d3aa8b9acf9 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -209,7 +209,11 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore,
 				enum forcewake_domains domains);
 void intel_uncore_forcewake_put(struct intel_uncore *uncore,
 				enum forcewake_domains domains);
-/* Like above but the caller must manage the uncore.lock itself.
+void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
+				  enum forcewake_domains fw_domains);
+
+/*
+ * Like above but the caller must manage the uncore.lock itself.
  * Must be used with I915_READ_FW and friends.
  */
 void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 8fbf6f4d3f26..dfd87d082218 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -70,11 +70,12 @@ unlock:
 
 void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
 {
-	INTEL_WAKEREF_BUG_ON(work_pending(&wf->work));
+	INTEL_WAKEREF_BUG_ON(delayed_work_pending(&wf->work));
 
 	/* Assume we are not in process context and so cannot sleep. */
 	if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) {
-		schedule_work(&wf->work);
+		mod_delayed_work(system_wq, &wf->work,
+				 FIELD_GET(INTEL_WAKEREF_PUT_DELAY, flags));
 		return;
 	}
 
@@ -83,7 +84,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
 
 static void __intel_wakeref_put_work(struct work_struct *wrk)
 {
-	struct intel_wakeref *wf = container_of(wrk, typeof(*wf), work);
+	struct intel_wakeref *wf = container_of(wrk, typeof(*wf), work.work);
 
 	if (atomic_add_unless(&wf->count, -1, 1))
 		return;
@@ -104,8 +105,9 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 	atomic_set(&wf->count, 0);
 	wf->wakeref = 0;
 
-	INIT_WORK(&wf->work, __intel_wakeref_put_work);
-	lockdep_init_map(&wf->work.lockdep_map, "wakeref.work", &key->work, 0);
+	INIT_DELAYED_WORK(&wf->work, __intel_wakeref_put_work);
+	lockdep_init_map(&wf->work.work.lockdep_map,
+			 "wakeref.work", &key->work, 0);
 }
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index 7d1e676b71ef..545c8f277c46 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -8,6 +8,7 @@
 #define INTEL_WAKEREF_H
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
@@ -41,7 +42,7 @@ struct intel_wakeref {
 	struct intel_runtime_pm *rpm;
 	const struct intel_wakeref_ops *ops;
 
-	struct work_struct work;
+	struct delayed_work work;
 };
 
 struct intel_wakeref_lockclass {
@@ -117,6 +118,11 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
 	return atomic_inc_not_zero(&wf->count);
 }
 
+enum {
+	INTEL_WAKEREF_PUT_ASYNC_BIT = 0,
+	__INTEL_WAKEREF_PUT_LAST_BIT__
+};
+
 /**
  * intel_wakeref_put_flags: Release the wakeref
  * @wf: the wakeref
@@ -134,7 +140,9 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
  */
 static inline void
 __intel_wakeref_put(struct intel_wakeref *wf, unsigned long flags)
-#define INTEL_WAKEREF_PUT_ASYNC BIT(0)
+#define INTEL_WAKEREF_PUT_ASYNC BIT(INTEL_WAKEREF_PUT_ASYNC_BIT)
+#define INTEL_WAKEREF_PUT_DELAY \
+	GENMASK(BITS_PER_LONG - 1, __INTEL_WAKEREF_PUT_LAST_BIT__)
 {
 	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
 	if (unlikely(!atomic_add_unless(&wf->count, -1, 1)))
@@ -154,6 +162,14 @@ intel_wakeref_put_async(struct intel_wakeref *wf)
 	__intel_wakeref_put(wf, INTEL_WAKEREF_PUT_ASYNC);
 }
 
+static inline void
+intel_wakeref_put_delay(struct intel_wakeref *wf, unsigned long delay)
+{
+	__intel_wakeref_put(wf,
+			    INTEL_WAKEREF_PUT_ASYNC |
+			    FIELD_PREP(INTEL_WAKEREF_PUT_DELAY, delay));
+}
+
 /**
  * intel_wakeref_lock: Lock the wakeref (mutex)
  * @wf: the wakeref
@@ -194,7 +210,7 @@ intel_wakeref_unlock_wait(struct intel_wakeref *wf)
 {
 	mutex_lock(&wf->mutex);
 	mutex_unlock(&wf->mutex);
-	flush_work(&wf->work);
+	flush_delayed_work(&wf->work);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c
index 2bb9f9f9a50a..ec776591e1cf 100644
--- a/drivers/gpu/drm/i915/intel_wopcm.c
+++ b/drivers/gpu/drm/i915/intel_wopcm.c
@@ -86,10 +86,10 @@ void intel_wopcm_init_early(struct intel_wopcm *wopcm)
 	else
 		wopcm->size = GEN9_WOPCM_SIZE;
 
-	DRM_DEV_DEBUG_DRIVER(i915->drm.dev, "WOPCM: %uK\n", wopcm->size / 1024);
+	drm_dbg(&i915->drm, "WOPCM: %uK\n", wopcm->size / 1024);
 }
 
-static inline u32 context_reserved_size(struct drm_i915_private *i915)
+static u32 context_reserved_size(struct drm_i915_private *i915)
 {
 	if (IS_GEN9_LP(i915))
 		return BXT_WOPCM_RC6_CTX_RESERVED;
@@ -99,8 +99,8 @@ static inline u32 context_reserved_size(struct drm_i915_private *i915)
 		return 0;
 }
 
-static inline bool gen9_check_dword_gap(struct drm_i915_private *i915,
-					u32 guc_wopcm_base, u32 guc_wopcm_size)
+static bool gen9_check_dword_gap(struct drm_i915_private *i915,
+				 u32 guc_wopcm_base, u32 guc_wopcm_size)
 {
 	u32 offset;
 
@@ -112,7 +112,7 @@ static inline bool gen9_check_dword_gap(struct drm_i915_private *i915,
 	offset = guc_wopcm_base + GEN9_GUC_WOPCM_OFFSET;
 	if (offset > guc_wopcm_size ||
 	    (guc_wopcm_size - offset) < sizeof(u32)) {
-		dev_err(i915->drm.dev,
+		drm_err(&i915->drm,
 			"WOPCM: invalid GuC region size: %uK < %uK\n",
 			guc_wopcm_size / SZ_1K,
 			(u32)(offset + sizeof(u32)) / SZ_1K);
@@ -122,8 +122,8 @@ static inline bool gen9_check_dword_gap(struct drm_i915_private *i915,
 	return true;
 }
 
-static inline bool gen9_check_huc_fw_fits(struct drm_i915_private *i915,
-					  u32 guc_wopcm_size, u32 huc_fw_size)
+static bool gen9_check_huc_fw_fits(struct drm_i915_private *i915,
+				   u32 guc_wopcm_size, u32 huc_fw_size)
 {
 	/*
 	 * On Gen9 & CNL A0, hardware requires the total available GuC WOPCM
@@ -131,7 +131,7 @@ static inline bool gen9_check_huc_fw_fits(struct drm_i915_private *i915,
 	 * firmware uploading would fail.
 	 */
 	if (huc_fw_size > guc_wopcm_size - GUC_WOPCM_RESERVED) {
-		dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n",
+		drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n",
 			intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC),
 			(guc_wopcm_size - GUC_WOPCM_RESERVED) / SZ_1K,
 			huc_fw_size / 1024);
@@ -141,32 +141,31 @@ static inline bool gen9_check_huc_fw_fits(struct drm_i915_private *i915,
 	return true;
 }
 
-static inline bool check_hw_restrictions(struct drm_i915_private *i915,
-					 u32 guc_wopcm_base, u32 guc_wopcm_size,
-					 u32 huc_fw_size)
+static bool check_hw_restrictions(struct drm_i915_private *i915,
+				  u32 guc_wopcm_base, u32 guc_wopcm_size,
+				  u32 huc_fw_size)
 {
 	if (IS_GEN(i915, 9) && !gen9_check_dword_gap(i915, guc_wopcm_base,
 						     guc_wopcm_size))
 		return false;
 
-	if ((IS_GEN(i915, 9) ||
-	     IS_CNL_REVID(i915, CNL_REVID_A0, CNL_REVID_A0)) &&
+	if (IS_GEN(i915, 9) &&
 	    !gen9_check_huc_fw_fits(i915, guc_wopcm_size, huc_fw_size))
 		return false;
 
 	return true;
 }
 
-static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size,
-				  u32 guc_wopcm_base, u32 guc_wopcm_size,
-				  u32 guc_fw_size, u32 huc_fw_size)
+static bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size,
+			   u32 guc_wopcm_base, u32 guc_wopcm_size,
+			   u32 guc_fw_size, u32 huc_fw_size)
 {
 	const u32 ctx_rsvd = context_reserved_size(i915);
 	u32 size;
 
 	size = wopcm_size - ctx_rsvd;
 	if (unlikely(range_overflows(guc_wopcm_base, guc_wopcm_size, size))) {
-		dev_err(i915->drm.dev,
+		drm_err(&i915->drm,
 			"WOPCM: invalid GuC region layout: %uK + %uK > %uK\n",
 			guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K,
 			size / SZ_1K);
@@ -175,7 +174,7 @@ static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size,
 
 	size = guc_fw_size + GUC_WOPCM_RESERVED + GUC_WOPCM_STACK_RESERVED;
 	if (unlikely(guc_wopcm_size < size)) {
-		dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n",
+		drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n",
 			intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC),
 			guc_wopcm_size / SZ_1K, size / SZ_1K);
 		return false;
@@ -183,7 +182,7 @@ static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size,
 
 	size = huc_fw_size + WOPCM_RESERVED_SIZE;
 	if (unlikely(guc_wopcm_base < size)) {
-		dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n",
+		drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n",
 			intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC),
 			guc_wopcm_base / SZ_1K, size / SZ_1K);
 		return false;
@@ -242,10 +241,8 @@ void intel_wopcm_init(struct intel_wopcm *wopcm)
 		return;
 
 	if (__wopcm_regs_locked(gt->uncore, &guc_wopcm_base, &guc_wopcm_size)) {
-		DRM_DEV_DEBUG_DRIVER(i915->drm.dev,
-				     "GuC WOPCM is already locked [%uK, %uK)\n",
-				     guc_wopcm_base / SZ_1K,
-				     guc_wopcm_size / SZ_1K);
+		drm_dbg(&i915->drm, "GuC WOPCM is already locked [%uK, %uK)\n",
+			guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K);
 		goto check;
 	}
 
@@ -266,8 +263,8 @@ void intel_wopcm_init(struct intel_wopcm *wopcm)
 	guc_wopcm_size = wopcm->size - ctx_rsvd - guc_wopcm_base;
 	guc_wopcm_size &= GUC_WOPCM_SIZE_MASK;
 
-	DRM_DEV_DEBUG_DRIVER(i915->drm.dev, "Calculated GuC WOPCM [%uK, %uK)\n",
-			     guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K);
+	drm_dbg(&i915->drm, "Calculated GuC WOPCM [%uK, %uK)\n",
+		guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K);
 
 check:
 	if (__check_layout(i915, wopcm->size, guc_wopcm_base, guc_wopcm_size,
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bdw.c b/drivers/gpu/drm/i915/oa/i915_oa_bdw.c
deleted file mode 100644
index 14da5c3b569d..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_bdw.c
+++ /dev/null
@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_bdw.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x000000a0 },
-	{ _MMIO(0x9888), 0x198b0000 },
-	{ _MMIO(0x9888), 0x078b0066 },
-	{ _MMIO(0x9888), 0x118b0000 },
-	{ _MMIO(0x9888), 0x258b0000 },
-	{ _MMIO(0x9888), 0x21850008 },
-	{ _MMIO(0x9888), 0x0d834000 },
-	{ _MMIO(0x9888), 0x07844000 },
-	{ _MMIO(0x9888), 0x17804000 },
-	{ _MMIO(0x9888), 0x21800000 },
-	{ _MMIO(0x9888), 0x4f800000 },
-	{ _MMIO(0x9888), 0x41800000 },
-	{ _MMIO(0x9888), 0x31800000 },
-	{ _MMIO(0x9840), 0x00000080 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_bdw(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"d6de6f55-e526-4f79-a6a6-d7315c09044e",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "d6de6f55-e526-4f79-a6a6-d7315c09044e";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bdw.h b/drivers/gpu/drm/i915/oa/i915_oa_bdw.h
deleted file mode 100644
index 0cee3334f0a6..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_bdw.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_BDW_H__
-#define __I915_OA_BDW_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_bdw(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bxt.c b/drivers/gpu/drm/i915/oa/i915_oa_bxt.c
deleted file mode 100644
index 3e785bafcf99..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_bxt.c
+++ /dev/null
@@ -1,88 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_bxt.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x19800000 },
-	{ _MMIO(0x9888), 0x07800063 },
-	{ _MMIO(0x9888), 0x11800000 },
-	{ _MMIO(0x9888), 0x23810008 },
-	{ _MMIO(0x9888), 0x1d950400 },
-	{ _MMIO(0x9888), 0x0f922000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x55900000 },
-	{ _MMIO(0x9888), 0x47900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_bxt(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"5ee72f5c-092f-421e-8b70-225f7c3e9612",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "5ee72f5c-092f-421e-8b70-225f7c3e9612";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bxt.h b/drivers/gpu/drm/i915/oa/i915_oa_bxt.h
deleted file mode 100644
index 0bdf391323ec..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_bxt.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_BXT_H__
-#define __I915_OA_BXT_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_bxt(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c
deleted file mode 100644
index 0ea86f70a06c..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_cflgt2.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_cflgt2(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"74fb4902-d3d3-4237-9e90-cbdc68d0a446",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "74fb4902-d3d3-4237-9e90-cbdc68d0a446";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h
deleted file mode 100644
index 6b862280ab78..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_CFLGT2_H__
-#define __I915_OA_CFLGT2_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_cflgt2(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c
deleted file mode 100644
index fc632dd890bf..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_cflgt3.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"577e8e2c-3fa0-4875-8743-3538d585e3b0",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "577e8e2c-3fa0-4875-8743-3538d585e3b0";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h
deleted file mode 100644
index 4ca9d8f89b2f..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_CFLGT3_H__
-#define __I915_OA_CFLGT3_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_chv.c b/drivers/gpu/drm/i915/oa/i915_oa_chv.c
deleted file mode 100644
index 6cd4e9921a8a..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_chv.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_chv.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x000000a0 },
-	{ _MMIO(0x9888), 0x59800000 },
-	{ _MMIO(0x9888), 0x59800001 },
-	{ _MMIO(0x9888), 0x338b0000 },
-	{ _MMIO(0x9888), 0x258b0066 },
-	{ _MMIO(0x9888), 0x058b0000 },
-	{ _MMIO(0x9888), 0x038b0000 },
-	{ _MMIO(0x9888), 0x03844000 },
-	{ _MMIO(0x9888), 0x47800080 },
-	{ _MMIO(0x9888), 0x57800000 },
-	{ _MMIO(0x1823a4), 0x00000000 },
-	{ _MMIO(0x9888), 0x59800000 },
-	{ _MMIO(0x9840), 0x00000080 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_chv(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"4a534b07-cba3-414d-8d60-874830e883aa",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "4a534b07-cba3-414d-8d60-874830e883aa";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_chv.h b/drivers/gpu/drm/i915/oa/i915_oa_chv.h
deleted file mode 100644
index 3cac7bbc9c71..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_chv.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_CHV_H__
-#define __I915_OA_CHV_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_chv(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cnl.c b/drivers/gpu/drm/i915/oa/i915_oa_cnl.c
deleted file mode 100644
index 1041e8914993..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cnl.c
+++ /dev/null
@@ -1,101 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_cnl.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x0000ffff },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x0000ffff },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x0000ffff },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0xd04), 0x00000200 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x17060000 },
-	{ _MMIO(0x9840), 0x00000000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x13034000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x07060066 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x05060000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x0f080040 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x07091000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x0f041000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x1d004000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x35000000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x49000000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x3d000000 },
-	{ _MMIO(0x9884), 0x00000007 },
-	{ _MMIO(0x9888), 0x31000000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"db41edd4-d8e7-4730-ad11-b9a2d6833503",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "db41edd4-d8e7-4730-ad11-b9a2d6833503";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cnl.h b/drivers/gpu/drm/i915/oa/i915_oa_cnl.h
deleted file mode 100644
index db379f5fcbb9..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_cnl.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_CNL_H__
-#define __I915_OA_CNL_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_glk.c b/drivers/gpu/drm/i915/oa/i915_oa_glk.c
deleted file mode 100644
index bd15ebe9aeeb..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_glk.c
+++ /dev/null
@@ -1,88 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_glk.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x19800000 },
-	{ _MMIO(0x9888), 0x07800063 },
-	{ _MMIO(0x9888), 0x11800000 },
-	{ _MMIO(0x9888), 0x23810008 },
-	{ _MMIO(0x9888), 0x1d950400 },
-	{ _MMIO(0x9888), 0x0f922000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x55900000 },
-	{ _MMIO(0x9888), 0x47900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_glk(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"dd3fd789-e783-4204-8cd0-b671bbccb0cf",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "dd3fd789-e783-4204-8cd0-b671bbccb0cf";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_glk.h b/drivers/gpu/drm/i915/oa/i915_oa_glk.h
deleted file mode 100644
index 779f343efd11..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_glk.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_GLK_H__
-#define __I915_OA_GLK_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_glk(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_hsw.c b/drivers/gpu/drm/i915/oa/i915_oa_hsw.c
deleted file mode 100644
index 133721a8619f..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_hsw.c
+++ /dev/null
@@ -1,118 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_hsw.h"
-
-static const struct i915_oa_reg b_counter_config_render_basic[] = {
-	{ _MMIO(0x2724), 0x00800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2714), 0x00800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-};
-
-static const struct i915_oa_reg flex_eu_config_render_basic[] = {
-};
-
-static const struct i915_oa_reg mux_config_render_basic[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x253a4), 0x01600000 },
-	{ _MMIO(0x25440), 0x00100000 },
-	{ _MMIO(0x25128), 0x00000000 },
-	{ _MMIO(0x2691c), 0x00000800 },
-	{ _MMIO(0x26aa0), 0x01500000 },
-	{ _MMIO(0x26b9c), 0x00006000 },
-	{ _MMIO(0x2791c), 0x00000800 },
-	{ _MMIO(0x27aa0), 0x01500000 },
-	{ _MMIO(0x27b9c), 0x00006000 },
-	{ _MMIO(0x2641c), 0x00000400 },
-	{ _MMIO(0x25380), 0x00000010 },
-	{ _MMIO(0x2538c), 0x00000000 },
-	{ _MMIO(0x25384), 0x0800aaaa },
-	{ _MMIO(0x25400), 0x00000004 },
-	{ _MMIO(0x2540c), 0x06029000 },
-	{ _MMIO(0x25410), 0x00000002 },
-	{ _MMIO(0x25404), 0x5c30ffff },
-	{ _MMIO(0x25100), 0x00000016 },
-	{ _MMIO(0x25110), 0x00000400 },
-	{ _MMIO(0x25104), 0x00000000 },
-	{ _MMIO(0x26804), 0x00001211 },
-	{ _MMIO(0x26884), 0x00000100 },
-	{ _MMIO(0x26900), 0x00000002 },
-	{ _MMIO(0x26908), 0x00700000 },
-	{ _MMIO(0x26904), 0x00000000 },
-	{ _MMIO(0x26984), 0x00001022 },
-	{ _MMIO(0x26a04), 0x00000011 },
-	{ _MMIO(0x26a80), 0x00000006 },
-	{ _MMIO(0x26a88), 0x00000c02 },
-	{ _MMIO(0x26a84), 0x00000000 },
-	{ _MMIO(0x26b04), 0x00001000 },
-	{ _MMIO(0x26b80), 0x00000002 },
-	{ _MMIO(0x26b8c), 0x00000007 },
-	{ _MMIO(0x26b84), 0x00000000 },
-	{ _MMIO(0x27804), 0x00004844 },
-	{ _MMIO(0x27884), 0x00000400 },
-	{ _MMIO(0x27900), 0x00000002 },
-	{ _MMIO(0x27908), 0x0e000000 },
-	{ _MMIO(0x27904), 0x00000000 },
-	{ _MMIO(0x27984), 0x00004088 },
-	{ _MMIO(0x27a04), 0x00000044 },
-	{ _MMIO(0x27a80), 0x00000006 },
-	{ _MMIO(0x27a88), 0x00018040 },
-	{ _MMIO(0x27a84), 0x00000000 },
-	{ _MMIO(0x27b04), 0x00004000 },
-	{ _MMIO(0x27b80), 0x00000002 },
-	{ _MMIO(0x27b8c), 0x000000e0 },
-	{ _MMIO(0x27b84), 0x00000000 },
-	{ _MMIO(0x26104), 0x00002222 },
-	{ _MMIO(0x26184), 0x0c006666 },
-	{ _MMIO(0x26284), 0x04000000 },
-	{ _MMIO(0x26304), 0x04000000 },
-	{ _MMIO(0x26400), 0x00000002 },
-	{ _MMIO(0x26410), 0x000000a0 },
-	{ _MMIO(0x26404), 0x00000000 },
-	{ _MMIO(0x25420), 0x04108020 },
-	{ _MMIO(0x25424), 0x1284a420 },
-	{ _MMIO(0x2541c), 0x00000000 },
-	{ _MMIO(0x25428), 0x00042049 },
-};
-
-static ssize_t
-show_render_basic_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_hsw(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"403d8832-1a27-4aa6-a64e-f5389ce7b212",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_render_basic;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_render_basic);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_render_basic;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_render_basic);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_render_basic;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_render_basic);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "403d8832-1a27-4aa6-a64e-f5389ce7b212";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_render_basic_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_hsw.h b/drivers/gpu/drm/i915/oa/i915_oa_hsw.h
deleted file mode 100644
index ba97f732f136..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_hsw.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_HSW_H__
-#define __I915_OA_HSW_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_hsw(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_icl.c b/drivers/gpu/drm/i915/oa/i915_oa_icl.c
deleted file mode 100644
index 2d92041b754f..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_icl.c
+++ /dev/null
@@ -1,98 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_icl.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x0000ffff },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x0000ffff },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x0000ffff },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0xd04), 0x00000200 },
-	{ _MMIO(0x9840), 0x00000000 },
-	{ _MMIO(0x9884), 0x00000000 },
-	{ _MMIO(0x9888), 0x10060000 },
-	{ _MMIO(0x9888), 0x22060000 },
-	{ _MMIO(0x9888), 0x16060000 },
-	{ _MMIO(0x9888), 0x24060000 },
-	{ _MMIO(0x9888), 0x18060000 },
-	{ _MMIO(0x9888), 0x1a060000 },
-	{ _MMIO(0x9888), 0x12060000 },
-	{ _MMIO(0x9888), 0x14060000 },
-	{ _MMIO(0x9888), 0x10060000 },
-	{ _MMIO(0x9888), 0x22060000 },
-	{ _MMIO(0x9884), 0x00000003 },
-	{ _MMIO(0x9888), 0x16130000 },
-	{ _MMIO(0x9888), 0x24000001 },
-	{ _MMIO(0x9888), 0x0e130056 },
-	{ _MMIO(0x9888), 0x10130000 },
-	{ _MMIO(0x9888), 0x1a130000 },
-	{ _MMIO(0x9888), 0x541f0001 },
-	{ _MMIO(0x9888), 0x181f0000 },
-	{ _MMIO(0x9888), 0x4c1f0000 },
-	{ _MMIO(0x9888), 0x301f0000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"a291665e-244b-4b76-9b9a-01de9d3c8068",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "a291665e-244b-4b76-9b9a-01de9d3c8068";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_icl.h b/drivers/gpu/drm/i915/oa/i915_oa_icl.h
deleted file mode 100644
index 5c64112d720e..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_icl.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_ICL_H__
-#define __I915_OA_ICL_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c
deleted file mode 100644
index 1c3a67c9cfe0..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_kblgt2.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_kblgt2(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"baa3c7e4-52b6-4b85-801e-465a94b746dd",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "baa3c7e4-52b6-4b85-801e-465a94b746dd";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h
deleted file mode 100644
index 810532fa6b63..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_KBLGT2_H__
-#define __I915_OA_KBLGT2_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_kblgt2(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c
deleted file mode 100644
index ebbe5a9c9fdc..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_kblgt3.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_kblgt3(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"f1792f32-6db2-4b50-b4b2-557128f1688d",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "f1792f32-6db2-4b50-b4b2-557128f1688d";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h
deleted file mode 100644
index 13d70456fabd..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_KBLGT3_H__
-#define __I915_OA_KBLGT3_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_kblgt3(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c
deleted file mode 100644
index 1bc359ed34e8..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c
+++ /dev/null
@@ -1,88 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_sklgt2.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810016 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_sklgt2(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"1651949f-0ac0-4cb1-a06f-dafd74a407d1",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "1651949f-0ac0-4cb1-a06f-dafd74a407d1";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h
deleted file mode 100644
index fda70c51a6ec..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_SKLGT2_H__
-#define __I915_OA_SKLGT2_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_sklgt2(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c
deleted file mode 100644
index 6e352f881310..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_sklgt3.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_sklgt3(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"2b985803-d3c9-4629-8a4f-634bfecba0e8",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "2b985803-d3c9-4629-8a4f-634bfecba0e8";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h
deleted file mode 100644
index df74eba5799e..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_SKLGT3_H__
-#define __I915_OA_SKLGT3_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_sklgt3(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c
deleted file mode 100644
index 8f345115a306..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_sklgt4.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0x2740), 0x00000000 },
-	{ _MMIO(0x2744), 0x00800000 },
-	{ _MMIO(0x2714), 0xf0800000 },
-	{ _MMIO(0x2710), 0x00000000 },
-	{ _MMIO(0x2724), 0xf0800000 },
-	{ _MMIO(0x2720), 0x00000000 },
-	{ _MMIO(0x2770), 0x00000004 },
-	{ _MMIO(0x2774), 0x00000000 },
-	{ _MMIO(0x2778), 0x00000003 },
-	{ _MMIO(0x277c), 0x00000000 },
-	{ _MMIO(0x2780), 0x00000007 },
-	{ _MMIO(0x2784), 0x00000000 },
-	{ _MMIO(0x2788), 0x00100002 },
-	{ _MMIO(0x278c), 0x0000fff7 },
-	{ _MMIO(0x2790), 0x00100002 },
-	{ _MMIO(0x2794), 0x0000ffcf },
-	{ _MMIO(0x2798), 0x00100082 },
-	{ _MMIO(0x279c), 0x0000ffef },
-	{ _MMIO(0x27a0), 0x001000c2 },
-	{ _MMIO(0x27a4), 0x0000ffe7 },
-	{ _MMIO(0x27a8), 0x00100001 },
-	{ _MMIO(0x27ac), 0x0000ffe7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x9840), 0x00000080 },
-	{ _MMIO(0x9888), 0x11810000 },
-	{ _MMIO(0x9888), 0x07810013 },
-	{ _MMIO(0x9888), 0x1f810000 },
-	{ _MMIO(0x9888), 0x1d810000 },
-	{ _MMIO(0x9888), 0x1b930040 },
-	{ _MMIO(0x9888), 0x07e54000 },
-	{ _MMIO(0x9888), 0x1f908000 },
-	{ _MMIO(0x9888), 0x11900000 },
-	{ _MMIO(0x9888), 0x37900000 },
-	{ _MMIO(0x9888), 0x53900000 },
-	{ _MMIO(0x9888), 0x45900000 },
-	{ _MMIO(0x9888), 0x33900000 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_sklgt4(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"882fa433-1f4a-4a67-a962-c741888fe5f5",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "882fa433-1f4a-4a67-a962-c741888fe5f5";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h
deleted file mode 100644
index 378ab7ab78d5..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018-2019 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_SKLGT4_H__
-#define __I915_OA_SKLGT4_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_sklgt4(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.c b/drivers/gpu/drm/i915/oa/i915_oa_tgl.c
deleted file mode 100644
index a29d93707345..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_tgl.c
+++ /dev/null
@@ -1,121 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2018 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#include <linux/sysfs.h>
-
-#include "i915_drv.h"
-#include "i915_oa_tgl.h"
-
-static const struct i915_oa_reg b_counter_config_test_oa[] = {
-	{ _MMIO(0xD920), 0x00000000 },
-	{ _MMIO(0xD900), 0x00000000 },
-	{ _MMIO(0xD904), 0xF0800000 },
-	{ _MMIO(0xD910), 0x00000000 },
-	{ _MMIO(0xD914), 0xF0800000 },
-	{ _MMIO(0xDC40), 0x00FF0000 },
-	{ _MMIO(0xD940), 0x00000004 },
-	{ _MMIO(0xD944), 0x0000FFFF },
-	{ _MMIO(0xDC00), 0x00000004 },
-	{ _MMIO(0xDC04), 0x0000FFFF },
-	{ _MMIO(0xD948), 0x00000003 },
-	{ _MMIO(0xD94C), 0x0000FFFF },
-	{ _MMIO(0xDC08), 0x00000003 },
-	{ _MMIO(0xDC0C), 0x0000FFFF },
-	{ _MMIO(0xD950), 0x00000007 },
-	{ _MMIO(0xD954), 0x0000FFFF },
-	{ _MMIO(0xDC10), 0x00000007 },
-	{ _MMIO(0xDC14), 0x0000FFFF },
-	{ _MMIO(0xD958), 0x00100002 },
-	{ _MMIO(0xD95C), 0x0000FFF7 },
-	{ _MMIO(0xDC18), 0x00100002 },
-	{ _MMIO(0xDC1C), 0x0000FFF7 },
-	{ _MMIO(0xD960), 0x00100002 },
-	{ _MMIO(0xD964), 0x0000FFCF },
-	{ _MMIO(0xDC20), 0x00100002 },
-	{ _MMIO(0xDC24), 0x0000FFCF },
-	{ _MMIO(0xD968), 0x00100082 },
-	{ _MMIO(0xD96C), 0x0000FFEF },
-	{ _MMIO(0xDC28), 0x00100082 },
-	{ _MMIO(0xDC2C), 0x0000FFEF },
-	{ _MMIO(0xD970), 0x001000C2 },
-	{ _MMIO(0xD974), 0x0000FFE7 },
-	{ _MMIO(0xDC30), 0x001000C2 },
-	{ _MMIO(0xDC34), 0x0000FFE7 },
-	{ _MMIO(0xD978), 0x00100001 },
-	{ _MMIO(0xD97C), 0x0000FFE7 },
-	{ _MMIO(0xDC38), 0x00100001 },
-	{ _MMIO(0xDC3C), 0x0000FFE7 },
-};
-
-static const struct i915_oa_reg flex_eu_config_test_oa[] = {
-};
-
-static const struct i915_oa_reg mux_config_test_oa[] = {
-	{ _MMIO(0x0D04), 0x00000200 },
-	{ _MMIO(0x9840), 0x00000000 },
-	{ _MMIO(0x9884), 0x00000000 },
-	{ _MMIO(0x9888), 0x280E0000 },
-	{ _MMIO(0x9888), 0x1E0E0147 },
-	{ _MMIO(0x9888), 0x180E0000 },
-	{ _MMIO(0x9888), 0x160E0000 },
-	{ _MMIO(0x9888), 0x1E0F1000 },
-	{ _MMIO(0x9888), 0x1E104000 },
-	{ _MMIO(0x9888), 0x2E020100 },
-	{ _MMIO(0x9888), 0x2C030004 },
-	{ _MMIO(0x9888), 0x38003000 },
-	{ _MMIO(0x9888), 0x1E0A8000 },
-	{ _MMIO(0x9884), 0x00000003 },
-	{ _MMIO(0x9888), 0x49110000 },
-	{ _MMIO(0x9888), 0x5D101400 },
-	{ _MMIO(0x9888), 0x1D140020 },
-	{ _MMIO(0x9888), 0x1D1103A3 },
-	{ _MMIO(0x9888), 0x01110000 },
-	{ _MMIO(0x9888), 0x61111000 },
-	{ _MMIO(0x9888), 0x1F128000 },
-	{ _MMIO(0x9888), 0x17100000 },
-	{ _MMIO(0x9888), 0x55100630 },
-	{ _MMIO(0x9888), 0x57100000 },
-	{ _MMIO(0x9888), 0x31100000 },
-	{ _MMIO(0x9884), 0x00000003 },
-	{ _MMIO(0x9888), 0x65100002 },
-	{ _MMIO(0x9884), 0x00000000 },
-	{ _MMIO(0x9888), 0x42000001 },
-};
-
-static ssize_t
-show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "1\n");
-}
-
-void
-i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv)
-{
-	strlcpy(dev_priv->perf.test_config.uuid,
-		"80a833f0-2504-4321-8894-e9277844ce7b",
-		sizeof(dev_priv->perf.test_config.uuid));
-	dev_priv->perf.test_config.id = 1;
-
-	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
-	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
-
-	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
-	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
-
-	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
-	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
-
-	dev_priv->perf.test_config.sysfs_metric.name = "80a833f0-2504-4321-8894-e9277844ce7b";
-	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
-
-	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
-
-	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
-	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
-	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
-}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.h b/drivers/gpu/drm/i915/oa/i915_oa_tgl.h
deleted file mode 100644
index 4c25f0be825c..000000000000
--- a/drivers/gpu/drm/i915/oa/i915_oa_tgl.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2018 Intel Corporation
- *
- * Autogenerated file by GPU Top : https://github.com/rib/gputop
- * DO NOT EDIT manually!
- */
-
-#ifndef __I915_OA_TGL_H__
-#define __I915_OA_TGL_H__
-
-struct drm_i915_private;
-
-void i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv);
-
-#endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 68bbb1580162..4002c984c2e0 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -153,7 +153,7 @@ static int live_active_wait(void *arg)
 	if (IS_ERR(active))
 		return PTR_ERR(active);
 
-	i915_active_wait(&active->base);
+	__i915_active_wait(&active->base, TASK_UNINTERRUPTIBLE);
 	if (!READ_ONCE(active->retired)) {
 		struct drm_printer p = drm_err_printer(__func__);
 
@@ -228,11 +228,11 @@ static int live_active_barrier(void *arg)
 	}
 
 	i915_active_release(&active->base);
+	if (err)
+		goto out;
 
-	if (err == 0)
-		err = i915_active_wait(&active->base);
-
-	if (err == 0 && !READ_ONCE(active->retired)) {
+	__i915_active_wait(&active->base, TASK_UNINTERRUPTIBLE);
+	if (!READ_ONCE(active->retired)) {
 		pr_err("i915_active not retired after flushing barriers!\n");
 		err = -EINVAL;
 	}
@@ -277,7 +277,7 @@ static struct intel_engine_cs *node_to_barrier(struct active_node *it)
 
 void i915_active_print(struct i915_active *ref, struct drm_printer *m)
 {
-	drm_printf(m, "active %pS:%pS\n", ref->active, ref->retire);
+	drm_printf(m, "active %ps:%ps\n", ref->active, ref->retire);
 	drm_printf(m, "\tcount: %d\n", atomic_read(&ref->count));
 	drm_printf(m, "\tpreallocated barriers? %s\n",
 		   yesno(!llist_empty(&ref->preallocated_barriers)));
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 623759b73bb4..88d400b9df88 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -125,8 +125,6 @@ static void pm_resume(struct drm_i915_private *i915)
 	 */
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		i915_ggtt_resume(&i915->ggtt);
-		i915_gem_restore_fences(&i915->ggtt);
-
 		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 06ef88510209..028baae9631f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -45,8 +45,8 @@ static void quirk_add(struct drm_i915_gem_object *obj,
 
 static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects)
 {
-	unsigned long unbound, bound, count;
 	struct drm_i915_gem_object *obj;
+	unsigned long count;
 
 	count = 0;
 	do {
@@ -72,30 +72,6 @@ static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects)
 	pr_debug("Filled GGTT with %lu pages [%llu total]\n",
 		 count, ggtt->vm.total / PAGE_SIZE);
 
-	bound = 0;
-	unbound = 0;
-	list_for_each_entry(obj, objects, st_link) {
-		GEM_BUG_ON(!obj->mm.quirked);
-
-		if (atomic_read(&obj->bind_count))
-			bound++;
-		else
-			unbound++;
-	}
-	GEM_BUG_ON(bound + unbound != count);
-
-	if (unbound) {
-		pr_err("%s: Found %lu objects unbound, expected %u!\n",
-		       __func__, unbound, 0);
-		return -EINVAL;
-	}
-
-	if (bound != count) {
-		pr_err("%s: Found %lu objects bound, expected %lu!\n",
-		       __func__, bound, count);
-		return -EINVAL;
-	}
-
 	if (list_empty(&ggtt->vm.bound_list)) {
 		pr_err("No objects on the GGTT inactive list!\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index b342bef5e7c9..2e471500a646 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -331,9 +331,6 @@ static void close_object_list(struct list_head *objects,
 		vma = i915_vma_instance(obj, vm, NULL);
 		if (!IS_ERR(vma))
 			ignored = i915_vma_unbind(vma);
-		/* Only ppgtt vma may be closed before the object is freed */
-		if (!IS_ERR(vma) && !i915_vma_is_ggtt(vma))
-			i915_vma_close(vma);
 
 		list_del(&obj->st_link);
 		i915_gem_object_put(obj);
@@ -591,7 +588,7 @@ static int walk_hole(struct i915_address_space *vm,
 				pr_err("%s bind failed at %llx + %llx [hole %llx- %llx] with err=%d\n",
 				       __func__, addr, vma->size,
 				       hole_start, hole_end, err);
-				goto err_close;
+				goto err_put;
 			}
 			i915_vma_unpin(vma);
 
@@ -600,14 +597,14 @@ static int walk_hole(struct i915_address_space *vm,
 				pr_err("%s incorrect at %llx + %llx\n",
 				       __func__, addr, vma->size);
 				err = -EINVAL;
-				goto err_close;
+				goto err_put;
 			}
 
 			err = i915_vma_unbind(vma);
 			if (err) {
 				pr_err("%s unbind failed at %llx + %llx  with err=%d\n",
 				       __func__, addr, vma->size, err);
-				goto err_close;
+				goto err_put;
 			}
 
 			GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
@@ -616,13 +613,10 @@ static int walk_hole(struct i915_address_space *vm,
 					"%s timed out at %llx\n",
 					__func__, addr)) {
 				err = -EINTR;
-				goto err_close;
+				goto err_put;
 			}
 		}
 
-err_close:
-		if (!i915_vma_is_ggtt(vma))
-			i915_vma_close(vma);
 err_put:
 		i915_gem_object_put(obj);
 		if (err)
@@ -675,7 +669,7 @@ static int pot_hole(struct i915_address_space *vm,
 				       addr,
 				       hole_start, hole_end,
 				       err);
-				goto err;
+				goto err_obj;
 			}
 
 			if (!drm_mm_node_allocated(&vma->node) ||
@@ -685,7 +679,7 @@ static int pot_hole(struct i915_address_space *vm,
 				i915_vma_unpin(vma);
 				err = i915_vma_unbind(vma);
 				err = -EINVAL;
-				goto err;
+				goto err_obj;
 			}
 
 			i915_vma_unpin(vma);
@@ -697,13 +691,10 @@ static int pot_hole(struct i915_address_space *vm,
 				"%s timed out after %d/%d\n",
 				__func__, pot, fls64(hole_end - 1) - 1)) {
 			err = -EINTR;
-			goto err;
+			goto err_obj;
 		}
 	}
 
-err:
-	if (!i915_vma_is_ggtt(vma))
-		i915_vma_close(vma);
 err_obj:
 	i915_gem_object_put(obj);
 	return err;
@@ -778,7 +769,7 @@ static int drunk_hole(struct i915_address_space *vm,
 				       addr, BIT_ULL(size),
 				       hole_start, hole_end,
 				       err);
-				goto err;
+				goto err_obj;
 			}
 
 			if (!drm_mm_node_allocated(&vma->node) ||
@@ -788,7 +779,7 @@ static int drunk_hole(struct i915_address_space *vm,
 				i915_vma_unpin(vma);
 				err = i915_vma_unbind(vma);
 				err = -EINVAL;
-				goto err;
+				goto err_obj;
 			}
 
 			i915_vma_unpin(vma);
@@ -799,13 +790,10 @@ static int drunk_hole(struct i915_address_space *vm,
 					"%s timed out after %d/%d\n",
 					__func__, n, count)) {
 				err = -EINTR;
-				goto err;
+				goto err_obj;
 			}
 		}
 
-err:
-		if (!i915_vma_is_ggtt(vma))
-			i915_vma_close(vma);
 err_obj:
 		i915_gem_object_put(obj);
 		kfree(order);
@@ -1229,7 +1217,6 @@ static void track_vma_bind(struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	atomic_inc(&obj->bind_count); /* track for eviction later */
 	__i915_gem_object_pin_pages(obj);
 
 	GEM_BUG_ON(vma->pages);
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 0a953bfc0585..5dd5d81646c4 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -37,6 +37,7 @@ selftest(gem, i915_gem_live_selftests)
 selftest(evict, i915_gem_evict_live_selftests)
 selftest(hugepages, i915_gem_huge_page_live_selftests)
 selftest(gem_contexts, i915_gem_context_live_selftests)
+selftest(gem_execbuf, i915_gem_execbuffer_live_selftests)
 selftest(blt, i915_gem_object_blt_live_selftests)
 selftest(client, i915_gem_client_blt_live_selftests)
 selftest(reset, intel_reset_live_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 5b39bab4da1d..6a2be7d0dd95 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -16,6 +16,7 @@
  * Tests are executed in order by igt/drv_selftest
  */
 selftest(sanitycheck, i915_mock_sanitycheck) /* keep first (igt selfcheck) */
+selftest(shmem, shmem_utils_mock_selftests)
 selftest(fence, i915_sw_fence_mock_selftests)
 selftest(scatterlist, scatterlist_mock_selftests)
 selftest(syncmap, i915_syncmap_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index d1a1568c47ba..8eb3108f1767 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -14,10 +14,85 @@
 #include "igt_flush_test.h"
 #include "lib_sw_fence.h"
 
+#define TEST_OA_CONFIG_UUID "12345678-1234-1234-1234-1234567890ab"
+
+static int
+alloc_empty_config(struct i915_perf *perf)
+{
+	struct i915_oa_config *oa_config;
+
+	oa_config = kzalloc(sizeof(*oa_config), GFP_KERNEL);
+	if (!oa_config)
+		return -ENOMEM;
+
+	oa_config->perf = perf;
+	kref_init(&oa_config->ref);
+
+	strlcpy(oa_config->uuid, TEST_OA_CONFIG_UUID, sizeof(oa_config->uuid));
+
+	mutex_lock(&perf->metrics_lock);
+
+	oa_config->id = idr_alloc(&perf->metrics_idr, oa_config, 2, 0, GFP_KERNEL);
+	if (oa_config->id < 0)  {
+		mutex_unlock(&perf->metrics_lock);
+		i915_oa_config_put(oa_config);
+		return -ENOMEM;
+	}
+
+	mutex_unlock(&perf->metrics_lock);
+
+	return 0;
+}
+
+static void
+destroy_empty_config(struct i915_perf *perf)
+{
+	struct i915_oa_config *oa_config = NULL, *tmp;
+	int id;
+
+	mutex_lock(&perf->metrics_lock);
+
+	idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+		if (!strcmp(tmp->uuid, TEST_OA_CONFIG_UUID)) {
+			oa_config = tmp;
+			break;
+		}
+	}
+
+	if (oa_config)
+		idr_remove(&perf->metrics_idr, oa_config->id);
+
+	mutex_unlock(&perf->metrics_lock);
+
+	if (oa_config)
+		i915_oa_config_put(oa_config);
+}
+
+static struct i915_oa_config *
+get_empty_config(struct i915_perf *perf)
+{
+	struct i915_oa_config *oa_config = NULL, *tmp;
+	int id;
+
+	mutex_lock(&perf->metrics_lock);
+
+	idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+		if (!strcmp(tmp->uuid, TEST_OA_CONFIG_UUID)) {
+			oa_config = i915_oa_config_get(tmp);
+			break;
+		}
+	}
+
+	mutex_unlock(&perf->metrics_lock);
+
+	return oa_config;
+}
+
 static struct i915_perf_stream *
 test_stream(struct i915_perf *perf)
 {
 	struct drm_i915_perf_open_param param = {};
+	struct i915_oa_config *oa_config = get_empty_config(perf);
 	struct perf_open_properties props = {
 		.engine = intel_engine_lookup_user(perf->i915,
 						   I915_ENGINE_CLASS_RENDER,
@@ -25,13 +100,19 @@ test_stream(struct i915_perf *perf)
 		.sample_flags = SAMPLE_OA_REPORT,
 		.oa_format = IS_GEN(perf->i915, 12) ?
 		I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8,
-		.metrics_set = 1,
 	};
 	struct i915_perf_stream *stream;
 
+	if (!oa_config)
+		return NULL;
+
+	props.metrics_set = oa_config->id;
+
 	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
-	if (!stream)
+	if (!stream) {
+		i915_oa_config_put(oa_config);
 		return NULL;
+	}
 
 	stream->perf = perf;
 
@@ -42,6 +123,8 @@ test_stream(struct i915_perf *perf)
 	}
 	mutex_unlock(&perf->lock);
 
+	i915_oa_config_put(oa_config);
+
 	return stream;
 }
 
@@ -138,8 +221,7 @@ static int live_noa_delay(void *arg)
 		goto out;
 	}
 
-	if (rq->engine->emit_init_breadcrumb &&
-	    i915_request_timeline(rq)->has_initial_breadcrumb) {
+	if (rq->engine->emit_init_breadcrumb) {
 		err = rq->engine->emit_init_breadcrumb(rq);
 		if (err) {
 			i915_request_add(rq);
@@ -180,8 +262,7 @@ static int live_noa_delay(void *arg)
 
 	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);
+	delay = i915_cs_timestamp_ticks_to_ns(i915, delay);
 	pr_info("GPU delay: %uns, expected %lluns\n",
 		delay, expected);
 
@@ -206,6 +287,7 @@ int i915_perf_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_noa_delay),
 	};
 	struct i915_perf *perf = &i915->perf;
+	int err;
 
 	if (!perf->metrics_kobj || !perf->ops.enable_metric_set)
 		return 0;
@@ -213,5 +295,13 @@ int i915_perf_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_subtests(tests, i915);
+	err = alloc_empty_config(&i915->perf);
+	if (err)
+		return err;
+
+	err = i915_subtests(tests, i915);
+
+	destroy_empty_config(&i915->perf);
+
+	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
index 3bf7f53e9924..d8da142985eb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
@@ -16,5 +16,6 @@
  * Tests are executed in order by igt/i915_selftest
  */
 selftest(engine_cs, intel_engine_cs_perf_selftests)
+selftest(request, i915_request_perf_selftests)
 selftest(blt, i915_gem_object_blt_perf_selftests)
 selftest(region, intel_memory_region_perf_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index f89d9c42f1fa..6014e8dfcbb1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -23,11 +23,13 @@
  */
 
 #include <linux/prime_numbers.h>
+#include <linux/pm_qos.h>
 
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/mock_context.h"
 
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 
 #include "i915_random.h"
@@ -51,6 +53,11 @@ static unsigned int num_uabi_engines(struct drm_i915_private *i915)
 	return count;
 }
 
+static struct intel_engine_cs *rcs0(struct drm_i915_private *i915)
+{
+	return intel_engine_lookup_user(i915, I915_ENGINE_CLASS_RENDER, 0);
+}
+
 static int igt_add_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -58,7 +65,7 @@ static int igt_add_request(void *arg)
 
 	/* Basic preliminary test to create a request and let it loose! */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, HZ / 10);
+	request = mock_request(rcs0(i915)->kernel_context, HZ / 10);
 	if (!request)
 		return -ENOMEM;
 
@@ -76,7 +83,7 @@ static int igt_wait_request(void *arg)
 
 	/* Submit a request, then wait upon it */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, T);
+	request = mock_request(rcs0(i915)->kernel_context, T);
 	if (!request)
 		return -ENOMEM;
 
@@ -145,7 +152,7 @@ static int igt_fence_wait(void *arg)
 
 	/* Submit a request, treat it as a fence and wait upon it */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, T);
+	request = mock_request(rcs0(i915)->kernel_context, T);
 	if (!request)
 		return -ENOMEM;
 
@@ -420,7 +427,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct smoketest t = {
-		.engine = i915->engine[RCS0],
+		.engine = rcs0(i915),
 		.ncontexts = 1024,
 		.max_batch = 1024,
 		.request_alloc = __mock_request_alloc
@@ -809,10 +816,12 @@ static int recursive_batch_resolve(struct i915_vma *batch)
 		return PTR_ERR(cmd);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(batch->vm->gt);
 
+	__i915_gem_object_flush_map(batch->obj, 0, sizeof(*cmd));
 	i915_gem_object_unpin_map(batch->obj);
 
+	intel_gt_chipset_flush(batch->vm->gt);
+
 	return 0;
 }
 
@@ -858,13 +867,6 @@ static int live_all_engines(void *arg)
 			goto out_request;
 		}
 
-		err = engine->emit_bb_start(request[idx],
-					    batch->node.start,
-					    batch->node.size,
-					    0);
-		GEM_BUG_ON(err);
-		request[idx]->batch = batch;
-
 		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx], batch->obj, 0);
 		if (err == 0)
@@ -872,6 +874,13 @@ static int live_all_engines(void *arg)
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
+		err = engine->emit_bb_start(request[idx],
+					    batch->node.start,
+					    batch->node.size,
+					    0);
+		GEM_BUG_ON(err);
+		request[idx]->batch = batch;
+
 		i915_request_get(request[idx]);
 		i915_request_add(request[idx]);
 		idx++;
@@ -986,13 +995,6 @@ static int live_sequential_engines(void *arg)
 			}
 		}
 
-		err = engine->emit_bb_start(request[idx],
-					    batch->node.start,
-					    batch->node.size,
-					    0);
-		GEM_BUG_ON(err);
-		request[idx]->batch = batch;
-
 		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx],
 						batch->obj, false);
@@ -1001,6 +1003,13 @@ static int live_sequential_engines(void *arg)
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
+		err = engine->emit_bb_start(request[idx],
+					    batch->node.start,
+					    batch->node.size,
+					    0);
+		GEM_BUG_ON(err);
+		request[idx]->batch = batch;
+
 		i915_request_get(request[idx]);
 		i915_request_add(request[idx]);
 
@@ -1053,9 +1062,12 @@ out_request:
 					      I915_MAP_WC);
 		if (!IS_ERR(cmd)) {
 			*cmd = MI_BATCH_BUFFER_END;
-			intel_gt_chipset_flush(engine->gt);
 
+			__i915_gem_object_flush_map(request[idx]->batch->obj,
+						    0, sizeof(*cmd));
 			i915_gem_object_unpin_map(request[idx]->batch->obj);
+
+			intel_gt_chipset_flush(engine->gt);
 		}
 
 		i915_vma_put(request[idx]->batch);
@@ -1233,7 +1245,7 @@ static int live_parallel_engines(void *arg)
 		struct igt_live_test t;
 		unsigned int idx;
 
-		snprintf(name, sizeof(name), "%pS", fn);
+		snprintf(name, sizeof(name), "%ps", *fn);
 		err = igt_live_test_begin(&t, i915, __func__, name);
 		if (err)
 			break;
@@ -1470,3 +1482,572 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 
 	return i915_subtests(tests, i915);
 }
+
+static int switch_to_kernel_sync(struct intel_context *ce, int err)
+{
+	struct i915_request *rq;
+	struct dma_fence *fence;
+
+	rq = intel_engine_create_kernel_request(ce->engine);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	fence = i915_active_fence_get(&ce->timeline->last_request);
+	if (fence) {
+		i915_request_await_dma_fence(rq, fence);
+		dma_fence_put(fence);
+	}
+
+	rq = i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 2) < 0 && !err)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	while (!err && !intel_engine_is_idle(ce->engine))
+		intel_engine_flush_submission(ce->engine);
+
+	return err;
+}
+
+struct perf_stats {
+	struct intel_engine_cs *engine;
+	unsigned long count;
+	ktime_t time;
+	ktime_t busy;
+	u64 runtime;
+};
+
+struct perf_series {
+	struct drm_i915_private *i915;
+	unsigned int nengines;
+	struct intel_context *ce[];
+};
+
+static int s_sync0(void *arg)
+{
+	struct perf_series *ps = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+	int err = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			break;
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+
+	return err;
+}
+
+static int s_sync1(void *arg)
+{
+	struct perf_series *ps = arg;
+	struct i915_request *prev = NULL;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+	int err = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (prev && i915_request_wait(prev, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(prev);
+		prev = rq;
+		if (err)
+			break;
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+	i915_request_put(prev);
+
+	return err;
+}
+
+static int s_many(void *arg)
+{
+	struct perf_series *ps = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq))
+			return PTR_ERR(rq);
+
+		i915_request_add(rq);
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+
+	return 0;
+}
+
+static int perf_series_engines(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		s_sync0,
+		s_sync1,
+		s_many,
+		NULL,
+	};
+	const unsigned int nengines = num_uabi_engines(i915);
+	struct intel_engine_cs *engine;
+	int (* const *fn)(void *arg);
+	struct pm_qos_request qos;
+	struct perf_stats *stats;
+	struct perf_series *ps;
+	unsigned int idx;
+	int err = 0;
+
+	stats = kcalloc(nengines, sizeof(*stats), GFP_KERNEL);
+	if (!stats)
+		return -ENOMEM;
+
+	ps = kzalloc(struct_size(ps, ce, nengines), GFP_KERNEL);
+	if (!ps) {
+		kfree(stats);
+		return -ENOMEM;
+	}
+
+	cpu_latency_qos_add_request(&qos, 0); /* disable cstates */
+
+	ps->i915 = i915;
+	ps->nengines = nengines;
+
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			goto out;
+
+		err = intel_context_pin(ce);
+		if (err) {
+			intel_context_put(ce);
+			goto out;
+		}
+
+		ps->ce[idx++] = ce;
+	}
+	GEM_BUG_ON(idx != ps->nengines);
+
+	for (fn = func; *fn && !err; fn++) {
+		char name[KSYM_NAME_LEN];
+		struct igt_live_test t;
+
+		snprintf(name, sizeof(name), "%ps", *fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
+		if (err)
+			break;
+
+		for (idx = 0; idx < nengines; idx++) {
+			struct perf_stats *p =
+				memset(&stats[idx], 0, sizeof(stats[idx]));
+			struct intel_context *ce = ps->ce[idx];
+
+			p->engine = ps->ce[idx]->engine;
+			intel_engine_pm_get(p->engine);
+
+			if (intel_engine_supports_stats(p->engine))
+				p->busy = intel_engine_get_busy_time(p->engine) + 1;
+			p->runtime = -intel_context_get_total_runtime_ns(ce);
+			p->time = ktime_get();
+		}
+
+		err = (*fn)(ps);
+		if (igt_live_test_end(&t))
+			err = -EIO;
+
+		for (idx = 0; idx < nengines; idx++) {
+			struct perf_stats *p = &stats[idx];
+			struct intel_context *ce = ps->ce[idx];
+			int integer, decimal;
+			u64 busy, dt;
+
+			p->time = ktime_sub(ktime_get(), p->time);
+			if (p->busy) {
+				p->busy = ktime_sub(intel_engine_get_busy_time(p->engine),
+						    p->busy - 1);
+			}
+
+			err = switch_to_kernel_sync(ce, err);
+			p->runtime += intel_context_get_total_runtime_ns(ce);
+			intel_engine_pm_put(p->engine);
+
+			busy = 100 * ktime_to_ns(p->busy);
+			dt = ktime_to_ns(p->time);
+			if (dt) {
+				integer = div64_u64(busy, dt);
+				busy -= integer * dt;
+				decimal = div64_u64(100 * busy, dt);
+			} else {
+				integer = 0;
+				decimal = 0;
+			}
+
+			pr_info("%s %5s: { seqno:%d, busy:%d.%02d%%, runtime:%lldms, walltime:%lldms }\n",
+				name, p->engine->name, ce->timeline->seqno,
+				integer, decimal,
+				div_u64(p->runtime, 1000 * 1000),
+				div_u64(ktime_to_ns(p->time), 1000 * 1000));
+		}
+	}
+
+out:
+	for (idx = 0; idx < nengines; idx++) {
+		if (IS_ERR_OR_NULL(ps->ce[idx]))
+			break;
+
+		intel_context_unpin(ps->ce[idx]);
+		intel_context_put(ps->ce[idx]);
+	}
+	kfree(ps);
+
+	cpu_latency_qos_remove_request(&qos);
+	kfree(stats);
+	return err;
+}
+
+static int p_sync0(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	bool busy;
+	int err = 0;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	p->time = ktime_get();
+	count = 0;
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		err = 0;
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			break;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int p_sync1(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct i915_request *prev = NULL;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	bool busy;
+	int err = 0;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	p->time = ktime_get();
+	count = 0;
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		err = 0;
+		if (prev && i915_request_wait(prev, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(prev);
+		prev = rq;
+		if (err)
+			break;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	i915_request_put(prev);
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int p_many(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	int err = 0;
+	bool busy;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	count = 0;
+	p->time = ktime_get();
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int perf_parallel_engines(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		p_sync0,
+		p_sync1,
+		p_many,
+		NULL,
+	};
+	const unsigned int nengines = num_uabi_engines(i915);
+	struct intel_engine_cs *engine;
+	int (* const *fn)(void *arg);
+	struct pm_qos_request qos;
+	struct {
+		struct perf_stats p;
+		struct task_struct *tsk;
+	} *engines;
+	int err = 0;
+
+	engines = kcalloc(nengines, sizeof(*engines), GFP_KERNEL);
+	if (!engines)
+		return -ENOMEM;
+
+	cpu_latency_qos_add_request(&qos, 0);
+
+	for (fn = func; *fn; fn++) {
+		char name[KSYM_NAME_LEN];
+		struct igt_live_test t;
+		unsigned int idx;
+
+		snprintf(name, sizeof(name), "%ps", *fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
+		if (err)
+			break;
+
+		atomic_set(&i915->selftest.counter, nengines);
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			intel_engine_pm_get(engine);
+
+			memset(&engines[idx].p, 0, sizeof(engines[idx].p));
+			engines[idx].p.engine = engine;
+
+			engines[idx].tsk = kthread_run(*fn, &engines[idx].p,
+						       "igt:%s", engine->name);
+			if (IS_ERR(engines[idx].tsk)) {
+				err = PTR_ERR(engines[idx].tsk);
+				intel_engine_pm_put(engine);
+				break;
+			}
+			get_task_struct(engines[idx++].tsk);
+		}
+
+		yield(); /* start all threads before we kthread_stop() */
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			int status;
+
+			if (IS_ERR(engines[idx].tsk))
+				break;
+
+			status = kthread_stop(engines[idx].tsk);
+			if (status && !err)
+				err = status;
+
+			intel_engine_pm_put(engine);
+			put_task_struct(engines[idx++].tsk);
+		}
+
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			break;
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			struct perf_stats *p = &engines[idx].p;
+			u64 busy = 100 * ktime_to_ns(p->busy);
+			u64 dt = ktime_to_ns(p->time);
+			int integer, decimal;
+
+			if (dt) {
+				integer = div64_u64(busy, dt);
+				busy -= integer * dt;
+				decimal = div64_u64(100 * busy, dt);
+			} else {
+				integer = 0;
+				decimal = 0;
+			}
+
+			GEM_BUG_ON(engine != p->engine);
+			pr_info("%s %5s: { count:%lu, busy:%d.%02d%%, runtime:%lldms, walltime:%lldms }\n",
+				name, engine->name, p->count, integer, decimal,
+				div_u64(p->runtime, 1000 * 1000),
+				div_u64(ktime_to_ns(p->time), 1000 * 1000));
+			idx++;
+		}
+	}
+
+	cpu_latency_qos_remove_request(&qos);
+	kfree(engines);
+	return err;
+}
+
+int i915_request_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_series_engines),
+		SUBTEST(perf_parallel_engines),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index d3bf9eefb682..1bc11c09faef 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -396,6 +396,35 @@ bool __igt_timeout(unsigned long timeout, const char *fmt, ...)
 	return true;
 }
 
+void igt_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;
+	}
+}
+
 module_param_named(st_random_seed, i915_selftest.random_seed, uint, 0400);
 module_param_named(st_timeout, i915_selftest.timeout_ms, uint, 0400);
 module_param_named(st_filter, i915_selftest.filter, charp, 0400);
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index 9ad4ab088466..e35ba5f9e73f 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -169,8 +169,7 @@ igt_spinner_create_request(struct igt_spinner *spin,
 
 	intel_gt_chipset_flush(engine->gt);
 
-	if (engine->emit_init_breadcrumb &&
-	    i915_request_timeline(rq)->has_initial_breadcrumb) {
+	if (engine->emit_init_breadcrumb) {
 		err = engine->emit_init_breadcrumb(rq);
 		if (err)
 			goto cancel_rq;
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 2a1d4ba1f9f3..6e80d99048e4 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -594,8 +594,11 @@ create_region_for_mapping(struct intel_memory_region *mr, u64 size, u32 type,
 	void *addr;
 
 	obj = i915_gem_object_create_region(mr, size, 0);
-	if (IS_ERR(obj))
+	if (IS_ERR(obj)) {
+		if (PTR_ERR(obj) == -ENOSPC) /* Stolen memory */
+			return ERR_PTR(-ENODEV);
 		return obj;
+	}
 
 	addr = i915_gem_object_pin_map(obj, type);
 	if (IS_ERR(addr)) {
diff --git a/drivers/gpu/drm/i915/selftests/librapl.c b/drivers/gpu/drm/i915/selftests/librapl.c
new file mode 100644
index 000000000000..58710ac3f979
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/librapl.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <asm/msr.h>
+
+#include "librapl.h"
+
+u64 librapl_energy_uJ(void)
+{
+	unsigned long long power;
+	u32 units;
+
+	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &power))
+		return 0;
+
+	units = (power & 0x1f00) >> 8;
+
+	if (rdmsrl_safe(MSR_PP1_ENERGY_STATUS, &power))
+		return 0;
+
+	return (1000000 * power) >> units; /* convert to uJ */
+}
diff --git a/drivers/gpu/drm/i915/selftests/librapl.h b/drivers/gpu/drm/i915/selftests/librapl.h
new file mode 100644
index 000000000000..887f3e91dd05
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/librapl.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef SELFTEST_LIBRAPL_H
+#define SELFTEST_LIBRAPL_H
+
+#include <linux/types.h>
+
+u64 librapl_energy_uJ(void);
+
+#endif /* SELFTEST_LIBRAPL_H */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 754d0eb6beaa..9b105b811f1f 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -25,6 +25,8 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 
+#include <drm/drm_managed.h>
+
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/mock_engine.h"
@@ -55,6 +57,9 @@ static void mock_device_release(struct drm_device *dev)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 
+	if (!i915->do_release)
+		goto out;
+
 	mock_device_flush(i915);
 	intel_gt_driver_remove(&i915->gt);
 
@@ -71,8 +76,9 @@ static void mock_device_release(struct drm_device *dev)
 
 	drm_mode_config_cleanup(&i915->drm);
 
-	drm_dev_fini(&i915->drm);
+out:
 	put_device(&i915->drm.pdev->dev);
+	i915->drm.pdev = NULL;
 }
 
 static struct drm_driver mock_driver = {
@@ -114,9 +120,14 @@ struct drm_i915_private *mock_gem_device(void)
 	struct pci_dev *pdev;
 	int err;
 
-	pdev = kzalloc(sizeof(*pdev) + sizeof(*i915), GFP_KERNEL);
+	pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
 	if (!pdev)
-		goto err;
+		return NULL;
+	i915 = kzalloc(sizeof(*i915), GFP_KERNEL);
+	if (!i915) {
+		kfree(pdev);
+		return NULL;
+	}
 
 	device_initialize(&pdev->dev);
 	pdev->class = PCI_BASE_CLASS_DISPLAY << 16;
@@ -129,7 +140,6 @@ struct drm_i915_private *mock_gem_device(void)
 	pdev->dev.archdata.iommu = (void *)-1;
 #endif
 
-	i915 = (struct drm_i915_private *)(pdev + 1);
 	pci_set_drvdata(pdev, i915);
 
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
@@ -141,9 +151,13 @@ struct drm_i915_private *mock_gem_device(void)
 	err = drm_dev_init(&i915->drm, &mock_driver, &pdev->dev);
 	if (err) {
 		pr_err("Failed to initialise mock GEM device: err=%d\n", err);
-		goto put_device;
+		put_device(&pdev->dev);
+		kfree(i915);
+
+		return NULL;
 	}
 	i915->drm.pdev = pdev;
+	drmm_add_final_kfree(&i915->drm, i915);
 
 	intel_runtime_pm_init_early(&i915->runtime_pm);
 
@@ -178,16 +192,18 @@ struct drm_i915_private *mock_gem_device(void)
 
 	mkwrite_device_info(i915)->engine_mask = BIT(0);
 
-	i915->engine[RCS0] = mock_engine(i915, "mock", RCS0);
-	if (!i915->engine[RCS0])
+	i915->gt.engine[RCS0] = mock_engine(i915, "mock", RCS0);
+	if (!i915->gt.engine[RCS0])
 		goto err_unlock;
 
-	if (mock_engine_init(i915->engine[RCS0]))
+	if (mock_engine_init(i915->gt.engine[RCS0]))
 		goto err_context;
 
 	__clear_bit(I915_WEDGED, &i915->gt.reset.flags);
 	intel_engines_driver_register(i915);
 
+	i915->do_release = true;
+
 	return i915;
 
 err_context:
@@ -198,9 +214,7 @@ err_drv:
 	intel_gt_driver_late_release(&i915->gt);
 	intel_memory_regions_driver_release(i915);
 	drm_mode_config_cleanup(&i915->drm);
-	drm_dev_fini(&i915->drm);
-put_device:
-	put_device(&pdev->dev);
-err:
+	drm_dev_put(&i915->drm);
+
 	return NULL;
 }
author	Linus Torvalds <torvalds@linux-foundation.org>	2020-06-03 00:04:15 +0200
committer	Linus Torvalds <torvalds@linux-foundation.org>	2020-06-03 00:04:15 +0200
commit	faa392181a0bd42c5478175cef601adeecdc91b6 (patch)
tree	e020e1142e34786676d0cd40f539bccdbb66099e /drivers/gpu/drm/i915
parent	Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rd... (diff)
parent	Merge tag 'amd-drm-next-5.8-2020-05-27' of git://people.freedesktop.org/~agd5... (diff)
download	linux-faa392181a0bd42c5478175cef601adeecdc91b6.tar.xz linux-faa392181a0bd42c5478175cef601adeecdc91b6.zip