Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux

Merge mainline to pick up c7513c2a2714 ("crypto/arm64: aes-ce-gcm -
add missing kernel_neon_begin/end pair").

28 files changed, 429 insertions, 103 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b51c05d03f14..7f562410f9cf 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -862,6 +862,7 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 {
 	struct intel_vgpu *vgpu = s->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
+	u32 ctx_sr_ctl;
 
 	if (offset + 4 > gvt->device_info.mmio_size) {
 		gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
@@ -894,6 +895,28 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 		patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE);
 	}
 
+	/* TODO
+	 * Right now only scan LRI command on KBL and in inhibit context.
+	 * It's good enough to support initializing mmio by lri command in
+	 * vgpu inhibit context on KBL.
+	 */
+	if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) &&
+			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
+			!strncmp(cmd, "lri", 3)) {
+		intel_gvt_hypervisor_read_gpa(s->vgpu,
+			s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4);
+		/* check inhibit context */
+		if (ctx_sr_ctl & 1) {
+			u32 data = cmd_val(s, index + 1);
+
+			if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset))
+				intel_vgpu_mask_mmio_write(vgpu,
+							offset, &data, 4);
+			else
+				vgpu_vreg(vgpu, offset) = data;
+		}
+	}
+
 	/* TODO: Update the global mask if this MMIO is a masked-MMIO */
 	intel_gvt_mmio_set_cmd_accessed(gvt, offset);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8180e8d1e2..4b072ade8c38 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -196,7 +196,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_B << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -216,7 +216,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_C << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -236,7 +236,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_D << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 23296547da95..4efec8fa6c1d 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1592,6 +1592,7 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu)
 		vgpu_free_mm(mm);
 		return ERR_PTR(-ENOMEM);
 	}
+	mm->ggtt_mm.last_partial_off = -1UL;
 
 	return mm;
 }
@@ -1616,6 +1617,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
+		mm->ggtt_mm.last_partial_off = -1UL;
 	}
 
 	vgpu_free_mm(mm);
@@ -1868,6 +1870,62 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
 			bytes);
 
+	/* If ggtt entry size is 8 bytes, and it's split into two 4 bytes
+	 * write, we assume the two 4 bytes writes are consecutive.
+	 * Otherwise, we abort and report error
+	 */
+	if (bytes < info->gtt_entry_size) {
+		if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) {
+			/* the first partial part*/
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+			return 0;
+		} else if ((g_gtt_index ==
+				(ggtt_mm->ggtt_mm.last_partial_off >>
+				info->gtt_entry_size_shift)) &&
+			(off !=	ggtt_mm->ggtt_mm.last_partial_off)) {
+			/* the second partial part */
+
+			int last_off = ggtt_mm->ggtt_mm.last_partial_off &
+				(info->gtt_entry_size - 1);
+
+			memcpy((void *)&e.val64 + last_off,
+				(void *)&ggtt_mm->ggtt_mm.last_partial_data +
+				last_off, bytes);
+
+			ggtt_mm->ggtt_mm.last_partial_off = -1UL;
+		} else {
+			int last_offset;
+
+			gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n",
+					ggtt_mm->ggtt_mm.last_partial_off, off,
+					bytes, info->gtt_entry_size);
+
+			/* set host ggtt entry to scratch page and clear
+			 * virtual ggtt entry as not present for last
+			 * partially write offset
+			 */
+			last_offset = ggtt_mm->ggtt_mm.last_partial_off &
+					(~(info->gtt_entry_size - 1));
+
+			ggtt_get_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate_pte(vgpu, &m);
+			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+			ops->clear_present(&m);
+			ggtt_set_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate(gvt->dev_priv);
+
+			ggtt_get_guest_entry(ggtt_mm, &e, last_offset);
+			ops->clear_present(&e);
+			ggtt_set_guest_entry(ggtt_mm, &e, last_offset);
+
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+
+			return 0;
+		}
+	}
+
 	if (ops->test_present(&e)) {
 		gfn = ops->get_pfn(&e);
 		m = e;
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 3792f2b7f4ff..97e62647418a 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -150,6 +150,8 @@ struct intel_vgpu_mm {
 		} ppgtt_mm;
 		struct {
 			void *virtual_ggtt;
+			unsigned long last_partial_off;
+			u64 last_partial_data;
 		} ggtt_mm;
 	};
 };
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 05d15a095310..858967daf04b 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -268,6 +268,8 @@ struct intel_gvt_mmio {
 #define F_CMD_ACCESSED	(1 << 5)
 /* This reg could be accessed by unaligned address */
 #define F_UNALIGN	(1 << 6)
+/* This reg is saved/restored in context */
+#define F_IN_CTX	(1 << 7)
 
 	struct gvt_mmio_block *mmio_block;
 	unsigned int num_mmio_block;
@@ -639,6 +641,33 @@ static inline bool intel_gvt_mmio_has_mode_mask(
 	return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK;
 }
 
+/**
+ * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if a MMIO has a in-context mask, false if it isn't.
+ *
+ */
+static inline bool intel_gvt_mmio_is_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX;
+}
+
+/**
+ * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ */
+static inline void intel_gvt_mmio_set_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX;
+}
+
 int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);
 int intel_gvt_debugfs_init(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index bcbc47a88a70..8f1caacdc78a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -3046,6 +3046,30 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 }
 
 /**
+ * intel_vgpu_mask_mmio_write - write mask register
+ * @vgpu: a vGPU
+ * @offset: access offset
+ * @p_data: write data buffer
+ * @bytes: access data length
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ */
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+		void *p_data, unsigned int bytes)
+{
+	u32 mask, old_vreg;
+
+	old_vreg = vgpu_vreg(vgpu, offset);
+	write_vreg(vgpu, offset, p_data, bytes);
+	mask = vgpu_vreg(vgpu, offset) >> 16;
+	vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) |
+				(vgpu_vreg(vgpu, offset) & mask);
+
+	return 0;
+}
+
+/**
  * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
  * force-nopriv register
  *
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 71b620875943..dac8c6401e26 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -98,4 +98,6 @@ bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
 int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 			   void *pdata, unsigned int bytes, bool is_read);
 
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+				  void *p_data, unsigned int bytes);
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 0f949554d118..5ca9caf7552a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -581,7 +581,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 
 	for (mmio = gvt->engine_mmio_list.mmio;
 	     i915_mmio_reg_valid(mmio->reg); mmio++) {
-		if (mmio->in_context)
+		if (mmio->in_context) {
 			gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++;
+			intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 34c125e2d90c..71e1aa54f774 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -340,14 +340,21 @@ struct drm_i915_file_private {
 
 	unsigned int bsd_engine;
 
-/* Client can have a maximum of 3 contexts banned before
- * it is denied of creating new contexts. As one context
- * ban needs 4 consecutive hangs, and more if there is
- * progress in between, this is a last resort stop gap measure
- * to limit the badly behaving clients access to gpu.
+/*
+ * Every context ban increments per client ban score. Also
+ * hangs in short succession increments ban score. If ban threshold
+ * is reached, client is considered banned and submitting more work
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
  */
-#define I915_MAX_CLIENT_CONTEXT_BANS 3
-	atomic_t context_bans;
+#define I915_CLIENT_SCORE_HANG_FAST	1
+#define   I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN   3
+#define I915_CLIENT_SCORE_BANNED	9
+	/** ban_score: Accumulated score of all ctx bans and fast hangs. */
+	atomic_t ban_score;
+	unsigned long hang_timestamp;
 };
 
 /* Interface history:
@@ -645,6 +652,7 @@ enum intel_sbi_destination {
 #define QUIRK_BACKLIGHT_PRESENT (1<<3)
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
+#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -2238,9 +2246,6 @@ static inline struct scatterlist *____sg_next(struct scatterlist *sg)
  **/
 static inline struct scatterlist *__sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	return sg_is_last(sg) ? NULL : ____sg_next(sg);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3704f4c0c2c9..17c5097721e8 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2002,7 +2002,6 @@ int i915_gem_fault(struct vm_fault *vmf)
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
 	struct i915_vma *vma;
 	pgoff_t page_offset;
-	unsigned int flags;
 	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset */
@@ -2038,27 +2037,34 @@ int i915_gem_fault(struct vm_fault *vmf)
 		goto err_unlock;
 	}
 
-	/* If the object is smaller than a couple of partial vma, it is
-	 * not worth only creating a single partial vma - we may as well
-	 * clear enough space for the full object.
-	 */
-	flags = PIN_MAPPABLE;
-	if (obj->base.size > 2 * MIN_CHUNK_PAGES << PAGE_SHIFT)
-		flags |= PIN_NONBLOCK | PIN_NONFAULT;
 
 	/* Now pin it into the GTT as needed */
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, flags);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       PIN_MAPPABLE |
+				       PIN_NONBLOCK |
+				       PIN_NONFAULT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
 			compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
+		unsigned int flags;
 
-		/* Userspace is now writing through an untracked VMA, abandon
+		flags = PIN_MAPPABLE;
+		if (view.type == I915_GGTT_VIEW_NORMAL)
+			flags |= PIN_NONBLOCK; /* avoid warnings for pinned */
+
+		/*
+		 * Userspace is now writing through an untracked VMA, abandon
 		 * all hope that the hardware is able to track future writes.
 		 */
 		obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
 
-		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		if (IS_ERR(vma) && !view.type) {
+			flags = PIN_MAPPABLE;
+			view.type = I915_GGTT_VIEW_PARTIAL;
+			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		}
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -2933,32 +2939,54 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
+static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
+					const struct i915_gem_context *ctx)
+{
+	unsigned int score;
+	unsigned long prev_hang;
+
+	if (i915_gem_context_is_banned(ctx))
+		score = I915_CLIENT_SCORE_CONTEXT_BAN;
+	else
+		score = 0;
+
+	prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
+	if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
+		score += I915_CLIENT_SCORE_HANG_FAST;
+
+	if (score) {
+		atomic_add(score, &file_priv->ban_score);
+
+		DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
+				 ctx->name, score,
+				 atomic_read(&file_priv->ban_score));
+	}
+}
+
 static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 {
-	bool banned;
+	unsigned int score;
+	bool banned, bannable;
 
 	atomic_inc(&ctx->guilty_count);
 
-	banned = false;
-	if (i915_gem_context_is_bannable(ctx)) {
-		unsigned int score;
+	bannable = i915_gem_context_is_bannable(ctx);
+	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
+	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-		score = atomic_add_return(CONTEXT_SCORE_GUILTY,
-					  &ctx->ban_score);
-		banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
+			 ctx->name, atomic_read(&ctx->guilty_count),
+			 score, yesno(banned && bannable));
 
-		DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
-				 ctx->name, score, yesno(banned));
-	}
-	if (!banned)
+	/* Cool contexts don't accumulate client ban score */
+	if (!bannable)
 		return;
 
-	i915_gem_context_set_banned(ctx);
-	if (!IS_ERR_OR_NULL(ctx->file_priv)) {
-		atomic_inc(&ctx->file_priv->context_bans);
-		DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
-				 ctx->name, atomic_read(&ctx->file_priv->context_bans));
-	}
+	if (banned)
+		i915_gem_context_set_banned(ctx);
+
+	if (!IS_ERR_OR_NULL(ctx->file_priv))
+		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
 }
 
 static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
@@ -5736,6 +5764,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	INIT_LIST_HEAD(&file_priv->mm.request_list);
 
 	file_priv->bsd_engine = -1;
+	file_priv->hang_timestamp = jiffies;
 
 	ret = i915_gem_context_open(i915, file);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 33f8a4b3c981..060335d3d9e0 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -652,7 +652,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 
 static bool client_is_banned(struct drm_i915_file_private *file_priv)
 {
-	return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS;
+	return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f627a8c47c58..22df17c8ca9b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -489,7 +489,9 @@ eb_validate_vma(struct i915_execbuffer *eb,
 }
 
 static int
-eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
+eb_add_vma(struct i915_execbuffer *eb,
+	   unsigned int i, unsigned batch_idx,
+	   struct i915_vma *vma)
 {
 	struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 	int err;
@@ -522,6 +524,24 @@ eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
 	eb->flags[i] = entry->flags;
 	vma->exec_flags = &eb->flags[i];
 
+	/*
+	 * SNA is doing fancy tricks with compressing batch buffers, which leads
+	 * to negative relocation deltas. Usually that works out ok since the
+	 * relocate address is still positive, except when the batch is placed
+	 * very low in the GTT. Ensure this doesn't happen.
+	 *
+	 * Note that actual hangs have only been observed on gen7, but for
+	 * paranoia do it everywhere.
+	 */
+	if (i == batch_idx) {
+		if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+			eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
+		if (eb->reloc_cache.has_fence)
+			eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
+
+		eb->batch = vma;
+	}
+
 	err = 0;
 	if (eb_pin_vma(eb, entry, vma)) {
 		if (entry->offset != vma->node.start) {
@@ -716,7 +736,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
 	struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
 	struct drm_i915_gem_object *obj;
-	unsigned int i;
+	unsigned int i, batch;
 	int err;
 
 	if (unlikely(i915_gem_context_is_closed(eb->ctx)))
@@ -728,6 +748,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 	INIT_LIST_HEAD(&eb->relocs);
 	INIT_LIST_HEAD(&eb->unbound);
 
+	batch = eb_batch_index(eb);
+
 	for (i = 0; i < eb->buffer_count; i++) {
 		u32 handle = eb->exec[i].handle;
 		struct i915_lut_handle *lut;
@@ -770,33 +792,16 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 		lut->handle = handle;
 
 add_vma:
-		err = eb_add_vma(eb, i, vma);
+		err = eb_add_vma(eb, i, batch, vma);
 		if (unlikely(err))
 			goto err_vma;
 
 		GEM_BUG_ON(vma != eb->vma[i]);
 		GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
+		GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
+			   eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i]));
 	}
 
-	/* take note of the batch buffer before we might reorder the lists */
-	i = eb_batch_index(eb);
-	eb->batch = eb->vma[i];
-	GEM_BUG_ON(eb->batch->exec_flags != &eb->flags[i]);
-
-	/*
-	 * SNA is doing fancy tricks with compressing batch buffers, which leads
-	 * to negative relocation deltas. Usually that works out ok since the
-	 * relocate address is still positive, except when the batch is placed
-	 * very low in the GTT. Ensure this doesn't happen.
-	 *
-	 * Note that actual hangs have only been observed on gen7, but for
-	 * paranoia do it everywhere.
-	 */
-	if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
-		eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
-	if (eb->reloc_cache.has_fence)
-		eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
-
 	eb->args->flags |= __EXEC_VALIDATED;
 	return eb_reserve(eb);
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f9bc3aaa90d0..c16cb025755e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1893,9 +1893,17 @@ static void i9xx_pipestat_irq_ack(struct drm_i915_private *dev_priv,
 
 		/*
 		 * Clear the PIPE*STAT regs before the IIR
+		 *
+		 * Toggle the enable bits to make sure we get an
+		 * edge in the ISR pipe event bit if we don't clear
+		 * all the enabled status bits. Otherwise the edge
+		 * triggered IIR on i965/g4x wouldn't notice that
+		 * an interrupt is still pending.
 		 */
-		if (pipe_stats[pipe])
-			I915_WRITE(reg, enable_mask | pipe_stats[pipe]);
+		if (pipe_stats[pipe]) {
+			I915_WRITE(reg, pipe_stats[pipe]);
+			I915_WRITE(reg, enable_mask);
+		}
 	}
 	spin_unlock(&dev_priv->irq_lock);
 }
@@ -1990,10 +1998,38 @@ static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv,
 
 static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+	u32 hotplug_status = 0, hotplug_status_mask;
+	int i;
 
-	if (hotplug_status)
+	if (IS_G4X(dev_priv) ||
+	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		hotplug_status_mask = HOTPLUG_INT_STATUS_G4X |
+			DP_AUX_CHANNEL_MASK_INT_STATUS_G4X;
+	else
+		hotplug_status_mask = HOTPLUG_INT_STATUS_I915;
+
+	/*
+	 * We absolutely have to clear all the pending interrupt
+	 * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port
+	 * interrupt bit won't have an edge, and the i965/g4x
+	 * edge triggered IIR will not notice that an interrupt
+	 * is still pending. We can't use PORT_HOTPLUG_EN to
+	 * guarantee the edge as the act of toggling the enable
+	 * bits can itself generate a new hotplug interrupt :(
+	 */
+	for (i = 0; i < 10; i++) {
+		u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask;
+
+		if (tmp == 0)
+			return hotplug_status;
+
+		hotplug_status |= tmp;
 		I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+	}
+
+	WARN_ONCE(1,
+		  "PORT_HOTPLUG_STAT did not clear (0x%08x)\n",
+		  I915_READ(PORT_HOTPLUG_STAT));
 
 	return hotplug_status;
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f11bb213ec07..7720569f2024 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2425,12 +2425,17 @@ enum i915_power_well_id {
 #define _3D_CHICKEN	_MMIO(0x2084)
 #define  _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB	(1 << 10)
 #define _3D_CHICKEN2	_MMIO(0x208c)
+
+#define FF_SLICE_CHICKEN	_MMIO(0x2088)
+#define  FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX	(1 << 1)
+
 /* Disables pipelining of read flushes past the SF-WIZ interface.
  * Required on all Ironlake steppings according to the B-Spec, but the
  * particular danger of not doing so is not specified.
  */
 # define _3D_CHICKEN2_WM_READ_PIPELINED			(1 << 14)
 #define _3D_CHICKEN3	_MMIO(0x2090)
+#define  _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX		(1 << 12)
 #define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
 #define  _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
 #define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9324d476e0a7..0531c01c3604 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -109,7 +109,7 @@ vma_create(struct drm_i915_gem_object *obj,
 						     obj->base.size >> PAGE_SHIFT));
 			vma->size = view->partial.size;
 			vma->size <<= PAGE_SHIFT;
-			GEM_BUG_ON(vma->size >= obj->base.size);
+			GEM_BUG_ON(vma->size > obj->base.size);
 		} else if (view->type == I915_GGTT_VIEW_ROTATED) {
 			vma->size = intel_rotation_info_size(&view->rotated);
 			vma->size <<= PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index de0e22322c76..072b326d5ee0 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -304,6 +304,9 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	int max_dotclk = dev_priv->max_dotclk_freq;
 	int max_clock;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (mode->clock < 25000)
 		return MODE_CLOCK_LOW;
 
@@ -337,6 +340,12 @@ static bool intel_crt_compute_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->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	return true;
 }
 
@@ -344,6 +353,12 @@ static bool pch_crt_compute_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->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_pch_encoder = true;
 
 	return true;
@@ -354,6 +369,11 @@ static bool hsw_crt_compute_config(struct intel_encoder *encoder,
 				   struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
 
 	pipe_config->has_pch_encoder = true;
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index f4a8598a2d39..fed26d6e4e27 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1782,15 +1782,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder)
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
 	uint32_t val = I915_READ(reg);
 
 	val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
 	val |= TRANS_DDI_PORT_NONE;
 	I915_WRITE(reg, val);
+
+	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");
+		/* Quirk time at 100ms for reliable operation */
+		msleep(100);
+	}
 }
 
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index dee3a8e659f1..dec0d60921bf 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5809,7 +5809,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		intel_ddi_set_vc_payload_alloc(intel_crtc->config, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
+		intel_ddi_disable_transcoder_func(old_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skylake_scaler_disable(intel_crtc);
@@ -14469,12 +14469,22 @@ static enum drm_mode_status
 intel_mode_valid(struct drm_device *dev,
 		 const struct drm_display_mode *mode)
 {
+	/*
+	 * Can't reject DBLSCAN here because Xorg ddxen can add piles
+	 * of DBLSCAN modes to the output's mode list when they detect
+	 * the scaling mode property on the connector. And they don't
+	 * ask the kernel to validate those modes in any way until
+	 * modeset time at which point the client gets a protocol error.
+	 * So in order to not upset those clients we silently ignore the
+	 * DBLSCAN flag on such connectors. For other connectors we will
+	 * reject modes with the DBLSCAN flag in encoder->compute_config().
+	 * And we always reject DBLSCAN modes in connector->mode_valid()
+	 * as we never want such modes on the connector's mode list.
+	 */
+
 	if (mode->vscan > 1)
 		return MODE_NO_VSCAN;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	if (mode->flags & DRM_MODE_FLAG_HSKEW)
 		return MODE_H_ILLEGAL;
 
@@ -14636,6 +14646,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev)
 	DRM_INFO("Applying T12 delay quirk\n");
 }
 
+/*
+ * GeminiLake NUC HDMI outputs require additional off time
+ * this allows the onboard retimer to correctly sync to signal
+ */
+static void quirk_increase_ddi_disabled_time(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME;
+	DRM_INFO("Applying Increase DDI Disabled quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -14722,6 +14744,13 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Toshiba Satellite P50-C-18C */
 	{ 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay },
+
+	/* GeminiLake NUC */
+	{ 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	/* ASRock ITX*/
+	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 8320f0e8e3be..16faea30114a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -420,6 +420,9 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	int max_rate, mode_rate, max_lanes, max_link_clock;
 	int max_dotclk;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	max_dotclk = intel_dp_downstream_max_dotclock(intel_dp);
 
 	if (intel_dp_is_edp(intel_dp) && fixed_mode) {
@@ -1862,7 +1865,10 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 						conn_state->scaling_mode);
 	}
 
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
+	if (HAS_GMCH_DISPLAY(dev_priv) &&
 	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
@@ -2784,16 +2790,6 @@ static void g4x_disable_dp(struct intel_encoder *encoder,
 			   const struct drm_connector_state *old_conn_state)
 {
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
-
-	/* disable the port before the pipe on g4x */
-	intel_dp_link_down(encoder, old_crtc_state);
-}
-
-static void ilk_disable_dp(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);
 }
 
 static void vlv_disable_dp(struct intel_encoder *encoder,
@@ -2807,13 +2803,19 @@ static void vlv_disable_dp(struct intel_encoder *encoder,
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
 
-static void ilk_post_disable_dp(struct intel_encoder *encoder,
+static void g4x_post_disable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = encoder->port;
 
+	/*
+	 * Bspec does not list a specific disable sequence for g4x DP.
+	 * Follow the ilk+ sequence (disable pipe before the port) for
+	 * g4x DP as it does not suffer from underruns like the normal
+	 * g4x modeset sequence (disable pipe after the port).
+	 */
 	intel_dp_link_down(encoder, old_crtc_state);
 
 	/* Only ilk+ has port A */
@@ -6337,7 +6339,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
 
-	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+	if (!HAS_GMCH_DISPLAY(dev_priv))
 		connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 
@@ -6436,15 +6438,11 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 		intel_encoder->enable = vlv_enable_dp;
 		intel_encoder->disable = vlv_disable_dp;
 		intel_encoder->post_disable = vlv_post_disable_dp;
-	} else if (INTEL_GEN(dev_priv) >= 5) {
-		intel_encoder->pre_enable = g4x_pre_enable_dp;
-		intel_encoder->enable = g4x_enable_dp;
-		intel_encoder->disable = ilk_disable_dp;
-		intel_encoder->post_disable = ilk_post_disable_dp;
 	} else {
 		intel_encoder->pre_enable = g4x_pre_enable_dp;
 		intel_encoder->enable = g4x_enable_dp;
 		intel_encoder->disable = g4x_disable_dp;
+		intel_encoder->post_disable = g4x_post_disable_dp;
 	}
 
 	intel_dig_port->dp.output_reg = output_reg;
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 9e6956c08688..5890500a3a8b 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -48,6 +48,9 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
 					   DP_DPCD_QUIRK_LIMITED_M_N);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_pch_encoder = false;
 	bpp = 24;
 	if (intel_dp->compliance.test_data.bpc) {
@@ -366,6 +369,9 @@ intel_dp_mst_mode_valid(struct drm_connector *connector,
 	if (!intel_dp)
 		return MODE_ERROR;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	max_link_clock = intel_dp_max_link_rate(intel_dp);
 	max_lanes = intel_dp_max_lane_count(intel_dp);
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0361130500a6..b8eefbffc77d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1388,8 +1388,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 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_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder);
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
 struct intel_encoder *
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index cf39ca90d887..f349b3920199 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -326,6 +326,9 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 						conn_state->scaling_mode);
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	/* DSI uses short packets for sync events, so clear mode flags for DSI */
 	adjusted_mode->flags = 0;
 
@@ -1266,6 +1269,9 @@ intel_dsi_mode_valid(struct drm_connector *connector,
 
 	DRM_DEBUG_KMS("\n");
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (fixed_mode) {
 		if (mode->hdisplay > fixed_mode->hdisplay)
 			return MODE_PANEL;
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index a70d767313aa..61d908e0df0e 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -219,6 +219,9 @@ intel_dvo_mode_valid(struct drm_connector *connector,
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	/* XXX: Validate clock range */
 
 	if (fixed_mode) {
@@ -254,6 +257,9 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 	if (fixed_mode)
 		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ee929f31f7db..d8cb53ef4351 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1557,6 +1557,9 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	bool force_dvi =
 		READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	clock = mode->clock;
 
 	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
@@ -1677,6 +1680,9 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	int desired_bpp;
 	bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink;
 
 	if (pipe_config->has_hdmi_sink)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 15434cad5430..7c4c8fb1dae4 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1545,11 +1545,21 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
 	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
+	*batch++ = MI_LOAD_REGISTER_IMM(3);
+
 	/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
-	*batch++ = MI_LOAD_REGISTER_IMM(1);
 	*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
 	*batch++ = _MASKED_BIT_DISABLE(
 			GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+
+	/* BSpec: 11391 */
+	*batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
+	*batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+
+	/* BSpec: 11299 */
+	*batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
+	*batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+
 	*batch++ = MI_NOOP;
 
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
@@ -2641,10 +2651,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 	context_size += LRC_HEADER_PAGES * PAGE_SIZE;
 
 	ctx_obj = i915_gem_object_create(ctx->i915, context_size);
-	if (IS_ERR(ctx_obj)) {
-		ret = PTR_ERR(ctx_obj);
-		goto error_deref_obj;
-	}
+	if (IS_ERR(ctx_obj))
+		return PTR_ERR(ctx_obj);
 
 	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
 	if (IS_ERR(vma)) {
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index d278f24ba6ae..48f618dc9abb 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -380,6 +380,8 @@ intel_lvds_mode_valid(struct drm_connector *connector,
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	int max_pixclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
 	if (mode->hdisplay > fixed_mode->hdisplay)
 		return MODE_PANEL;
 	if (mode->vdisplay > fixed_mode->vdisplay)
@@ -429,6 +431,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
 			       adjusted_mode);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	if (HAS_PCH_SPLIT(dev_priv)) {
 		pipe_config->has_pch_encoder = true;
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 25005023c243..26975df4e593 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1160,6 +1160,9 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 							   adjusted_mode);
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	/*
 	 * Make the CRTC code factor in the SDVO pixel multiplier.  The
 	 * SDVO device will factor out the multiplier during mode_set.
@@ -1621,6 +1624,9 @@ intel_sdvo_mode_valid(struct drm_connector *connector,
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (intel_sdvo->pixel_clock_min > mode->clock)
 		return MODE_CLOCK_LOW;
 
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 885fc3809f7f..b55b5c157e38 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -850,6 +850,9 @@ intel_tv_mode_valid(struct drm_connector *connector,
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (mode->clock > max_dotclk)
 		return MODE_CLOCK_HIGH;
 
@@ -877,16 +880,21 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 			struct drm_connector_state *conn_state)
 {
 	const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
 
 	if (!tv_mode)
 		return false;
 
-	pipe_config->base.adjusted_mode.crtc_clock = tv_mode->clock;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
+	adjusted_mode->crtc_clock = tv_mode->clock;
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;
 
 	/* TV has it's own notion of sync and other mode flags, so clear them. */
-	pipe_config->base.adjusted_mode.flags = 0;
+	adjusted_mode->flags = 0;
 
 	/*
 	 * FIXME: We don't check whether the input mode is actually what we want