Merge tag 'v5.6' into mips-next

Linux 5.6

42 files changed, 454 insertions, 273 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index ba9595960bbe..907c4471f591 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -75,9 +75,8 @@ config DRM_I915_CAPTURE_ERROR
 	help
 	  This option enables capturing the GPU state when a hang is detected.
 	  This information is vital for triaging hangs and assists in debugging.
-	  Please report any hang to
-	    https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
-	  for triaging.
+	  Please report any hang for triaging according to:
+	    https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 
 	  If in doubt, say "Y".
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index b8c5f8934dbd..a1f2411aa21b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -294,7 +294,7 @@ extra-$(CONFIG_DRM_I915_WERROR) += \
 		$(shell cd $(srctree)/$(src) && find * -name '*.h')))
 
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
-      cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@
+      cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
 	$(call if_changed_dep,hdrtest)
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 33f1dc3d7c1a..d9a61f341070 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4251,7 +4251,9 @@ static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
 void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 					 struct intel_crtc_state *crtc_state)
 {
-	if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
+	if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000)
+		crtc_state->min_voltage_level = 3;
+	else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 1;
 	else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 2;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 064dd99bbc49..aa453953908b 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11087,7 +11087,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 	u32 base;
 
 	if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
-		base = obj->phys_handle->busaddr;
+		base = sg_dma_address(obj->mm.pages->sgl);
 	else
 		base = intel_plane_ggtt_offset(plane_state);
 
@@ -17433,6 +17433,24 @@ retry:
 			 * have readout for pipe gamma enable.
 			 */
 			crtc_state->uapi.color_mgmt_changed = true;
+
+			/*
+			 * FIXME hack to force full modeset when DSC is being
+			 * used.
+			 *
+			 * As long as we do not have full state readout and
+			 * config comparison of crtc_state->dsc, we have no way
+			 * to ensure reliable fastset. Remove once we have
+			 * readout for DSC.
+			 */
+			if (crtc_state->dsc.compression_enable) {
+				ret = drm_atomic_add_affected_connectors(state,
+									 &crtc->base);
+				if (ret)
+					goto out;
+				crtc_state->uapi.mode_changed = true;
+				drm_dbg_kms(dev, "Force full modeset for DSC\n");
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 21561acfa3ac..46c40db992dd 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4466,13 +4466,19 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv)
 
 static void icl_mbus_init(struct drm_i915_private *dev_priv)
 {
-	u32 val;
+	u32 mask, val;
 
-	val = MBUS_ABOX_BT_CREDIT_POOL1(16) |
-	      MBUS_ABOX_BT_CREDIT_POOL2(16) |
-	      MBUS_ABOX_B_CREDIT(1) |
-	      MBUS_ABOX_BW_CREDIT(1);
+	mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK |
+		MBUS_ABOX_BT_CREDIT_POOL2_MASK |
+		MBUS_ABOX_B_CREDIT_MASK |
+		MBUS_ABOX_BW_CREDIT_MASK;
 
+	val = I915_READ(MBUS_ABOX_CTL);
+	val &= ~mask;
+	val |= MBUS_ABOX_BT_CREDIT_POOL1(16) |
+		MBUS_ABOX_BT_CREDIT_POOL2(16) |
+		MBUS_ABOX_B_CREDIT(1) |
+		MBUS_ABOX_BW_CREDIT(1);
 	I915_WRITE(MBUS_ABOX_CTL, val);
 }
 
@@ -4968,8 +4974,21 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
 		I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE);
 		I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE);
 	} else {
+		u32 val;
+
 		I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask);
 		I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask);
+
+		/* Wa_22010178259:tgl */
+		val = I915_READ(BW_BUDDY1_CTL);
+		val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+		val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+		I915_WRITE(BW_BUDDY1_CTL, val);
+
+		val = I915_READ(BW_BUDDY2_CTL);
+		val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+		val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+		I915_WRITE(BW_BUDDY2_CTL, val);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 89c9cf5f38d2..83025052c965 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -852,10 +852,12 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
-	if (!crtc_state->has_psr)
+	if (!CAN_PSR(dev_priv) || dev_priv->psr.dp != intel_dp)
 		return;
 
-	if (WARN_ON(!CAN_PSR(dev_priv)))
+	dev_priv->psr.force_mode_changed = false;
+
+	if (!crtc_state->has_psr)
 		return;
 
 	WARN_ON(dev_priv->drrs.dp);
@@ -1009,6 +1011,8 @@ void intel_psr_update(struct intel_dp *intel_dp,
 	if (!CAN_PSR(dev_priv) || READ_ONCE(psr->dp) != intel_dp)
 		return;
 
+	dev_priv->psr.force_mode_changed = false;
+
 	mutex_lock(&dev_priv->psr.lock);
 
 	enable = crtc_state->has_psr && psr_global_enabled(psr->debug);
@@ -1534,7 +1538,7 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 	struct drm_crtc_state *crtc_state;
 
 	if (!CAN_PSR(dev_priv) || !new_state->crtc ||
-	    dev_priv->psr.initially_probed)
+	    !dev_priv->psr.force_mode_changed)
 		return;
 
 	intel_connector = to_intel_connector(connector);
@@ -1545,5 +1549,18 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 	crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
 						   new_state->crtc);
 	crtc_state->mode_changed = true;
-	dev_priv->psr.initially_probed = true;
+}
+
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv;
+
+	if (!intel_dp)
+		return;
+
+	dev_priv = dp_to_i915(intel_dp);
+	if (!CAN_PSR(dev_priv) || intel_dp != dev_priv->psr.dp)
+		return;
+
+	dev_priv->psr.force_mode_changed = true;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index c58a1d438808..274fc6bb6221 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -40,5 +40,6 @@ bool intel_psr_enabled(struct intel_dp *intel_dp);
 void intel_psr_atomic_check(struct drm_connector *connector,
 			    struct drm_connector_state *old_state,
 			    struct drm_connector_state *new_state);
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index a2e57e62af30..151a1e8ae36a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -565,6 +565,22 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
 		if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
 			return -ENODEV;
 
+		/*
+		 * If the cancel fails, we then need to reset, cleanly!
+		 *
+		 * If the per-engine reset fails, all hope is lost! We resort
+		 * to a full GPU reset in that unlikely case, but realistically
+		 * if the engine could not reset, the full reset does not fare
+		 * much better. The damage has been done.
+		 *
+		 * However, if we cannot reset an engine by itself, we cannot
+		 * cleanup a hanging persistent context without causing
+		 * colateral damage, and we should not pretend we can by
+		 * exposing the interface.
+		 */
+		if (!intel_has_reset_engine(&ctx->i915->gt))
+			return -ENODEV;
+
 		i915_gem_context_clear_persistence(ctx);
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 60c984e10c4a..7643a30ba4cd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -423,7 +423,8 @@ eb_validate_vma(struct i915_execbuffer *eb,
 	if (unlikely(entry->flags & eb->invalid_flags))
 		return -EINVAL;
 
-	if (unlikely(entry->alignment && !is_power_of_2(entry->alignment)))
+	if (unlikely(entry->alignment &&
+		     !is_power_of_2_u64(entry->alignment)))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 35985218bd85..5da9f9e534b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -225,6 +225,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 		/* But keep the pointer alive for RCU-protected lookups */
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
+		cond_resched();
 	}
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
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 f64ad77e6b1e..c2174da35bb0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -285,9 +285,6 @@ struct drm_i915_gem_object {
 
 		void *gvt_info;
 	};
-
-	/** for phys allocated objects */
-	struct drm_dma_handle *phys_handle;
 };
 
 static inline struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index b1b7c1b3038a..b07bb40edd5a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -22,88 +22,87 @@
 static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
 	struct address_space *mapping = obj->base.filp->f_mapping;
-	struct drm_dma_handle *phys;
-	struct sg_table *st;
 	struct scatterlist *sg;
-	char *vaddr;
+	struct sg_table *st;
+	dma_addr_t dma;
+	void *vaddr;
+	void *dst;
 	int i;
-	int err;
 
 	if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
 		return -EINVAL;
 
-	/* Always aligning to the object size, allows a single allocation
+	/*
+	 * Always aligning to the object size, allows a single allocation
 	 * to handle all possible callers, and given typical object sizes,
 	 * the alignment of the buddy allocation will naturally match.
 	 */
-	phys = drm_pci_alloc(obj->base.dev,
-			     roundup_pow_of_two(obj->base.size),
-			     roundup_pow_of_two(obj->base.size));
-	if (!phys)
+	vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev,
+				   roundup_pow_of_two(obj->base.size),
+				   &dma, GFP_KERNEL);
+	if (!vaddr)
 		return -ENOMEM;
 
-	vaddr = phys->vaddr;
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_pci;
+
+	if (sg_alloc_table(st, 1, GFP_KERNEL))
+		goto err_st;
+
+	sg = st->sgl;
+	sg->offset = 0;
+	sg->length = obj->base.size;
+
+	sg_assign_page(sg, (struct page *)vaddr);
+	sg_dma_address(sg) = dma;
+	sg_dma_len(sg) = obj->base.size;
+
+	dst = vaddr;
 	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
 		struct page *page;
-		char *src;
+		void *src;
 
 		page = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			goto err_phys;
-		}
+		if (IS_ERR(page))
+			goto err_st;
 
 		src = kmap_atomic(page);
-		memcpy(vaddr, src, PAGE_SIZE);
-		drm_clflush_virt_range(vaddr, PAGE_SIZE);
+		memcpy(dst, src, PAGE_SIZE);
+		drm_clflush_virt_range(dst, PAGE_SIZE);
 		kunmap_atomic(src);
 
 		put_page(page);
-		vaddr += PAGE_SIZE;
+		dst += PAGE_SIZE;
 	}
 
 	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
 
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st) {
-		err = -ENOMEM;
-		goto err_phys;
-	}
-
-	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
-		kfree(st);
-		err = -ENOMEM;
-		goto err_phys;
-	}
-
-	sg = st->sgl;
-	sg->offset = 0;
-	sg->length = obj->base.size;
-
-	sg_dma_address(sg) = phys->busaddr;
-	sg_dma_len(sg) = obj->base.size;
-
-	obj->phys_handle = phys;
-
 	__i915_gem_object_set_pages(obj, st, sg->length);
 
 	return 0;
 
-err_phys:
-	drm_pci_free(obj->base.dev, phys);
-
-	return err;
+err_st:
+	kfree(st);
+err_pci:
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
+	return -ENOMEM;
 }
 
 static void
 i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
+	dma_addr_t dma = sg_dma_address(pages->sgl);
+	void *vaddr = sg_page(pages->sgl);
+
 	__i915_gem_object_release_shmem(obj, pages, false);
 
 	if (obj->mm.dirty) {
 		struct address_space *mapping = obj->base.filp->f_mapping;
-		char *vaddr = obj->phys_handle->vaddr;
+		void *src = vaddr;
 		int i;
 
 		for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
@@ -115,15 +114,16 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 				continue;
 
 			dst = kmap_atomic(page);
-			drm_clflush_virt_range(vaddr, PAGE_SIZE);
-			memcpy(dst, vaddr, PAGE_SIZE);
+			drm_clflush_virt_range(src, PAGE_SIZE);
+			memcpy(dst, src, PAGE_SIZE);
 			kunmap_atomic(dst);
 
 			set_page_dirty(page);
 			if (obj->mm.madv == I915_MADV_WILLNEED)
 				mark_page_accessed(page);
 			put_page(page);
-			vaddr += PAGE_SIZE;
+
+			src += PAGE_SIZE;
 		}
 		obj->mm.dirty = false;
 	}
@@ -131,7 +131,9 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 	sg_free_table(pages);
 	kfree(pages);
 
-	drm_pci_free(obj->base.dev, obj->phys_handle);
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
 }
 
 static void phys_release(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index f7e4b39c734f..59b387ade49c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -256,8 +256,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		freed = i915_gem_shrink(i915, -1UL, NULL,
 					I915_SHRINK_BOUND |
-					I915_SHRINK_UNBOUND |
-					I915_SHRINK_ACTIVE);
+					I915_SHRINK_UNBOUND);
 	}
 
 	return freed;
@@ -336,7 +335,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 	freed_pages = 0;
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
-					       I915_SHRINK_ACTIVE |
 					       I915_SHRINK_BOUND |
 					       I915_SHRINK_UNBOUND |
 					       I915_SHRINK_WRITEBACK);
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 ef7c74cff28a..43912e9b683d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 0ba524a414c6..cbad7fe722ce 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -136,6 +136,9 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 	struct intel_engine_cs *engine =
 		container_of(b, struct intel_engine_cs, breadcrumbs);
 
+	if (unlikely(intel_engine_is_virtual(engine)))
+		engine = intel_virtual_engine_get_sibling(engine, 0);
+
 	intel_engine_add_retire(engine, tl);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 7ef1d37970f6..24c99d0838af 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -99,6 +99,9 @@ static bool add_retire(struct intel_engine_cs *engine,
 void intel_engine_add_retire(struct intel_engine_cs *engine,
 			     struct intel_timeline *tl)
 {
+	/* We don't deal well with the engine disappearing beneath us */
+	GEM_BUG_ON(intel_engine_is_virtual(engine));
+
 	if (add_retire(engine, tl))
 		schedule_work(&engine->retire_work);
 }
@@ -144,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
+				mutex_unlock(&tl->mutex);
+
 				timeout = dma_fence_wait_timeout(fence,
 								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
+
+				/* Retirement is best effort */
+				if (!mutex_trylock(&tl->mutex)) {
+					active_count++;
+					goto out_active;
+				}
 			}
 		}
 
 		if (!retire_requests(tl) || flush_submission(gt))
 			active_count++;
+		mutex_unlock(&tl->mutex);
 
-		spin_lock(&timelines->lock);
+out_active:	spin_lock(&timelines->lock);
 
-		/* Resume iteration after dropping lock */
+		/* Resume list iteration after reacquiring spinlock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a13a8c4b65ab..31455eceeb0c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -237,7 +237,8 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     bool close);
 static void
 __execlists_update_reg_state(const struct intel_context *ce,
-			     const struct intel_engine_cs *engine);
+			     const struct intel_engine_cs *engine,
+			     u32 head);
 
 static void mark_eio(struct i915_request *rq)
 {
@@ -1186,12 +1187,11 @@ static void reset_active(struct i915_request *rq,
 		head = rq->tail;
 	else
 		head = active_request(ce->timeline, rq)->head;
-	ce->ring->head = intel_ring_wrap(ce->ring, head);
-	intel_ring_update_space(ce->ring);
+	head = intel_ring_wrap(ce->ring, head);
 
 	/* Scrub the context image to prevent replaying the previous batch */
 	restore_default_state(ce, engine);
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 
 	/* We've switched away, so this should be a no-op, but intent matters */
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
@@ -1321,7 +1321,7 @@ static u64 execlists_update_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
 	u64 desc = ce->lrc_desc;
-	u32 tail;
+	u32 tail, prev;
 
 	/*
 	 * WaIdleLiteRestore:bdw,skl
@@ -1334,9 +1334,15 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * subsequent resubmissions (for lite restore). Should that fail us,
 	 * and we try and submit the same tail again, force the context
 	 * reload.
+	 *
+	 * If we need to return to a preempted context, we need to skip the
+	 * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+	 * HW has a tendency to ignore us rewinding the TAIL to the end of
+	 * an earlier request.
 	 */
 	tail = intel_ring_set_tail(rq->ring, rq->tail);
-	if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+	prev = ce->lrc_reg_state[CTX_RING_TAIL];
+	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
 	rq->tail = rq->wa_tail;
@@ -1594,16 +1600,10 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 	spin_unlock(&old->breadcrumbs.irq_lock);
 }
 
-static struct i915_request *
-last_active(const struct intel_engine_execlists *execlists)
-{
-	struct i915_request * const *last = READ_ONCE(execlists->active);
-
-	while (*last && i915_request_completed(*last))
-		last++;
-
-	return *last;
-}
+#define for_each_waiter(p__, rq__) \
+	list_for_each_entry_lockless(p__, \
+				     &(rq__)->sched.waiters_list, \
+				     wait_link)
 
 static void defer_request(struct i915_request *rq, struct list_head * const pl)
 {
@@ -1622,7 +1622,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 		GEM_BUG_ON(i915_request_is_active(rq));
 		list_move_tail(&rq->sched.link, pl);
 
-		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+		for_each_waiter(p, rq) {
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
@@ -1668,11 +1668,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 	if (!intel_engine_has_timeslices(engine))
 		return false;
 
-	if (list_is_last(&rq->sched.link, &engine->active.requests))
-		return false;
-
-	hint = max(rq_prio(list_next_entry(rq, sched.link)),
-		   engine->execlists.queue_priority_hint);
+	hint = engine->execlists.queue_priority_hint;
+	if (!list_is_last(&rq->sched.link, &engine->active.requests))
+		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
 
 	return hint >= effective_prio(rq);
 }
@@ -1714,16 +1712,26 @@ static void set_timeslice(struct intel_engine_cs *engine)
 	set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
 }
 
+static void start_timeslice(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *execlists = &engine->execlists;
+
+	execlists->switch_priority_hint = execlists->queue_priority_hint;
+
+	if (timer_pending(&execlists->timer))
+		return;
+
+	set_timer_ms(&execlists->timer, timeslice(engine));
+}
+
 static void record_preemption(struct intel_engine_execlists *execlists)
 {
 	(void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++);
 }
 
-static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
+static unsigned long active_preempt_timeout(struct intel_engine_cs *engine,
+					    const struct i915_request *rq)
 {
-	struct i915_request *rq;
-
-	rq = last_active(&engine->execlists);
 	if (!rq)
 		return 0;
 
@@ -1734,13 +1742,14 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.preempt_timeout_ms);
 }
 
-static void set_preempt_timeout(struct intel_engine_cs *engine)
+static void set_preempt_timeout(struct intel_engine_cs *engine,
+				const struct i915_request *rq)
 {
 	if (!intel_engine_has_preempt_reset(engine))
 		return;
 
 	set_timer_ms(&engine->execlists.preempt,
-		     active_preempt_timeout(engine));
+		     active_preempt_timeout(engine, rq));
 }
 
 static inline void clear_ports(struct i915_request **ports, int count)
@@ -1753,6 +1762,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
+	struct i915_request * const *active;
 	struct i915_request *last;
 	struct rb_node *rb;
 	bool submit = false;
@@ -1807,7 +1817,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * i.e. we will retrigger preemption following the ack in case
 	 * of trouble.
 	 */
-	last = last_active(execlists);
+	active = READ_ONCE(execlists->active);
+	while ((last = *active) && i915_request_completed(last))
+		active++;
+
 	if (last) {
 		if (need_preempt(engine, last, rb)) {
 			ENGINE_TRACE(engine,
@@ -1834,14 +1847,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 */
 			__unwind_incomplete_requests(engine);
 
-			/*
-			 * If we need to return to the preempted context, we
-			 * need to skip the lite-restore and force it to
-			 * reload the RING_TAIL. Otherwise, the HW has a
-			 * tendency to ignore us rewinding the TAIL to the
-			 * end of an earlier request.
-			 */
-			last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {
@@ -1885,11 +1890,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				if (!execlists->timer.expires &&
-				    need_timeslice(engine, last))
-					set_timer_ms(&execlists->timer,
-						     timeslice(engine));
-
+				start_timeslice(engine);
 				return;
 			}
 		}
@@ -1924,7 +1925,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
-				return; /* leave this for another */
+				start_timeslice(engine);
+				return; /* leave this for another sibling */
 			}
 
 			ENGINE_TRACE(engine,
@@ -2100,7 +2102,7 @@ done:
 		 * Skip if we ended up with exactly the same set of requests,
 		 * e.g. trying to timeslice a pair of ordered contexts
 		 */
-		if (!memcmp(execlists->active, execlists->pending,
+		if (!memcmp(active, execlists->pending,
 			    (port - execlists->pending + 1) * sizeof(*port))) {
 			do
 				execlists_schedule_out(fetch_and_zero(port));
@@ -2111,7 +2113,7 @@ done:
 		clear_ports(port + 1, last_port - port);
 
 		execlists_submit_ports(engine);
-		set_preempt_timeout(engine);
+		set_preempt_timeout(engine, *active);
 	} else {
 skip_submit:
 		ring_set_paused(engine, 0);
@@ -2860,16 +2862,17 @@ static void execlists_context_unpin(struct intel_context *ce)
 
 static void
 __execlists_update_reg_state(const struct intel_context *ce,
-			     const struct intel_engine_cs *engine)
+			     const struct intel_engine_cs *engine,
+			     u32 head)
 {
 	struct intel_ring *ring = ce->ring;
 	u32 *regs = ce->lrc_reg_state;
 
-	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
 	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
-	regs[CTX_RING_HEAD] = ring->head;
+	regs[CTX_RING_HEAD] = head;
 	regs[CTX_RING_TAIL] = ring->tail;
 
 	/* RPCS */
@@ -2898,7 +2901,7 @@ __execlists_context_pin(struct intel_context *ce,
 
 	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, ce->ring->tail);
 
 	return 0;
 }
@@ -2939,7 +2942,7 @@ static void execlists_context_reset(struct intel_context *ce)
 	/* Scrub away the garbage */
 	execlists_init_reg_state(ce->lrc_reg_state,
 				 ce, ce->engine, ce->ring, true);
-	__execlists_update_reg_state(ce, ce->engine);
+	__execlists_update_reg_state(ce, ce->engine, ce->ring->tail);
 
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
@@ -3494,6 +3497,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct intel_context *ce;
 	struct i915_request *rq;
+	u32 head;
 
 	mb(); /* paranoia: read the CSB pointers from after the reset */
 	clflush(execlists->csb_write);
@@ -3521,15 +3525,15 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 
 	if (i915_request_completed(rq)) {
 		/* Idle context; tidy up the ring so we can restart afresh */
-		ce->ring->head = intel_ring_wrap(ce->ring, rq->tail);
+		head = intel_ring_wrap(ce->ring, rq->tail);
 		goto out_replay;
 	}
 
 	/* Context has requests still in-flight; it should not be idle! */
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
 	rq = active_request(ce->timeline, rq);
-	ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
-	GEM_BUG_ON(ce->ring->head == ce->ring->tail);
+	head = intel_ring_wrap(ce->ring, rq->head);
+	GEM_BUG_ON(head == ce->ring->tail);
 
 	/*
 	 * If this request hasn't started yet, e.g. it is waiting on a
@@ -3574,10 +3578,9 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 
 out_replay:
 	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
-		     ce->ring->head, ce->ring->tail);
-	intel_ring_update_space(ce->ring);
+		     head, ce->ring->tail);
 	__execlists_reset_reg_state(ce, engine);
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
 
 unwind:
@@ -3997,26 +4000,6 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
-
-		/*
-		 * Wa_1604544889:tgl
-		 */
-		if (IS_TGL_REVID(request->i915, TGL_REVID_A0, TGL_REVID_A0)) {
-			flags = 0;
-			flags |= PIPE_CONTROL_CS_STALL;
-			flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
-
-			flags |= PIPE_CONTROL_STORE_DATA_INDEX;
-			flags |= PIPE_CONTROL_QW_WRITE;
-
-			cs = intel_ring_begin(request, 6);
-			if (IS_ERR(cs))
-				return PTR_ERR(cs);
-
-			cs = gen8_emit_pipe_control(cs, flags,
-						    LRC_PPHWSP_SCRATCH_ADDR);
-			intel_ring_advance(request, cs);
-		}
 	}
 
 	return 0;
@@ -5220,10 +5203,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 		restore_default_state(ce, engine);
 
 	/* Rerun the request; its payload has been neutered (if guilty). */
-	ce->ring->head = head;
-	intel_ring_update_space(ce->ring);
-
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 }
 
 bool
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 374b28f13ca0..6ff803f397c4 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -145,6 +145,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 
 	kref_init(&ring->ref);
 	ring->size = size;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
 
 	/*
 	 * Workaround an erratum on the i830 which causes a hang if
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index ea2839d9e044..5bdce24994aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
 	return pos & (ring->size - 1);
 }
 
+static inline int intel_ring_direction(const struct intel_ring *ring,
+				       u32 next, u32 prev)
+{
+	typecheck(typeof(ring->size), next);
+	typecheck(typeof(ring->size), prev);
+	return (next - prev) << ring->wrap;
+}
+
 static inline bool
 intel_ring_offset_valid(const struct intel_ring *ring,
 			unsigned int pos)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h
index d9f17f38e0cc..1a189ea00fd8 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h
@@ -39,12 +39,13 @@ struct intel_ring {
 	 */
 	atomic_t pin_count;
 
-	u32 head;
-	u32 tail;
-	u32 emit;
+	u32 head; /* updated during retire, loosely tracks RING_HEAD */
+	u32 tail; /* updated on submission, used for RING_TAIL */
+	u32 emit; /* updated during request construction */
 
 	u32 space;
 	u32 size;
+	u32 wrap;
 	u32 effective_size;
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 87716529cd2f..d8d9f1179c2b 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl)
 
 static void cacheline_free(struct intel_timeline_cacheline *cl)
 {
+	if (!i915_active_acquire_if_busy(&cl->active)) {
+		__idle_cacheline_free(cl);
+		return;
+	}
+
 	GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE));
 	cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE);
 
-	if (i915_active_is_idle(&cl->active))
-		__idle_cacheline_free(cl);
+	i915_active_release(&cl->active);
 }
 
 int intel_timeline_init(struct intel_timeline *timeline,
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4e292d4bf7b9..6c2f8462e0f3 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -575,24 +575,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	u32 val;
-
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
-	/* Wa_1604555607:tgl */
-	val = intel_uncore_read(engine->uncore, FF_MODE2);
-	val &= ~FF_MODE2_TDS_TIMER_MASK;
-	val |= FF_MODE2_TDS_TIMER_128;
 	/*
-	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
-	 * enable verification of WA from the later steppings, which enables
-	 * the read of FF_MODE2.
+	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * FF_MODE2 register will return the wrong value when read. The default
+	 * value for this register is zero for all fields and there are no bit
+	 * masks. So instead of doing a RMW we should just write the TDS timer
+	 * value for Wa_1604555607.
 	 */
-	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
-	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
-			    FF_MODE2_TDS_TIMER_MASK);
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128, 0);
 }
 
 static void
@@ -1534,15 +1529,34 @@ err_obj:
 	return ERR_PTR(err);
 }
 
+static const struct {
+	u32 start;
+	u32 end;
+} mcr_ranges_gen8[] = {
+	{ .start = 0x5500, .end = 0x55ff },
+	{ .start = 0x7000, .end = 0x7fff },
+	{ .start = 0x9400, .end = 0x97ff },
+	{ .start = 0xb000, .end = 0xb3ff },
+	{ .start = 0xe000, .end = 0xe7ff },
+	{},
+};
+
 static bool mcr_range(struct drm_i915_private *i915, u32 offset)
 {
+	int i;
+
+	if (INTEL_GEN(i915) < 8)
+		return false;
+
 	/*
-	 * Registers in this range are affected by the MCR selector
+	 * Registers in these ranges are affected by the MCR selector
 	 * which only controls CPU initiated MMIO. Routing does not
 	 * work for CS access so we cannot verify them on this path.
 	 */
-	if (INTEL_GEN(i915) >= 8 && (offset >= 0xb000 && offset <= 0xb4ff))
-		return true;
+	for (i = 0; mcr_ranges_gen8[i].start; i++)
+		if (offset >= mcr_ranges_gen8[i].start &&
+		    offset <= mcr_ranges_gen8[i].end)
+			return true;
 
 	return false;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 65718ca2326e..b292f8cbd0bf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -186,7 +186,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		}
 		GEM_BUG_ON(!ce[1]->ring->size);
 		intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
-		__execlists_update_reg_state(ce[1], engine);
+		__execlists_update_reg_state(ce[1], engine, ce[1]->ring->head);
 
 		rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
 		if (IS_ERR(rq[0])) {
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e1c313da6c00..a62bdf9be682 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -457,7 +457,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	/* TODO: add more platforms support */
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+		IS_COFFEELAKE(dev_priv)) {
 		if (connected) {
 			vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
 				SFUSE_STRAP_DDID_DETECTED;
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2477a1e5a166..ae139f0877ae 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref)
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 867e7629025b..33569b910ed5 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v)
 	/* there's features depending on version! */
 	v->header.version = 155;
 	v->header.header_size = sizeof(v->header);
-	v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header);
+	v->header.vbt_size = sizeof(struct vbt);
 	v->header.bdb_offset = offsetof(struct vbt, bdb_header);
 
 	strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK");
 	v->bdb_header.version = 186; /* child_dev_size = 33 */
 	v->bdb_header.header_size = sizeof(v->bdb_header);
 
-	v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header)
-		- sizeof(struct bdb_header);
+	v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header);
 
 	/* general features */
 	v->general_features_header.id = BDB_GENERAL_FEATURES;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 85bd9bf4f6ee..345c2aa3b491 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
-	mutex_lock(&vgpu->vgpu_lock);
-
 	WARN(vgpu->active, "vGPU is still active!\n");
 
+	/*
+	 * remove idr first so later clean can judge if need to stop
+	 * service if no active vgpu.
+	 */
+	mutex_lock(&gvt->lock);
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	mutex_unlock(&gvt->lock);
+
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_gvt_debugfs_remove_vgpu(vgpu);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
@@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	mutex_unlock(&vgpu->vgpu_lock);
 
 	mutex_lock(&gvt->lock);
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
 	if (idr_is_empty(&gvt->vgpu_idr))
 		intel_gvt_clean_irq(gvt);
 	intel_gvt_update_vgpu_types(gvt);
@@ -560,9 +566,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f7385abdd74b..8410330ce4f0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -56,6 +56,7 @@
 #include "display/intel_hotplug.h"
 #include "display/intel_overlay.h"
 #include "display/intel_pipe_crc.h"
+#include "display/intel_psr.h"
 #include "display/intel_sprite.h"
 #include "display/intel_vga.h"
 
@@ -330,6 +331,8 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 
 	intel_init_ipc(i915);
 
+	intel_psr_set_force_mode_changed(i915->psr.dp);
+
 	return 0;
 
 cleanup_gem:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 077af22b8340..810e3ccd56ec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -505,7 +505,7 @@ struct i915_psr {
 	bool dc3co_enabled;
 	u32 dc3co_exit_delay;
 	struct delayed_work idle_work;
-	bool initially_probed;
+	bool force_mode_changed;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c2de2f45b459..5f6e63952821 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -180,7 +180,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	void *vaddr = obj->phys_handle->vaddr + args->offset;
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 
 	/*
@@ -844,10 +844,10 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		ret = i915_gem_gtt_pwrite_fast(obj, args);
 
 	if (ret == -EFAULT || ret == -ENOSPC) {
-		if (obj->phys_handle)
-			ret = i915_gem_phys_pwrite(obj, args, file);
-		else
+		if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(obj, args);
+		else
+			ret = i915_gem_phys_pwrite(obj, args, file);
 	}
 
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 594341e27a47..9e401a5fcae8 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1852,7 +1852,8 @@ void i915_error_state_store(struct i915_gpu_coredump *error)
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
 		pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
-		pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+		pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n");
+		pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n");
 		pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
 		pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n");
 		pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n",
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 83f01401b8b5..f631f6d21127 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -437,7 +437,7 @@ static const struct intel_device_info snb_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
-	.ppgtt_type = INTEL_PPGTT_FULL, \
+	.ppgtt_type = INTEL_PPGTT_ALIASING, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
@@ -494,7 +494,7 @@ static const struct intel_device_info vlv_info = {
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
-	.ppgtt_type = INTEL_PPGTT_FULL,
+	.ppgtt_type = INTEL_PPGTT_ALIASING,
 	.ppgtt_size = 31,
 	.has_snoop = true,
 	.has_coherent_ggtt = false,
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0f556d80ba36..3b6b913bd27a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1954,9 +1954,10 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static int emit_oa_config(struct i915_perf_stream *stream,
-			  struct i915_oa_config *oa_config,
-			  struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+	       struct i915_oa_config *oa_config,
+	       struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1964,7 +1965,7 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return ERR_CAST(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
@@ -1989,13 +1990,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
+	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;
+	return err ? ERR_PTR(err) : rq;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -2003,7 +2008,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2406,7 +2412,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
 }
 
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2448,7 +2455,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
@@ -2460,7 +2467,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2491,7 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2501,7 +2509,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	if (stream->ctx) {
 		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
@@ -2696,6 +2704,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 	.read = i915_oa_read,
 };
 
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+	struct i915_request *rq;
+
+	rq = stream->perf->ops.enable_metric_set(stream);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return 0;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2829,7 +2851,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
-	ret = perf->ops.enable_metric_set(stream);
+	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
@@ -3147,7 +3169,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		int err;
+		struct i915_request *rq;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3158,11 +3180,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, config, oa_context(stream));
-		if (err == 0)
+		rq = emit_oa_config(stream, config, oa_context(stream));
+		if (!IS_ERR(rq)) {
 			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+			i915_request_put(rq);
+		} else {
+			ret = PTR_ERR(rq);
+		}
 	}
 
 	i915_oa_config_put(config);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 45e581455f5d..a0e22f00f6cf 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -339,7 +339,8 @@ struct i915_oa_ops {
 	 * counter reports being sampled. May apply system constraints such as
 	 * disabling EU clock gating as required.
 	 */
-	int (*enable_metric_set)(struct i915_perf_stream *stream);
+	struct i915_request *
+		(*enable_metric_set)(struct i915_perf_stream *stream);
 
 	/**
 	 * @disable_metric_set: Remove system constraints associated with using
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index ec0299490dd4..aa729d04abe2 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -822,11 +822,6 @@ static ssize_t i915_pmu_event_show(struct device *dev,
 	return sprintf(buf, "config=0x%lx\n", eattr->val);
 }
 
-static struct attribute_group i915_pmu_events_attr_group = {
-	.name = "events",
-	/* Patch in attrs at runtime. */
-};
-
 static ssize_t
 i915_pmu_get_attr_cpumask(struct device *dev,
 			  struct device_attribute *attr,
@@ -846,13 +841,6 @@ static const struct attribute_group i915_pmu_cpumask_attr_group = {
 	.attrs = i915_cpumask_attrs,
 };
 
-static const struct attribute_group *i915_pmu_attr_groups[] = {
-	&i915_pmu_format_attr_group,
-	&i915_pmu_events_attr_group,
-	&i915_pmu_cpumask_attr_group,
-	NULL
-};
-
 #define __event(__config, __name, __unit) \
 { \
 	.config = (__config), \
@@ -1026,23 +1014,23 @@ err_alloc:
 
 static void free_event_attributes(struct i915_pmu *pmu)
 {
-	struct attribute **attr_iter = i915_pmu_events_attr_group.attrs;
+	struct attribute **attr_iter = pmu->events_attr_group.attrs;
 
 	for (; *attr_iter; attr_iter++)
 		kfree((*attr_iter)->name);
 
-	kfree(i915_pmu_events_attr_group.attrs);
+	kfree(pmu->events_attr_group.attrs);
 	kfree(pmu->i915_attr);
 	kfree(pmu->pmu_attr);
 
-	i915_pmu_events_attr_group.attrs = NULL;
+	pmu->events_attr_group.attrs = NULL;
 	pmu->i915_attr = NULL;
 	pmu->pmu_attr = NULL;
 }
 
 static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
 
 	GEM_BUG_ON(!pmu->base.event_init);
 
@@ -1055,7 +1043,7 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 {
-	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
 	unsigned int target;
 
 	GEM_BUG_ON(!pmu->base.event_init);
@@ -1072,8 +1060,6 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
-static enum cpuhp_state cpuhp_slot = CPUHP_INVALID;
-
 static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
 {
 	enum cpuhp_state slot;
@@ -1087,21 +1073,22 @@ static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
 		return ret;
 
 	slot = ret;
-	ret = cpuhp_state_add_instance(slot, &pmu->node);
+	ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node);
 	if (ret) {
 		cpuhp_remove_multi_state(slot);
 		return ret;
 	}
 
-	cpuhp_slot = slot;
+	pmu->cpuhp.slot = slot;
 	return 0;
 }
 
 static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu)
 {
-	WARN_ON(cpuhp_slot == CPUHP_INVALID);
-	WARN_ON(cpuhp_state_remove_instance(cpuhp_slot, &pmu->node));
-	cpuhp_remove_multi_state(cpuhp_slot);
+	WARN_ON(pmu->cpuhp.slot == CPUHP_INVALID);
+	WARN_ON(cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node));
+	cpuhp_remove_multi_state(pmu->cpuhp.slot);
+	pmu->cpuhp.slot = CPUHP_INVALID;
 }
 
 static bool is_igp(struct drm_i915_private *i915)
@@ -1118,6 +1105,13 @@ static bool is_igp(struct drm_i915_private *i915)
 void i915_pmu_register(struct drm_i915_private *i915)
 {
 	struct i915_pmu *pmu = &i915->pmu;
+	const struct attribute_group *attr_groups[] = {
+		&i915_pmu_format_attr_group,
+		&pmu->events_attr_group,
+		&i915_pmu_cpumask_attr_group,
+		NULL
+	};
+
 	int ret = -ENOMEM;
 
 	if (INTEL_GEN(i915) <= 2) {
@@ -1128,6 +1122,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	spin_lock_init(&pmu->lock);
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
+	pmu->cpuhp.slot = CPUHP_INVALID;
 
 	if (!is_igp(i915)) {
 		pmu->name = kasprintf(GFP_KERNEL,
@@ -1143,11 +1138,16 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	if (!pmu->name)
 		goto err;
 
-	i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
-	if (!i915_pmu_events_attr_group.attrs)
+	pmu->events_attr_group.name = "events";
+	pmu->events_attr_group.attrs = create_event_attributes(pmu);
+	if (!pmu->events_attr_group.attrs)
 		goto err_name;
 
-	pmu->base.attr_groups	= i915_pmu_attr_groups;
+	pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups),
+					GFP_KERNEL);
+	if (!pmu->base.attr_groups)
+		goto err_attr;
+
 	pmu->base.task_ctx_nr	= perf_invalid_context;
 	pmu->base.event_init	= i915_pmu_event_init;
 	pmu->base.add		= i915_pmu_event_add;
@@ -1159,7 +1159,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 	ret = perf_pmu_register(&pmu->base, pmu->name, -1);
 	if (ret)
-		goto err_attr;
+		goto err_groups;
 
 	ret = i915_pmu_register_cpuhp_state(pmu);
 	if (ret)
@@ -1169,6 +1169,8 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 err_unreg:
 	perf_pmu_unregister(&pmu->base);
+err_groups:
+	kfree(pmu->base.attr_groups);
 err_attr:
 	pmu->base.event_init = NULL;
 	free_event_attributes(pmu);
@@ -1194,6 +1196,7 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	perf_pmu_unregister(&pmu->base);
 	pmu->base.event_init = NULL;
+	kfree(pmu->base.attr_groups);
 	if (!is_igp(i915))
 		kfree(pmu->name);
 	free_event_attributes(pmu);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 6c1647c5daf2..f1d6cad0d7d5 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -39,9 +39,12 @@ struct i915_pmu_sample {
 
 struct i915_pmu {
 	/**
-	 * @node: List node for CPU hotplug handling.
+	 * @cpuhp: Struct used for CPU hotplug handling.
 	 */
-	struct hlist_node node;
+	struct {
+		struct hlist_node node;
+		enum cpuhp_state slot;
+	} cpuhp;
 	/**
 	 * @base: PMU base.
 	 */
@@ -105,6 +108,10 @@ struct i915_pmu {
 	 */
 	ktime_t sleep_last;
 	/**
+	 * @events_attr_group: Device events attribute group.
+	 */
+	struct attribute_group events_attr_group;
+	/**
 	 * @i915_attr: Memory block holding device attributes.
 	 */
 	void *i915_attr;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6cc55c103f67..3575fd30756b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7757,6 +7757,7 @@ enum {
 #define BW_BUDDY1_CTL			_MMIO(0x45140)
 #define BW_BUDDY2_CTL			_MMIO(0x45150)
 #define   BW_BUDDY_DISABLE		REG_BIT(31)
+#define   BW_BUDDY_TLB_REQ_TIMER_MASK	REG_GENMASK(21, 16)
 
 #define BW_BUDDY1_PAGE_MASK		_MMIO(0x45144)
 #define BW_BUDDY2_PAGE_MASK		_MMIO(0x45154)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 78a5f5d3c070..a18b2a244706 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -275,7 +275,7 @@ bool i915_request_retire(struct i915_request *rq)
 	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
-	list_del(&rq->link);
+	list_del_rcu(&rq->link);
 
 	intel_context_exit(rq->context);
 	intel_context_unpin(rq->context);
@@ -527,19 +527,31 @@ 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)
 {
-	struct i915_request *request =
-		container_of(fence, typeof(*request), semaphore);
+	struct i915_request *rq = container_of(fence, typeof(*rq), semaphore);
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
+		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:
-		i915_request_put(request);
+		i915_request_put(rq);
 		break;
 	}
 
@@ -595,6 +607,8 @@ static void __i915_request_ctor(void *arg)
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
+
 	rq->file_priv = NULL;
 	rq->capture_list = NULL;
 
@@ -653,25 +667,30 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 		}
 	}
 
-	ret = intel_timeline_get_seqno(tl, rq, &seqno);
-	if (ret)
-		goto err_free;
-
 	rq->i915 = ce->engine->i915;
 	rq->context = ce;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
+	kref_init(&rq->fence.refcount);
+	rq->fence.flags = 0;
+	rq->fence.error = 0;
+	INIT_LIST_HEAD(&rq->fence.cb_list);
+
+	ret = intel_timeline_get_seqno(tl, rq, &seqno);
+	if (ret)
+		goto err_free;
+
+	rq->fence.context = tl->fence_context;
+	rq->fence.seqno = seqno;
+
 	RCU_INIT_POINTER(rq->timeline, tl);
 	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
-		       tl->fence_context, seqno);
-
 	/* We bump the ref for the fence chain */
 	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
 	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
@@ -714,6 +733,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	intel_context_mark_active(ce);
+	list_add_tail_rcu(&rq->link, &tl->requests);
+
 	return rq;
 
 err_unwind:
@@ -767,16 +788,26 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	struct dma_fence *fence;
 	int err;
 
-	GEM_BUG_ON(i915_request_timeline(rq) ==
-		   rcu_access_pointer(signal->timeline));
+	if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline))
+		return 0;
+
+	if (i915_request_started(signal))
+		return 0;
 
 	fence = NULL;
 	rcu_read_lock();
 	spin_lock_irq(&signal->lock);
-	if (!i915_request_started(signal) &&
-	    !list_is_first(&signal->link,
-			   &rcu_dereference(signal->timeline)->requests)) {
-		struct i915_request *prev = list_prev_entry(signal, link);
+	do {
+		struct list_head *pos = READ_ONCE(signal->link.prev);
+		struct i915_request *prev;
+
+		/* Confirm signal has not been retired, the link is valid */
+		if (unlikely(i915_request_started(signal)))
+			break;
+
+		/* Is signal the earliest request on its timeline? */
+		if (pos == &rcu_dereference(signal->timeline)->requests)
+			break;
 
 		/*
 		 * Peek at the request before us in the timeline. That
@@ -784,20 +815,25 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		 * after acquiring a reference to it, confirm that it is
 		 * still part of the signaler's timeline.
 		 */
-		if (i915_request_get_rcu(prev)) {
-			if (list_next_entry(prev, link) == signal)
-				fence = &prev->fence;
-			else
-				i915_request_put(prev);
+		prev = list_entry(pos, typeof(*prev), link);
+		if (!i915_request_get_rcu(prev))
+			break;
+
+		/* After the strong barrier, confirm prev is still attached */
+		if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+			i915_request_put(prev);
+			break;
 		}
-	}
+
+		fence = &prev->fence;
+	} while (0);
 	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
 		return 0;
 
 	err = 0;
-	if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
+	if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
 		err = i915_sw_fence_await_dma_fence(&rq->submit,
 						    fence, 0,
 						    I915_FENCE_GFP);
@@ -1235,8 +1271,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
-	list_add_tail(&rq->link, &timeline->requests);
-
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before
@@ -1296,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq,
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	i915_sw_fence_commit(&rq->semaphore);
 	if (attr && rq->engine->schedule)
 		rq->engine->schedule(rq, attr);
+	i915_sw_fence_commit(&rq->semaphore);
 	i915_sw_fence_commit(&rq->submit);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index f57eadcf3583..fccc339949ec 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -26,6 +26,7 @@
 #define I915_REQUEST_H
 
 #include <linux/dma-fence.h>
+#include <linux/irq_work.h>
 #include <linux/lockdep.h>
 
 #include "gem/i915_gem_context_types.h"
@@ -208,6 +209,7 @@ 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.
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 5d96cfba40f8..34b654b4e58a 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -423,8 +423,6 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
 		dep->signaler = signal;
 		dep->waiter = node;
 		dep->flags = flags;
@@ -434,6 +432,10 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 		    !node_started(signal))
 			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
+		/* All set, now publish. Beware the lockless walkers. */
+		list_add(&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
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index c47261ae86ea..632d6953c78d 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -8,9 +8,8 @@
 #include "i915_drv.h"
 #include "i915_utils.h"
 
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
-		    "providing the dmesg log by booting with drm.debug=0xf"
+#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs"
+#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details."
 
 void
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index b0ade76bec90..d34141f7dcd8 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -234,6 +234,11 @@ static inline u64 ptr_to_u64(const void *ptr)
 	__idx;								\
 })
 
+static inline bool is_power_of_2_u64(u64 n)
+{
+	return (n != 0 && ((n & (n - 1)) == 0));
+}
+
 static inline void __list_del_many(struct list_head *head,
 				   struct list_head *first)
 {