Merge tag 'drm-intel-gt-next-2020-11-12-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Cross-subsystem Changes:
- DMA mapped scatterlist fixes in i915 to unblock merging of
  https://lkml.org/lkml/2020/9/27/70 (Tvrtko, Tom)

Driver Changes:

- Fix for user reported issue #2381 (Graphical output stops with "switching to inteldrmfb from simple"):
  Mark ininitial fb obj as WT on eLLC machines to avoid rcu lockup during fbdev init (Ville, Chris)
- Fix for Tigerlake (and earlier) to avoid spurious empty CSB events leading to hang (Chris, Bruce)
- Delay execlist processing for Tigerlake to avoid hang (Chris)
- Fix for Tigerlake RCS engine health check through heartbeat (Chris)
- Fix for Tigerlake reserved MOCS entries (Ayaz, Chris)
- Fix Media power gate sequence on Tigerlake (Rodrigo)
- Enable eLLC caching of display buffers for SKL+ (Ville)
- Support parsing of oversize batches on Gen9 (Matt, Chris)
- Exclude low pages (128KiB) of stolen from use to avoid thrashing during reset (Chris)
- Flush engines before Tigerlake breadcrumbs (Chris)

- Use the local HWSP offset during submission (Chris)
- Flush coherency domains on first set-domain-ioctl (Chris, Zbigniew)
- Use the active reference on the vma while capturing to avoid use-after-free (Chris)
- Fix MOCS PTE setting for gen9+ (Ville)
- Avoid NULL dereference on IPS driver callback while unbinding i915 (Chris)
- Avoid NULL dereference from PT/PD stash allocation error (Matt)
- Hold request reference for canceling an active context (Chris)
- Avoid infinite loop on x86-32 when mapping a lot of objects (Chris)
- Disallow WC mappings when processor doesn't support them (Chris)
- Return correct error in i915_gem_object_copy_blt() error path (Dan)
- Return correct error in intel_context_create_request() error path (Maarten)
- Tune down GuC communication enabled/disabled messages to debug (Jani)
- Fix rebased commit "Remove i915_request.lock requirement for execution callbacks" (Chris)
- Cancel outstanding work after disabling heartbeats on an engine (Chris)
- Signal cancelled requests (Chris)
- Retire cancelled requests on unload (Chris)
- Scrub HW state on driver remove (Chris)
- Undo forced context restores after trivial preemptions (Chris)
- Handle PCI unbind in PMU code (Tvrtko)
- Fix CPU hotplug with multiple GPUs in PMU code (Trtkko)
- Correctly set SFC capability for video engines (Venkata)

- Update GuC code to use firmware v49.0.1 (John, Matthew B., Daniele, Oscar, Michel, Rodrigo, Michal)
- Improve GuC warnings on loading failure (John)
- Avoid ownership race in buffer pool by clearing age (Chris)
- Use MMIO to read CSB in case of failure (Chris, Mika)
- Show engine properties in engine state dump to indicate changes (Chris, Joonas)
- Break up error capture compression loops with cond_resched() (Chris)
- Reduce GPU error capture mutex hold time to avoid khungtaskd (Chris)
- Serialise debugfs i915_gem_objects with ctx->mutex (Chris)
- Always test execution status on closing the context and close if not persistent (Chris)
- Avoid mixing integer types during batch copies (Chris, Jared)
- Skip over MI_NOOP when parsing to avoid overhead (Chris)
- Hold onto an explicit ref to i915_vma_work.pinned (Chris)
- Perform all asynchronous waits prior to marking payload start (Chris)
- Pull phys pread/pwrite implementations to the backend (Matt)

- Improve record of hung engines in error state (Tvrtko)
- Allow backends to override pread implementation (Matt)
- Reinforce LRC poisoning checks to confirm context survives execution (Chris)
- Fix memory region max size calculation (Matt)
- Fix order when adding blocks to memory region (Matt)
- Eliminate unused intel_virtual_engine_get_sibling func (Chris)
- Cleanup kasan warning for on-stack (unsigned long) casting (Chris)
- Onion unwind for scratch page allocation failure (Chris)
- Poison stolen pages before use (Chris)
- Selftest improvements (Chris)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201112163407.GA20320@jlahtine-mobl.ger.corp.intel.com

52 files changed, 1176 insertions, 406 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
index 272cf3ea68d5..44821d94544f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -202,12 +202,6 @@ retry:
 	if (unlikely(err))
 		goto out_request;
 
-	if (w->ce->engine->emit_init_breadcrumb) {
-		err = w->ce->engine->emit_init_breadcrumb(rq);
-		if (unlikely(err))
-			goto out_request;
-	}
-
 	/*
 	 * w->dma is already exported via (vma|obj)->resv we need only
 	 * keep track of the GPU activity within this vma/request, and
@@ -217,9 +211,15 @@ retry:
 	if (err)
 		goto out_request;
 
-	err = w->ce->engine->emit_bb_start(rq,
-					   batch->node.start, batch->node.size,
-					   0);
+	if (rq->engine->emit_init_breadcrumb) {
+		err = rq->engine->emit_init_breadcrumb(rq);
+		if (unlikely(err))
+			goto out_request;
+	}
+
+	err = rq->engine->emit_bb_start(rq,
+					batch->node.start, batch->node.size,
+					0);
 out_request:
 	if (unlikely(err)) {
 		i915_request_set_error_once(rq, err);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 3389ac972d16..00d24000b5e8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -82,6 +82,8 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 	obj->mm.madv = I915_MADV_WILLNEED;
 	INIT_RADIX_TREE(&obj->mm.get_page.radix, GFP_KERNEL | __GFP_NOWARN);
 	mutex_init(&obj->mm.get_page.lock);
+	INIT_RADIX_TREE(&obj->mm.get_dma_page.radix, GFP_KERNEL | __GFP_NOWARN);
+	mutex_init(&obj->mm.get_dma_page.lock);
 
 	if (IS_ENABLED(CONFIG_LOCKDEP) && i915_gem_object_is_shrinkable(obj))
 		i915_gem_shrinker_taints_mutex(to_i915(obj->base.dev),
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index eaf3d4147be0..be14486f63a7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -272,8 +272,26 @@ int i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 			       unsigned int tiling, unsigned int stride);
 
 struct scatterlist *
+__i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
+			 struct i915_gem_object_page_iter *iter,
+			 unsigned int n,
+			 unsigned int *offset);
+
+static inline struct scatterlist *
 i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
-		       unsigned int n, unsigned int *offset);
+		       unsigned int n,
+		       unsigned int *offset)
+{
+	return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset);
+}
+
+static inline struct scatterlist *
+i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj,
+			   unsigned int n,
+			   unsigned int *offset)
+{
+	return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset);
+}
 
 struct page *
 i915_gem_object_get_page(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index b5c15557cc87..e2d9b7e1e152 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops {
 	void (*truncate)(struct drm_i915_gem_object *obj);
 	void (*writeback)(struct drm_i915_gem_object *obj);
 
+	int (*pread)(struct drm_i915_gem_object *obj,
+		     const struct drm_i915_gem_pread *arg);
 	int (*pwrite)(struct drm_i915_gem_object *obj,
 		      const struct drm_i915_gem_pwrite *arg);
 
@@ -80,6 +82,14 @@ struct i915_mmap_offset {
 	struct rb_node offset;
 };
 
+struct i915_gem_object_page_iter {
+	struct scatterlist *sg_pos;
+	unsigned int sg_idx; /* in pages, but 32bit eek! */
+
+	struct radix_tree_root radix;
+	struct mutex lock; /* protects this cache */
+};
+
 struct drm_i915_gem_object {
 	struct drm_gem_object base;
 
@@ -246,13 +256,8 @@ struct drm_i915_gem_object {
 
 		I915_SELFTEST_DECLARE(unsigned int page_mask);
 
-		struct i915_gem_object_page_iter {
-			struct scatterlist *sg_pos;
-			unsigned int sg_idx; /* in pages, but 32bit eek! */
-
-			struct radix_tree_root radix;
-			struct mutex lock; /* protects this cache */
-		} get_page;
+		struct i915_gem_object_page_iter get_page;
+		struct i915_gem_object_page_iter get_dma_page;
 
 		/**
 		 * Element within i915->mm.unbound_list or i915->mm.bound_list,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index f60ca6dc911f..e2c7b2a7895f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -33,6 +33,8 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 
 	obj->mm.get_page.sg_pos = pages->sgl;
 	obj->mm.get_page.sg_idx = 0;
+	obj->mm.get_dma_page.sg_pos = pages->sgl;
+	obj->mm.get_dma_page.sg_idx = 0;
 
 	obj->mm.pages = pages;
 
@@ -155,6 +157,8 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 	rcu_read_lock();
 	radix_tree_for_each_slot(slot, &obj->mm.get_page.radix, &iter, 0)
 		radix_tree_delete(&obj->mm.get_page.radix, iter.index);
+	radix_tree_for_each_slot(slot, &obj->mm.get_dma_page.radix, &iter, 0)
+		radix_tree_delete(&obj->mm.get_dma_page.radix, iter.index);
 	rcu_read_unlock();
 }
 
@@ -438,11 +442,12 @@ void __i915_gem_object_release_map(struct drm_i915_gem_object *obj)
 }
 
 struct scatterlist *
-i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
-		       unsigned int n,
-		       unsigned int *offset)
+__i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
+			 struct i915_gem_object_page_iter *iter,
+			 unsigned int n,
+			 unsigned int *offset)
 {
-	struct i915_gem_object_page_iter *iter = &obj->mm.get_page;
+	const bool dma = iter == &obj->mm.get_dma_page;
 	struct scatterlist *sg;
 	unsigned int idx, count;
 
@@ -471,7 +476,7 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 
 	sg = iter->sg_pos;
 	idx = iter->sg_idx;
-	count = __sg_page_count(sg);
+	count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);
 
 	while (idx + count <= n) {
 		void *entry;
@@ -499,7 +504,7 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 
 		idx += count;
 		sg = ____sg_next(sg);
-		count = __sg_page_count(sg);
+		count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);
 	}
 
 scan:
@@ -517,7 +522,7 @@ scan:
 	while (idx + count <= n) {
 		idx += count;
 		sg = ____sg_next(sg);
-		count = __sg_page_count(sg);
+		count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);
 	}
 
 	*offset = n - idx;
@@ -584,7 +589,7 @@ i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 	struct scatterlist *sg;
 	unsigned int offset;
 
-	sg = i915_gem_object_get_sg(obj, n, &offset);
+	sg = i915_gem_object_get_sg_dma(obj, n, &offset);
 
 	if (len)
 		*len = sg_dma_len(sg) - (offset << PAGE_SHIFT);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 28147aab47b9..3a4dfe2ef1da 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -134,6 +134,58 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 			  vaddr, dma);
 }
 
+static int
+phys_pwrite(struct drm_i915_gem_object *obj,
+	    const struct drm_i915_gem_pwrite *args)
+{
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+	char __user *user_data = u64_to_user_ptr(args->data_ptr);
+	int err;
+
+	err = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE |
+				   I915_WAIT_ALL,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
+
+	/*
+	 * We manually control the domain here and pretend that it
+	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
+	 */
+	i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
+
+	if (copy_from_user(vaddr, user_data, args->size))
+		return -EFAULT;
+
+	drm_clflush_virt_range(vaddr, args->size);
+	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
+
+	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
+	return 0;
+}
+
+static int
+phys_pread(struct drm_i915_gem_object *obj,
+	   const struct drm_i915_gem_pread *args)
+{
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+	char __user *user_data = u64_to_user_ptr(args->data_ptr);
+	int err;
+
+	err = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
+
+	drm_clflush_virt_range(vaddr, args->size);
+	if (copy_to_user(user_data, vaddr, args->size))
+		return -EFAULT;
+
+	return 0;
+}
+
 static void phys_release(struct drm_i915_gem_object *obj)
 {
 	fput(obj->base.filp);
@@ -144,6 +196,9 @@ static const struct drm_i915_gem_object_ops i915_gem_phys_ops = {
 	.get_pages = i915_gem_object_get_pages_phys,
 	.put_pages = i915_gem_object_put_pages_phys,
 
+	.pread  = phys_pread,
+	.pwrite = phys_pwrite,
+
 	.release = phys_release,
 };
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 84b2707d8b17..29bffc6afcc1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -497,6 +497,43 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915)
 	return 0;
 }
 
+static void dbg_poison(struct i915_ggtt *ggtt,
+		       dma_addr_t addr, resource_size_t size,
+		       u8 x)
+{
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+	if (!drm_mm_node_allocated(&ggtt->error_capture))
+		return;
+
+	if (ggtt->vm.bind_async_flags & I915_VMA_GLOBAL_BIND)
+		return; /* beware stop_machine() inversion */
+
+	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
+
+	mutex_lock(&ggtt->error_mutex);
+	while (size) {
+		void __iomem *s;
+
+		ggtt->vm.insert_page(&ggtt->vm, addr,
+				     ggtt->error_capture.start,
+				     I915_CACHE_NONE, 0);
+		mb();
+
+		s = io_mapping_map_wc(&ggtt->iomap,
+				      ggtt->error_capture.start,
+				      PAGE_SIZE);
+		memset_io(s, x, PAGE_SIZE);
+		io_mapping_unmap(s);
+
+		addr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+	mb();
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE);
+	mutex_unlock(&ggtt->error_mutex);
+#endif
+}
+
 static struct sg_table *
 i915_pages_create_for_stolen(struct drm_device *dev,
 			     resource_size_t offset, resource_size_t size)
@@ -540,6 +577,11 @@ static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
+	dbg_poison(&to_i915(obj->base.dev)->ggtt,
+		   sg_dma_address(pages->sgl),
+		   sg_dma_len(pages->sgl),
+		   POISON_INUSE);
+
 	__i915_gem_object_set_pages(obj, pages, obj->stolen->size);
 
 	return 0;
@@ -549,6 +591,12 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj,
 					     struct sg_table *pages)
 {
 	/* Should only be called from i915_gem_object_release_stolen() */
+
+	dbg_poison(&to_i915(obj->base.dev)->ggtt,
+		   sg_dma_address(pages->sgl),
+		   sg_dma_len(pages->sgl),
+		   POISON_FREE);
+
 	sg_free_table(pages);
 	kfree(pages);
 }
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index c30adc05fa98..680bd9442eb0 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -131,17 +131,17 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
 	do {
-		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
+		GEM_BUG_ON(sg_dma_len(iter.sg) < I915_GTT_PAGE_SIZE);
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
 
 		iter.dma += I915_GTT_PAGE_SIZE;
 		if (iter.dma == iter.max) {
 			iter.sg = __sg_next(iter.sg);
-			if (!iter.sg)
+			if (!iter.sg || sg_dma_len(iter.sg) == 0)
 				break;
 
 			iter.dma = sg_dma_address(iter.sg);
-			iter.max = iter.dma + iter.sg->length;
+			iter.max = iter.dma + sg_dma_len(iter.sg);
 		}
 
 		if (++act_pte == GEN6_PTES) {
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 38c7069b7749..a37c968ef8f7 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -372,19 +372,19 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
-		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
+		GEM_BUG_ON(sg_dma_len(iter->sg) < I915_GTT_PAGE_SIZE);
 		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
 
 		iter->dma += I915_GTT_PAGE_SIZE;
 		if (iter->dma >= iter->max) {
 			iter->sg = __sg_next(iter->sg);
-			if (!iter->sg) {
+			if (!iter->sg || sg_dma_len(iter->sg) == 0) {
 				idx = 0;
 				break;
 			}
 
 			iter->dma = sg_dma_address(iter->sg);
-			iter->max = iter->dma + iter->sg->length;
+			iter->max = iter->dma + sg_dma_len(iter->sg);
 		}
 
 		if (gen8_pd_index(++idx, 0) == 0) {
@@ -413,8 +413,8 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				   u32 flags)
 {
 	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma->node.start;
-	dma_addr_t rem = iter->sg->length;
 
 	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
 
@@ -456,7 +456,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		}
 
 		do {
-			GEM_BUG_ON(iter->sg->length < page_size);
+			GEM_BUG_ON(sg_dma_len(iter->sg) < page_size);
 			vaddr[index++] = encode | iter->dma;
 
 			start += page_size;
@@ -467,7 +467,10 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				if (!iter->sg)
 					break;
 
-				rem = iter->sg->length;
+				rem = sg_dma_len(iter->sg);
+				if (!rem)
+					break;
+
 				iter->dma = sg_dma_address(iter->sg);
 				iter->max = iter->dma + rem;
 
@@ -525,7 +528,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		}
 
 		vma->page_sizes.gtt |= page_size;
-	} while (iter->sg);
+	} while (iter->sg && sg_dma_len(iter->sg));
 }
 
 static void gen8_ppgtt_insert(struct i915_address_space *vm,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5bfb5f7ed02c..0b31670343f5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -305,8 +305,9 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->i915 = i915;
 	engine->gt = gt;
 	engine->uncore = gt->uncore;
-	engine->hw_id = engine->guc_id = info->hw_id;
 	engine->mmio_base = __engine_mmio_base(i915, info->mmio_bases);
+	engine->hw_id = info->hw_id;
+	engine->guc_id = MAKE_GUC_ID(info->class, info->instance);
 
 	engine->class = info->class;
 	engine->instance = info->instance;
@@ -371,7 +372,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine)
 		 * instances.
 		 */
 		if ((INTEL_GEN(i915) >= 11 &&
-		     engine->gt->info.vdbox_sfc_access & engine->mask) ||
+		     (engine->gt->info.vdbox_sfc_access &
+		      BIT(engine->instance))) ||
 		    (INTEL_GEN(i915) >= 9 && engine->instance == 0))
 			engine->uabi_capabilities |=
 				I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
@@ -1599,6 +1601,41 @@ static unsigned long list_count(struct list_head *list)
 	return count;
 }
 
+static unsigned long read_ul(void *p, size_t x)
+{
+	return *(unsigned long *)(p + x);
+}
+
+static void print_properties(struct intel_engine_cs *engine,
+			     struct drm_printer *m)
+{
+	static const struct pmap {
+		size_t offset;
+		const char *name;
+	} props[] = {
+#define P(x) { \
+	.offset = offsetof(typeof(engine->props), x), \
+	.name = #x \
+}
+		P(heartbeat_interval_ms),
+		P(max_busywait_duration_ns),
+		P(preempt_timeout_ms),
+		P(stop_timeout_ms),
+		P(timeslice_duration_ms),
+
+		{},
+#undef P
+	};
+	const struct pmap *p;
+
+	drm_printf(m, "\tProperties:\n");
+	for (p = props; p->name; p++)
+		drm_printf(m, "\t\t%s: %lu [default %lu]\n",
+			   p->name,
+			   read_ul(&engine->props, p->offset),
+			   read_ul(&engine->defaults, p->offset));
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1641,6 +1678,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
 		   i915_reset_count(error));
+	print_properties(engine, m);
 
 	drm_printf(m, "\tRequests:\n");
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 5067d0524d4b..9060385cd69e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -41,6 +41,8 @@ static void idle_pulse(struct intel_engine_cs *engine, struct i915_request *rq)
 {
 	engine->wakeref_serial = READ_ONCE(engine->serial) + 1;
 	i915_request_add_active_barriers(rq);
+	if (!engine->heartbeat.systole && intel_engine_has_heartbeat(engine))
+		engine->heartbeat.systole = i915_request_get(rq);
 }
 
 static void show_heartbeat(const struct i915_request *rq,
@@ -144,8 +146,6 @@ static void heartbeat(struct work_struct *wrk)
 		goto unlock;
 
 	idle_pulse(engine, rq);
-	if (engine->i915->params.enable_hangcheck)
-		engine->heartbeat.systole = i915_request_get(rq);
 
 	__i915_request_commit(rq);
 	__i915_request_queue(rq, &attr);
@@ -153,7 +153,7 @@ static void heartbeat(struct work_struct *wrk)
 unlock:
 	mutex_unlock(&ce->timeline->mutex);
 out:
-	if (!next_heartbeat(engine))
+	if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine))
 		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
 	intel_engine_pm_put(engine);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index f7b2e07e2229..499b09cb4acf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -17,6 +17,25 @@
 #include "intel_ring.h"
 #include "shmem_utils.h"
 
+static void dbg_poison_ce(struct intel_context *ce)
+{
+	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		re