Merge tag 'drm-intel-gt-next-2022-02-17' of git://anongit.freedesktop.org/drm/drm-intel into drm-intel-next

UAPI Changes: - Weak parallel submission support for execlists Minimal implementation of the parallel submission support for execlists backend that was previously only implemented for GuC. Support one sibling non-virtual engine. Core Changes: - Two backmerges of drm/drm-next for header file renames/changes and i915_regs reorganization Driver Changes: - Add new DG2 subplatform: DG2-G12 (Matt R) - Add new DG2 workarounds (Matt R, Ram, Bruce) - Handle pre-programmed WOPCM registers for DG2+ (Daniele) - Update guc shim control programming on XeHP SDV+ (Daniele) - Add RPL-S C0/D0 stepping information (Anusha) - Improve GuC ADS initialization to work on ARM64 on dGFX (Lucas) - Fix KMD and GuC race on accessing PMU busyness (Umesh) - Use PM timestamp instead of RING TIMESTAMP for reference in PMU with GuC (Umesh) - Report error on invalid reset notification from GuC (John) - Avoid WARN splat by holding RPM wakelock during PXP unbind (Juston) - Fixes to parallel submission implementation (Matt B.) - Improve GuC loading status check/error reports (John) - Tweak TTM LRU priority hint selection (Matt A.) - Align the plane_vma to min_page_size of stolen mem (Ram) - Introduce vma resources and implement async unbinding (Thomas) - Use struct vma_resource instead of struct vma_snapshot (Thomas) - Return some TTM accel move errors instead of trying memcpy move (Thomas) - Fix a race between vma / object destruction and unbinding (Thomas) - Remove short-term pins from execbuf (Maarten) - Update to GuC version 69.0.3 (John, Michal Wa.) - Improvements to GT reset paths in GuC backend (Matt B.) - Use shrinker_release_pages instead of writeback in shmem object hooks (Matt A., Tvrtko) - Use trylock instead of blocking lock when freeing GEM objects (Maarten) - Allocate intel_engine_coredump_alloc with ALLOW_FAIL (Matt B.) - Fixes to object unmapping and purging (Matt A) - Check for wedged device in GuC backend (John) - Avoid lockdep splat by locking dpt_obj around set_cache_level (Maarten) - Allow dead vm to unbind vma's without lock (Maarten) - s/engine->i915/i915/ for DG2 engine workarounds (Matt R) - Use to_gt() helper for GGTT accesses (Michal Wi.) - Selftest improvements (Matt B., Thomas, Ram) - Coding style and compiler warning fixes (Matt B., Jasmine, Andi, Colin, Gustavo, Dan) From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/Yg4i2aCZvvee5Eai@jlahtine-mobl.ger.corp.intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> [Fixed conflicts while applying, using the fixups/drm-intel-gt-next.patch from drm-rerere's 1f2b1742abdd ("2022y-02m-23d-16h-07m-57s UTC: drm-tip rerere cache update")]
author: Rodrigo Vivi <rodrigo.vivi@intel.com> 2022-02-23 14:19:43 -0500
committer: Rodrigo Vivi <rodrigo.vivi@intel.com> 2022-02-23 15:03:51 -0500
commit: 30424ebae8df0f786835e7a31ad790fa00764f35 (patch)
tree: ef8d835947f4bb8bb608ae2841c34f0d6cb93030 /drivers/gpu/drm/i915/gt
parent: 6d8ebef53c2ccea482ed77769b7b5cbb453b7715 (diff)
parent: 154cfae6158141b18d65abb0db679bb51a8294e7 (diff)
37 files changed, 1071 insertions, 463 deletions
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index 0bd0d611e0c8..871fe7bda0e0 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -108,17 +108,17 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 }
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
-				      struct i915_vma *vma,
+				      struct i915_vma_resource *vma_res,
 				      enum i915_cache_level cache_level,
 				      u32 flags)
 {
 	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct i915_page_directory * const pd = ppgtt->pd;
-	unsigned int first_entry = vma->node.start / I915_GTT_PAGE_SIZE;
+	unsigned int first_entry = vma_res->start / I915_GTT_PAGE_SIZE;
 	unsigned int act_pt = first_entry / GEN6_PTES;
 	unsigned int act_pte = first_entry % GEN6_PTES;
 	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
-	struct sgt_dma iter = sgt_dma(vma);
+	struct sgt_dma iter = sgt_dma(vma_res);
 	gen6_pte_t *vaddr;
 
 	GEM_BUG_ON(!pd->entry[act_pt]);
@@ -144,7 +144,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 		}
 	} while (1);
 
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 }
 
 static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end)
@@ -275,13 +275,13 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 static void pd_vma_bind(struct i915_address_space *vm,
 			struct i915_vm_pt_stash *stash,
-			struct i915_vma *vma,
+			struct i915_vma_resource *vma_res,
 			enum i915_cache_level cache_level,
 			u32 unused)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	struct gen6_ppgtt *ppgtt = vma->private;
-	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
+	struct gen6_ppgtt *ppgtt = vma_res->private;
+	u32 ggtt_offset = vma_res->start / I915_GTT_PAGE_SIZE;
 
 	ppgtt->pp_dir = ggtt_offset * sizeof(gen6_pte_t) << 10;
 	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
@@ -289,9 +289,10 @@ static void pd_vma_bind(struct i915_address_space *vm,
 	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
 }
 
-static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
+static void pd_vma_unbind(struct i915_address_space *vm,
+			  struct i915_vma_resource *vma_res)
 {
-	struct gen6_ppgtt *ppgtt = vma->private;
+	struct gen6_ppgtt *ppgtt = vma_res->private;
 	struct i915_page_directory * const pd = ppgtt->base.pd;
 	struct i915_page_table *pt;
 	unsigned int pde;
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index b012c50f7ce7..c43e724afa9f 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -453,20 +453,21 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	return idx;
 }
 
-static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
+static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
+				   struct i915_vma_resource *vma_res,
 				   struct sgt_dma *iter,
 				   enum i915_cache_level cache_level,
 				   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;
+	u64 start = vma_res->start;
 
-	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
+	GEM_BUG_ON(!i915_vm_is_4lvl(vm));
 
 	do {
 		struct i915_page_directory * const pdp =
-			gen8_pdp_for_page_address(vma->vm, start);
+			gen8_pdp_for_page_address(vm, start);
 		struct i915_page_directory * const pd =
 			i915_pd_entry(pdp, __gen8_pte_index(start, 2));
 		gen8_pte_t encode = pte_encode;
@@ -475,7 +476,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		gen8_pte_t *vaddr;
 		u16 index;
 
-		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
+		if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
 		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
 		    rem >= I915_GTT_PAGE_SIZE_2M &&
 		    !__gen8_pte_index(start, 0)) {
@@ -492,7 +493,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			page_size = I915_GTT_PAGE_SIZE;
 
 			if (!index &&
-			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
+			    vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
 			    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
 			    (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
 			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
@@ -541,9 +542,9 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		 */
 		if (maybe_64K != -1 &&
 		    (index == I915_PDES ||
-		     (i915_vm_has_scratch_64K(vma->vm) &&
-		      !iter->sg && IS_ALIGNED(vma->node.start +
-					      vma->node.size,
+		     (i915_vm_has_scratch_64K(vm) &&
+		      !iter->sg && IS_ALIGNED(vma_res->start +
+					      vma_res->node_size,
 					      I915_GTT_PAGE_SIZE_2M)))) {
 			vaddr = px_vaddr(pd);
 			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
@@ -559,10 +560,10 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			 * instead - which we detect as missing results during
 			 * selftests.
 			 */
-			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
+			if (I915_SELFTEST_ONLY(vm->scrub_64K)) {
 				u16 i;
 
-				encode = vma->vm->scratch[0]->encode;
+				encode = vm->scratch[0]->encode;
 				vaddr = px_vaddr(i915_pt_entry(pd, maybe_64K));
 
 				for (i = 1; i < index; i += 16)
@@ -572,22 +573,22 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			}
 		}
 
-		vma->page_sizes.gtt |= page_size;
+		vma_res->page_sizes_gtt |= page_size;
 	} while (iter->sg && sg_dma_len(iter->sg));
 }
 
 static void gen8_ppgtt_insert(struct i915_address_space *vm,
-			      struct i915_vma *vma,
+			      struct i915_vma_resource *vma_res,
 			      enum i915_cache_level cache_level,
 			      u32 flags)
 {
 	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
-	struct sgt_dma iter = sgt_dma(vma);
+	struct sgt_dma iter = sgt_dma(vma_res);
 
-	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags);
+	if (vma_res->bi.page_sizes.sg > I915_GTT_PAGE_SIZE) {
+		gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
 	} else  {
-		u64 idx = vma->node.start >> GEN8_PTE_SHIFT;
+		u64 idx = vma_res->start >> GEN8_PTE_SHIFT;
 
 		do {
 			struct i915_page_directory * const pdp =
@@ -597,7 +598,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 						    cache_level, flags);
 		} while (idx);
 
-		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+		vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ba083d800a08..5d0ec7c49b6a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -79,7 +79,8 @@ static int intel_context_active_acquire(struct intel_context *ce)
 
 	__i915_active_acquire(&ce->active);
 
-	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine))
+	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine) ||
+	    intel_context_is_parallel(ce))
 		return 0;
 
 	/* Preallocate tracking nodes */
@@ -563,7 +564,6 @@ void intel_context_bind_parent_child(struct intel_context *parent,
 	 * Callers responsibility to validate that this function is used
 	 * correctly but we use GEM_BUG_ON here ensure that they do.
 	 */
-	GEM_BUG_ON(!intel_engine_uses_guc(parent->engine));
 	GEM_BUG_ON(intel_context_is_pinned(parent));
 	GEM_BUG_ON(intel_context_is_child(parent));
 	GEM_BUG_ON(intel_context_is_pinned(child));
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 959e9300ac9e..e53008b4dd05 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1700,18 +1700,15 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
 {
-	struct i915_vma_snapshot *vsnap = &rq->batch_snapshot;
+	struct i915_vma_resource *vma_res = rq->batch_res;
 	void *ring;
 	int size;
 
-	if (!i915_vma_snapshot_present(vsnap))
-		vsnap = NULL;
-
 	drm_printf(m,
 		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
 		   rq->head, rq->postfix, rq->tail,
-		   vsnap ? upper_32_bits(vsnap->gtt_offset) : ~0u,
-		   vsnap ? lower_32_bits(vsnap->gtt_offset) : ~0u);
+		   vma_res ? upper_32_bits(vma_res->start) : ~0u,
+		   vma_res ? lower_32_bits(vma_res->start) : ~0u);
 
 	size = rq->tail - rq->head;
 	if (rq->tail < rq->head)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 4a9ef688fac2..961d795220a3 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2601,6 +2601,43 @@ static void execlists_context_cancel_request(struct intel_context *ce,
 				      current->comm);
 }
 
+static struct intel_context *
+execlists_create_parallel(struct intel_engine_cs **engines,
+			  unsigned int num_siblings,
+			  unsigned int width)
+{
+	struct intel_context *parent = NULL, *ce, *err;
+	int i;
+
+	GEM_BUG_ON(num_siblings != 1);
+
+	for (i = 0; i < width; ++i) {
+		ce = intel_context_create(engines[i]);
+		if (IS_ERR(ce)) {
+			err = ce;
+			goto unwind;
+		}
+
+		if (i == 0)
+			parent = ce;
+		else
+			intel_context_bind_parent_child(parent, ce);
+	}
+
+	parent->parallel.fence_context = dma_fence_context_alloc(1);
+
+	intel_context_set_nopreempt(parent);
+	for_each_child(parent, ce)
+		intel_context_set_nopreempt(ce);
+
+	return parent;
+
+unwind:
+	if (parent)
+		intel_context_put(parent);
+	return err;
+}
+
 static const struct intel_context_ops execlists_context_ops = {
 	.flags = COPS_HAS_INFLIGHT,
 
@@ -2619,6 +2656,7 @@ static const struct intel_context_ops execlists_context_ops = {
 	.reset = lrc_reset,
 	.destroy = lrc_destroy,
 
+	.create_parallel = execlists_create_parallel,
 	.create_virtual = execlists_create_virtual,
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index d2922f64d1c8..8850d4e0f9cc 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -87,7 +87,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915)
 	 * beyond the end of the batch buffer, across the page boundary,
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
-	ret = ggtt_init_hw(&i915->ggtt);
+	ret = ggtt_init_hw(to_gt(i915)->ggtt);
 	if (ret)
 		return ret;
 
@@ -130,22 +130,51 @@ void i915_ggtt_suspend_vm(struct i915_address_space *vm)
 
 	drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
 
+retry:
+	i915_gem_drain_freed_objects(vm->i915);
+
 	mutex_lock(&vm->mutex);
 
 	/* Skip rewriting PTE on VMA unbind. */
 	open = atomic_xchg(&vm->open, 0);
 
 	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
 		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-		i915_vma_wait_for_bind(vma);
 
-		if (i915_vma_is_pinned(vma))
+		if (i915_vma_is_pinned(vma) || !i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
 			continue;
 
+		/* unlikely to race when GPU is idle, so no worry about slowpath.. */
+		if (WARN_ON(!i915_gem_object_trylock(obj, NULL))) {
+			/*
+			 * No dead objects should appear here, GPU should be
+			 * completely idle, and userspace suspended
+			 */
+			i915_gem_object_get(obj);
+
+			atomic_set(&vm->open, open);
+			mutex_unlock(&vm->mutex);
+
+			i915_gem_object_lock(obj, NULL);
+			open = i915_vma_unbind(vma);
+			i915_gem_object_unlock(obj);
+
+			GEM_WARN_ON(open);
+
+			i915_gem_object_put(obj);
+			goto retry;
+		}
+
 		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
-			__i915_vma_evict(vma);
+			i915_vma_wait_for_bind(vma);
+
+			__i915_vma_evict(vma, false);
 			drm_mm_remove_node(&vma->node);
 		}
+
+		i915_gem_object_unlock(obj);
 	}
 
 	vm->clear_range(vm, 0, vm->total);
@@ -236,7 +265,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 }
 
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
+				     struct i915_vma_resource *vma_res,
 				     enum i915_cache_level level,
 				     u32 flags)
 {
@@ -253,10 +282,10 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 
 	gte = (gen8_pte_t __iomem *)ggtt->gsm;
-	gte += vma->node.start / I915_GTT_PAGE_SIZE;
-	end = gte + vma->node.size / I915_GTT_PAGE_SIZE;
+	gte += vma_res->start / I915_GTT_PAGE_SIZE;
+	end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
 
-	for_each_sgt_daddr(addr, iter, vma->pages)
+	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
 		gen8_set_pte(gte++, pte_encode | addr);
 	GEM_BUG_ON(gte > end);
 
@@ -293,7 +322,7 @@ static void gen6_ggtt_insert_page(struct i915_address_space *vm,
  * through the GMADR mapped BAR (i915->mm.gtt->gtt).
  */
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
+				     struct i915_vma_resource *vma_res,
 				     enum i915_cache_level level,
 				     u32 flags)
 {
@@ -304,10 +333,10 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	dma_addr_t addr;
 
 	gte = (gen6_pte_t __iomem *)ggtt->gsm;
-	gte += vma->node.start / I915_GTT_PAGE_SIZE;
-	end = gte + vma->node.size / I915_GTT_PAGE_SIZE;
+	gte += vma_res->start / I915_GTT_PAGE_SIZE;
+	end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
 
-	for_each_sgt_daddr(addr, iter, vma->pages)
+	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
 		iowrite32(vm->pte_encode(addr, level, flags), gte++);
 	GEM_BUG_ON(gte > end);
 
@@ -390,7 +419,7 @@ static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
 
 struct insert_entries {
 	struct i915_address_space *vm;
-	struct i915_vma *vma;
+	struct i915_vma_resource *vma_res;
 	enum i915_cache_level level;
 	u32 flags;
 };
@@ -399,18 +428,18 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 {
 	struct insert_entries *arg = _arg;
 
-	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma_res, arg->level, arg->flags);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
 }
 
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
-					     struct i915_vma *vma,
+					     struct i915_vma_resource *vma_res,
 					     enum i915_cache_level level,
 					     u32 flags)
 {
-	struct insert_entries arg = { vm, vma, level, flags };
+	struct insert_entries arg = { vm, vma_res, level, flags };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -449,14 +478,14 @@ static void i915_ggtt_insert_page(struct i915_address_space *vm,
 }
 
 static void i915_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
+				     struct i915_vma_resource *vma_res,
 				     enum i915_cache_level cache_level,
 				     u32 unused)
 {
 	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
 		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
 
-	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
+	intel_gtt_insert_sg_entries(vma_res->bi.pages, vma_res->start >> PAGE_SHIFT,
 				    flags);
 }
 
@@ -468,30 +497,32 @@ static void i915_ggtt_clear_range(struct i915_address_space *vm,
 
 static void ggtt_bind_vma(struct i915_address_space *vm,
 			  struct i915_vm_pt_stash *stash,
-			  struct i915_vma *vma,
+			  struct i915_vma_resource *vma_res,
 			  enum i915_cache_level cache_level,
 			  u32 flags)
 {
-	struct drm_i915_gem_object *obj = vma->obj;
 	u32 pte_flags;
 
-	if (i915_vma_is_bound(vma, ~flags & I915_VMA_BIND_MASK))
+	if (vma_res->bound_flags & (~flags & I915_VMA_BIND_MASK))
 		return;
 
+	vma_res->bound_flags |= flags;
+
 	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
-	if (i915_gem_object_is_readonly(obj))
+	if (vma_res->bi.readonly)
 		pte_flags |= PTE_READ_ONLY;
-	if (i915_gem_object_is_lmem(obj))
+	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma, cache_level, pte_flags);
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 }
 
-static void ggtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
+static void ggtt_unbind_vma(struct i915_address_space *vm,
+			    struct i915_vma_resource *vma_res)
 {
-	vm->clear_range(vm, vma->node.start, vma->size);
+	vm->clear_range(vm, vma_res->start, vma_res->vma_size);
 }
 
 static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
@@ -505,7 +536,7 @@ static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
 	GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
 	size = ggtt->vm.total - GUC_GGTT_TOP;
 
-	ret = i915_gem_gtt_reserve(&ggtt->vm, &ggtt->uc_fw, size,
+	ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, size,
 				   GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
 				   PIN_NOEVICT);
 	if (ret)
@@ -624,7 +655,7 @@ err:
 
 static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
 				  struct i915_vm_pt_stash *stash,
-				  struct i915_vma *vma,
+				  struct i915_vma_resource *vma_res,
 				  enum i915_cache_level cache_level,
 				  u32 flags)
 {
@@ -632,25 +663,27 @@ static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
+	if (vma_res->bi.readonly)
 		pte_flags |= PTE_READ_ONLY;
 
 	if (flags & I915_VMA_LOCAL_BIND)
 		ppgtt_bind_vma(&i915_vm_to_ggtt(vm)->alias->vm,
-			       stash, vma, cache_level, flags);
+			       stash, vma_res, cache_level, flags);
 
 	if (flags & I915_VMA_GLOBAL_BIND)
-		vm->insert_entries(vm, vma, cache_level, pte_flags);
+		vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+
+	vma_res->bound_flags |= flags;
 }
 
 static void aliasing_gtt_unbind_vma(struct i915_address_space *vm,
-				    struct i915_vma *vma)
+				    struct i915_vma_resource *vma_res)
 {
-	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
-		vm->clear_range(vm, vma->node.start, vma->size);
+	if (vma_res->bound_flags & I915_VMA_GLOBAL_BIND)
+		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
 
-	if (i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND))
-		ppgtt_unbind_vma(&i915_vm_to_ggtt(vm)->alias->vm, vma);
+	if (vma_res->bound_flags & I915_VMA_LOCAL_BIND)
+		ppgtt_unbind_vma(&i915_vm_to_ggtt(vm)->alias->vm, vma_res);
 }
 
 static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
@@ -723,14 +756,14 @@ int i915_init_ggtt(struct drm_i915_private *i915)
 {
 	int ret;
 
-	ret = init_ggtt(&i915->ggtt);
+	ret = init_ggtt(to_gt(i915)->ggtt);
 	if (ret)
 		return ret;
 
 	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
-		ret = init_aliasing_ppgtt(&i915->ggtt);
+		ret = init_aliasing_ppgtt(to_gt(i915)->ggtt);
 		if (ret)
-			cleanup_init_ggtt(&i915->ggtt);
+			cleanup_init_ggtt(to_gt(i915)->ggtt);
 	}
 
 	return 0;
@@ -743,11 +776,21 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 	atomic_set(&ggtt->vm.open, 0);
 
 	flush_workqueue(ggtt->vm.i915->wq);
+	i915_gem_drain_freed_objects(ggtt->vm.i915);
 
 	mutex_lock(&ggtt->vm.mutex);
 
-	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+		bool trylock;
+
+		trylock = i915_gem_object_trylock(obj, NULL);
+		WARN_ON(!trylock);
+
 		WARN_ON(__i915_vma_unbind(vma));
+		if (trylock)
+			i915_gem_object_unlock(obj);
+	}
 
 	if (drm_mm_node_allocated(&ggtt->error_capture))
 		drm_mm_remove_node(&ggtt->error_capture);
@@ -773,7 +816,7 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
  */
 void i915_ggtt_driver_release(struct drm_i915_private *i915)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
 
 	fini_aliasing_ppgtt(ggtt);
 
@@ -788,7 +831,7 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915)
  */
 void i915_ggtt_driver_late_release(struct drm_i915_private *i915)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
 
 	GEM_WARN_ON(kref_read(&ggtt->vm.resv_ref) != 1);
 	dma_resv_fini(&ggtt->vm._resv);
@@ -1209,7 +1252,7 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915)
 {
 	int ret;
 
-	ret = ggtt_probe_hw(&i915->ggtt, to_gt(i915));
+	ret = ggtt_probe_hw(to_gt(i915)->ggtt, to_gt(i915));
 	if (ret)
 		return ret;
 
@@ -1281,7 +1324,7 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 			atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
 
 		GEM_BUG_ON(!was_bound);
-		vma->ops->bind_vma(vm, NULL, vma,
+		vma->ops->bind_vma(vm, NULL, vma->resource,
 				   obj ? obj->cache_level : 0,
 				   was_bound);
 		if (obj) { /* only used during resume => exclusive access */
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index f294753bc947..76880fb8fc19 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -428,7 +428,6 @@ int i915_vma_pin_fence(struct i915_vma *vma)
 	 * must keep the device awake whilst using the fence.
 	 */
 	assert_rpm_wakelock_held(vma->vm->gt->uncore->rpm);
-	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 
 	err = mutex_lock_interruptible(&vma->vm->mutex);
@@ -731,8 +730,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt)
 		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
 	}
 
-	i915->ggtt.bit_6_swizzle_x = swizzle_x;
-	i915->ggtt.bit_6_swizzle_y = swizzle_y;
+	to_gt(i915)->ggtt->bit_6_swizzle_x = swizzle_x;
+	to_gt(i915)->ggtt->bit_6_swizzle_y = swizzle_y;
 }
 
 /*
@@ -899,7 +898,7 @@ void intel_gt_init_swizzling(struct intel_gt *gt)
 	struct intel_uncore *uncore = gt->uncore;
 
 	if (GRAPHICS_VER(i915) < 5 ||
-	    i915->ggtt.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
+	    to_gt(i915)->ggtt->bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
 		return;
 
 	intel_uncore_rmw(uncore, DISP_ARB_CTL, 0, DISP_TILE_SURFACE_SWIZZLING);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 545a2b1f1834..e8403fa53909 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -3,6 +3,7 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <drm/drm_managed.h>
 #include <drm/intel-gtt.h>
 
 #include "gem/i915_gem_internal.h"
@@ -90,9 +91,11 @@ int intel_gt_probe_lmem(struct intel_gt *gt)
 	return 0;
 }
 
-void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
+int intel_gt_assign_ggtt(struct intel_gt *gt)
 {
-	gt->ggtt = ggtt;
+	gt->ggtt = drmm_kzalloc(&gt->i915->drm, sizeof(*gt->ggtt), GFP_KERNEL);
+
+	return gt->ggtt ? 0 : -ENOMEM;
 }
 
 static const struct intel_mmio_range icl_l3bank_steering_table[] = {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index a913fb6ffec3..2dad46c3eff2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -36,7 +36,7 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc)
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
 void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
-void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt);
+int intel_gt_assign_ggtt(struct intel_gt *gt);
 int intel_gt_probe_lmem(struct intel_gt *gt);
 int intel_gt_init_mmio(struct intel_gt *gt);
 int __must_check intel_gt_init_hw(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index e8143fa4b5a8..18d158d77aba 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -322,6 +322,9 @@
 
 #define GEN12_PAT_INDEX(index)			_MMIO(0x4800 + (index) * 4)
 
+#define XEHPSDV_FLAT_CCS_BASE_ADDR		_MMIO(0x4910)
+#define   XEHPSDV_CCS_BASE_SHIFT		8
+
 #define GAMTARBMODE				_MMIO(0x4a08)
 #define   ARB_MODE_BWGTLB_DISABLE		(1 << 9)
 #define   ARB_MODE_SWIZZLE_BDW			(1 << 1)
@@ -1042,6 +1045,7 @@
 
 #define GEN9_ROW_CHICKEN4			_MMIO(0xe48c)
 #define   GEN12_DISABLE_GRF_CLEAR		REG_BIT(13)
+#define   XEHP_DIS_BBL_SYSPIPE			REG_BIT(11)
 #define   GEN12_DISABLE_TDL_PUSH		REG_BIT(9)
 #define   GEN11_DIS_PICK_2ND_EU			REG_BIT(7)
 #define   GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX	REG_BIT(4)
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 8506db9983da..49a8fb63e6e5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -163,6 +163,9 @@ static void __i915_vm_release(struct work_struct *work)
 	struct i915_address_space *vm =
 		container_of(work, struct i915_address_space, release_work);
 
+	/* Synchronize async unbinds. */
+	i915_vma_resource_bind_dep_sync_all(vm);
+
 	vm->cleanup(vm);
 	i915_address_space_fini(vm);
 
@@ -191,6 +194,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 	if (!kref_read(&vm->resv_ref))
 		kref_init(&vm->resv_ref);
 
+	vm->pending_unbind = RB_ROOT_CACHED;
 	INIT_WORK(&vm->release_work, __i915_vm_release);
 	atomic_set(&vm->open, 1);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 177b42b935a1..8073438b67c8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -27,6 +27,7 @@
 
 #include "gt/intel_reset.h"
 #include "i915_selftest.h"
+#include "i915_vma_resource.h"
 #include "i915_vma_types.h"
 
 #define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
@@ -200,7 +201,7 @@ struct i915_vma_ops {
 	/* Map an object into an address space with the given cache flags. */
 	void (*bind_vma)(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
-			 struct i915_vma *vma,
+			 struct i915_vma_resource *vma_res,
 			 enum i915_cache_level cache_level,
 			 u32 flags);
 	/*
@@ -208,7 +209,8 @@ struct i915_vma_ops {
 	 * setting the valid PTE entries to a reserved scratch page.
 	 */
 	void (*unbind_vma)(struct i915_address_space *vm,
-			   struct i915_vma *vma);
+			   struct i915_vma_resource *vma_res);
+
 };
 
 struct i915_address_space {
@@ -263,6 +265,9 @@ struct i915_address_space {
 	/* Flags used when creating page-table objects for this vm */
 	unsigned long lmem_pt_obj_flags;
 
+	/* Interval tree for pending unbind vma resources */
+	struct rb_root_cached pending_unbind;
+
 	struct drm_i915_gem_object *
 		(*alloc_pt_dma)(struct i915_address_space *vm, int sz);
 	struct drm_i915_gem_object *
@@ -285,7 +290,7 @@ struct i915_address_space {
 			    enum i915_cache_level cache_level,
 			    u32 flags);
 	void (*insert_entries)(struct i915_address_space *vm,
-			       struct i915_vma *vma,
+			       struct i915_vma_resource *vma_res,
 			       enum i915_cache_level cache_level,
 			       u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
@@ -600,11 +605,11 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
 
 void ppgtt_bind_vma(struct i915_address_space *vm,
 		    struct i915_vm_pt_stash *stash,
-		    struct i915_vma *vma,
+		    struct i915_vma_resource *vma_res,
 		    enum i915_cache_level cache_level,
 		    u32 flags);
 void ppgtt_unbind_vma(struct i915_address_space *vm,
-		      struct i915_vma *vma);
+		      struct i915_vma_resource *vma_res);
 
 void gtt_write_workarounds(struct intel_gt *gt);
 
@@ -627,8 +632,8 @@ __vm_create_scratch_for_read_pinned(struct i915_address_space *vm, unsigned long
 static inline struct sgt_dma {
 	struct scatterlist *sg;
 	dma_addr_t dma, max;
-} sgt_dma(struct i915_vma *vma) {
-	struct scatterlist *sg = vma->pages->sgl;
+} sgt_dma(struct i915_vma_resource *vma_res) {
+	struct scatterlist *sg = vma_res->bi.pages->sgl;
 	dma_addr_t addr = sg_dma_address(sg);
 
 	return (struct sgt_dma){ sg, addr, addr + sg_dma_len(sg) };
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 91c87a3a8e0b..004e1216e654 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1069,6 +1069,10 @@ lrc_pin(struct intel_context *ce,
 
 void lrc_unpin(struct intel_context *ce)
 {
+	if (unlikely(ce->parallel.last_rq)) {
+		i915_request_put(ce->parallel.last_rq);
+		ce->parallel.last_rq = NULL;
+	}
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
 		      ce->engine);
 }
@@ -1164,6 +1168,29 @@ gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs)
 	return cs;
 }
 
+/*
+ * On DG2 during context restore of a preempted context in GPGPU mode,
+ * RCS restore hang is detected. This is extremely timing dependent.
+ * To address this below sw wabb is implemented for DG2 A steppings.
+ */
+static u32 *
+dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG);
+	*cs++ = 0x21;
+
+	*cs++ = MI_LOAD_REGISTER_REG;
+	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
+	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT1);
+
+	*cs++ = MI_LOAD_REGISTER_REG;
+	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
+	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT2);
+
+	return cs;
+}
+
 static u32 *
 gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 {
@@ -1171,6 +1198,11 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 	cs = gen12_emit_cmd_buf_wa(ce, cs);
 	cs = gen12_emit_restore_scratch(ce, cs);
 
+	/* Wa_22011450934:dg2 */
+	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_A0, STEP_B0) ||
+	    IS_DG2_GRAPHICS_STEP(ce->engine->i915, G11, STEP_A0, STEP_B0))
+		cs = dg2_emit_rcs_hang_wabb(ce, cs);
+
 	/* Wa_16013000631:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) ||
 	    IS_DG2_G11(ce->engine->i915))
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index 083b3090c69c..48e6e2f87700 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -179,32 +179,34 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt,
 
 void ppgtt_bind_vma(struct i915_address_space *vm,
 		    struct i915_vm_pt_stash *stash,
-		    struct i915_vma *vma,
+		    struct i915_vma_resource *vma_res,
 		    enum i915_cache_level cache_level,
 		    u32 flags)
 {
 	u32 pte_flags;
 
-	if (!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
-		vm->allocate_va_range(vm, stash, vma->node.start, vma->size);
-		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
+	if (!vma_res->allocated) {
+		vm->allocate_va_range(vm, stash, vma_res->start,
+				      vma_res->vma_size);
+		vma_res->allocated = true;
 	}
 
 	/* Applicable to VLV, and gen8+ */
 	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
+	if (vma_res->bi.readonly)
 		pte_flags |= PTE_READ_ONLY;
-	if (i915_gem_object_is_lmem(vma->obj))
+	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma, cache_level, pte_flags);
+	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
 	wmb();
 }
 
-void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
+void ppgtt_unbind_vma(struct i915_address_space *vm,
+		      struct i915_vma_resource *vma_res)
 {
-	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
-		vm->clear_range(vm, vma->node.start, vma->size);
+	if (vma_res->allocated)
+		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
 }
 
 static unsigned long pd_count(u64 size, int shift)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index cb5a67c98f30..a04e0cf4a94b 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -12,11 +12,12 @@
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_ttm.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_regs.h"
 
 static int init_fake_lmem_bar(struct intel_memory_region *mem)
 {
 	struct drm_i915_private *i915 = mem->i915;
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
 	unsigned long n;
 	int ret;
 
@@ -132,7 +133,7 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt)
 	if (!i915->params.fake_lmem_start)
 		return ERR_PTR(-ENODEV);
 
-	GEM_BUG_ON(i915_ggtt_has_aperture(&i915->ggtt));
+	GEM_BUG_ON(i915_ggtt_has_aperture(to_gt(i915)->ggtt));
 
 	/* Your mappable aperture belongs to me now! */
 	mappable_end = pci_resource_len(pdev, 2);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ae7542f70afb..82713264b96c 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -604,6 +604,15 @@ static int gen8_reset_engines(struct intel_gt *gt,
 		 */
 	}
 
+	/*
+	 * Wa_22011100796:dg2, whenever Full soft reset is required,
+	 * reset all individual engines firstly, and then do a full soft reset.
+	 *
+	 * This is best effort, so ignore any error from the initial reset.
+	 */
+	if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES)
+		gen11_reset_engines(gt, gt->info.engine_mask, 0);
+
 	if (GRAPHICS_VER(gt->i915) >= 11)
 		ret = gen11_reset_engines(gt, engine_mask, retry);
 	else
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index eeda1692d845..26038066e90b 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1510,6 +1510,12 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	 */
 	wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
 	wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS);
+
+	/* Wa_18018781329:dg2 */
+	wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB);
 }
 
 static void
@@ -2040,7 +2046,12 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) {
+	if (IS_DG2(i915)) {
+		/* Wa_14015227452:dg2 */
+		wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE);
+	}
+
+	if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14013392000:dg2_g11 */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE);
 
@@ -2048,15 +2059,15 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) ||
-	    IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) ||
+	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14012419201:dg2 */
 		wa_masked_en(wal, GEN9_ROW_CHICKEN4,
 			     GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) ||
-	    IS_DG2_G11(engine->i915)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
+	    IS_DG2_G11(i915)) {
 		/*
 		 * Wa_22012826095:dg2
 		 * Wa_22013059131:dg2
@@ -2071,14 +2082,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}
 
 	/* Wa_1308578152:dg2_g10 when first gslice is fused off */
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) &&
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) &&
 	    needs_wa_1308578152(engine)) {
 		wa_masked_dis(wal, GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON,
 			      GEN12_REPLAY_MODE_GRANULARITY);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) ||
-	    IS_DG2_G11(engine->i915)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) ||
+	    IS_DG2_G11(i915) || IS_DG2_G12(i915)) {
 		/* Wa_22013037850:dg2 */
 		wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW,
 			    DISABLE_128B_EVICTION_COMMAND_UDW);
@@ -2095,7 +2106,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			      LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) {
 		/*
 		 * Wa_1608949956:dg2_g10
 		 * Wa_14010198302:dg2_g10
@@ -2114,7 +2125,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		       0, false);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) {
 		/* Wa_22010430635:dg2 */
 		wa_masked_en(wal,
 			     GEN9_ROW_CHICKEN4,
@@ -2124,8 +2135,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) ||
-	    IS_DG2_G11(engine->i915)) {
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_C0) ||
+	    IS_DG2_G11(i915)) {
 		/* Wa_22012654132:dg2 */
 		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
 		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
@@ -2134,8 +2145,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}
 
 	/* Wa_14013202645:dg2 */
-	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) ||
-	    IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0))
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
+	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0))
 		wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY);
 
 	if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 9e9ccb139ba7..83ff4c2e57c5 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1384,7 +1384,7 @@ static int evict_vma(void *data)
 	complete(&arg->completion);
 
 	mutex_lock(&vm->mutex);
-	err = i915_gem_evict_for_node(vm, &evict, 0);
+	err = i915_gem_evict_for_node(vm, NULL, &evict, 0);
 	mutex_unlock(&vm->mutex);
 
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 8a873f6bda7f..37c38bdd5f47 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -19,7 +19,7 @@ __igt_reset_stolen(struct intel_gt *gt,
 		   intel_engine_mask_t mask,
 		   const char *msg)
 {
-	struct i915_ggtt *ggtt = &gt->i915->ggtt;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	const struct resource *dsm = &gt->i915->dsm;
 	resource_size_t num_pages, page;
 	struct intel_engine_cs *engine;
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
index fe5d7d261797..7afdadc7656f 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
@@ -7,9 +7,9 @@
 #define _ABI_GUC_ACTIONS_ABI_H
 
 /**
- * DOC: HOST2GUC_REGISTER_CTB
+ * DOC: HOST2GUC_SELF_CFG
  *
- * This message is used as part of the `CTB based communication`_ setup.
+ * This message is used by Host KMD to setup of the `GuC Self Config KLVs`_.
  *
  * This message must be sent as `MMIO HXG Message`_.
  *
@@ -22,20 +22,18 @@
  *  |   +-------+--------------------------------------------------------------+
  *  |   | 27:16 | DATA0 = MBZ                                                  |
  *  |   +-------+--------------------------------------------------------------+
- *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_REGISTER_CTB` = 0x4505        |
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_SELF_CFG` = 0x0508            |
  *  +---+-------+--------------------------------------------------------------+
- *  | 1 | 31:12 | RESERVED = MBZ                                               |
+ *  | 1 | 31:16 | **KLV_KEY** - KLV key, see `GuC Self Config KLVs`_           |
  *  |   +-------+--------------------------------------------------------------+
- *  |   |  11:8 | **TYPE** - type for the `CT Buffer`_                         |
+ *  |   |  15:0 | **KLV_LEN** - KLV length                                     |
  *  |   |       |                                                              |
- *  |   |       |   - _`GUC_CTB_TYPE_HOST2GUC` = 0                             |
- *  |   |       |   - _`GUC_CTB_TYPE_GUC2HOST` = 1                             |
- *  |   +-------+--------------------------------------------------------------+
- *  |   |   7:0 | **SIZE** - size of the `CT Buffer`_ in 4K units minus 1      |
+ *  |   |       |   - 32 bit KLV = 1                                           |
+ *  |   |       |   - 64 bit KLV = 2                                           |
  *  +---+-------+--------------------------------------------------------------+
- *  | 2 |  31:0 | **DESC_ADDR** - GGTT address of the `CTB Descriptor`_        |
+ *  | 2 |  31:0 | **VALUE32** - Bits 31-0 of the KLV value                     |
  *  +---+-------+--------------------------------------------------------------+
- *  | 3 |  31:0 | **BUFF_ADDF** - GGTT address of the `CT Buffer`_             |
+ *  | 3 |  31:0 | **VALUE64** - Bits 63-32 of the KLV value (**KLV_LEN** = 2)  |
  *  +---+-------+--------------------------------------------------------------+
  *
  *  +---+-------+--------------------------------------------------------------+
@@ -45,28 +43,25 @@
  *  |   +-------+--------------------------------------------------------------+
  *  |   | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_                        |
  *  |   +-------+--------------------------------------------------------------+
- *  |   |  27:0 | DATA0 = MBZ                                                  |
+ *  |   |  27:0 | DATA0 = **NUM** - 1 if KLV was parsed, 0 if not recognized   |
  *  +---+-------+--------------------------------------------------------------+
  */
-#define GUC_ACTION_HOST2GUC_REGISTER_CTB		0x4505
+#define GUC_ACTION_HOST2GUC_SELF_CFG			0x0508
 
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_MBZ		(0xfffff << 12)
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE	(0xf << 8)
-#define   GUC_CTB_TYPE_HOST2GUC				0u
-#define   GUC_CTB_TYPE_GUC2HOST				1u
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE	(0xff << 0)
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR	GUC_HXG_REQUEST_MSG_n_DATAn
-#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR	GUC_HXG_REQUEST_MSG_n_DATAn
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffff << 16)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffff << 0)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32		GUC_HXG_REQUEST_MSG_n_DATAn
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64		GUC_HXG_REQUEST_MSG_n_DATAn
 
-#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_LEN		GUC_HXG_RESPONSE_MSG_MIN_LEN
-#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_0_MBZ	GUC_HXG_RESPONSE_MSG_0_DATA0
+#define HOST2GUC_SELF_CFG_RESPONSE_MSG_LEN		GUC_HXG_RESPONSE_MSG_MIN_LEN
+#define HOST2GUC_SELF_CFG_RESPONSE_MSG_0_NUM		GUC_HXG_RESPONSE_MSG_0_DATA0
 
 /**
- * DOC: HOST2GUC_DEREGISTER_CTB
+ * DOC: HOST2GUC_CONTROL_CTB
  *
- * This message is used as part of the `CTB based communication`_ teardown.
+ * This H2G action allows Vf Host to enable or disable H2G and G2H `CT Buffer`_.
  *
  * This message must be sent as `MMIO HXG Message`_.
  *
@@ -79,15 +74,12 @@
  *  |   +-------+--------------------------------------------------------------+
  *  |   | 27:16 | DATA0 = MBZ                                                  |
  *  |   +-------+--------------------------------------------------------------+
- *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_DEREGISTER_CTB` = 0x4506      |
+ *  |   |  15:0 | ACTION = _`GUC_ACTION_HOST2GUC_CONTROL_CTB` = 0x4509         |
  *  +---+-------+--------------------------------------------------------------+
- *  | 1 | 31:12 | RESERVED = MBZ                                               |
- *  |   +-------+--------------------------------------------------------------+
- *  |   |  11:8 | **TYPE** - type of the `CT Buffer`_                          |
+ *  | 1 |  31:0 | **CONTROL** - control `CTB based communication`_             |
  *  |   |       |                                                              |
- *  |   |       | see `GUC_ACTION_HOST2GUC_REGISTER_CTB`_                      |
- *  |   +-------+--------------------------------------------------------------+
- *  |   |   7:0 | RESERVED = MBZ                                               |
+ *  |   |       |   - _`GUC_CTB_CONTROL_DISABLE` = 0                           |
+ *  |   |       |   - _`GUC_CTB_CONTROL_ENABLE` = 1                            |
  *  +---+-------+--------------------------------------------------------------+
  *
  *  +---+-------+--------------------------------------------------------------+
@@ -100,16 +92,16 @@
  *  |   |  27:0 | DATA0 = MBZ                                                  |
  *  +---+-------+--------------------------------------------------------------+
  */
-#define GUC_ACTION_HOST2GUC_DEREGISTER_CTB		0x4506
+#define GUC_ACTION_HOST2GUC_CONTROL_CTB			0x4509
 
-#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 1u)
-#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_0_MBZ	GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ	(0xfffff << 12)
-#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE	(0xf << 8)
-#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ2	(0xff << 0)
+#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 1u)
+#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
+#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_1_CONTROL	GUC_HXG_REQUEST_MSG_n_DATAn
+#define   GUC_CTB_CONTROL_DISABLE			0u
+#define   GUC_CTB_CONTROL_ENABLE			1u
 
-#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_LEN	GUC_HXG_RESPONSE_MSG_MIN_LEN
-#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_0_MBZ	GUC_HXG_RESPONSE_MSG_0_DATA0
+#define HOST2GUC_CONTROL_CTB_RESPONSE_MSG_LEN		GUC_HXG_RESPONSE_MSG_MIN_LEN
+#define HOST2GUC_CONTROL_CTB_RESPONSE_MSG_0_MBZ		GUC_HXG_RESPONSE_MSG_0_DATA0
 
 /* legacy definitions */
 
@@ -143,8 +135,12 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
 	INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600,
 	INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601,
-	INTEL_GUC_ACTION_RESET_CLIENT = 0x5507,
+	INTEL_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507,
 	INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A,
+	INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION = 0x8002,
+	INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE = 0x8003,
+	INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED = 0x8004,
+	INTEL_GUC_ACTION_NOTIFY_EXCEPTION = 0x8005,
 	INTEL_GUC_ACTION_LIMIT
 };
 
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
index 488b6061ee89..c20658ee85a5 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h
@@ -11,4 +11,27 @@ enum intel_guc_response_status {
 	INTEL_GUC_RESPONSE_STATUS_GENERIC_FAIL = 0xF000,
 };
 
+enum intel_guc_load_status {
+	INTEL_GUC_LOAD_STATUS_DEFAULT                          = 0x00,
+	INTEL_GUC_LOAD_STATUS_START                            = 0x01,
+	INTEL_GUC_LOAD_STATUS_ERROR_DEVID_BUILD_MISMATCH       = 0x02,
+	INTEL_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH       = 0x03,
+	INTEL_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE      = 0x04,
+	INTEL_GUC_LOAD_STATUS_GDT_DONE                         = 0x10,
+	INTEL_GUC_LOAD_STATUS_IDT_DONE                         = 0x20,
+	INTEL_GUC_LOAD_STATUS_LAPIC_DONE                       = 0x30,
+	INTEL_GUC_LOAD_STATUS_GUCINT_DONE                      = 0x40,
+	INTEL_GUC_LOAD_STATUS_DPC_READY                        = 0x50,
+	INTEL_GUC_LOAD_STATUS_DPC_ERROR                        = 0x60,
+	INTEL_GUC_LOAD_STATUS_EXCEPTION                        = 0x70,
+	INTEL_GUC_LOAD_STATUS_INIT_DATA_INVALID                = 0x71,
+	INTEL_GUC_LOAD_STATUS_PXP_TEARDOWN_CTRL_ENABLED        = 0x72,
+	INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_START,
+	INTEL_GUC_LOAD_STATUS_MPU_DATA_INVALID                 = 0x73,
+	INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID   = 0x74,
+	INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_END,
+
+	INTEL_GUC_LOAD_STATUS_READY                            = 0xF0,
+};
+
 #endif /* _ABI_GUC_ERRORS_ABI_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
new file mode 100644
index 000000000000..f0814a57c191
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef _ABI_GUC_KLVS_ABI_H
+#define _ABI_GUC_KLVS_ABI_H
+
+/**
+ * DOC: GuC KLV
+ *
+ *  +---+-------+--------------------------------------------------------------+
+ *  |   | Bits  | Description                                                  |
+ *  +===+=======+==============================================================+
+ *  | 0 | 31:16 | **KEY** - KLV key identifier                                 |
+ *  |   |       |   - `GuC Self Config KLVs`_                                  |
+ *  |   |       |                                                              |
+ *  |   +-------+--------------------------------------------------------------+
+ *  |   |  15:0 | **LEN** - length of VALUE (in 32bit dwords)                  |
+ *  +---+-------+--------------------------------------------------------------+
+ *  | 1 |  31:0 | **VALUE** - actual value of the KLV (format depends on KEY)  |
+ *  +---+-------+                                                              |
+ *  |...|       |                                                              |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
+ *  +---+-------+--------------------------------------------------------------+
+ */
+
+#define GUC_KLV_LEN_MIN				1u
+#define GUC_KLV_0_KEY				(0xffff << 16)
+#define GUC_KLV_0_LEN				(0xffff << 0)
+#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+
+/**
+ * DOC: GuC Self Config KLVs
+ *
+ * `GuC KLV`_ keys available for use with HOST2GUC_SELF_CFG_.
+ *
+ * _`GUC_KLV_SELF_CFG_H2G_CTB_ADDR` : 0x0902
+ *      Refers to 64 bit Global Gfx address of H2G `CT Buffer`_.
+ *      Should be above WOPCM address but below APIC base address for native mode.
+ *
+ * _`GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR` : 0x0903
+ *      Refers to 64 bit Global Gfx address of H2G `CTB Descriptor`_.
+ *      Should be above WOPCM address but below APIC base address for native mode.
+ *
+ * _`GUC_KLV_SELF_CFG_H2G_CTB_SIZE` : 0x0904
+ *      Refers to size of H2G `CT Buffer`_ in bytes.
+ *      Should be a multiple of 4K.
+ *
+ * _`GUC_KLV_SELF_CFG_G2H_CTB_ADDR` : 0x0905
+ *      Refers to 64 bit Global Gfx address of G2H `CT Buffer`_.
+ *      Should be above WOPCM address but below APIC base address for native mode.
+ *
+ * _`GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR` : 0x0906
+ *      Refers to 64 bit Global Gfx address of G2H `CTB Descriptor`_.
+ *      Should be above WOPCM address but below APIC base address for native mode.
+ *
+ * _`GUC_KLV_SELF_CFG_G2H_CTB_SIZE` : 0x0907
+ *      Refers to size of G2H `CT Buffer`_ in bytes.
+ *      Should be a multiple of 4K.
+ */
+
+#define GUC_KLV_SELF_CFG_H2G_CTB_ADDR_KEY		0x0902
+#define GUC_KLV_SELF_CFG_H2G_CTB_ADDR_LEN		2u
+
+#define GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_KEY	0x0903
+#define GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_LEN	2u
+
+#define GUC_KLV_SELF_CFG_H2G_CTB_SIZE_KEY		0x0904
+#define GUC_KLV_SELF_CFG_H2G_CTB_SIZE_LEN		1u
+
+#define GUC_KLV_SELF_CFG_G2H_CTB_ADDR_KEY		0x0905
+#define GUC_KLV_SELF_CFG_G2H_CTB_ADDR_LEN		2u
+
+#define GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_KEY	0x0906
+#define GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_LEN	2u
+
+#define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_KEY		0x0907
+#define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_LEN		1u
+
+#endif /* _ABI_GUC_KLVS_ABI_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 5bab32fef120..447a976c9f25 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -184,6 +184,9 @@ void intel_guc_init_early(struct intel_guc *guc)
 		guc->send_regs.count = GUC_MAX_MMIO_MSG_LEN;
 		BUILD_BUG_ON(GUC_MAX_MMIO_MSG_LEN > SOFT_SCRATCH_COUNT);
 	}
+
+	intel_guc_enable_msg(guc, INTEL_GUC_RECV_MSG_EXCEPTION |
+				  INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED);
 }
 
 void intel_guc_init_late(struct intel_guc *guc)
@@ -224,32 +227,48 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 	u32 flags;
 
 	#if (((CRASH_BUFFER_SIZE) % SZ_1M) == 0)
-	#define UNIT SZ_1M
-	#define FLAG GUC_LOG_ALLOC_IN_MEGABYTE
+	#define LOG_UNIT SZ_1M
+	#define LOG_FLAG GUC_LOG_LOG_ALLOC_UNITS
 	#else
-	#define UNIT SZ_4K
-	#define FLAG 0
+	#define LOG_UNIT SZ_4K
+	#define LOG_FLAG 0
+	#endif
+
+	#if (((CAPTURE_BUFFER_SIZE) % SZ_1M) == 0)
+	#define CAPTURE_UNIT SZ_1M
+	#define CAPTURE_FLAG GUC_LOG_CAPTURE_ALLOC_UNITS
+	#else
+	#define CAPTURE_UNIT SZ_4K
+	#define CAPTURE_FLAG 0
 	#endif
 
 	BUILD_BUG_ON(!CRASH_BUFFER_SIZE);
-	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, LOG_UNIT));
 	BUILD_BUG_ON(!DEBUG_BUFFER_SIZE);
-	BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, LOG_UNIT));
+	BUILD_BUG_ON(!CAPTURE_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(CAPTURE_BUFFER_SIZE, CAPTURE_UNIT));
 
-	BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) >
+	BUILD_BUG_ON((CRASH_BUFFER_SIZE / LOG_UNIT - 1) >
 			(GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT));
-	BUILD_BUG_ON((DEBUG_BUFFER_SIZE / UNIT - 1) >
+	BUILD_BUG_ON((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) >
 			(GUC_LOG_DEBUG_MASK >> GUC_LOG_DEBUG_SHIFT));
+	BUILD_BUG_ON((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) >
+			(GUC_LOG_CAPTURE_MASK >> GUC_LOG_CAPTURE_SHIFT));
 
 	flags = GUC_LOG_VALID |
 		GUC_LOG_NOTIFY_ON_HALF_FULL |
-		FLAG |
-		((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
-		((DEBUG_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DEBUG_SHIFT) |
+		CAPTURE_FLAG |
+		LOG_FLAG |
+		((CRASH_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
+		((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_DEBUG_SHIFT) |
+		((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) << GUC_LOG_CAPTURE_SHIFT) |
 		(offset << GUC_LOG_BUF_ADDR_SHIFT);
 
-	#undef UNIT
-	#undef FLAG
+	#undef LOG_UNIT
+	#undef LOG_FLAG
+	#undef CAPTURE_UNIT
+	#undef CAPTURE_FLAG
 
 	return flags;
 }
@@ -262,6 +281,26 @@ static u32 guc_ctl_ads_flags(struct intel_guc *guc)
 	return flags;
 }
 
+static u32 guc_ctl_wa_flags(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	u32 flags = 0;
+
+	/* Wa_22012773006:gen11,gen12 < XeHP */
+	if (GRAPHICS_VER(gt->i915) >= 11 &&
+	    GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 50))
+		flags |= GUC_WA_POLLCS;
+
+	return flags;
+}
+
+static u32 guc_ctl_devid(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+
+	return (INTEL_DEVID(i915) << 16) | INTEL_REVID(i915);
+}
+
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -278,6 +317,8 @@ static void guc_init_params(struct intel_guc *guc)
 	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
 	params[GUC_CTL_ADS] = guc_ctl_ads_flags(guc);
+	params[GUC_CTL_WA] = guc_ctl_wa_flags(guc);
+	params[GUC_CTL_DEVID] = guc_ctl_devid(guc);
 
 	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
 		DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]);
@@ -515,9 +556,10 @@ int intel_guc_to_host_process_recv_msg(struct intel_guc *guc,
 	/* Make sure to handle only enabled messages */
 	msg = payload[0] & guc->msg_enabled_mask;
 
-	if (msg & (INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
-		   INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED))
-		intel_guc_log_handle_flush_event(&guc->log);
+	if (msg & INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED)
+		drm_err(&guc_to_gt(guc)->i915->drm, "Received early GuC crash dump notification!\n");
+	if (msg & INTEL_GUC_RECV_MSG_EXCEPTION)
+		drm_err(&guc_to_gt(guc)->i915->drm, "Received early GuC exception notification!\n");
 
 	return 0;
 }
@@ -551,7 +593,7 @@ int intel_guc_suspend(struct intel_guc *guc)
 {
 	int ret;
 	u32 action[] = {
-		INTEL_GUC_ACTION_RESET_CLIENT,
+		INTEL_GUC_ACTION_CLIENT_SOFT_RESET,
 	};
 
 	if (!intel_guc_is_ready(guc))
@@ -715,6 +757,56 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
 	return 0;
 }
 
+static int __guc_action_self_cfg(struct intel_guc *guc, u16 key, u16 len, u64 value)
+{
+	u32 request[HOST2GUC_SELF_CFG_REQUEST_MSG_LEN] = {
+		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
+		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_SELF_CFG),
+		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY, key) |
+		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN, len),
+		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32, lower_32_bits(value)),
+		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64, upper_32_bits(value)),
+	};
+	int ret;
+
+	GEM_BUG_ON(len > 2);
+	GEM_BUG_ON(len == 1 && upper_32_bits(value));
+
+	/* Self config must go over MMIO */
+	ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
+
+	if (unlikely(ret < 0))
+		return ret;
+	if (unlikely(ret > 1))
+		return -EPROTO;
+	if (unlikely(!ret))
+		return -ENOKEY;
+
+	return 0;
+}
+
+static int __guc_self_cfg(struct intel_guc *guc, u16 key, u16 len, u64 value)
+{
+	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	int err = __guc_action_self_cfg(guc, key, len, value);
+
+	if (unlikely(err))
+		i915_probe_error(i915, "Unsuccessful self-config (%pe) key %#hx value %#llx\n",
+				 ERR_PTR(err), key, value);
+	return err;
+}
+
+int intel_guc_self_cfg32(struct intel_guc *guc, u16 key, u32 value)
+{
+	return __guc_self_cfg(guc, key, 1, value);
+}
+
+int intel_guc_self_cfg64(struct intel_guc *guc, u16 key, u64 value)
+{
+	return __guc_self_cfg(guc, key, 2, value);
+}
+
 /**
  * intel_guc_load_status - dump information about GuC load status
  * @guc: the GuC
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index f9240d4baa69..9d779de16613 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -119,6 +119,15 @@ struct intel_guc {
 		 * function as it might be in an atomic context (no sleeping)
 		 */
 		struct work_struct destroyed_worker;
+		/**
+		 * @reset_fail_worker: worker to trigger a GT reset after an
+		 * engine reset fails
+		 */
+		struct work_struct reset_fail_worker;
+		/**
+		 * @reset_fail_mask: mask of engines that failed to reset
+		 */
+		intel_engine_mask_t reset_fail_mask;
 	} submission_state;
 
 	/**
@@ -141,6 +150,13 @@ struct intel_guc {
 	struct __guc_ads_blob *ads_blob;
 	/** @ads_regset_size: size of the save/restore regsets in the ADS */
 	u32 ads_regset_size;
+	/**
+	 * @ads_regset_count: number of save/restore registers in the ADS for
+	 * each engine
+	 */
+	u32 ads_regset_count[I915_NUM_ENGINES];
+	/** @ads_regset: save/restore regsets in the ADS */
+	struct guc_mmio_reg *ads_regset;
 	/** @ads_golden_ctxt_size: size of the golden contexts in the ADS */
 	u32 ads_golden_ctxt_size;
 	/** @ads_engine_usage_size: size of engine usage in the ADS */
@@ -206,6 +222,11 @@ struct intel_guc {
 		 * context usage for overflows.
 		 */
 		struct delayed_work work;
+
+		/**
+		 * @shift: Right shift value for the gpm timestamp
+		 */
+		u32 shift;
 	} timestamp;
 
 #ifdef CONFIG_DRM_I915_SELFTEST
@@ -328,6 +349,8 @@ int intel_guc_resume(struct intel_guc *guc);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
 int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
 				   struct i915_vma **out_vma, void **out_vaddr);
+int intel_guc_self_cfg32(struct intel_guc *guc, u16 key, u32 value);
+int intel_guc_self_cfg64(struct intel_guc *guc, u16 key, u64 value);
 
 static inline bool intel_guc_is_supported(struct intel_guc *guc)
 {
@@ -404,6 +427,8 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 					const u32 *msg, u32 len);
 int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 					 const u32 *msg, u32 len);
+int intel_guc_error_capture_process_msg(struct intel_guc *guc,
+					const u32 *msg, u32 len);
 
 void intel_guc_find_hung_context(struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index 162b89198567..7e41175618f5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -42,6 +42,10 @@
  *      +---------------------------------------+
  *      | padding                               |
  *      +---------------------------------------+ <== 4K aligned
+ *      | capture lists                         |
+ *      +---------------------------------------+
+ *      | padding                               |
+ *      +---------------------------------------+ <== 4K aligned
  *      | private data                          |
  *      +---------------------------------------+
  *      | padding                               |
@@ -67,6 +71,12 @@ static u32 guc_ads_golden_ctxt_size(struct intel_guc *guc)
 	return PAGE_ALIGN(guc->ads_golden_ctxt_size);
 }
 
+static u32 guc_ads_capture_size(struct intel_guc *guc)
+{
+	/* FIXME: Allocate a proper capture list */
+	return PAGE_ALIGN(PAGE_SIZE);
+}
+
 static u32 guc_ads_private_data_size(struct intel_guc *guc)
 {
 	return PAGE_ALIGN(guc->fw.private_data_size);
@@ -87,7 +97,7 @@ static u32 guc_ads_golden_ctxt_offset(struct intel_guc *guc)
 	return PAGE_ALIGN(offset);
 }
 
-static u32 guc_ads_private_data_offset(struct intel_guc *guc)
+static u32 guc_ads_capture_offset(struct intel_guc *guc)
 {
 	u32 offset;
 
@@ -97,6 +107,16 @@ static u32 guc_ads_private_data_offset(struct intel_guc *guc)
 	return PAGE_ALIGN(offset);
 }
 
+static u32 guc_ads_private_data_offset(struct intel_guc *guc)
+{
+	u32 offset;
+
+	offset = guc_ads_capture_offset(guc) +
+		 guc_ads_capture_size(guc);
+
+	return PAGE_ALIGN(offset);
+}
+
 static u32 guc_ads_blob_size(struct intel_guc *guc)
 {
 	return guc_ads_private_data_offset(guc) +
@@ -188,14 +208,18 @@ static void guc_mapping_table_init(struct intel_gt *gt,
 
 /*
  * The save/restore register list must be pre-calculated to a temporary
- * buffer of driver defined size before it can be generated in place
- * inside the ADS.
+ * buffer before it can be copied inside the ADS.
  */
-#define MAX_MMIO_REGS	128	/* Arbitrary size, increase as needed */
 struct temp_regset {
+	/*
+	 * ptr to the section of the storage for the engine currently being
+	 * worked on
+	 */
 	struct guc_mmio_reg *registers;
-	u32 used;
-	u32 size;
+	/* ptr to the base of the allocated storage for all engines */
+	struct guc_mmio_reg *storage;
+	u32 storage_used;
+	u32 storage_max;
 };
 
 static int guc_mmio_reg_cmp(const void *a, const void *b)
@@ -206,18 +230,44 @@ static int guc_mmio_reg_cmp(const void *a, const void *b)
 	return (int)ra->offset - (int)rb->offset;
 }
 
-static void guc_mmio_reg_add(struct temp_regset *regset,
-			     u32 offset, u32 flags)
+static struct guc_mmio_reg * __must_check
+__mmio_reg_add(struct temp_regset *regset, struct guc_mmio_reg *reg)
 {
-	u32 count = regset->used;
+	u32 pos = regset->storage_used;
+	struct guc_mmio_reg *slot;
+
+	if (pos >= regset->storage_max) {
+		size_t size = ALIGN((pos + 1) * sizeof(*slot), PAGE_SIZE);
+		struct guc_mmio_reg *r = krealloc(regset->storage,
+						  size, GFP_KERNEL);
+		if (!r) {
+			WARN_ONCE(1, "Incomplete regset list: can't add register (%d)\n",
+				  -ENOMEM);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		regset->registers = r + (regset->registers - regset->storage);
+		regset->storage = r;
+		regset->storage_max = size / sizeof(*slot);
+	}
+
+	slot = &regset->storage[pos];
+	regset->storage_used++;
+	*slot = *reg;
+
+	return slot;
+}
+
+static long __must_check guc_mmio_reg_add(struct temp_regset *regset,
+					  u32 offset, u32 flags)
+{
+	u32 count = regset->storage_used - (regset->registers - regset->storage);
 	struct guc_mmio_reg reg = {
 		.offset = offset,
 		.flags = flags,
 	};
 	struct guc_mmio_reg *slot;
 
-	GEM_BUG_ON(count >= regset->size);
-
 	/*
 	 * The mmio list is built using separate lists within the driver.
 	 * It's possible that at some point we may attempt to add the same
@@ -226,11 +276,11 @@ static void guc_mmio_reg_add(struct temp_regset *regset,
 	 */
 	if (bsearch(&reg, regset->registers, count,
 		    sizeof(reg), guc_mmio_reg_cmp))
-		return;
+		return 0;
 
-	slot = &regset->registers[count];
-	regset->used++;
-	*slot = reg;
+	slot = __mmio_reg_add(regset, &reg);
+	if (IS_ERR(slot))
+		return PTR_ERR(slot);
 
 	while (slot-- > regset->registers) {
 		GEM_BUG_ON(slot[0].offset == slot[1].offset);
@@ -239,6 +289,8 @@ static void guc_mmio_reg_add(struct temp_regset *regset,
 
 		swap(slot[1], slot[0]);
 	}
+
+	return 0;
 }
 
 #define GUC_MMIO_REG_ADD(regset, reg, masked) \
@@ -246,62 +298,71 @@ static void guc_mmio_reg_add(struct temp_regset *regset,
 			 i915_mmio_reg_offset((reg)), \
 			 (masked) ? GUC_REGSET_MASKED : 0)
 
-static void guc_mmio_regset_init(struct temp_regset *regset,
-				 struct intel_engine_cs *engine)
+static int guc_mmio_regset_init(struct temp_regset *regset,
+				struct intel_engine_cs *engine)
 {
 	const u32 base = engine->mmio_base;
 	struct i915_wa_list *wal = &engine->wa_list;
 	struct i915_wa *wa;
 	unsigned int i;
+	int ret = 0;
 
-	regset->used = 0;
+	/*
+	 * Each engine's registers point to a new start relative to
+	 * storage
+	 */
+	regset->registers = regset->storage + regset->storage_used;
 
-	GUC_MMIO_REG_ADD(regset, RING_MODE_GEN7(base), true);
-	GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false);
-	GUC_MMIO_REG_ADD(regset, RING_IMR(base), false);
+	ret |= GUC_MMIO_REG_ADD(regset, RING_MODE_GEN7(base), true);
+	ret |= GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false);
+	ret |= GUC_MMIO_REG_ADD(regset, RING_IMR(base), false);
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
-		GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg);
+		ret |= GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg);
 
 	/* Be extra paranoid and include all whitelist registers. */
 	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++)
-		GUC_MMIO_REG_ADD(regset,
-				 RING_FORCE_TO_NONPRIV(base, i),
-				 false);
+		ret |= GUC_MMIO_REG_ADD(regset,
+					RING_FORCE_TO_NONPRIV(base, i),
+					false);
 
 	/* add in local MOCS registers */
 	for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++)
-		GUC_MMIO_REG_ADD(regset, GEN9_LNCFCMOCS(i), false);
+		ret |= GUC_MMIO_REG_ADD(regset, GEN9_LNCFCMOCS(i), false);
+
+	return ret ? -1 : 0;
 }
 
-static int guc_mmio_reg_state_query(struct intel_guc *guc)
+static long guc_mmio_reg_state_create(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	struct temp_regset temp_set;
-	u32 total;
+	struct temp_regset temp_set = {};
+	long total = 0;
+	long ret;
 
-	/*
-	 * Need to actually build the list in order to filter out
-	 * duplicates and other such data dependent constructions.
-	 */
-	temp_set.size = MAX_MMIO_REGS;
-	temp_set.registers = kmalloc_array(temp_set.size,
-					   sizeof(*temp_set.registers),
-					   GFP_KERNEL);
-	if (!temp_set.registers)
-		return -ENOMEM;
-
-	total = 0;
 	for_each_engine(engine, gt, id) {
-		guc_mmio_regset_init(&temp_set, engine);
-		total += temp_set.used;
+		u32 used = temp_set.storage_used;
+
+		ret = guc_mmio_regset_init(&temp_set, engine);
+		if (ret < 0)
+			goto fail_regset_init;
+
+		guc->ads_regset_count[id] = temp_set.storage_used - used;
+		total += guc->ads_regset_count[id];
 	}
 
-	kfree(temp_set.registers);
+	guc->ads_regset = temp_set.storage;
+
+	drm_dbg(&guc_to_gt(guc)->i915->drm, "Used %zu KB for temporary ADS regset\n",
+		(temp_set.storage_max * sizeof(struct guc_mmio_reg)) >> 10);
 
 	return total * sizeof(struct guc_mmio_reg);
+
+fail_regset_init:
+	kfree(temp_set.storage);
+	return ret;
 }
 
 static void guc_mmio_reg_state_init(struct intel_guc *guc,
@@ -309,40 +370,38 @@ static void guc_mmio_reg_state_init(struct intel_guc *guc,
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
+	struct guc_mmio_reg *ads_registers;
 	enum intel_engine_id id;
-	struct temp_regset temp_set;
-	struct guc_mmio_reg_set *ads_reg_set;
 	u32 addr_ggtt, offset;
-	u8 guc_class;
 
 	offset = guc_ads_regset_offset(guc);
 	addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
-	temp_set.registers = (struct guc_mmio_reg *)(((u8 *)blob) + offset);
-	temp_set.size = guc->ads_regset_size / sizeof(temp_set.registers[0]);
+	ads_registers = (struct guc_mmio_reg *)(((u8 *)blob) + offset);
+
+	memcpy(ads_registers, guc->ads_regset, guc->ads_regset_size);
 
 	for_each_engine(engine, gt, id) {
+		u32 count = guc->ads_regset_count[id];
+		struct guc_mmio_reg_set *ads_reg_set;
+		u8 guc_class;
+
 		/* Class index is checked in class converter */
 		GEM_BUG_ON(engine->instance >= GUC_MAX_INSTANCES_PER_CLASS);
 
 		guc_class = engine_class_to_guc_class(engine->class);
 		ads_reg_set = &blob->ads.reg_state_list[guc_class][engine->instance];
 
-		guc_mmio_regset_init(&temp_set, engine);
-		if (!temp_set.used) {
+		if (!count) {
 			ads_reg_set->address = 0;
 			ads_reg_set->count = 0;
 			continue;
 		}
 
 		ads_reg_set->address = addr_ggtt;
-		ads_reg_set->count = temp_set.used;
+		ads_reg_set->count = count;
 
-		temp_set.size -= temp_set.used;
-		temp_set.registers += temp_set.used;
-		addr_ggtt += temp_set.used * sizeof(struct guc_mmio_reg);
+		addr_ggtt += count * sizeof(struct guc_mmio_reg);
 	}
-
-	GEM_BUG_ON(temp_set.size);
 }
 
 static void fill_engine_enable_masks(struct intel_gt *gt,
@@ -501,6 +560,26 @@ static void guc_init_golden_context(struct intel_guc *guc)
 	GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size);
 }
 
+static void guc_capture_list_init(struct intel_guc *guc, struct __guc_ads_blob *blob)
+{
+	int i, j;
+	u32 addr_ggtt, offset;
+
+	offset = guc_ads_capture_offset(guc);
+	addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
+
+	/* FIXME: Populate a proper capture list */
+
+	for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) {
+		for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) {
+			blob->ads.capture_instance[i][j] = addr_ggtt;
+			blob->ads.capture_class[i][j] = addr_ggtt;
+		}
+
+		blob->ads.capture_global[i] = addr_ggtt;
+	}
+}
+
 static void __guc_ads_init(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -534,6 +613,9 @@ static void __guc_ads_init(struct intel_guc *guc)
 
 	base = intel_guc_ggtt_offset(guc, guc->ads_vma);
 
+	/* Capture list for hang debug */
+	guc_capture_list_init(guc, blob);
+
 	/* ADS */
 	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
 	blob->ads.gt_system_info = base + ptr_offset(blob, system_info);
@@ -561,8 +643,11 @@ int intel_guc_ads_create(struct intel_guc *guc)
 
 	GEM_BUG_ON(guc->ads_vma);
 
-	/* Need to calculate the reg state size dynamically: */
-	ret = guc_mmio_reg_state_query(guc);
+	/*
+	 * Create reg state size dynamically on system memory to be copied to
+	 * the final ads blob on gt init/reset
+	 */
+	ret = guc_mmio_reg_state_create(guc);
 	if (ret < 0)
 		return ret;
 	guc->ads_regset_size = ret;
@@ -602,6 +687,7 @@ void intel_guc_ads_destroy(struct intel_guc *guc)
 {
 	i915_vma_unpin_and_release(&guc->ads_vma, I915_VMA_RELEASE_MAP);
 	guc->ads_blob = NULL;
+	kfree(guc->ads_regset);
 }
 
 static void guc_ads_private_data_reset(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index aa6dd6415202..2f7fc87a78e1 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -112,18 +112,6 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	init_waitqueue_head(&ct->wq);
 }
 
-static inline const char *guc_ct_buffer_type_to_str(u32 type)
-{
-	switch (type) {
-	case GUC_CTB_TYPE_HOST2GUC:
-		return "SEND";
-	case GUC_CTB_TYPE_GUC2HOST:
-		return "RECV";
-	default:
-		return "<invalid>";
-	}
-}
-
 static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc)
 {
 	memset(desc, 0, sizeof(*desc));
@@ -156,71 +144,65 @@ static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb,
 	guc_ct_buffer_reset(ctb);
 }
 
-static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type,
-					 u32 desc_addr, u32 buff_addr, u32 size)
+static int guc_action_control_ctb(struct intel_guc *guc, u32 control)
 {
-	u32 request[HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN] = {
+	u32 request[HOST2GUC_CONTROL_CTB_REQUEST_MSG_LEN] = {
 		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
 		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
-		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_REGISTER_CTB),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE, size / SZ_4K - 1) |
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE, type),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr),
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_CONTROL_CTB),
+		FIELD_PREP(HOST2GUC_CONTROL_CTB_REQUEST_MSG_1_CONTROL, control),
 	};
 	int ret;
 
-	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
-	GEM_BUG_ON(size % SZ_4K);
+	GEM_BUG_ON(control != GUC_CTB_CONTROL_DISABLE && control != GUC_CTB_CONTROL_ENABLE);
 
-	/* CT registration must go over MMIO */
+	/* CT control must go over MMIO */
 	ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
 
 	return ret > 0 ? -EPROTO : ret;
 }
 
-static int ct_register_buffer(struct intel_guc_ct *ct, u32 type,
-			      u32 desc_addr, u32 buff_addr, u32 size)
+static int ct_control_enable(struct intel_guc_ct *ct, bool enable)
 {
 	int err;
 
-	err = i915_inject_probe_error(guc_to_gt(ct_to_guc(ct))->i915, -ENXIO);
+	err = guc_action_control_ctb(ct_to_guc(ct), enable ?
+				     GUC_CTB_CONTROL_ENABLE : GUC_CTB_CONTROL_DISABLE);
 	if (unlikely(err))
-		return err;
+		CT_PROBE_ERROR(ct, "Failed to control/%s CTB (%pe)\n",
+			       enabledisable(enable), ERR_PTR(err));
 
-	err = guc_action_register_ct_buffer(ct_to_guc(ct), type,
-					    desc_addr, buff_addr, size);
-	if (unlikely(err))
-		CT_ERROR(ct, "Failed to register %s buffer (%pe)\n",
-			 guc_ct_buffer_type_to_str(type), ERR_PTR(err));
 	return err;
 }
 
-static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type)
+static int ct_register_buffer(struct intel_guc_ct *ct, bool send,
+			      u32 desc_addr, u32 buff_addr, u32 size)
 {
-	u32 request[HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN] = {
-		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
-		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
-		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB),
-		FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type),
-	};
-	int ret;
-
-	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
-
-	/* CT deregistration must go over MMIO */
-	ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
+	int err;
 
-	return ret > 0 ? -EPROTO : ret;
-}
+	err = intel_guc_self_cfg64(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_KEY,
+				   desc_addr);
+	if (unlikely(err))
+		goto failed;
 
-static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type)
-{
-	int err = guc_action_deregister_ct_buffer(ct_to_guc(ct), type);
+	err = intel_guc_self_cfg64(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_ADDR_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_ADDR_KEY,
+				   buff_addr);
+	if (unlikely(err))
+		goto failed;
 
+	err = intel_guc_self_cfg32(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_SIZE_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_SIZE_KEY,
+				   size);
 	if (unlikely(err))
-		CT_ERROR(ct, "Failed to deregister %s buffer (%pe)\n",
-			 guc_ct_buffer_type_to_str(type), ERR_PTR(err));
+failed:
+		CT_PROBE_ERROR(ct, "Failed to register %s buffer (%pe)\n",
+			       send ? "SEND" : "RECV", ERR_PTR(err));
+
 	return err;
 }
 
@@ -308,7 +290,7 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct)
 int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
 	struct intel_guc *guc = ct_to_guc(ct);
-	u32 base, desc, cmds;
+	u32 base, desc, cmds, size;
 	void *blob;
 	int err;
 
@@ -333,27 +315,27 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 	 */
 	desc = base + ptrdiff(ct->ctbs.recv.desc, blob);
 	cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob);
-	err = ct_register_buffer(ct, GUC_CTB_TYPE_GUC2HOST,
-				 desc, cmds, ct->ctbs.recv.size * 4);
-
+	size = ct->ctbs.recv.size * 4;
+	err = ct_register_buffer(ct, false, desc, cmds, size);
 	if (unlikely(err))
 		goto err_out;
 
 	desc = base + ptrdiff(ct->ctbs.send.desc, blob);
 	cmds = base + ptrdiff(ct->ctbs.send.cmds, blob);
-	err = ct_register_buffer(ct, GUC_CTB_TYPE_HOST2GUC,
-				 desc, cmds, ct->ctbs.send.size * 4);
+	size = ct->ctbs.send.size * 4;
+	err = ct_register_buffer(ct, true, desc, cmds, size);
+	if (unlikely(err))
+		goto err_out;
 
+	err = ct_control_enable(ct, true);
 	if (unlikely(err))
-		goto err_deregister;
+		goto err_out;
 
 	ct->enabled = true;
 	ct->stall_time = KTIME_MAX;
 
 	return 0;
 
-err_deregister:
-	ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
 err_out:
 	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
 	return err;
@@ -372,8 +354,7 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct)
 	ct->enabled = false;
 
 	if (intel_guc_is_fw_running(guc)) {
-		ct_deregister_buffer(ct, GUC_CTB_TYPE_HOST2GUC);
-		ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
+		ct_control_enable(ct, false);
 	}
 }
 
@@ -662,6 +643,7 @@ static int ct_send(struct intel_guc_ct *ct,
 	struct ct_request request;
 	unsigned long flags;
 	unsigned int sleep_period_ms = 1;
+	bool send_again;
 	u32 fence;
 	int err;
 
@@ -671,6 +653,9 @@ static int ct_send(struct intel_guc_ct *ct,
 	GEM_BUG_ON(!response_buf && response_buf_size);
 	might_sleep();
 
+resend:
+	send_again = false;
+
 	/*
 	 * We use a lazy spin wait loop here as we believe that if the CT
 	 * buffers are sized correctly the flow control condition should be
@@ -725,6 +710,13 @@ retry:
 		goto unlink;
 	}
 
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) {
+		CT_DEBUG(ct, "retrying request %#x (%u)\n", *action,
+			 FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, *status));
+		send_again = true;
+		goto unlink;
+	}
+
 	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) {
 		err = -EIO;
 		goto unlink;
@@ -747,6 +739,9 @@ unlink:
 	list_del(&request.link);
 	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
+	if (unlikely(send_again))
+		goto resend;
+
 	return err;
 }
 
@@ -789,7 +784,7 @@ static struct ct_incoming_msg *ct_alloc_msg(u32 num_dwords)
 {
 	struct ct_incoming_msg *msg;
 
-	msg = kmalloc(sizeof(*msg) + sizeof(u32) * num_dwords, GFP_ATOMIC);
+	msg = kmalloc(struct_size(msg, msg, num_dwords), GFP_ATOMIC);
 	if (msg)
 		msg->size = num_dwords;
 	return msg;
@@ -918,6 +913,7 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	GEM_BUG_ON(len < GUC_HXG_MSG_MIN_LEN);
 	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]) != GUC_HXG_ORIGIN_GUC);
 	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_SUCCESS &&
+		   FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_NO_RESPONSE_RETRY &&
 		   FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_FAILURE);
 
 	CT_DEBUG(ct, "response fence %u status %#x\n", fence, hxg[0]);
@@ -990,9 +986,27 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION:
 		ret = intel_guc_context_reset_process_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION:
+		ret = intel_guc_error_capture_process_msg(guc, payload, len);
+		if (unlikely(ret))
+			CT_ERROR(ct, "error capture notification failed %x %*ph\n",
+				 action, 4 * len, payload);
+		break;
 	case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION:
 		ret = intel_guc_engine_failure_process_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE:
+		intel_guc_log_handle_flush_event(&guc->log);
+		ret = 0;
+		break;
+	case INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED:
+		CT_ERROR(ct, "Received GuC crash dump notification!\n");
+		ret = 0;
+		break;
+	case INTEL_GUC_ACTION_NOTIFY_EXCEPTION:
+		CT_ERROR(ct, "Received GuC exception notification!\n");
+		ret = 0;
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -1098,6 +1112,7 @@ static int ct_handle_hxg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg)
 		break;
 	case GUC_HXG_TYPE_RESPONSE_SUCCESS:
 	case GUC_HXG_TYPE_RESPONSE_FAILURE:
+	case GUC_HXG_TYPE_NO_RESPONSE_RETRY:
 		err = ct_handle_response(ct, msg);
 		break;
 	default:
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index dcb51b53b495..a0372735cddb 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -16,13 +16,15 @@
 
 static void guc_prepare_xfer(struct intel_uncore *uncore)
 {
-	u32 shim_flags = GUC_DISABLE_SRAM_INIT_TO_ZEROES |
-			 GUC_ENABLE_READ_CACHE_LOGIC |
-			 GUC_ENABLE_MIA_CACHING |
+	u32 shim_flags = GUC_ENABLE_READ_CACHE_LOGIC |
 			 GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA |
 			 GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA |
 			 GUC_ENABLE_MIA_CLOCK_GATING;
 
+	if (GRAPHICS_VER_FULL(uncore->i915) < IP_VER(12, 50))
+		shim_flags |= GUC_DISABLE_SRAM_INIT_TO_ZEROES |
+			      GUC_ENABLE_MIA_CACHING;
+
 	/* Must program this register before loading the ucode with DMA */
 	intel_uncore_write(uncore, GUC_SHIM_CONTROL, shim_flags);
 
@@ -91,11 +93,10 @@ static int guc_xfer_rsa(struct intel_uc_fw *guc_fw,
 static inline bool guc_ready(struct intel_uncore *uncore, u32 *status)
 {
 	u32 val = intel_uncore_read(uncore, GUC_STATUS);
-	u32 uk_val = val & GS_UKERNEL_MASK;
+	u32 uk_val = REG_FIELD_GET(GS_UKERNEL_MASK, val);
 
 	*status = val;
-	return (uk_val == GS_UKERNEL_READY) ||
-		((val & GS_MIA_CORE_STATE) && (uk_val == GS_UKERNEL_LAPIC_DONE));
+	return uk_val == INTEL_GUC_LOAD_STATUS_READY;
 }
 
 static int guc_wait_ucode(struct intel_uncore *uncore)
@@ -106,17 +107,26 @@ static int guc_wait_ucode(struct intel_uncore *uncore)
 	/*
 	 * Wait for the GuC to start up.
 	 * NB: Docs recommend not using the interrupt for completion.
-	 * Measurements indicate this should take no more than 20ms, so a
+	 * Measurements indicate this should take no more than 20ms
+	 * (assuming the GT clock is at maximum frequency). So, a
 	 * timeout here indicates that the GuC has failed and is unusable.
 	 * (Higher levels of the driver may decide to reset the GuC and
 	 * attempt the ucode load again if this happens.)
+	 *
+	 * FIXME: There is a known (but exceedingly unlikely) race condition
+	 * where the asynchronous frequency management code could reduce
+	 * the GT clock while a GuC reload is in progress (during a full
+	 * GT reset). A fix is in progress but there are complex locking
+	 * issues to be resolved. In the meantime bump the timeout to
+	 * 200ms. Even at slowest clock, this should be sufficient. And
+	 * in the working case, a larger timeout makes no difference.
 	 */
-	ret = wait_for(guc_ready(uncore, &status), 100);
+	ret = wait_for(guc_ready(uncore, &status), 200);
 	if (ret) {
 		struct drm_device *drm = &uncore->i915->drm;
 
-		drm_dbg(drm, "GuC load failed: status = 0x%08X\n", status);
-		drm_dbg(drm, "GuC load failed: status: Reset = %d, "
+		drm_info(drm, "GuC load failed: status = 0x%08X\n", status);
+		drm_info(drm, "GuC load failed: status: Reset = %d, "
 			"BootROM = 0x%02X, UKernel = 0x%02X, "
 			"MIA = 0x%02X, Auth = 0x%02X\n",
 			REG_FIELD_GET(GS_MIA_IN_RESET, status),
@@ -126,13 +136,13 @@ static int guc_wait_ucode(struct intel_uncore *uncore)
 			REG_FIELD_GET(GS_AUTH_STATUS_MASK, status));
 
 		if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) {
-			drm_dbg(drm, "GuC firmware signature verification failed\n");
+			drm_info(drm, "GuC firmware signature verification failed\n");
 			ret = -ENOEXEC;
 		}
 
-		if ((status & GS_UKERNEL_MASK) == GS_UKERNEL_EXCEPTION) {
-			drm_dbg(drm, "GuC firmware exception. EIP: %#x\n",
-				intel_uncore_read(uncore, SOFT_SCRATCH(13)));
+		if (REG_FIELD_GET(GS_UKERNEL_MASK, status) == INTEL_GUC_LOAD_STATUS_EXCEPTION) {
+			drm_info(drm, "GuC firmware exception. EIP: %#x\n",
+				 intel_uncore_read(uncore, SOFT_SCRATCH(13)));
 			ret = -ENXIO;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index 7072e30e99f4..6a4612a852e2 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -16,6 +16,7 @@
 #include "abi/guc_errors_abi.h"
 #include "abi/guc_communication_mmio_abi.h"
 #include "abi/guc_communication_ctb_abi.h"
+#include "abi/guc_klvs_abi.h"
 #include "abi/guc_messages_abi.h"
 
 /* Payload length only i.e. don't include G2H header length */
@@ -84,19 +85,24 @@
 #define GUC_STAGE_DESC_ATTR_TERMINATED	BIT(7)
 
 #define GUC_CTL_LOG_PARAMS		0
-#define   GUC_LOG_VALID			(1 << 0)
-#define   GUC_LOG_NOTIFY_ON_HALF_FULL	(1 << 1)
-#define   GUC_LOG_ALLOC_IN_MEGABYTE	(1 << 3)
+#define   GUC_LOG_VALID			BIT(0)
+#define   GUC_LOG_NOTIFY_ON_HALF_FULL	BIT(1)
+#define   GUC_LOG_CAPTURE_ALLOC_UNITS	BIT(2)
+#define   GUC_LOG_LOG_ALLOC_UNITS	BIT(3)
 #define   GUC_LOG_CRASH_SHIFT		4
 #define   GUC_LOG_CRASH_MASK		(0x3 << GUC_LOG_CRASH_SHIFT)
 #define   GUC_LOG_DEBUG_SHIFT		6
 #define   GUC_LOG_DEBUG_MASK	        (0xF << GUC_LOG_DEBUG_SHIFT)
+#define   GUC_LOG_CAPTURE_SHIFT		10
+#define   GUC_LOG_CAPTURE_MASK	        (0x3 << GUC_LOG_CAPTURE_SHIFT)
 #define   GUC_LOG_BUF_ADDR_SHIFT	12
 
 #define GUC_CTL_WA			1
+#define   GUC_WA_POLLCS                 BIT(18)
+
 #define GUC_CTL_FEATURE			2
-#define   GUC_CTL_DISABLE_SCHEDULER	(1 << 14)
 #define   GUC_CTL_ENABLE_SLPC		BIT(2)
+#define   GUC_CTL_DISABLE_SCHEDULER	BIT(14)
 
 #define GUC_CTL_DEBUG			3
 #define   GUC_LOG_VERBOSITY_SHIFT	0
@@ -116,6 +122,8 @@
 #define   GUC_ADS_ADDR_SHIFT		1
 #define   GUC_ADS_ADDR_MASK		(0xFFFFF << GUC_ADS_ADDR_SHIFT)
 
+#define GUC_CTL_DEVID			5
+
 #define GUC_CTL_MAX_DWORDS		(SOFT_SCRATCH_COUNT - 2) /* [1..14] */
 
 /* Generic GT SysInfo data types */
@@ -263,7 +271,10 @@ struct guc_mmio_reg {
 	u32 offset;
 	u32 value;
 	u32 flags;
-#define GUC_REGSET_MASKED		(1 << 0)
+	u32 mask;
+#define GUC_REGSET_MASKED		BIT(0)
+#define GUC_REGSET_MASKED_WITH_VALUE	BIT(2)
+#define GUC_REGSET_RESTORE_ONLY		BIT(3)
 } __packed;
 
 /* GuC register sets */
@@ -280,6 +291,12 @@ struct guc_gt_system_info {
 	u32 generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_MAX];
 } __packed;
 
+enum {
+	GUC_CAPTURE_LIST_INDEX_PF = 0,
+	GUC_CAPTURE_LIST_INDEX_VF = 1,
+	GUC_CAPTURE_LIST_INDEX_MAX = 2,
+};
+
 /* GuC Additional Data Struct */
 struct guc_ads {
 	struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS];
@@ -291,7 +308,11 @@ struct guc_ads {
 	u32 golden_context_lrca[GUC_MAX_ENGINE_CLASSES];
 	u32 eng_state_size[GUC_MAX_ENGINE_CLASSES];
 	u32 private_data;
-	u32 reserved[15];
+	u32 reserved2;
+	u32 capture_instance[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES];
+	u32 capture_class[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES];
+	u32 capture_global[GUC_CAPTURE_LIST_INDEX_MAX];
+	u32 reserved[14];
 } __packed;
 
 /* Engine usage stats */
@@ -312,6 +333,7 @@ struct guc_engine_usage {
 enum guc_log_buffer_type {
 	GUC_DEBUG_LOG_BUFFER,
 	GUC_CRASH_DUMP_LOG_BUFFER,
+	GUC_CAPTURE_LOG_BUFFER,
 	GUC_MAX_LOG_BUFFER
 };
 
@@ -342,6 +364,7 @@ struct guc_log_buffer_state {
 	u32 write_ptr;
 	u32 size;
 	u32 sampled_write_ptr;
+	u32 wrap_offset;
 	union {
 		struct {
 			u32 flush_to_file:1;
@@ -382,7 +405,7 @@ struct guc_shared_ctx_data {
 /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */
 enum intel_guc_recv_message {
 	INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1),
-	INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER = BIT(3)
+	INTEL_GUC_RECV_MSG_EXCEPTION = BIT(30),
 };
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 7b0b43e87244..b53f61f3101f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -56,20 +56,6 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable,
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static void guc_log_enable_flush_events(struct intel_guc_log *log)
-{
-	intel_guc_enable_msg(log_to_guc(log),
-			     INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
-			     INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED);
-}
-
-static void guc_log_disable_flush_events(struct intel_guc_log *log)
-{
-	intel_guc_disable_msg(log_to_guc(log),
-			      INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
-			      INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED);
-}
-
 /*
  * Sub buffer switch callback. Called whenever relay has to switch to a new
  * sub buffer, relay stays on the same sub buffer if 0 is returned.
@@ -202,6 +188,8 @@ static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
 		return DEBUG_BUFFER_SIZE;
 	case GUC_CRASH_DUMP_LOG_BUFFER:
 		return CRASH_BUFFER_SIZE;
+	case GUC_CAPTURE_LOG_BUFFER:
+		return CAPTURE_BUFFER_SIZE;
 	default:
 		MISSING_CASE(type);
 	}
@@ -464,14 +452,19 @@ int intel_guc_log_create(struct intel_guc_log *log)
 	 *  +-------------------------------+ 32B
 	 *  |      Debug state header       |
 	 *  +-------------------------------+ 64B
+	 *  |     Capture state header      |
+	 *  +-------------------------------+ 96B
 	 *  |                               |
 	 *  +===============================+ PAGE_SIZE (4KB)
 	 *  |        Crash Dump logs        |
 	 *  +===============================+ + CRASH_SIZE
 	 *  |          Debug logs           |
 	 *  +===============================+ + DEBUG_SIZE
+	 *  |         Capture logs          |
+	 *  +===============================+ + CAPTURE_SIZE
 	 */
-	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE;
+	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE +
+		       CAPTURE_BUFFER_SIZE;
 
 	vma = intel_guc_allocate_vma(guc, guc_log_size);
 	if (IS_ERR(vma)) {
@@ -593,8 +586,6 @@ int intel_guc_log_relay_start(struct intel_guc_log *log)
 	if (log->relay.started)
 		return -EEXIST;
 
-	guc_log_enable_flush_events(log);
-
 	/*
 	 * When GuC is logging without us relaying to userspace, we're ignoring
 	 * the flush notification. This means that we need to unconditionally
@@ -641,7 +632,6 @@ static void guc_log_relay_stop(struct intel_guc_log *log)
 	if (!log->relay.started)
 		return;
 
-	guc_log_disable_flush_events(log);
 	intel_synchronize_irq(i915);
 
 	flush_work(&log->relay.flush_work);
@@ -662,7 +652,8 @@ void intel_guc_log_relay_close(struct intel_guc_log *log)
 
 void intel_guc_log_handle_flush_event(struct intel_guc_log *log)
 {
-	queue_work(system_highpri_wq, &log->relay.flush_work);
+	if (log->relay.started)
+		queue_work(system_highpri_wq, &log->relay.flush_work);
 }
 
 static const char *
@@ -673,6 +664,8 @@ stringify_guc_log_type(enum guc_log_buffer_type type)
 		return "DEBUG";
 	case GUC_CRASH_DUMP_LOG_BUFFER:
 		return "CRASH";
+	case GUC_CAPTURE_LOG_BUFFER:
+		return "CAPTURE";
 	default:
 		MISSING_CASE(type);
 	}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
index fe6ab7550a14..d7e1b6471fed 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
@@ -18,12 +18,15 @@ struct intel_guc;
 #if defined(CONFIG_DRM_I915_DEBUG_GUC)
 #define CRASH_BUFFER_SIZE	SZ_2M
 #define DEBUG_BUFFER_SIZE	SZ_16M
+#define CAPTURE_BUFFER_SIZE	SZ_4M
 #elif defined(CONFIG_DRM_I915_DEBUG_GEM)
 #define CRASH_BUFFER_SIZE	SZ_1M
 #define DEBUG_BUFFER_SIZE	SZ_2M
+#define CAPTURE_BUFFER_SIZE	SZ_1M
 #else
 #define CRASH_BUFFER_SIZE	SZ_8K
 #define DEBUG_BUFFER_SIZE	SZ_64K
+#define CAPTURE_BUFFER_SIZE	SZ_16K
 #endif
 
 /*
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
index 85846c5570c5..66027a42cda9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
@@ -22,10 +22,6 @@
 #define   GS_BOOTROM_JUMP_PASSED	  (0x76 << GS_BOOTROM_SHIFT)
 #define   GS_UKERNEL_SHIFT		8
 #define   GS_UKERNEL_MASK		  (0xFF << GS_UKERNEL_SHIFT)
-#define   GS_UKERNEL_LAPIC_DONE		  (0x30 << GS_UKERNEL_SHIFT)
-#define   GS_UKERNEL_DPC_ERROR		  (0x60 << GS_UKERNEL_SHIFT)
-#define   GS_UKERNEL_EXCEPTION		  (0x70 << GS_UKERNEL_SHIFT)
-#define   GS_UKERNEL_READY		  (0xF0 << GS_UKERNEL_SHIFT)
 #define   GS_MIA_SHIFT			16
 #define   GS_MIA_MASK			  (0x07 << GS_MIA_SHIFT)
 #define   GS_MIA_CORE_STATE		  (0x01 << GS_MIA_SHIFT)
@@ -98,6 +94,9 @@
 #define   GUC_ENABLE_MIA_CLOCK_GATING		(1<<15)
 #define   GUC_GEN10_SHIM_WC_ENABLE		(1<<21)
 
+#define GUC_SHIM_CONTROL2		_MMIO(0xc068)
+#define   GUC_IS_PRIVILEGED		(1<<29)
+
 #define GUC_SEND_INTERRUPT		_MMIO(0xc4c8)
 #define   GUC_SEND_TRIGGER		  (1<<0)
 #define GEN11_GUC_HOST_INTERRUPT	_MMIO(0x1901f0)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 0cb51c5bb765..b3a429a92c0d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1115,6 +1115,19 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start)
 	if (new_start == lower_32_bits(*prev_start))
 		return;
 
+	/*
+	 * When gt is unparked, we update the gt timestamp and start the ping
+	 * worker that updates the gt_stamp every POLL_TIME_CLKS. As long as gt
+	 * is unparked, all switched in contexts will have a start time that is
+	 * within +/- POLL_TIME_CLKS of the most recent gt_stamp.
+	 *
+	 * If neither gt_stamp nor new_start has rolled over, then the
+	 * gt_stamp_hi does not need to be adjusted, however if one of them has
+	 * rolled over, we need to adjust gt_stamp_hi accordingly.
+	 *
+	 * The below conditions address the cases of new_start rollover and
+	 * gt_stamp_last rollover respectively.
+	 */
 	if (new_start < gt_stamp_last &&
 	    (new_start - gt_stamp_last) <= POLL_TIME_CLKS)
 		gt_stamp_hi++;
@@ -1126,17 +1139,45 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start)
 	*prev_start = ((u64)gt_stamp_hi << 32) | new_start;
 }
 
-static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
+/*
+ * GuC updates shared memory and KMD reads it. Since this is not synchronized,
+ * we run into a race where the value read is inconsistent. Sometimes the
+ * inconsistency is in reading the upper MSB bytes of the last_in value when
+ * this race occurs. 2 types of cases are seen - upper 8 bits are zero and upper
+ * 24 bits are zero. Since these are non-zero values, it is non-trivial to
+ * determine validity of these values. Instead we read the values multiple times
+ * until they are consistent. In test runs, 3 attempts results in consistent
+ * values. The upper bound is set to 6 attempts and may need to be tuned as per
+ * any new occurences.
+ */
+static void __get_engine_usage_record(struct intel_engine_cs *engine,
+				      u32 *last_in, u32 *id, u32 *total)
 {
 	struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine);
+	int i = 0;
+
+	do {
+		*last_in = READ_ONCE(rec->last_switch_in_stamp);
+		*id = READ_ONCE(rec->current_context_index);
+		*total = READ_ONCE(rec->total_runtime);
+
+		if (READ_ONCE(rec->last_switch_in_stamp) == *last_in &&
+		    READ_ONCE(rec->current_context_index) == *id &&
+		    READ_ONCE(rec->total_runtime) == *total)
+			break;
+	} while (++i < 6);
+}
+
+static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
+{
 	struct intel_engine_guc_stats *stats = &engine->stats.guc;
 	struct intel_guc *guc = &engine->gt->uc.guc;
-	u32 last_switch = rec->last_switch_in_stamp;
-	u32 ctx_id = rec->current_context_index;
-	u32 total = rec->total_runtime;
+	u32 last_switch, ctx_id, total;
 
 	lockdep_assert_held(&guc->timestamp.lock);
 
+	__get_engine_usage_record(engine, &last_switch, &ctx_id, &total);
+
 	stats->running = ctx_id != ~0U && last_switch;
 	if (stats->running)
 		__extend_last_switch(guc, &stats->start_gt_clk, last_switch);
@@ -1151,23 +1192,51 @@ static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
 	}
 }
 
-static void guc_update_pm_timestamp(struct intel_guc *guc,
-				    struct intel_engine_cs *engine,
-				    ktime_t *now)
+static u32 gpm_timestamp_shift(struct intel_gt *gt)
+{
+	intel_wakeref_t wakeref;
+	u32 reg, shift;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		reg = intel_uncore_read(gt->uncore, RPM_CONFIG0);
+
+	shift = (reg & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
+		GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT;
+
+	return 3 - shift;
+}
+
+static u64 gpm_timestamp(struct intel_gt *gt)
 {
-	u32 gt_stamp_now, gt_stamp_hi;
+	u32 lo, hi, old_hi, loop = 0;
+
+	hi = intel_uncore_read(gt->uncore, MISC_STATUS1);
+	do {
+		lo = intel_uncore_read(gt->uncore, MISC_STATUS0);
+		old_hi = hi;
+		hi = intel_uncore_read(gt->uncore, MISC_STATUS1);
+	} while (old_hi != hi && loop++ < 2);
+
+	return ((u64)hi << 32) | lo;
+}
+
+static void guc_update_pm_timestamp(struct intel_guc *guc, ktime_t *now)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	u32 gt_stamp_lo, gt_stamp_hi;
+	u64 gpm_ts;
 
 	lockdep_assert_held(&guc->timestamp.lock);
 
 	gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp);
-	gt_stamp_now = intel_uncore_read(engine->uncore,
-					 RING_TIMESTAMP(engine->mmio_base));
+	gpm_ts = gpm_timestamp(gt) >> guc->timestamp.shift;
+	gt_stamp_lo = lower_32_bits(gpm_ts);
 	*now = ktime_get();
 
-	if (gt_stamp_now < lower_32_bits(guc->timestamp.gt_stamp))
+	if (gt_stamp_lo < lower_32_bits(guc->timestamp.gt_stamp))
 		gt_stamp_hi++;
 
-	guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_now;
+	guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_lo;
 }
 
 /*
@@ -1210,8 +1279,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 	if (!in_reset && intel_gt_pm_get_if_awake(gt)) {
 		stats_saved = *stats;
 		gt_stamp_saved = guc->timestamp.gt_stamp;
+		/*
+		 * Update gt_clks, then gt timestamp to simplify the 'gt_stamp -
+		 * start_gt_clk' calculation below for active engines.
+		 */
 		guc_update_engine_gt_clks(engine);
-		guc_update_pm_timestamp(guc, engine, now);
+		guc_update_pm_timestamp(guc, now);
 		intel_gt_pm_put_async(gt);
 		if (i915_reset_count(gpu_error) != reset_count) {
 			*stats = stats_saved;
@@ -1243,8 +1316,8 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 
+	guc_update_pm_timestamp(guc, &unused);
 	for_each_engine(engine, gt, id) {
-		guc_update_pm_timestamp(guc, engine, &unused);
 		guc_update_engine_gt_clks(engine);
 		engine->stats.guc.prev_total = 0;
 	}
@@ -1261,10 +1334,11 @@ static void __update_guc_busyness_stats(struct intel_guc *guc)
 	ktime_t unused;
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
-	for_each_engine(engine, gt, id) {
-		guc_update_pm_timestamp(guc, engine, &unused);
+
+	guc_update_pm_timestamp(guc, &unused);
+	for_each_engine(engine, gt, id)
 		guc_update_engine_gt_clks(engine);
-	}
+
 	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 }
 
@@ -1337,10 +1411,15 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 void intel_guc_busyness_unpark(struct intel_gt *gt)
 {
 	struct intel_guc *guc = &gt->uc.guc;
+	unsigned long flags;
+	ktime_t unused;
 
 	if (!guc_submission_initialized(guc))
 		return;
 
+	spin_lock_irqsave(&guc->timestamp.lock, flags);
+	guc_update_pm_timestamp(guc, &unused);
+	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 	mod_delayed_work(system_highpri_wq, &guc->timestamp.work,
 			 guc->timestamp.ping_delay);
 }
@@ -1351,7 +1430,8 @@ submission_disabled(struct intel_guc *guc)
 	struct i915_sched_engine * const sched_engine = guc->sched_engine;
 
 	return unlikely(!sched_engine ||
-			!__tasklet_is_enabled(&sched_engine->tasklet));
+			!__tasklet_is_enabled(&sched_engine->tasklet) ||
+			intel_gt_is_wedged(guc_to_gt(guc)));
 }
 
 static void disable_submission(struct intel_guc *guc)
@@ -1396,8 +1476,6 @@ static void guc_flush_destroyed_contexts(struct intel_guc *guc);
 
 void intel_guc_submission_reset_prepare(struct intel_guc *guc)
 {
-	int i;
-
 	if (unlikely(!guc_submission_initialized(guc))) {
 		/* Reset called during driver load? GuC not yet initialised! */
 		return;
@@ -1414,21 +1492,7 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc)
 
 	guc_flush_submissions(guc);
 	guc_flush_destroyed_contexts(guc);
-
-	/*
-	 * Handle any outstanding G2Hs before reset. Call IRQ handler directly
-	 * each pass as interrupt have been disabled. We always scrub for
-	 * outstanding G2H as it is possible for outstanding_submission_g2h to
-	 * be incremented after the context state update.
-	 */
-	for (i = 0; i < 4 && atomic_read(&guc->outstanding_submission_g2h); ++i) {
-		intel_guc_to_host_event_handler(guc);
-#define wait_for_reset(guc, wait_var) \
-		intel_guc_wait_for_pending_msg(guc, wait_var, false, (HZ / 20))
-		do {
-			wait_for_reset(guc, &guc->outstanding_submission_g2h);
-		} while (!list_empty(&guc->ct.requests.incoming));
-	}
+	flush_work(&guc->ct.requests.worker);
 
 	scrub_guc_desc_for_outstanding_g2h(guc);
 }
@@ -1533,7 +1597,6 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	unsigned long flags;
 	u32 head;
 	int i, number_children = ce->parallel.number_children;
-	bool skip = false;
 	struct intel_context *parent = ce;
 
 	GEM_BUG_ON(intel_context_is_child(ce));
@@ -1544,23 +1607,10 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	 * GuC will implicitly mark the context as non-schedulable when it sends
 	 * the reset notification. Make sure our state reflects this change. The
 	 * context will be marked enabled on resubmission.
-	 *
-	 * XXX: If the context is reset as a result of the request cancellation
-	 * this G2H is received after the schedule disable complete G2H which is
-	 * wrong as this creates a race between the request cancellation code
-	 * re-submitting the context and this G2H handler. This is a bug in the
-	 * GuC but can be worked around in the meantime but converting this to a
-	 * NOP if a pending enable is in flight as this indicates that a request
-	 * cancellation has occurred.
 	 */
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
-	if (likely(!context_pending_enable(ce)))
-		clr_context_enabled(ce);
-	else
-		skip = true;
+	clr_context_enabled(ce);
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-	if (unlikely(skip))
-		goto out_put;
 
 	/*
 	 * For each context in the relationship find the hanging request
@@ -1592,7 +1642,6 @@ next_context:
 	}
 
 	__unwind_incomplete_requests(parent);
-out_put:
 	intel_context_put(parent);
 }
 
@@ -1727,7 +1776,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc)
 {
 	/* Reset called during driver load or during wedge? */
 	if (unlikely(!guc_submission_initialized(guc) ||
-		     test_bit(I915_WEDGED, &guc_to_gt(guc)->reset.flags))) {
+		     intel_gt_is_wedged(guc_to_gt(guc)))) {
 		return;
 	}
 
@@ -1746,6 +1795,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc)
 }
 
 static void destroyed_worker_func(struct work_struct *w);
+static void reset_fail_worker_func(struct work_struct *w);
 
 /*
  * Set up the memory resources to be shared with the GuC (via the GGTT)
@@ -1776,6 +1826,8 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts);
 	INIT_WORK(&guc->submission_state.destroyed_worker,
 		  destroyed_worker_func);
+	INIT_WORK(&guc->submission_state.reset_fail_worker,
+		  reset_fail_worker_func);
 
 	guc->submission_state.guc_ids_bitmap =
 		bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL);
@@ -1785,6 +1837,7 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	spin_lock_init(&guc->timestamp.lock);
 	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
 	guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ;
+	guc->timestamp.shift = gpm_timestamp_shift(gt);
 
 	return 0;
 }
@@ -2531,12 +2584,6 @@ static void guc_context_cancel_request(struct intel_context *ce,
 					true);
 		}
 
-		/*
-		 * XXX: Racey if context is reset, see comment in
-		 * __guc_reset_context().
-		 */
-		flush_work(&ce_to_guc(ce)->ct.requests.worker);
-
 		guc_context_unblock(block_context);
 		intel_context_put(ce);
 	}
@@ -3250,8 +3297,6 @@ static void guc_parent_context_unpin(struct intel_context *ce)
 	GEM_BUG_ON(!intel_context_is_parent(ce));
 	GEM_BUG_ON(!intel_engine_is_virtual(ce->engine));
 
-	if (ce->parallel.last_rq)
-		i915_request_put(ce->parallel.last_rq);
 	unpin_guc_id(guc, ce);
 	lrc_unpin(ce);
 }
@@ -3973,14 +4018,14 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	/*
-	 * XXX: Racey if request cancellation has occurred, see comment in
-	 * __guc_reset_context().
-	 */
-	if (likely(!intel_context_is_banned(ce) &&
-		   !context_blocked(ce))) {
+	if (likely(!intel_context_is_banned(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
+	} else {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Invalid GuC engine reset notificaion for 0x%04X on %s: banned = %d, blocked = %d",
+			ce->guc_id.id, ce->engine->name, intel_context_is_banned(ce),
+			context_blocked(ce));
 	}
 }
 
@@ -4019,6 +4064,24 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 	return 0;
 }
 
+int intel_guc_error_capture_process_msg(struct intel_guc *guc,
+					const u32 *msg, u32 len)
+{
+	int status;
+
+	if (unlikely(len != 1)) {
+		drm_dbg(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	status = msg[0];
+	drm_info(&guc_to_gt(guc)->i915->drm, "Got error capture: status = %d", status);
+
+	/* FIXME: Do something with the capture */
+
+	return 0;
+}
+
 static struct intel_engine_cs *
 guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
 {
@@ -4031,6 +4094,26 @@ guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
 	return gt->engine_class[engine_class][instance];
 }
 
+static void reset_fail_worker_func(struct work_struct *w)
+{
+	struct intel_guc *guc = container_of(w, struct intel_guc,
+					     submission_state.reset_fail_worker);
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_engine_mask_t reset_fail_mask;
+	unsigned long flags;
+
+	spin_lock_irqsave(&guc->submission_state.lock, flags);
+	reset_fail_mask = guc->submission_state.reset_fail_mask;
+	guc->submission_state.reset_fail_mask = 0;
+	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+	if (likely(reset_fail_mask))
+		intel_gt_handle_error(gt, reset_fail_mask,
+				      I915_ERROR_CAPTURE,
+				      "GuC failed to reset engine mask=0x%x\n",
+				      reset_fail_mask);
+}
+
 int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 					 const u32 *msg, u32 len)
 {
@@ -4038,6 +4121,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 	struct intel_gt *gt = guc_to_gt(guc);
 	u8 guc_class, instance;
 	u32 reason;
+	unsigned long flags;
 
 	if (unlikely(len != 3)) {
 		drm_err(&gt->i915->drm, "Invalid length %u", len);
@@ -4062,10 +4146,15 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 	drm_err(&gt->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X",
 		guc_class, instance, engine->name, reason);
 
-	intel_gt_handle_error(gt, engine->mask,
-			      I915_ERROR_CAPTURE,
-			      "GuC failed to reset %s (reason=0x%08x)\n",
-			      engine->name, reason);
+	spin_lock_irqsave(&guc->submission_state.lock, flags);
+	guc->submission_state.reset_fail_mask |= engine->mask;
+	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+	/*
+	 * A GT reset flushes this worker queue (G2H handler) so we must use
+	 * another worker to trigger a GT reset.
+	 */
+	queue_work(system_unbound_wq, &guc->submission_state.reset_fail_worker);
 
 	return 0;
 }
@@ -4434,27 +4523,31 @@ static inline bool skip_handshake(struct i915_request *rq)
 	return test_bit(I915_FENCE_FLAG_SKIP_PARALLEL, &rq->fence.flags);
 }
 
+#define NON_SKIP_LEN	6
 static u32 *
 emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
 						 u32 *cs)
 {
 	struct intel_context *ce = rq->context;
+	__maybe_unused u32 *before_fini_breadcrumb_user_interrupt_cs;
+	__maybe_unused u32 *start_fini_breadcrumb_cs = cs;
 
 	GEM_BUG_ON(!intel_context_is_parent(ce));
 
 	if (unlikely(skip_handshake(rq))) {
 		/*
 		 * NOP everything in __emit_fini_breadcrumb_parent_no_preempt_mid_batch,
-		 * the -6 comes from the length of the emits below.
+		 * the NON_SKIP_LEN comes from the length of the emits below.
 		 */
 		memset(cs, 0, sizeof(u32) *
-		       (ce->engine->emit_fini_breadcrumb_dw - 6));
-		cs += ce->engine->emit_fini_breadcrumb_dw - 6;
+		       (ce->engine->emit_fini_breadcrumb_dw - NON_SKIP_LEN));
+		cs += ce->engine->emit_fini_breadcrumb_dw - NON_SKIP_LEN;
 	} else {
 		cs = __emit_fini_breadcrumb_parent_no_preempt_mid_batch(rq, cs);
 	}
 
 	/* Emit fini breadcrumb */
+	before_fini_breadcrumb_user_interrupt_cs = cs;
 	cs = gen8_emit_ggtt_write(cs,
 				  rq->fence.seqno,
 				  i915_request_active_timeline(rq)->hwsp_offset,
@@ -4464,6 +4557,12 @@ emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
 	*cs++ = MI_USER_INTERRUPT;
 	*cs++ = MI_NOOP;
 
+	/* Ensure our math for skip + emit is correct */
+	GEM_BUG_ON(before_fini_breadcrumb_user_interrupt_cs + NON_SKIP_LEN !=
+		   cs);
+	GEM_BUG_ON(start_fini_breadcrumb_cs +
+		   ce->engine->emit_fini_breadcrumb_dw != cs);
+
 	rq->tail = intel_ring_offset(rq, cs);
 
 	return cs;
@@ -4506,22 +4605,25 @@ emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq,
 						u32 *cs)
 {
 	struct intel_context *ce = rq->context;
+	__maybe_unused u32 *before_fini_breadcrumb_user_interrupt_cs;
+	__maybe_unused u32 *start_fini_breadcrumb_cs = cs;
 
 	GEM_BUG_ON(!intel_context_is_child(ce));
 
 	if (unlikely(skip_handshake(rq))) {
 		/*
 		 * NOP everything in __emit_fini_breadcrumb_child_no_preempt_mid_batch,
-		 * the -6 comes from the length of the emits below.
+		 * the NON_SKIP_LEN comes from the length of the emits below.
 		 */
 		memset(cs, 0, sizeof(u32) *
-		       (ce->engine->emit_fini_breadcrumb_dw - 6));
-		cs += ce->engine->emit_fini_breadcrumb_dw - 6;
+		       (ce->engine->emit_fini_breadcrumb_dw - NON_SKIP_LEN));
+		cs += ce->engine->emit_fini_breadcrumb_dw - NON_SKIP_LEN;
 	} else {
 		cs = __emit_fini_breadcrumb_child_no_preempt_mid_batch(rq, cs);
 	}
 
 	/* Emit fini breadcrumb */
+	before_fini_breadcrumb_user_interrupt_cs = cs;
 	cs = gen8_emit_ggtt_write(cs,
 				  rq->fence.seqno,
 				  i915_request_active_timeline(rq)->hwsp_offset,
@@ -4531,11 +4633,19 @@ emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq,
 	*cs++ = MI_USER_INTERRUPT;
 	*cs++ = MI_NOOP;
 
+	/* Ensure our math for skip + emit is correct */
+	GEM_BUG_ON(before_fini_breadcrumb_user_interrupt_cs + NON_SKIP_LEN !=
+		   cs);
+	GEM_BUG_ON(start_fini_breadcrumb_cs +
+		   ce->engine->emit_fini_breadcrumb_dw != cs);
+
 	rq->tail = intel_ring_offset(rq, cs);
 
 	return cs;
 }
 
+#undef NON_SKIP_LEN
+
 static struct intel_context *
 guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
 		   unsigned long flags)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index d10b227ac4aa..556829de9c17 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -124,6 +124,7 @@ int intel_huc_auth(struct intel_huc *huc)
 	}
 
 	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING);
+	drm_info(&gt->i915->drm, "HuC authenticated\n");
 	return 0;
 
 fail:
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 09ed29df67bc..da199aa6989f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -432,6 +432,15 @@ static int __uc_check_hw(struct intel_uc *uc)
 	return 0;
 }
 
+static void print_fw_ver(struct intel_uc *uc, struct intel_uc_fw *fw)
+{
+	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
+
+	drm_info(&i915->drm, "%s firmware %s version %u.%u\n",
+		 intel_uc_fw_type_repr(fw->type), fw->path,
+		 fw->major_ver_found, fw->minor_ver_found);
+}
+
 static int __uc_init_hw(struct intel_uc *uc)
 {
 	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
@@ -442,6 +451,11 @@ static int __uc_init_hw(struct intel_uc *uc)
 	GEM_BUG_ON(!intel_uc_supports_guc(uc));
 	GEM_BUG_ON(!intel_uc_wants_guc(uc));
 
+	print_fw_ver(uc, &guc->fw);
+
+	if (intel_uc_uses_huc(uc))
+		print_fw_ver(uc, &huc->fw);
+
 	if (!intel_uc_fw_is_loadable(&guc->fw)) {
 		ret = __uc_check_hw(uc) ||
 		      intel_uc_fw_is_overridden(&guc->fw) ||
@@ -507,24 +521,11 @@ static int __uc_init_hw(struct intel_uc *uc)
 		intel_rps_lower_unslice(&uc_to_gt(uc)->rps);
 	}
 
-	drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
-		 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path,
-		 guc->fw.major_ver_found, guc->fw.minor_ver_found,
-		 "submission",
+	drm_info(&i915->drm, "GuC submission %s\n",
 		 enableddisabled(intel_uc_uses_guc_submission(uc)));
-
-	drm_info(&i915->drm, "GuC SLPC: %s\n",
+	drm_info(&i915->drm, "GuC SLPC %s\n",
 		 enableddisabled(intel_uc_uses_guc_slpc(uc)));
 
-	if (intel_uc_uses_huc(uc)) {
-		drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
-			 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC),
-			 huc->fw.path,
-			 huc->fw.major_ver_found, huc->fw.minor_ver_found,
-			 "authenticated",
-			 yesno(intel_huc_is_authenticated(huc)));
-	}
-
 	return 0;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 549d5919dc70..c88113044494 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -52,21 +52,21 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * firmware as TGL.
  */
 #define INTEL_GUC_FIRMWARE_DEFS(fw_def, guc_def) \
-	fw_def(ALDERLAKE_P,  0, guc_def(adlp, 62, 0, 3)) \
-	fw_def(ALDERLAKE_S,  0, guc_def(tgl,  62, 0, 0)) \
-	fw_def(DG1,          0, guc_def(dg1,  62, 0, 0)) \
-	fw_def(ROCKETLAKE,   0, guc_def(tgl,  62, 0, 0)) \
-	fw_def(TIGERLAKE,    0, guc_def(tgl,  62, 0, 0)) \
-	fw_def(JASPERLAKE,   0, guc_def(ehl,  62, 0, 0)) \
-	fw_def(ELKHARTLAKE,  0, guc_def(ehl,  62, 0, 0)) \
-	fw_def(ICELAKE,      0, guc_def(icl,  62, 0, 0)) \
-	fw_def(COMETLAKE,    5, guc_def(cml,  62, 0, 0)) \
-	fw_def(COMETLAKE,    0, guc_def(kbl,  62, 0, 0)) \
-	fw_def(COFFEELAKE,   0, guc_def(kbl,  62, 0, 0)) \
-	fw_def(GEMINILAKE,   0, guc_def(glk,  62, 0, 0)) \
-	fw_def(KABYLAKE,     0, guc_def(kbl,  62, 0, 0)) \
-	fw_def(BROXTON,      0, guc_def(bxt,  62, 0, 0)) \
-	fw_def(SKYLAKE,      0, guc_def(skl,  62, 0, 0))
+	fw_def(ALDERLAKE_P,  0, guc_def(adlp, 69, 0, 3)) \
+	fw_def(ALDERLAKE_S,  0, guc_def(tgl,  69, 0, 3)) \
+	fw_def(DG1,          0, guc_def(dg1,  69, 0, 3)) \
+	fw_def(ROCKETLAKE,   0, guc_def(tgl,  69, 0, 3)) \
+	fw_def(TIGERLAKE,    0, guc_def(tgl,  69, 0, 3)) \
+	fw_def(JASPERLAKE,   0, guc_def(ehl,  69, 0, 3)) \
+	fw_def(ELKHARTLAKE,  0, guc_def(ehl,  69, 0, 3)) \
+	fw_def(ICELAKE,      0, guc_def(icl,  69, 0, 3)) \
+	fw_def(COMETLAKE,    5, guc_def(cml,  69, 0, 3)) \
+	fw_def(COMETLAKE,    0, guc_def(kbl,  69, 0, 3)) \
+	fw_def(COFFEELAKE,   0, guc_def(kbl,  69, 0, 3)) \
+	fw_def(GEMINILAKE,   0, guc_def(glk,  69, 0, 3)) \
+	fw_def(KABYLAKE,     0, guc_def(kbl,  69, 0, 3)) \
+	fw_def(BROXTON,      0, guc_def(bxt,  69, 0, 3)) \
+	fw_def(SKYLAKE,      0, guc_def(skl,  69, 0, 3))
 
 #define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_def) \
 	fw_def(ALDERLAKE_P,  0, huc_def(tgl,  7, 9, 3)) \
@@ -451,20 +451,19 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw)
 {
 	struct drm_i915_gem_object *obj = uc_fw->obj;
 	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
-	struct i915_vma *dummy = &uc_fw->dummy;
+	struct i915_vma_resource *dummy = &uc_fw->dummy;
 	u32 pte_flags = 0;
 
-	dummy->node.start = uc_fw_ggtt_offset(uc_fw);
-	dummy->node.size = obj->base.size;
-	dummy->pages = obj->mm.pages;
-	dummy->vm = &ggtt->vm;
+	dummy->start = uc_fw_ggtt_offset(uc_fw);
+	dummy->node_size = obj->base.size;
+	dummy->bi.pages = obj->mm.pages;
 
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
-	GEM_BUG_ON(dummy->node.size > ggtt->uc_fw.size);
+	GEM_BUG_ON(dummy->node_size > ggtt->uc_fw.size);
 
 	/* uc_fw->obj cache domains were not controlled across suspend */
 	if (i915_gem_object_has_struct_page(obj))
-		drm_clflush_sg(dummy->pages);
+		drm_clflush_sg(dummy->bi.pages);
 
 	if (i915_gem_object_is_lmem(obj))
 		pte_flags |= PTE_LM;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index d9d1dc0b4cbb..3229018877d3 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -85,7 +85,7 @@ struct intel_uc_fw {
 	 * threaded as it done during driver load (inherently single threaded)
 	 * or during a GT reset (mutex guarantees single threaded).
 	 */
-	struct i915_vma dummy;
+	struct i915_vma_resource dummy;
 	struct i915_vma *rsa_data;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
index d3327b802b76..a115894d5896 100644
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
@@ -157,7 +157,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 	engine = intel_selftest_find_any_engine(gt);
 	sv = guc->submission_state.num_guc_ids;
-	guc->submission_state.num_guc_ids = 4096;
+	guc->submission_state.num_guc_ids = 512;
 
 	/* Create spinner to block requests in below loop */
 	ce[context_index] = intel_context_create(engine);
author	Rodrigo Vivi <rodrigo.vivi@intel.com>	2022-02-23 14:19:43 -0500
committer	Rodrigo Vivi <rodrigo.vivi@intel.com>	2022-02-23 15:03:51 -0500
commit	30424ebae8df0f786835e7a31ad790fa00764f35 (patch)
tree	ef8d835947f4bb8bb608ae2841c34f0d6cb93030 /drivers/gpu/drm/i915/gt
parent	6d8ebef53c2ccea482ed77769b7b5cbb453b7715 (diff)
parent	154cfae6158141b18d65abb0db679bb51a8294e7 (diff)