diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 101dde3eb1ea..311e10400708 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -495,6 +495,8 @@ GuC
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
    :doc: GuC
 
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.h
+
 GuC Firmware Layout
 ~~~~~~~~~~~~~~~~~~~
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 166bb46408a9..65eabca57228 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -442,6 +442,13 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
 	u16 idx, num_bonds;
 	int err, n;
 
+	if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915) &&
+	    !IS_ROCKETLAKE(i915) && !IS_ALDERLAKE_S(i915)) {
+		drm_dbg(&i915->drm,
+			"Bonding on gen12+ aside from TGL, RKL, and ADL_S not supported\n");
+		return -ENODEV;
+	}
+
 	if (get_user(idx, &ext->virtual_index))
 		return -EFAULT;
 
@@ -735,44 +742,6 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 	return ret;
 }
 
-static struct i915_address_space *
-context_get_vm_rcu(struct i915_gem_context *ctx)
-{
-	GEM_BUG_ON(!rcu_access_pointer(ctx->vm));
-
-	do {
-		struct i915_address_space *vm;
-
-		/*
-		 * We do not allow downgrading from full-ppgtt [to a shared
-		 * global gtt], so ctx->vm cannot become NULL.
-		 */
-		vm = rcu_dereference(ctx->vm);
-		if (!kref_get_unless_zero(&vm->ref))
-			continue;
-
-		/*
-		 * This ppgtt may have be reallocated between
-		 * the read and the kref, and reassigned to a third
-		 * context. In order to avoid inadvertent sharing
-		 * of this ppgtt with that third context (and not
-		 * src), we have to confirm that we have the same
-		 * ppgtt after passing through the strong memory
-		 * barrier implied by a successful
-		 * kref_get_unless_zero().
-		 *
-		 * Once we have acquired the current ppgtt of ctx,
-		 * we no longer care if it is released from ctx, as
-		 * it cannot be reallocated elsewhere.
-		 */
-
-		if (vm == rcu_access_pointer(ctx->vm))
-			return rcu_pointer_handoff(vm);
-
-		i915_vm_put(vm);
-	} while (1);
-}
-
 static int intel_context_set_gem(struct intel_context *ce,
 				 struct i915_gem_context *ctx,
 				 struct intel_sseu sseu)
@@ -784,16 +753,8 @@ static int intel_context_set_gem(struct intel_context *ce,
 
 	ce->ring_size = SZ_16K;
 
-	if (rcu_access_pointer(ctx->vm)) {
-		struct i915_address_space *vm;
-
-		rcu_read_lock();
-		vm = context_get_vm_rcu(ctx); /* hmm */
-		rcu_read_unlock();
-
-		i915_vm_put(ce->vm);
-		ce->vm = vm;
-	}
+	i915_vm_put(ce->vm);
+	ce->vm = i915_gem_context_get_eb_vm(ctx);
 
 	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
 	    intel_engine_has_timeslices(ce->engine) &&
@@ -982,9 +943,11 @@ free_engines:
 	return err;
 }
 
-void i915_gem_context_release(struct kref *ref)
+static void i915_gem_context_release_work(struct work_struct *work)
 {
-	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
+	struct i915_gem_context *ctx = container_of(work, typeof(*ctx),
+						    release_work);
+	struct i915_address_space *vm;
 
 	trace_i915_context_free(ctx);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
@@ -992,6 +955,10 @@ void i915_gem_context_release(struct kref *ref)
 	if (ctx->syncobj)
 		drm_syncobj_put(ctx->syncobj);
 
+	vm = ctx->vm;
+	if (vm)
+		i915_vm_put(vm);
+
 	mutex_destroy(&ctx->engines_mutex);
 	mutex_destroy(&ctx->lut_mutex);
 
@@ -1001,6 +968,13 @@ void i915_gem_context_release(struct kref *ref)
 	kfree_rcu(ctx, rcu);
 }
 
+void i915_gem_context_release(struct kref *ref)
+{
+	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
+
+	queue_work(ctx->i915->wq, &ctx->release_work);
+}
+
 static inline struct i915_gem_engines *
 __context_engines_static(const struct i915_gem_context *ctx)
 {
@@ -1207,9 +1181,16 @@ static void context_close(struct i915_gem_context *ctx)
 
 	set_closed_name(ctx);
 
-	vm = i915_gem_context_vm(ctx);
-	if (vm)
+	vm = ctx->vm;
+	if (vm) {
+		/* i915_vm_close drops the final reference, which is a bit too
+		 * early and could result in surprises with concurrent
+		 * operations racing with thist ctx close. Keep a full reference
+		 * until the end.
+		 */
+		i915_vm_get(vm);
 		i915_vm_close(vm);
+	}
 
 	ctx->file_priv = ERR_PTR(-EBADF);
 
@@ -1280,49 +1261,6 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
 	return 0;
 }
 
-static inline struct i915_gem_engines *
-__context_engines_await(const struct i915_gem_context *ctx,
-			bool *user_engines)
-{
-	struct i915_gem_engines *engines;
-
-	rcu_read_lock();
-	do {
-		engines = rcu_dereference(ctx->engines);
-		GEM_BUG_ON(!engines);
-
-		if (user_engines)
-			*user_engines = i915_gem_context_user_engines(ctx);
-
-		/* successful await => strong mb */
-		if (unlikely(!i915_sw_fence_await(&engines->fence)))
-			continue;
-
-		if (likely(engines == rcu_access_pointer(ctx->engines)))
-			break;
-
-		i915_sw_fence_complete(&engines->fence);
-	} while (1);
-	rcu_read_unlock();
-
-	return engines;
-}
-
-static void
-context_apply_all(struct i915_gem_context *ctx,
-		  void (*fn)(struct intel_context *ce, void *data),
-		  void *data)
-{
-	struct i915_gem_engines_iter it;
-	struct i915_gem_engines *e;
-	struct intel_context *ce;
-
-	e = __context_engines_await(ctx, NULL);
-	for_each_gem_engine(ce, e, it)
-		fn(ce, data);
-	i915_sw_fence_complete(&e->fence);
-}
-
 static struct i915_gem_context *
 i915_gem_create_context(struct drm_i915_private *i915,
 			const struct i915_gem_proto_context *pc)
@@ -1342,6 +1280,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 	ctx->sched = pc->sched;
 	mutex_init(&ctx->mutex);
 	INIT_LIST_HEAD(&ctx->link);
+	INIT_WORK(&ctx->release_work, i915_gem_context_release_work);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
@@ -1361,7 +1300,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 		vm = &ppgtt->vm;
 	}
 	if (vm) {
-		RCU_INIT_POINTER(ctx->vm, i915_vm_open(vm));
+		ctx->vm = i915_vm_open(vm);
 
 		/* i915_vm_open() takes a reference */
 		i915_vm_put(vm);
@@ -1584,18 +1523,15 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	int err;
 	u32 id;
 
-	if (!rcu_access_pointer(ctx->vm))
+	if (!i915_gem_context_has_full_ppgtt(ctx))
 		return -ENODEV;
 
-	rcu_read_lock();
-	vm = context_get_vm_rcu(ctx);
-	rcu_read_unlock();
-	if (!vm)
-		return -ENODEV;
+	vm = ctx->vm;
+	GEM_BUG_ON(!vm);
 
 	err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
 	if (err)
-		goto err_put;
+		return err;
 
 	i915_vm_open(vm);
 
@@ -1603,8 +1539,6 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	args->value = id;
 	args->size = 0;
 
-err_put:
-	i915_vm_put(vm);
 	return err;
 }
 
@@ -1772,23 +1706,11 @@ set_persistence(struct i915_gem_context *ctx,
 	return __context_set_persistence(ctx, args->value);
 }
 
-static void __apply_priority(struct intel_context *ce, void *arg)
-{
-	struct i915_gem_context *ctx = arg;
-
-	if (!intel_engine_has_timeslices(ce->engine))
-		return;
-
-	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
-	    intel_engine_has_semaphores(ce->engine))
-		intel_context_set_use_semaphores(ce);
-	else
-		intel_context_clear_use_semaphores(ce);
-}
-
 static int set_priority(struct i915_gem_context *ctx,
 			const struct drm_i915_gem_context_param *args)
 {
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
 	int err;
 
 	err = validate_priority(ctx->i915, args);
@@ -1796,7 +1718,18 @@ static int set_priority(struct i915_gem_context *ctx,
 		return err;
 
 	ctx->sched.priority = args->value;
-	context_apply_all(ctx, __apply_priority, ctx);
+
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		if (!intel_engine_has_timeslices(ce->engine))
+			continue;
+
+		if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
+		    intel_engine_has_semaphores(ce->engine))
+			intel_context_set_use_semaphores(ce);
+		else
+			intel_context_clear_use_semaphores(ce);
+	}
+	i915_gem_context_unlock_engines(ctx);
 
 	return 0;
 }
@@ -2127,6 +2060,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_gem_context_param *args = data;
 	struct i915_gem_context *ctx;
+	struct i915_address_space *vm;
 	int ret = 0;
 
 	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
@@ -2136,12 +2070,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	switch (args->param) {
 	case I915_CONTEXT_PARAM_GTT_SIZE:
 		args->size = 0;
-		rcu_read_lock();
-		if (rcu_access_pointer(ctx->vm))
-			args->value = rcu_dereference(ctx->vm)->total;
-		else
-			args->value = to_i915(dev)->ggtt.vm.total;
-		rcu_read_unlock();
+		vm = i915_gem_context_get_eb_vm(ctx);
+		args->value = vm->total;
+		i915_vm_put(vm);
+
 		break;
 
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 18060536b0c2..d3279086a5e7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -154,17 +154,22 @@ i915_gem_context_vm(struct i915_gem_context *ctx)
 	return rcu_dereference_protected(ctx->vm, lockdep_is_held(&ctx->mutex));
 }
 
+static inline bool i915_gem_context_has_full_ppgtt(struct i915_gem_context *ctx)
+{
+	GEM_BUG_ON(!!ctx->vm != HAS_FULL_PPGTT(ctx->i915));
+
+	return !!ctx->vm;
+}
+
 static inline struct i915_address_space *
-i915_gem_context_get_vm_rcu(struct i915_gem_context *ctx)
+i915_gem_context_get_eb_vm(struct i915_gem_context *ctx)
 {
 	struct i915_address_space *vm;
 
-	rcu_read_lock();
-	vm = rcu_dereference(ctx->vm);
+	vm = ctx->vm;
 	if (!vm)
 		vm = &ctx->i915->ggtt.vm;
 	vm = i915_vm_get(vm);
-	rcu_read_unlock();
 
 	return vm;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 94c03a97cb77..c4617e4d9fa9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -262,7 +262,7 @@ struct i915_gem_context {
 	 * In other modes, this is a NULL pointer with the expectation that
 	 * the caller uses the shared global GTT.
 	 */
-	struct i915_address_space __rcu *vm;
+	struct i915_address_space *vm;
 
 	/**
 	 * @pid: process id of creator
@@ -288,6 +288,18 @@ struct i915_gem_context {
 	 */
 	struct kref ref;
 
+	/**
+	 * @release_work:
+	 *
+	 * Work item for deferred cleanup, since i915_gem_context_put() tends to
+	 * be called from hardirq context.
+	 *
+	 * FIXME: The only real reason for this is &i915_gem_engines.fence, all
+	 * other callers are from process context and need at most some mild
+	 * shuffling to pull the i915_gem_context_put() call out of a spinlock.
+	 */
+	struct work_struct release_work;
+
 	/**
 	 * @rcu: rcu_head for deferred freeing.
 	 */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index 23fee13a3384..1d341b8c47c0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -347,9 +347,6 @@ static int ext_set_placements(struct i915_user_extension __user *base,
 {
 	struct drm_i915_gem_create_ext_memory_regions ext;
 
-	if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM))
-		return -ENODEV;
-
 	if (copy_from_user(&ext, base, sizeof(ext)))
 		return -EFAULT;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1aa249908b64..c2f74dba0557 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -733,7 +733,7 @@ static int eb_select_context(struct i915_execbuffer *eb)
 		return PTR_ERR(ctx);
 
 	eb->gem_context = ctx;
-	if (rcu_access_pointer(ctx->vm))
+	if (i915_gem_context_has_full_ppgtt(ctx))
 		eb->invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
 
 	return 0;
@@ -759,11 +759,7 @@ static int __eb_add_lut(struct i915_execbuffer *eb,
 	/* Check that the context hasn't been closed in the meantime */
 	err = -EINTR;
 	if (!mutex_lock_interruptible(&ctx->lut_mutex)) {
-		struct i915_address_space *vm = rcu_access_pointer(ctx->vm);
-
-		if (unlikely(vm && vma->vm != vm))
-			err = -EAGAIN; /* user racing with ctx set-vm */
-		else if (likely(!i915_gem_context_is_closed(ctx)))
+		if (likely(!i915_gem_context_is_closed(ctx)))
 			err = radix_tree_insert(&ctx->handles_vma, handle, vma);
 		else
 			err = -ENOENT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 1cc8f0b453ae..2f672f06b169 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -426,6 +426,7 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
 }
 
 static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
+			       bool clear,
 			       struct ttm_resource *dst_mem,
 			       struct sg_table *dst_st)
 {
@@ -444,13 +445,10 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
 		return -EINVAL;
 
 	dst_level = i915_ttm_cache_level(i915, dst_mem, ttm);
-	if (!ttm || !ttm_tt_is_populated(ttm)) {
+	if (clear) {
 		if (bo->type == ttm_bo_type_kernel)
 			return -EINVAL;
 
-		if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))
-			return 0;
-
 		intel_engine_pm_get(i915->gt.migrate.context->engine);
 		ret = intel_context_migrate_clear(i915->gt.migrate.context, NULL,
 						  dst_st->sgl, dst_level,
@@ -484,6 +482,41 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
 	return ret;
 }
 
+static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
+			    struct ttm_resource *dst_mem,
+			    struct sg_table *dst_st)
+{
+	int ret;
+
+	ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_st);
+	if (ret) {
+		struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+		struct intel_memory_region *dst_reg, *src_reg;
+		union {
+			struct ttm_kmap_iter_tt tt;
+			struct ttm_kmap_iter_iomap io;
+		} _dst_iter, _src_iter;
+		struct ttm_kmap_iter *dst_iter, *src_iter;
+
+		dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type);
+		src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type);
+		GEM_BUG_ON(!dst_reg || !src_reg);
+
+		dst_iter = !cpu_maps_iomem(dst_mem) ?
+			ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) :
+			ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
+						 dst_st, dst_reg->region.start);
+
+		src_iter = !cpu_maps_iomem(bo->resource) ?
+			ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
+			ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
+						 obj->ttm.cached_io_st,
+						 src_reg->region.start);
+
+		ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter);
+	}
+}
+
 static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 			 struct ttm_operation_ctx *ctx,
 			 struct ttm_resource *dst_mem,
@@ -492,19 +525,11 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 	struct ttm_resource_manager *dst_man =
 		ttm_manager_type(bo->bdev, dst_mem->mem_type);
-	struct intel_memory_region *dst_reg, *src_reg;
-	union {
-		struct ttm_kmap_iter_tt tt;
-		struct ttm_kmap_iter_iomap io;
-	} _dst_iter, _src_iter;
-	struct ttm_kmap_iter *dst_iter, *src_iter;
+	struct ttm_tt *ttm = bo->ttm;
 	struct sg_table *dst_st;
+	bool clear;
 	int ret;
 
-	dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type);
-	src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type);
-	GEM_BUG_ON(!dst_reg || !src_reg);
-
 	/* Sync for now. We could do the actual copy async. */
 	ret = ttm_bo_wait_ctx(bo, ctx);
 	if (ret)
@@ -521,9 +546,8 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* Populate ttm with pages if needed. Typically system memory. */
-	if (bo->ttm && (dst_man->use_tt ||
-			(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) {
-		ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
+	if (ttm && (dst_man->use_tt || (ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) {
+		ret = ttm_tt_populate(bo->bdev, ttm, ctx);
 		if (ret)
 			return ret;
 	}
@@ -532,23 +556,10 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 	if (IS_ERR(dst_st))
 		return PTR_ERR(dst_st);
 
-	ret = i915_ttm_accel_move(bo, dst_mem, dst_st);
-	if (ret) {
-		/* If we start mapping GGTT, we can no longer use man::use_tt here. */
-		dst_iter = !cpu_maps_iomem(dst_mem) ?
-			ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) :
-			ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
-						 dst_st, dst_reg->region.start);
+	clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm));
+	if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)))
+		__i915_ttm_move(bo, clear, dst_mem, dst_st);
 
-		src_iter = !cpu_maps_iomem(bo->resource) ?
-			ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
-			ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
-						 obj->ttm.cached_io_st,
-						 src_reg->region.start);
-
-		ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter);
-	}
-	/* Below dst_mem becomes bo->resource. */
 	ttm_bo_move_sync_cleanup(bo, dst_mem);
 	i915_ttm_adjust_domains_after_move(obj);
 	i915_ttm_free_cached_io_st(obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.c b/drivers/gpu/drm/i915/gem/i915_gemfs.c
index 5e6e8c91ab38..dbdbdc344d87 100644
--- a/drivers/gpu/drm/i915/gem/i915_gemfs.c
+++ b/drivers/gpu/drm/i915/gem/i915_gemfs.c
@@ -6,7 +6,6 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
-#include <linux/pagemap.h>
 
 #include "i915_drv.h"
 #include "i915_gemfs.h"
@@ -15,6 +14,7 @@ int i915_gemfs_init(struct drm_i915_private *i915)
 {
 	struct file_system_type *type;
 	struct vfsmount *gemfs;
+	char *opts;
 
 	type = get_fs_type("tmpfs");
 	if (!type)
@@ -26,10 +26,26 @@ int i915_gemfs_init(struct drm_i915_private *i915)
 	 *
 	 * One example, although it is probably better with a per-file
 	 * control, is selecting huge page allocations ("huge=within_size").
-	 * Currently unused due to bandwidth issues (slow reads) on Broadwell+.
+	 * However, we only do so to offset the overhead of iommu lookups
+	 * due to bandwidth issues (slow reads) on Broadwell+.
 	 */
 
-	gemfs = kern_mount(type);
+	opts = NULL;
+	if (intel_vtd_active()) {
+		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+			static char huge_opt[] = "huge=within_size"; /* r/w */
+
+			opts = huge_opt;
+			drm_info(&i915->drm,
+				 "Transparent Hugepage mode '%s'\n",
+				 opts);
+		} else {
+			drm_notice(&i915->drm,
+				   "Transparent Hugepage support is recommended for optimal performance when IOMMU is enabled!\n");
+		}
+	}
+
+	gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, opts);
 	if (IS_ERR(gemfs))
 		return PTR_ERR(gemfs);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index a094f3ce1a90..0827634c842c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1456,7 +1456,7 @@ static int igt_tmpfs_fallback(void *arg)
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
 	struct vfsmount *gemfs = i915->mm.gemfs;
-	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(ctx);
+	struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	u32 *vaddr;
@@ -1512,13 +1512,14 @@ static int igt_shrink_thp(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(ctx);
+	struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER;
 	unsigned int n;
+	bool should_swap;
 	int err = 0;
 
 	/*
@@ -1567,23 +1568,38 @@ static int igt_shrink_thp(void *arg)
 			break;
 	}
 	i915_gem_context_unlock_engines(ctx);
+	/*
+	 * Nuke everything *before* we unpin the pages so we can be reasonably
+	 * sure that when later checking get_nr_swap_pages() that some random
+	 * leftover object doesn't steal the remaining swap space.
+	 */
+	i915_gem_shrink(NULL, i915, -1UL, NULL,
+			I915_SHRINK_BOUND |
+			I915_SHRINK_UNBOUND |
+			I915_SHRINK_ACTIVE);
 	i915_vma_unpin(vma);
 	if (err)
 		goto out_put;
 
 	/*
-	 * Now that the pages are *unpinned* shrink-all should invoke
-	 * shmem to truncate our pages.
+	 * Now that the pages are *unpinned* shrinking should invoke
+	 * shmem to truncate our pages, if we have available swap.
 	 */
-	i915_gem_shrink_all(i915);
-	if (i915_gem_object_has_pages(obj)) {
-		pr_err("shrink-all didn't truncate the pages\n");
+	should_swap = get_nr_swap_pages() > 0;
+	i915_gem_shrink(NULL, i915, -1UL, NULL,
+			I915_SHRINK_BOUND |
+			I915_SHRINK_UNBOUND |
+			I915_SHRINK_ACTIVE);
+	if (should_swap == i915_gem_object_has_pages(obj)) {
+		pr_err("unexpected pages mismatch, should_swap=%s\n",
+		       yesno(should_swap));
 		err = -EINVAL;
 		goto out_put;
 	}
 
-	if (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys) {
-		pr_err("residual page-size bits left\n");
+	if (should_swap == (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys)) {
+		pr_err("unexpected residual page-size bits, should_swap=%s\n",
+		       yesno(should_swap));
 		err = -EINVAL;
 		goto out_put;
 	}
@@ -1688,11 +1704,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		goto out_file;
 	}
 
-	mutex_lock(&ctx->mutex);
-	vm = i915_gem_context_vm(ctx);
+	vm = ctx->vm;
 	if (vm)
 		WRITE_ONCE(vm->scrub_64K, true);
-	mutex_unlock(&ctx->mutex);
 
 	err = i915_subtests(tests, ctx);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 8eb5050f8cb3..b32f7fed2d9c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -27,12 +27,6 @@
 
 #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32))
 
-static inline struct i915_address_space *ctx_vm(struct i915_gem_context *ctx)
-{
-	/* single threaded, private ctx */
-	return rcu_dereference_protected(ctx->vm, true);
-}
-
 static int live_nop_switch(void *arg)
 {
 	const unsigned int nctx = 1024;
@@ -94,7 +88,7 @@ static int live_nop_switch(void *arg)
 			rq = i915_request_get(this);
 			i915_request_add(this);
 		}
-		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		if (i915_request_wait(rq, 0, HZ) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
 			intel_gt_set_wedged(&i915->gt);
 			i915_request_put(rq);
@@ -704,7 +698,7 @@ static int igt_ctx_exec(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name,
-				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       yesno(i915_gem_context_has_full_ppgtt(ctx)),
 				       err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
@@ -813,7 +807,7 @@ static int igt_shared_ctx_exec(void *arg)
 			struct i915_gem_context *ctx;
 			struct intel_context *ce;
 
-			ctx = kernel_context(i915, ctx_vm(parent));
+			ctx = kernel_context(i915, parent->vm);
 			if (IS_ERR(ctx)) {
 				err = PTR_ERR(ctx);
 				goto out_test;
@@ -823,7 +817,7 @@ static int igt_shared_ctx_exec(void *arg)
 			GEM_BUG_ON(IS_ERR(ce));
 
 			if (!obj) {
-				obj = create_test_object(ctx_vm(parent),
+				obj = create_test_object(parent->vm,
 							 file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
@@ -838,7 +832,7 @@ static int igt_shared_ctx_exec(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name,
-				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       yesno(i915_gem_context_has_full_ppgtt(ctx)),
 				       err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
@@ -1380,7 +1374,7 @@ static int igt_ctx_readonly(void *arg)
 		goto out_file;
 	}
 
-	vm = ctx_vm(ctx) ?: &i915->ggtt.alias->vm;
+	vm = ctx->vm ?: &i915->ggtt.alias->vm;
 	if (!vm || !vm->has_read_only) {
 		err = 0;
 		goto out_file;
@@ -1417,7 +1411,7 @@ static int igt_ctx_readonly(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       ce->engine->name,
-				       yesno(!!ctx_vm(ctx)),
+				       yesno(i915_gem_context_has_full_ppgtt(ctx)),
 				       err);
 				i915_gem_context_unlock_engines(ctx);
 				goto out_file;
@@ -1499,7 +1493,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 
 	GEM_BUG_ON(offset < I915_GTT_PAGE_SIZE);
 
-	err = check_scratch(ctx_vm(ctx), offset);
+	err = check_scratch(ctx->vm, offset);
 	if (err)
 		return err;
 
@@ -1528,7 +1522,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 
 	intel_gt_chipset_flush(engine->gt);
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
+	vm = i915_gem_context_get_eb_vm(ctx);
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
@@ -1596,7 +1590,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 
 	GEM_BUG_ON(offset < I915_GTT_PAGE_SIZE);
 
-	err = check_scratch(ctx_vm(ctx), offset);
+	err = check_scratch(ctx->vm, offset);
 	if (err)
 		return err;
 
@@ -1607,7 +1601,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	if (GRAPHICS_VER(i915) >= 8) {
 		const u32 GPR0 = engine->mmio_base + 0x600;
 
-		vm = i915_gem_context_get_vm_rcu(ctx);
+		vm = i915_gem_context_get_eb_vm(ctx);
 		vma = i915_vma_instance(obj, vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
@@ -1739,7 +1733,7 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
 	u32 *vaddr;
 	int err = 0;
 
-	vm = ctx_vm(ctx);
+	vm = ctx->vm;
 	if (!vm)
 		return -ENODEV;
 
@@ -1801,7 +1795,7 @@ static int igt_vm_isolation(void *arg)
 	}
 
 	/* We can only test vm isolation, if the vm are distinct */
-	if (ctx_vm(ctx_a) == ctx_vm(ctx_b))
+	if (ctx_a->vm == ctx_b->vm)
 		goto out_file;
 
 	/* Read the initial state of the scratch page */
@@ -1813,8 +1807,8 @@ static int igt_vm_isolation(void *arg)
 	if (err)
 		goto out_file;
 
-	vm_total = ctx_vm(ctx_a)->total;
-	GEM_BUG_ON(ctx_vm(ctx_b)->total != vm_total);
+	vm_total = ctx_a->vm->total;
+	GEM_BUG_ON(ctx_b->vm->total != vm_total);
 
 	count = 0;
 	num_engines = 0;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
deleted file mode 100644
index 16162fc2782d..000000000000
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ /dev/null
@@ -1,190 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2020 Intel Corporation
- */
-
-#include "i915_selftest.h"
-
-#include "gt/intel_engine_pm.h"
-#include "selftests/igt_flush_test.h"
-
-static u64 read_reloc(const u32 *map, int x, const u64 mask)
-{
-	u64 reloc;
-
-	memcpy(&reloc, &map[x], sizeof(reloc));
-	return reloc & mask;
-}
-
-static int __igt_gpu_reloc(struct i915_execbuffer *eb,
-			   struct drm_i915_gem_object *obj)
-{
-	const unsigned int offsets[] = { 8, 3, 0 };
-	const u64 mask =
-		GENMASK_ULL(eb->reloc_cache.use_64bit_reloc ? 63 : 31, 0);
-	const u32 *map = page_mask_bits(obj->mm.mapping);
-	struct i915_request *rq;
-	struct i915_vma *vma;
-	int err;
-	int i;
-
-	vma = i915_vma_instance(obj, eb->context->vm, NULL);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	err = i915_gem_object_lock(obj, &eb->ww);
-	if (err)
-		return err;
-
-	err = i915_vma_pin_ww(vma, &eb->ww, 0, 0, PIN_USER | PIN_HIGH);
-	if (err)
-		return err;
-
-	/* 8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
-	if (err <= 0)
-		goto reloc_err;
-
-	/* !8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1);
-	if (err <= 0)
-		goto reloc_err;
-
-	/* Skip to the end of the cmd page */
-	i = PAGE_SIZE / sizeof(u32) - 1;
-	i -= eb->reloc_cache.rq_size;
-	memset32(eb->reloc_cache.rq_cmd + eb->reloc_cache.rq_size,
-		 MI_NOOP, i);
-	eb->reloc_cache.rq_size += i;
-
-	/* Force next batch */
-	err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2);
-	if (err <= 0)
-		goto reloc_err;
-
-	GEM_BUG_ON(!eb->reloc_cache.rq);
-	rq = i915_request_get(eb->reloc_cache.rq);
-	reloc_gpu_flush(eb, &eb->reloc_cache);
-	GEM_BUG_ON(eb->reloc_cache.rq);
-
-	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
-	if (err) {
-		intel_gt_set_wedged(eb->engine->gt);
-		goto put_rq;
-	}
-
-	if (!i915_request_completed(rq)) {
-		pr_err("%s: did not wait for relocations!\n", eb->engine->name);
-		err = -EINVAL;
-		goto put_rq;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
-		u64 reloc = read_reloc(map, offsets[i], mask);
-
-		if (reloc != i) {
-			pr_err("%s[%d]: map[%d] %llx != %x\n",
-			       eb->engine->name, i, offsets[i], reloc, i);
-			err = -EINVAL;
-		}
-	}
-	if (err)
-		igt_hexdump(map, 4096);
-
-put_rq:
-	i915_request_put(rq);
-unpin_vma:
-	i915_vma_unpin(vma);
-	return err;
-
-reloc_err:
-	if (!err)
-		err = -EIO;
-	goto unpin_vma;
-}
-
-static int igt_gpu_reloc(void *arg)
-{
-	struct i915_execbuffer eb;
-	struct drm_i915_gem_object *scratch;
-	int err = 0;
-	u32 *map;
-
-	eb.i915 = arg;
-
-	scratch = i915_gem_object_create_internal(eb.i915, 4096);
-	if (IS_ERR(scratch))
-		return PTR_ERR(scratch);
-
-	map = i915_gem_object_pin_map_unlocked(scratch, I915_MAP_WC);
-	if (IS_ERR(map)) {
-		err = PTR_ERR(map);
-		goto err_scratch;
-	}
-
-	intel_gt_pm_get(&eb.i915->gt);
-
-	for_each_uabi_engine(eb.engine, eb.i915) {
-		if (intel_engine_requires_cmd_parser(eb.engine) ||
-		    intel_engine_using_cmd_parser(eb.engine))
-			continue;
-
-		reloc_cache_init(&eb.reloc_cache, eb.i915);
-		memset(map, POISON_INUSE, 4096);
-
-		intel_engine_pm_get(eb.engine);
-		eb.context = intel_context_create(eb.engine);
-		if (IS_ERR(eb.context)) {
-			err = PTR_ERR(eb.context);
-			goto err_pm;
-		}
-		eb.reloc_pool = NULL;
-		eb.reloc_context = NULL;
-
-		i915_gem_ww_ctx_init(&eb.ww, false);
-retry:
-		err = intel_context_pin_ww(eb.context, &eb.ww);
-		if (!err) {
-			err = __igt_gpu_reloc(&eb, scratch);
-
-			intel_context_unpin(eb.context);
-		}
-		if (err == -EDEADLK) {
-			err = i915_gem_ww_ctx_backoff(&eb.ww);
-			if (!err)
-				goto retry;
-		}
-		i915_gem_ww_ctx_fini(&eb.ww);
-
-		if (eb.reloc_pool)
-			intel_gt_buffer_pool_put(eb.reloc_pool);
-		if (eb.reloc_context)
-			intel_context_put(eb.reloc_context);
-
-		intel_context_put(eb.context);
-err_pm:
-		intel_engine_pm_put(eb.engine);
-		if (err)
-			break;
-	}
-
-	if (igt_flush_test(eb.i915))
-		err = -EIO;
-
-	intel_gt_pm_put(&eb.i915->gt);
-err_scratch:
-	i915_gem_object_put(scratch);
-	return err;
-}
-
-int i915_gem_execbuffer_live_selftests(struct drm_i915_private *i915)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(igt_gpu_reloc),
-	};
-
-	if (intel_gt_is_wedged(&i915->gt))
-		return 0;
-
-	return i915_live_subtests(tests, i915);
-}
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index fee070df1c97..067d68a6fe4c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -23,6 +23,7 @@ mock_context(struct drm_i915_private *i915,
 	kref_init(&ctx->ref);
 	INIT_LIST_HEAD(&ctx->link);
 	ctx->i915 = i915;
+	INIT_WORK(&ctx->release_work, i915_gem_context_release_work);
 
 	mutex_init(&ctx->mutex);
 
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
index d6f5836396f8..f6733f279890 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -309,13 +309,11 @@ static int frequency_show(struct seq_file *m, void *unused)
 		int max_freq;
 
 		rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
-		if (IS_GEN9_LP(i915)) {
-			rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);
+		rp_state_cap = intel_rps_read_state_cap(rps);
+		if (IS_GEN9_LP(i915))
 			gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
-		} else {
-			rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+		else
 			gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS);
-		}
 
 		/* RPSTAT1 is in the GT power well */
 		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 6e0e52eeb87a..6a5af995f5b1 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -548,6 +548,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 					      I915_GTT_PAGE_SIZE_2M)))) {
 			vaddr = px_vaddr(pd);
 			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
+			clflush_cache_range(vaddr, PAGE_SIZE);
 			page_size = I915_GTT_PAGE_SIZE_64K;
 
 			/*
@@ -568,6 +569,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				for (i = 1; i < index; i += 16)
 					memset64(vaddr + i, encode, 15);
 
+				clflush_cache_range(vaddr, PAGE_SIZE);
 			}
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 17ca4dc4d0cb..c35c151f652f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -395,19 +395,18 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 
 	spin_lock_init(&ce->guc_state.lock);
 	INIT_LIST_HEAD(&ce->guc_state.fences);
+	INIT_LIST_HEAD(&ce->guc_state.requests);
 
-	spin_lock_init(&ce->guc_active.lock);
-	INIT_LIST_HEAD(&ce->guc_active.requests);
-
-	ce->guc_id = GUC_INVALID_LRC_ID;
-	INIT_LIST_HEAD(&ce->guc_id_link);
+	ce->guc_id.id = GUC_INVALID_LRC_ID;
+	INIT_LIST_HEAD(&ce->guc_id.link);
 
 	/*
 	 * Initialize fence to be complete as this is expected to be complete
 	 * unless there is a pending schedule disable outstanding.
 	 */
-	i915_sw_fence_init(&ce->guc_blocked, sw_fence_dummy_notify);
-	i915_sw_fence_commit(&ce->guc_blocked);
+	i915_sw_fence_init(&ce->guc_state.blocked,
+			   sw_fence_dummy_notify);
+	i915_sw_fence_commit(&ce->guc_state.blocked);
 
 	i915_active_init(&ce->active,
 			 __intel_context_active, __intel_context_retire, 0);
@@ -421,7 +420,6 @@ void intel_context_fini(struct intel_context *ce)
 
 	mutex_destroy(&ce->pin_mutex);
 	i915_active_fini(&ce->active);
-	i915_sw_fence_fini(&ce->guc_blocked);
 }
 
 void i915_context_module_exit(void)
@@ -522,15 +520,15 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 
 	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
 
-	spin_lock_irqsave(&ce->guc_active.lock, flags);
-	list_for_each_entry_reverse(rq, &ce->guc_active.requests,
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	list_for_each_entry_reverse(rq, &ce->guc_state.requests,
 				    sched.link) {
 		if (i915_request_completed(rq))
 			break;
 
 		active = rq;
 	}
-	spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
 	return active;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index e54351a170e2..930569a1a01f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -112,6 +112,7 @@ struct intel_context {
 #define CONTEXT_FORCE_SINGLE_SUBMISSION	7
 #define CONTEXT_NOPREEMPT		8
 #define CONTEXT_LRCA_DIRTY		9
+#define CONTEXT_GUC_INIT		10
 
 	struct {
 		u64 timeout_us;
@@ -155,49 +156,72 @@ struct intel_context {
 	u8 wa_bb_page; /* if set, page num reserved for context workarounds */
 
 	struct {
-		/** lock: protects everything in guc_state */
+		/** @lock: protects everything in guc_state */
 		spinlock_t lock;
 		/**
-		 * sched_state: scheduling state of this context using GuC
+		 * @sched_state: scheduling state of this context using GuC
 		 * submission
 		 */
-		u16 sched_state;
+		u32 sched_state;
 		/*
-		 * fences: maintains of list of requests that have a submit
-		 * fence related to GuC submission
+		 * @fences: maintains a list of requests that are currently
+		 * being fenced until a GuC operation completes
 		 */
 		struct list_head fences;
+		/**
+		 * @blocked: fence used to signal when the blocking of a
+		 * context's submissions is complete.
+		 */
+		struct i915_sw_fence blocked;
+		/** @number_committed_requests: number of committed requests */
+		int number_committed_requests;
+		/** @requests: list of active requests on this context */
+		struct list_head requests;
+		/** @prio: the context's current guc priority */
+		u8 prio;
+		/**
+		 * @prio_count: a counter of the number requests in flight in
+		 * each priority bucket
+		 */
+		u32 prio_count[GUC_CLIENT_PRIORITY_NUM];
 	} guc_state;
 
 	struct {
-		/** lock: protects everything in guc_active */
-		spinlock_t lock;
-		/** requests: active requests on this context */
-		struct list_head requests;
-	} guc_active;
+		/**
+		 * @id: handle which is used to uniquely identify this context
+		 * with the GuC, protected by guc->contexts_lock
+		 */
+		u16 id;
+		/**
+		 * @ref: the number of references to the guc_id, when
+		 * transitioning in and out of zero protected by
+		 * guc->contexts_lock
+		 */
+		atomic_t ref;
+		/**
+		 * @link: in guc->guc_id_list when the guc_id has no refs but is
+		 * still valid, protected by guc->contexts_lock
+		 */
+		struct list_head link;
+	} guc_id;
 
-	/* GuC scheduling state flags that do not require a lock. */
-	atomic_t guc_sched_state_no_lock;
-
-	/* GuC LRC descriptor ID */
-	u16 guc_id;
-
-	/* GuC LRC descriptor reference count */
-	atomic_t guc_id_ref;
-
-	/*
-	 * GuC ID link - in list when unpinned but guc_id still valid in GuC
+#ifdef CONFIG_DRM_I915_SELFTEST
+	/**
+	 * @drop_schedule_enable: Force drop of schedule enable G2H for selftest
 	 */
-	struct list_head guc_id_link;
+	bool drop_schedule_enable;
 
-	/* GuC context blocked fence */
-	struct i915_sw_fence guc_blocked;
-
-	/*
-	 * GuC priority management
+	/**
+	 * @drop_schedule_disable: Force drop of schedule disable G2H for
+	 * selftest
 	 */
-	u8 guc_prio;
-	u32 guc_prio_count[GUC_CLIENT_PRIORITY_NUM];
+	bool drop_schedule_disable;
+
+	/**
+	 * @drop_deregister: Force drop of deregister G2H for selftest
+	 */
+	bool drop_deregister;
+#endif
 };
 
 #endif /* __INTEL_CONTEXT_TYPES__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 0d9105a31d84..332efea696a5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1163,16 +1163,16 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 	u32 mmio_base = engine->mmio_base;
 	int slice;
 	int subslice;
+	int iter;
 
 	memset(instdone, 0, sizeof(*instdone));
 
-	switch (GRAPHICS_VER(i915)) {
-	default:
+	if (GRAPHICS_VER(i915) >= 8) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
 		if (engine->id != RCS0)
-			break;
+			return;
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1182,21 +1182,39 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			instdone->slice_common_extra[1] =
 				intel_uncore_read(uncore, GEN12_SC_INSTDONE_EXTRA2);
 		}
-		for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
-			instdone->sampler[slice][subslice] =
-				read_subslice_reg(engine, slice, subslice,
-						  GEN7_SAMPLER_INSTDONE);
-			instdone->row[slice][subslice] =
-				read_subslice_reg(engine, slice, subslice,
-						  GEN7_ROW_INSTDONE);
+
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
+				instdone->sampler[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_SAMPLER_INSTDONE);
+				instdone->row[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_ROW_INSTDONE);
+			}
+		} else {
+			for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
+				instdone->sampler[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_SAMPLER_INSTDONE);
+				instdone->row[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_ROW_INSTDONE);
+			}
 		}
-		break;
-	case 7:
+
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
+			for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice)
+				instdone->geom_svg[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  XEHPG_INSTDONE_GEOM_SVG);
+		}
+	} else if (GRAPHICS_VER(i915) >= 7) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
 		if (engine->id != RCS0)
-			break;
+			return;
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1204,22 +1222,15 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			intel_uncore_read(uncore, GEN7_SAMPLER_INSTDONE);
 		instdone->row[0][0] =
 			intel_uncore_read(uncore, GEN7_ROW_INSTDONE);
-
-		break;
-	case 6:
-	case 5:
-	case 4:
+	} else if (GRAPHICS_VER(i915) >= 4) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 		if (engine->id == RCS0)
 			/* HACK: Using the wrong struct member */
 			instdone->slice_common =
 				intel_uncore_read(uncore, GEN4_INSTDONE1);
-		break;
-	case 3:
-	case 2:
+	} else {
 		instdone->instdone = intel_uncore_read(uncore, GEN2_INSTDONE);
-		break;
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index ed91bcff20eb..bfbfe53c23dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -67,8 +67,11 @@ struct intel_instdone {
 	/* The following exist only in the RCS engine */
 	u32 slice_common;
 	u32 slice_common_extra[2];
-	u32 sampler[I915_MAX_SLICES][I915_MAX_SUBSLICES];
-	u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES];
+	u32 sampler[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
+	u32 row[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
+
+	/* Added in XeHPG */
+	u32 geom_svg[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
 };
 
 /*
@@ -578,4 +581,12 @@ intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
 		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
 			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
 						    subslice_)))
+
+#define for_each_instdone_gslice_dss_xehp(dev_priv_, sseu_, iter_, gslice_, dss_) \
+	for ((iter_) = 0, (gslice_) = 0, (dss_) = 0; \
+	     (iter_) < GEN_MAX_SUBSLICES; \
+	     (iter_)++, (gslice_) = (iter_) / GEN_DSS_PER_GSLICE, \
+	     (dss_) = (iter_) % GEN_DSS_PER_GSLICE) \
+		for_each_if(intel_sseu_has_subslice((sseu_), 0, (iter_)))
+
 #endif /* __INTEL_ENGINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index de5f9c86b9a4..87c595e4efe2 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2140,10 +2140,6 @@ static void __execlists_unhold(struct i915_request *rq)
 			if (p->flags & I915_DEPENDENCY_WEAK)
 				continue;
 
-			/* Propagate any change in error status */
-			if (rq->fence.error)
-				i915_request_set_error_once(w, rq->fence.error);
-
 			if (w->engine != rq->engine)
 				continue;
 
@@ -2565,7 +2561,7 @@ __execlists_context_pre_pin(struct intel_context *ce,
 	if (!__test_and_set_bit(CONTEXT_INIT_BIT, &ce->flags)) {
 		lrc_init_state(ce, engine, *vaddr);
 
-		 __i915_gem_object_flush_map(ce->state->obj, 0, engine->context_size);
+		__i915_gem_object_flush_map(ce->state->obj, 0, engine->context_size);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index de3ac58fceec..8d71f67926f1 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -727,7 +727,6 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 
 	atomic_set(&ggtt->vm.open, 0);
 
-	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
 	flush_workqueue(ggtt->vm.i915->wq);
 
 	mutex_lock(&ggtt->vm.mutex);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 62d40c986642..2aeaae036a6f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -682,6 +682,8 @@ int intel_gt_init(struct intel_gt *gt)
 		goto err_pm;
 	}
 
+	set_mocs_index(gt);
+
 	err = intel_engines_init(gt);
 	if (err)
 		goto err_engines;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index a81e21bf1bd1..6fdcde64c180 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -192,6 +192,10 @@ struct intel_gt {
 
 		unsigned long mslice_mask;
 	} info;
+
+	struct {
+		u8 uc_index;
+	} mocs;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index e137dd32b5b8..a0c2b952aa57 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -155,7 +155,7 @@ void i915_vm_resv_release(struct kref *kref)
 static void __i915_vm_release(struct work_struct *work)
 {
 	struct i915_address_space *vm =
-		container_of(work, struct i915_address_space, rcu.work);
+		container_of(work, struct i915_address_space, release_work);
 
 	vm->cleanup(vm);
 	i915_address_space_fini(vm);
@@ -171,7 +171,7 @@ void i915_vm_release(struct kref *kref)
 	GEM_BUG_ON(i915_is_ggtt(vm));
 	trace_i915_ppgtt_release(vm);
 
-	queue_rcu_work(vm->i915->wq, &vm->rcu);
+	queue_work(vm->i915->wq, &vm->release_work);
 }
 
 void i915_address_space_init(struct i915_address_space *vm, int subclass)
@@ -185,7 +185,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 	if (!kref_read(&vm->resv_ref))
 		kref_init(&vm->resv_ref);
 
-	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
+	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 bc7153018ebd..5b539bd7645d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -213,7 +213,7 @@ struct i915_vma_ops {
 
 struct i915_address_space {
 	struct kref ref;
-	struct rcu_work rcu;
+	struct work_struct release_work;
 
 	struct drm_mm mm;
 	struct intel_gt *gt;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bb4af4977920..6ba8daea2f56 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -226,6 +226,40 @@ static const u8 gen12_xcs_offsets[] = {
 	END
 };
 
+static const u8 dg2_xcs_offsets[] = {
+	NOP(1),
+	LRI(15, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+	REG(0x120),
+	REG(0x124),
+
+	NOP(1),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	END
+};
+
 static const u8 gen8_rcs_offsets[] = {
 	NOP(1),
 	LRI(14, POSTED),
@@ -525,6 +559,49 @@ static const u8 xehp_rcs_offsets[] = {
 	END
 };
 
+static const u8 dg2_rcs_offsets[] = {
+	NOP(1),
+	LRI(15, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+	REG(0x120),
+	REG(0x124),
+
+	NOP(1),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	LRI(3, POSTED),
+	REG(0x1b0),
+	REG16(0x5a8),
+	REG16(0x5ac),
+
+	NOP(6),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END
+};
+
 #undef END
 #undef REG16
 #undef REG
@@ -543,7 +620,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		   !intel_engine_has_relative_mmio(engine));
 
 	if (engine->class == RENDER_CLASS) {
-		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+			return dg2_rcs_offsets;
+		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
 			return xehp_rcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_rcs_offsets;
@@ -554,7 +633,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		else
 			return gen8_rcs_offsets;
 	} else {
-		if (GRAPHICS_VER(engine->i915) >= 12)
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+			return dg2_xcs_offsets;
+		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_xcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 9)
 			return gen9_xcs_offsets;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 582c4423b95d..e4b97cd14cf9 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -22,6 +22,8 @@ struct drm_i915_mocs_table {
 	unsigned int size;
 	unsigned int n_entries;
 	const struct drm_i915_mocs_entry *table;
+	u8 uc_index;
+	u8 unused_entries_index;
 };
 
 /* Defines for the tables (XXX_MOCS_0 - XXX_MOCS_63) */
@@ -40,6 +42,8 @@ struct drm_i915_mocs_table {
 #define L3_ESC(value)		((value) << 0)
 #define L3_SCC(value)		((value) << 1)
 #define _L3_CACHEABILITY(value)	((value) << 4)
+#define L3_GLBGO(value)		((value) << 6)
+#define L3_LKUP(value)		((value) << 7)
 
 /* Helper defines */
 #define GEN9_NUM_MOCS_ENTRIES	64  /* 63-64 are reserved, but configured. */
@@ -88,18 +92,25 @@ struct drm_i915_mocs_table {
  *
  * Entries not part of the following tables are undefined as far as
  * userspace is concerned and shouldn't be relied upon.  For Gen < 12
- * they will be initialized to PTE. Gen >= 12 onwards don't have a setting for
- * PTE and will be initialized to an invalid value.
+ * they will be initialized to PTE. Gen >= 12 don't have a setting for
+ * PTE and those platforms except TGL/RKL will be initialized L3 WB to
+ * catch accidental use of reserved and unused mocs indexes.
  *
  * The last few entries are reserved by the hardware. For ICL+ they
  * should be initialized according to bspec and never used, for older
  * platforms they should never be written to.
  *
- * NOTE: These tables are part of bspec and defined as part of hardware
+ * NOTE1: These tables are part of bspec and defined as part of hardware
  *       interface for ICL+. For older platforms, they are part of kernel
  *       ABI. It is expected that, for specific hardware platform, existing
  *       entries will remain constant and the table will only be updated by
  *       adding new entries, filling unused positions.
+ *
+ * NOTE2: For GEN >= 12 except TGL and RKL, reserved and unspecified MOCS
+ *       indices have been set to L3 WB. These reserved entries should never
+ *       be used, they may be changed to low performant variants with better
+ *       coherency in the future if more entries are needed.
+ *       For TGL/RKL, all the unspecified MOCS indexes are mapped to L3 UC.
  */
 #define GEN9_MOCS_ENTRIES \
 	MOCS_ENTRY(I915_MOCS_UNCACHED, \
@@ -282,17 +293,9 @@ static const struct drm_i915_mocs_entry icl_mocs_table[] = {
 };
 
 static const struct drm_i915_mocs_entry dg1_mocs_table[] = {
-	/* Error */
-	MOCS_ENTRY(0, 0, L3_0_DIRECT),
 
 	/* UC */
 	MOCS_ENTRY(1, 0, L3_1_UC),
-
-	/* Reserved */
-	MOCS_ENTRY(2, 0, L3_0_DIRECT),
-	MOCS_ENTRY(3, 0, L3_0_DIRECT),
-	MOCS_ENTRY(4, 0, L3_0_DIRECT),
-
 	/* WB - L3 */
 	MOCS_ENTRY(5, 0, L3_3_WB),
 	/* WB - L3 50% */
@@ -314,6 +317,83 @@ static const struct drm_i915_mocs_entry dg1_mocs_table[] = {
 	MOCS_ENTRY(63, 0, L3_1_UC),
 };
 
+static const struct drm_i915_mocs_entry gen12_mocs_table[] = {
+	GEN11_MOCS_ENTRIES,
+	/* Implicitly enable L1 - HDC:L1 + L3 + LLC */
+	MOCS_ENTRY(48,
+		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+		   L3_3_WB),
+	/* Implicitly enable L1 - HDC:L1 + L3 */
+	MOCS_ENTRY(49,
+		   LE_1_UC | LE_TC_1_LLC,
+		   L3_3_WB),
+	/* Implicitly enable L1 - HDC:L1 + LLC */
+	MOCS_ENTRY(50,
+		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+		   L3_1_UC),
+	/* Implicitly enable L1 - HDC:L1 */
+	MOCS_ENTRY(51,
+		   LE_1_UC | LE_TC_1_LLC,
+		   L3_1_UC),
+	/* HW Special Case (CCS) */
+	MOCS_ENTRY(60,
+		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+		   L3_1_UC),
+	/* HW Special Case (Displayable) */
+	MOCS_ENTRY(61,
+		   LE_1_UC | LE_TC_1_LLC,
+		   L3_3_WB),
+};
+
+static const struct drm_i915_mocs_entry xehpsdv_mocs_table[] = {
+	/* wa_1608975824 */
+	MOCS_ENTRY(0, 0, L3_3_WB | L3_LKUP(1)),
+
+	/* UC - Coherent; GO:L3 */
+	MOCS_ENTRY(1, 0, L3_1_UC | L3_LKUP(1)),
+	/* UC - Coherent; GO:Memory */
+	MOCS_ENTRY(2, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)),
+	/* UC - Non-Coherent; GO:Memory */
+	MOCS_ENTRY(3, 0, L3_1_UC | L3_GLBGO(1)),
+	/* UC - Non-Coherent; GO:L3 */
+	MOCS_ENTRY(4, 0, L3_1_UC),
+
+	/* WB */
+	MOCS_ENTRY(5, 0, L3_3_WB | L3_LKUP(1)),
+
+	/* HW Reserved - SW program but never use. */
+	MOCS_ENTRY(48, 0, L3_3_WB | L3_LKUP(1)),
+	MOCS_ENTRY(49, 0, L3_1_UC | L3_LKUP(1)),
+	MOCS_ENTRY(60, 0, L3_1_UC),
+	MOCS_ENTRY(61, 0, L3_1_UC),
+	MOCS_ENTRY(62, 0, L3_1_UC),
+	MOCS_ENTRY(63, 0, L3_1_UC),
+};
+
+static const struct drm_i915_mocs_entry dg2_mocs_table[] = {
+	/* UC - Coherent; GO:L3 */
+	MOCS_ENTRY(0, 0, L3_1_UC | L3_LKUP(1)),
+	/* UC - Coherent; GO:Memory */
+	MOCS_ENTRY(1, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)),
+	/* UC - Non-Coherent; GO:Memory */
+	MOCS_ENTRY(2, 0, L3_1_UC | L3_GLBGO(1)),
+
+	/* WB - LC */
+	MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)),
+};
+
+static const struct drm_i915_mocs_entry dg2_mocs_table_g10_ax[] = {
+	/* Wa_14011441408: Set Go to Memory for MOCS#0 */
+	MOCS_ENTRY(0, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)),
+	/* UC - Coherent; GO:Memory */
+	MOCS_ENTRY(1, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)),
+	/* UC - Non-Coherent; GO:Memory */
+	MOCS_ENTRY(2, 0, L3_1_UC | L3_GLBGO(1)),
+
+	/* WB - LC */
+	MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)),
+};
+
 enum {
 	HAS_GLOBAL_MOCS = BIT(0),
 	HAS_ENGINE_MOCS = BIT(1),
@@ -340,14 +420,45 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
 {
 	unsigned int flags;
 
-	if (IS_DG1(i915)) {
+	memset(table, 0, sizeof(struct drm_i915_mocs_table));
+
+	table->unused_entries_index = I915_MOCS_PTE;
+	if (IS_DG2(i915)) {
+		if (IS_DG2_GT_STEP(i915, G10, STEP_A0, STEP_B0)) {
+			table->size = ARRAY_SIZE(dg2_mocs_table_g10_ax);
+			table->table = dg2_mocs_table_g10_ax;
+		} else {
+			table->size = ARRAY_SIZE(dg2_mocs_table);
+			table->table = dg2_mocs_table;
+		}
+		table->uc_index = 1;
+		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
+		table->unused_entries_index = 3;
+	} else if (IS_XEHPSDV(i915)) {
+		table->size = ARRAY_SIZE(xehpsdv_mocs_table);
+		table->table = xehpsdv_mocs_table;
+		table->uc_index = 2;
+		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
+		table->unused_entries_index = 5;
+	} else if (IS_DG1(i915)) {
 		table->size = ARRAY_SIZE(dg1_mocs_table);
 		table->table = dg1_mocs_table;
+		table->uc_index = 1;
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
-	} else if (GRAPHICS_VER(i915) >= 12) {
+		table->uc_index = 1;
+		table->unused_entries_index = 5;
+	} else if (IS_TIGERLAKE(i915) || IS_ROCKETLAKE(i915)) {
+		/* For TGL/RKL, Can't be changed now for ABI reasons */
 		table->size  = ARRAY_SIZE(tgl_mocs_table);
 		table->table = tgl_mocs_table;
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
+		table->uc_index = 3;
+	} else if (GRAPHICS_VER(i915) >= 12) {
+		table->size  = ARRAY_SIZE(gen12_mocs_table);
+		table->table = gen12_mocs_table;
+		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
+		table->uc_index = 3;
+		table->unused_entries_index = 2;
 	} else if (GRAPHICS_VER(i915) == 11) {
 		table->size  = ARRAY_SIZE(icl_mocs_table);
 		table->table = icl_mocs_table;
@@ -393,16 +504,16 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
 }
 
 /*
- * Get control_value from MOCS entry taking into account when it's not used:
- * I915_MOCS_PTE's value is returned in this case.
+ * Get control_value from MOCS entry taking into account when it's not used
+ * then if unused_entries_index is non-zero then its value will be returned
+ * otherwise I915_MOCS_PTE's value is returned in this case.
  */
 static u32 get_entry_control(const struct drm_i915_mocs_table *table,
 			     unsigned int index)
 {
 	if (index < table->size && table->table[index].used)
 		return table->table[index].control_value;
-
-	return table->table[I915_MOCS_PTE].control_value;
+	return table->table[table->unused_entries_index].control_value;
 }
 
 #define for_each_mocs(mocs, t, i) \
@@ -417,6 +528,8 @@ static void __init_mocs_table(struct intel_uncore *uncore,
 	unsigned int i;
 	u32 mocs;
 
+	drm_WARN_ONCE(&uncore->i915->drm, !table->unused_entries_index,
+		      "Unused entries index should have been defined\n");
 	for_each_mocs(mocs, table, i)
 		intel_uncore_write_fw(uncore, _MMIO(addr + i * 4), mocs);
 }
@@ -443,16 +556,16 @@ static void init_mocs_table(struct intel_engine_cs *engine,
 }
 
 /*
- * Get l3cc_value from MOCS entry taking into account when it's not used:
- * I915_MOCS_PTE's value is returned in this case.
+ * Get l3cc_value from MOCS entry taking into account when it's not used
+ * then if unused_entries_index is not zero then its value will be returned
+ * otherwise I915_MOCS_PTE's value is returned in this case.
  */
 static u16 get_entry_l3cc(const struct drm_i915_mocs_table *table,
 			  unsigned int index)
 {
 	if (index < table->size && table->table[index].used)
 		return table->table[index].l3cc_value;
-
-	return table->table[I915_MOCS_PTE].l3cc_value;
+	return table->table[table->unused_entries_index].l3cc_value;
 }
 
 static u32 l3cc_combine(u16 low, u16 high)
@@ -468,10 +581,9 @@ static u32 l3cc_combine(u16 low, u16 high)
 	     0; \
 	     i++)
 
-static void init_l3cc_table(struct intel_engine_cs *engine,
+static void init_l3cc_table(struct intel_uncore *uncore,
 			    const struct drm_i915_mocs_table *table)
 {
-	struct intel_uncore *uncore = engine->uncore;
 	unsigned int i;
 	u32 l3cc;
 
@@ -496,7 +608,7 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
 		init_mocs_table(engine, &table);
 
 	if (flags & HAS_RENDER_L3CC && engine->class == RENDER_CLASS)
-		init_l3cc_table(engine, &table);
+		init_l3cc_table(engine->uncore, &table);
 }
 
 static u32 global_mocs_offset(void)
@@ -504,6 +616,14 @@ static u32 global_mocs_offset(void)
 	return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
 }
 
+void set_mocs_index(struct intel_gt *gt)
+{
+	struct drm_i915_mocs_table table;
+
+	get_mocs_settings(gt->i915, &table);
+	gt->mocs.uc_index = table.uc_index;
+}
+
 void intel_mocs_init(struct intel_gt *gt)
 {
 	struct drm_i915_mocs_table table;
@@ -515,6 +635,14 @@ void intel_mocs_init(struct intel_gt *gt)
 	flags = get_mocs_settings(gt->i915, &table);
 	if (flags & HAS_GLOBAL_MOCS)
 		__init_mocs_table(gt->uncore, &table, global_mocs_offset());
+
+	/*
+	 * Initialize the L3CC table as part of mocs initalization to make
+	 * sure the LNCFCMOCSx registers are programmed for the subsequent
+	 * memory transactions including guc transactions
+	 */
+	if (flags & HAS_RENDER_L3CC)
+		init_l3cc_table(gt->uncore, &table);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.h b/drivers/gpu/drm/i915/gt/intel_mocs.h
index d83274f5163b..8a09d64b115f 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.h
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.h
@@ -36,5 +36,6 @@ struct intel_gt;
 
 void intel_mocs_init(struct intel_gt *gt);
 void intel_mocs_init_engine(struct intel_engine_cs *engine);
+void set_mocs_index(struct intel_gt *gt);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 2958e2fae380..3c65efcb7bed 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -1265,7 +1265,7 @@ static struct i915_vma *gen7_ctx_vma(struct intel_engine_cs *engine)
 	int size, err;
 
 	if (GRAPHICS_VER(engine->i915) != 7 || engine->class != RENDER_CLASS)
-		return 0;
+		return NULL;
 
 	err = gen7_ctx_switch_bb_setup(engine, NULL /* probe size */);
 	if (err < 0)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 0a03fbed9f9b..172de6c9f949 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -994,20 +994,16 @@ int intel_rps_set(struct intel_rps *rps, u8 val)
 static void gen6_rps_init(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
-	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 rp_state_cap = intel_rps_read_state_cap(rps);
 
 	/* All of these values are in units of 50MHz */
 
 	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
 	if (IS_GEN9_LP(i915)) {
-		u32 rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);
-
 		rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
 		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
 		rps->min_freq = (rp_state_cap >>  0) & 0xff;
 	} else {
-		u32 rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
-
 		rps->rp0_freq = (rp_state_cap >>  0) & 0xff;
 		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
 		rps->min_freq = (rp_state_cap >> 16) & 0xff;
@@ -2144,6 +2140,19 @@ int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val)
 		return set_min_freq(rps, val);
 }
 
+u32 intel_rps_read_state_cap(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	if (IS_XEHPSDV(i915))
+		return intel_uncore_read(uncore, XEHPSDV_RP_STATE_CAP);
+	else if (IS_GEN9_LP(i915))
+		return intel_uncore_read(uncore, BXT_RP_STATE_CAP);
+	else
+		return intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+}
+
 /* External interface for intel_ips.ko */
 
 static struct drm_i915_private __rcu *ips_mchdev;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 4213bcce1667..11960d64ca82 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -41,6 +41,7 @@ u32 intel_rps_get_rp1_frequency(struct intel_rps *rps);
 u32 intel_rps_get_rpn_frequency(struct intel_rps *rps);
 u32 intel_rps_read_punit_req(struct intel_rps *rps);
 u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps);
+u32 intel_rps_read_state_cap(struct intel_rps *rps);
 
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index bbd272943c3f..b0e09b58005e 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -46,11 +46,11 @@ u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
 }
 
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
-			      u32 ss_mask)
+			      u8 *subslice_mask, u32 ss_mask)
 {
 	int offset = slice * sseu->ss_stride;
 
-	memcpy(&sseu->subslice_mask[offset], &ss_mask, sseu->ss_stride);
+	memcpy(&subslice_mask[offset], &ss_mask, sseu->ss_stride);
 }
 
 unsigned int
@@ -100,14 +100,24 @@ static u16 compute_eu_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
-static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
-				    u8 s_en, u32 ss_en, u16 eu_en)
+static u32 get_ss_stride_mask(struct sseu_dev_info *sseu, u8 s, u32 ss_en)
+{
+	u32 ss_mask;
+
+	ss_mask = ss_en >> (s * sseu->max_subslices);
+	ss_mask &= GENMASK(sseu->max_subslices - 1, 0);
+
+	return ss_mask;
+}
+
+static void gen11_compute_sseu_info(struct sseu_dev_info *sseu, u8 s_en,
+				    u32 g_ss_en, u32 c_ss_en, u16 eu_en)
 {
 	int s, ss;
 
-	/* ss_en represents entire subslice mask across all slices */
+	/* g_ss_en/c_ss_en represent entire subslice mask across all slices */
 	GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
-		   sizeof(ss_en) * BITS_PER_BYTE);
+		   sizeof(g_ss_en) * BITS_PER_BYTE);
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		if ((s_en & BIT(s)) == 0)
@@ -115,7 +125,22 @@ static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
 
 		sseu->slice_mask |= BIT(s);
 
-		intel_sseu_set_subslices(sseu, s, ss_en);
+		/*
+		 * XeHP introduces the concept of compute vs geometry DSS. To
+		 * reduce variation between GENs around subslice usage, store a
+		 * mask for both the geometry and compute enabled masks since
+		 * userspace will need to be able to query these masks
+		 * independently.  Also compute a total enabled subslice count
+		 * for the purposes of selecting subslices to use in a
+		 * particular GEM context.
+		 */
+		intel_sseu_set_subslices(sseu, s, sseu->compute_subslice_mask,
+					 get_ss_stride_mask(sseu, s, c_ss_en));
+		intel_sseu_set_subslices(sseu, s, sseu->geometry_subslice_mask,
+					 get_ss_stride_mask(sseu, s, g_ss_en));
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 get_ss_stride_mask(sseu, s,
+							    g_ss_en | c_ss_en));
 
 		for (ss = 0; ss < sseu->max_subslices; ss++)
 			if (intel_sseu_has_subslice(sseu, s, ss))
@@ -129,7 +154,7 @@ static void gen12_sseu_info_init(struct intel_gt *gt)
 {
 	struct sseu_dev_info *sseu = &gt->info.sseu;
 	struct intel_uncore *uncore = gt->uncore;
-	u32 dss_en;
+	u32 g_dss_en, c_dss_en = 0;
 	u16 eu_en = 0;
 	u8 eu_en_fuse;
 	u8 s_en;
@@ -160,7 +185,9 @@ static void gen12_sseu_info_init(struct intel_gt *gt)
 		s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
 		       GEN11_GT_S_ENA_MASK;
 
-	dss_en = intel_uncore_read(uncore, GEN12_GT_DSS_ENABLE);
+	g_dss_en = intel_uncore_read(uncore, GEN12_GT_GEOMETRY_DSS_ENABLE);
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+		c_dss_en = intel_uncore_read(uncore, GEN12_GT_COMPUTE_DSS_ENABLE);
 
 	/* one bit per pair of EUs */
 	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
@@ -173,7 +200,7 @@ static void gen12_sseu_info_init(struct intel_gt *gt)
 		if (eu_en_fuse & BIT(eu))
 			eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
 
-	gen11_compute_sseu_info(sseu, s_en, dss_en, eu_en);
+	gen11_compute_sseu_info(sseu, s_en, g_dss_en, c_dss_en, eu_en);
 
 	/* TGL only supports slice-level power gating */
 	sseu->has_slice_pg = 1;
@@ -199,7 +226,7 @@ static void gen11_sseu_info_init(struct intel_gt *gt)
 	eu_en = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
 		  GEN11_EU_DIS_MASK);
 
-	gen11_compute_sseu_info(sseu, s_en, ss_en, eu_en);
+	gen11_compute_sseu_info(sseu, s_en, ss_en, 0, eu_en);
 
 	/* ICL has no power gating restrictions. */
 	sseu->has_slice_pg = 1;
@@ -240,7 +267,7 @@ static void cherryview_sseu_info_init(struct intel_gt *gt)
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
-	intel_sseu_set_subslices(sseu, 0, subslice_mask);
+	intel_sseu_set_subslices(sseu, 0, sseu->subslice_mask, subslice_mask);
 
 	sseu->eu_total = compute_eu_total(sseu);
 
@@ -296,7 +323,8 @@ static void gen9_sseu_info_init(struct intel_gt *gt)
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		eu_disable = intel_uncore_read(uncore, GEN9_EU_DISABLE(s));
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
@@ -408,7 +436,8 @@ static void bdw_sseu_info_init(struct intel_gt *gt)
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u8 eu_disabled_mask;
@@ -506,7 +535,8 @@ static void hsw_sseu_info_init(struct intel_gt *gt)
 			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
+					 subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 22fef98887c0..60882a74741e 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -26,9 +26,14 @@ struct drm_printer;
 #define GEN_DSS_PER_CSLICE	8
 #define GEN_DSS_PER_MSLICE	8
 
+#define GEN_MAX_GSLICES		(GEN_MAX_SUBSLICES / GEN_DSS_PER_GSLICE)
+#define GEN_MAX_CSLICES		(GEN_MAX_SUBSLICES / GEN_DSS_PER_CSLICE)
+
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 geometry_subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 compute_subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
 	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES * GEN_MAX_EU_STRIDE];
 	u16 eu_total;
 	u8 eu_per_subslice;
@@ -78,6 +83,10 @@ intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
 	u8 mask;
 	int ss_idx = subslice / BITS_PER_BYTE;
 
+	if (slice >= sseu->max_slices ||
+	    subslice >= sseu->max_subslices)
+		return false;
+
 	GEM_BUG_ON(ss_idx >= sseu->ss_stride);
 
 	mask = sseu->subslice_mask[slice * sseu->ss_stride + ss_idx];
@@ -97,7 +106,7 @@ intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
 
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
-			      u32 ss_mask);
+			      u8 *subslice_mask, u32 ss_mask);
 
 void intel_sseu_info_init(struct intel_gt *gt);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index aae609d7d85d..c314d4917b6b 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -644,6 +644,72 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
 		     DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE);
 }
 
+static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
+					 struct i915_wa_list *wal)
+{
+	/*
+	 * This is a "fake" workaround defined by software to ensure we
+	 * maintain reliable, backward-compatible behavior for userspace with
+	 * regards to how nested MI_BATCH_BUFFER_START commands are handled.
+	 *
+	 * The per-context setting of MI_MODE[12] determines whether the bits
+	 * of a nested MI_BATCH_BUFFER_START instruction should be interpreted
+	 * in the traditional manner or whether they should instead use a new
+	 * tgl+ meaning that breaks backward compatibility, but allows nesting
+	 * into 3rd-level batchbuffers.  When this new capability was first
+	 * added in TGL, it remained off by default unless a context
+	 * intentionally opted in to the new behavior.  However Xe_HPG now
+	 * flips this on by default and requires that we explicitly opt out if
+	 * we don't want the new behavior.
+	 *
+	 * From a SW perspective, we want to maintain the backward-compatible
+	 * behavior for userspace, so we'll apply a fake workaround to set it
+	 * back to the legacy behavior on platforms where the hardware default
+	 * is to break compatibility.  At the moment there is no Linux
+	 * userspace that utilizes third-level batchbuffers, so this will avoid
+	 * userspace from needing to make any changes.  using the legacy
+	 * meaning is the correct thing to do.  If/when we have userspace
+	 * consumers that want to utilize third-level batch nesting, we can
+	 * provide a context parameter to allow them to opt-in.
+	 */
+	wa_masked_dis(wal, RING_MI_MODE(engine->mmio_base), TGL_NESTED_BB_EN);
+}
+
+static void gen12_ctx_gt_mocs_init(struct intel_engine_cs *engine,
+				   struct i915_wa_list *wal)
+{
+	u8 mocs;
+
+	/*
+	 * Some blitter commands do not have a field for MOCS, those
+	 * commands will use MOCS index pointed by BLIT_CCTL.
+	 * BLIT_CCTL registers are needed to be programmed to un-cached.
+	 */
+	if (engine->class == COPY_ENGINE_CLASS) {
+		mocs = engine->gt->mocs.uc_index;
+		wa_write_clr_set(wal,
+				 BLIT_CCTL(engine->mmio_base),
+				 BLIT_CCTL_MASK,
+				 BLIT_CCTL_MOCS(mocs, mocs));
+	}
+}
+
+/*
+ * gen12_ctx_gt_fake_wa_init() aren't programmingan official workaround
+ * defined by the hardware team, but it programming general context registers.
+ * Adding those context register programming in context workaround
+ * allow us to use the wa framework for proper application and validation.
+ */
+static void
+gen12_ctx_gt_fake_wa_init(struct intel_engine_cs *engine,
+			  struct i915_wa_list *wal)
+{
+	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+		fakewa_disable_nestedbb_mode(engine, wal);
+
+	gen12_ctx_gt_mocs_init(engine, wal);
+}
+
 static void
 __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 			   struct i915_wa_list *wal,
@@ -651,11 +717,19 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (engine->class != RENDER_CLASS)
-		return;
-
 	wa_init_start(wal, name, engine->name);
 
+	/* Applies to all engines */
+	/*
+	 * Fake workarounds are not the actual workaround but
+	 * programming of context registers using workaround framework.
+	 */
+	if (GRAPHICS_VER(i915) >= 12)
+		gen12_ctx_gt_fake_wa_init(engine, wal);
+
+	if (engine->class != RENDER_CLASS)
+		goto done;
+
 	if (IS_DG1(i915))
 		dg1_ctx_workarounds_init(engine, wal);
 	else if (GRAPHICS_VER(i915) == 12)
@@ -685,6 +759,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 	else
 		MISSING_CASE(GRAPHICS_VER(i915));
 
+done:
 	wa_init_finish(wal);
 }
 
@@ -1604,6 +1679,31 @@ void intel_engine_apply_whitelist(struct intel_engine_cs *engine)
 				   i915_mmio_reg_offset(RING_NOPID(base)));
 }
 
+/*
+ * engine_fake_wa_init(), a place holder to program the registers
+ * which are not part of an official workaround defined by the
+ * hardware team.
+ * Adding programming of those register inside workaround will
+ * allow utilizing wa framework to proper application and verification.
+ */
+static void
+engine_fake_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+	u8 mocs;
+
+	/*
+	 * RING_CMD_CCTL are need to be programed to un-cached
+	 * for memory writes and reads outputted by Command
+	 * Streamers on Gen12 onward platforms.
+	 */
+	if (GRAPHICS_VER(engine->i915) >= 12) {
+		mocs = engine->gt->mocs.uc_index;
+		wa_masked_field_set(wal,
+				    RING_CMD_CCTL(engine->mmio_base),
+				    CMD_CCTL_MOCS_MASK,
+				    CMD_CCTL_MOCS_OVERRIDE(mocs, mocs));
+	}
+}
 static void
 rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
@@ -2044,6 +2144,8 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
 	if (I915_SELFTEST_ONLY(GRAPHICS_VER(engine->i915) < 4))
 		return;
 
+	engine_fake_wa_init(engine, wal);
+
 	if (engine->class == RENDER_CLASS)
 		rcs_engine_wa_init(engine, wal);
 	else
@@ -2067,12 +2169,7 @@ void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
 	wa_list_apply(engine->gt, &engine->wa_list);
 }
 
-struct mcr_range {
-	u32 start;
-	u32 end;
-};
-
-static const struct mcr_range mcr_ranges_gen8[] = {
+static const struct i915_range mcr_ranges_gen8[] = {
 	{ .start = 0x5500, .end = 0x55ff },
 	{ .start = 0x7000, .end = 0x7fff },
 	{ .start = 0x9400, .end = 0x97ff },
@@ -2081,7 +2178,7 @@ static const struct mcr_range mcr_ranges_gen8[] = {
 	{},
 };
 
-static const struct mcr_range mcr_ranges_gen12[] = {
+static const struct i915_range mcr_ranges_gen12[] = {
 	{ .start =  0x8150, .end =  0x815f },
 	{ .start =  0x9520, .end =  0x955f },
 	{ .start =  0xb100, .end =  0xb3ff },
@@ -2090,7 +2187,7 @@ static const struct mcr_range mcr_ranges_gen12[] = {
 	{},
 };
 
-static const struct mcr_range mcr_ranges_xehp[] = {
+static const struct i915_range mcr_ranges_xehp[] = {
 	{ .start =  0x4000, .end =  0x4aff },
 	{ .start =  0x5200, .end =  0x52ff },
 	{ .start =  0x5400, .end =  0x7fff },
@@ -2109,7 +2206,7 @@ static const struct mcr_range mcr_ranges_xehp[] = {
 
 static bool mcr_range(struct drm_i915_private *i915, u32 offset)
 {
-	const struct mcr_range *mcr_ranges;
+	const struct i915_range *mcr_ranges;
 	int i;
 
 	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index f12ffe797639..b3863abc51f5 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -3493,7 +3493,7 @@ static int smoke_submit(struct preempt_smoke *smoke,
 	if (batch) {
 		struct i915_address_space *vm;
 
-		vm = i915_gem_context_get_vm_rcu(ctx);
+		vm = i915_gem_context_get_eb_vm(ctx);
 		vma = i915_vma_instance(batch, vm, NULL);
 		i915_vm_put(vm);
 		if (IS_ERR(vma))
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 2c1ed32ca5ac..7e6fdabac599 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -117,7 +117,7 @@ static struct i915_request *
 hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 {
 	struct intel_gt *gt = h->gt;
-	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(h->ctx);
+	struct i915_address_space *vm = i915_gem_context_get_eb_vm(h->ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
@@ -789,7 +789,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 				if (err)
 					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
 					       engine->name, rq->fence.context,
-					       rq->fence.seqno, rq->context->guc_id, err);
+					       rq->fence.seqno, rq->context->guc_id.id, err);
 			}
 
 skip:
@@ -1098,7 +1098,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 				if (err)
 					pr_err("[%s] Wait for request %lld:%lld [0x%04X] failed: %d!\n",
 					       engine->name, rq->fence.context,
-					       rq->fence.seqno, rq->context->guc_id, err);
+					       rq->fence.seqno, rq->context->guc_id.id, err);
 			}
 
 			count++;
@@ -1108,7 +1108,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 					pr_err("i915_reset_engine(%s:%s): failed to reset request %lld:%lld [0x%04X]\n",
 					       engine->name, test_name,
 					       rq->fence.context,
-					       rq->fence.seqno, rq->context->guc_id);
+					       rq->fence.seqno, rq->context->guc_id.id);
 					i915_request_put(rq);
 
 					GEM_TRACE_DUMP();
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 2e27fe59786b..5dd174babf7a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -22,74 +22,121 @@
 
 struct __guc_ads_blob;
 
-/*
- * Top level structure of GuC. It handles firmware loading and manages client
- * pool. intel_guc owns a intel_guc_client to replace the legacy ExecList
- * submission.
+/**
+ * struct intel_guc - Top level structure of GuC.
+ *
+ * It handles firmware loading and manages client pool. intel_guc owns an
+ * i915_sched_engine for submission.
  */
 struct intel_guc {
+	/** @fw: the GuC firmware */
 	struct intel_uc_fw fw;
+	/** @log: sub-structure containing GuC log related data and objects */
 	struct intel_guc_log log;
+	/** @ct: the command transport communication channel */
 	struct intel_guc_ct ct;
+	/** @slpc: sub-structure containing SLPC related data and objects */
 	struct intel_guc_slpc slpc;
 
-	/* Global engine used to submit requests to GuC */
+	/** @sched_engine: Global engine used to submit requests to GuC */
 	struct i915_sched_engine *sched_engine;
+	/**
+	 * @stalled_request: if GuC can't process a request for any reason, we
+	 * save it until GuC restarts processing. No other request can be
+	 * submitted until the stalled request is processed.
+	 */
 	struct i915_request *stalled_request;
 
 	/* intel_guc_recv interrupt related state */
+	/** @irq_lock: protects GuC irq state */
 	spinlock_t irq_lock;
+	/**
+	 * @msg_enabled_mask: mask of events that are processed when receiving
+	 * an INTEL_GUC_ACTION_DEFAULT G2H message.
+	 */
 	unsigned int msg_enabled_mask;
 
+	/**
+	 * @outstanding_submission_g2h: number of outstanding GuC to Host
+	 * responses related to GuC submission, used to determine if the GT is
+	 * idle
+	 */
 	atomic_t outstanding_submission_g2h;
 
+	/** @interrupts: pointers to GuC interrupt-managing functions. */
 	struct {
 		void (*reset)(struct intel_guc *guc);
 		void (*enable)(struct intel_guc *guc);
 		void (*disable)(struct intel_guc *guc);
 	} interrupts;
 
-	/*
-	 * contexts_lock protects the pool of free guc ids and a linked list of
-	 * guc ids available to be stolen
+	/**
+	 * @contexts_lock: protects guc_ids, guc_id_list, ce->guc_id.id, and
+	 * ce->guc_id.ref when transitioning in and out of zero
 	 */
 	spinlock_t contexts_lock;
+	/** @guc_ids: used to allocate unique ce->guc_id.id values */
 	struct ida guc_ids;
+	/**
+	 * @guc_id_list: list of intel_context with valid guc_ids but no refs
+	 */
 	struct list_head guc_id_list;
 
+	/**
+	 * @submission_supported: tracks whether we support GuC submission on
+	 * the current platform
+	 */
 	bool submission_supported;
+	/** @submission_selected: tracks whether the user enabled GuC submission */
 	bool submission_selected;
+	/**
+	 * @rc_supported: tracks whether we support GuC rc on the current platform
+	 */
 	bool rc_supported;
+	/** @rc_selected: tracks whether the user enabled GuC rc */
 	bool rc_selected;
 
+	/** @ads_vma: object allocated to hold the GuC ADS */
 	struct i915_vma *ads_vma;
+	/** @ads_blob: contents of the GuC ADS */
 	struct __guc_ads_blob *ads_blob;
+	/** @ads_regset_size: size of the save/restore regsets in the ADS */
 	u32 ads_regset_size;
+	/** @ads_golden_ctxt_size: size of the golden contexts in the ADS */
 	u32 ads_golden_ctxt_size;
 
+	/** @lrc_desc_pool: object allocated to hold the GuC LRC descriptor pool */
 	struct i915_vma *lrc_desc_pool;
+	/** @lrc_desc_pool_vaddr: contents of the GuC LRC descriptor pool */
 	void *lrc_desc_pool_vaddr;
 
-	/* guc_id to intel_context lookup */
+	/**
+	 * @context_lookup: used to resolve intel_context from guc_id, if a
+	 * context is present in this structure it is registered with the GuC
+	 */
 	struct xarray context_lookup;
 
-	/* Control params for fw initialization */
+	/** @params: Control params for fw initialization */
 	u32 params[GUC_CTL_MAX_DWORDS];
 
-	/* GuC's FW specific registers used in MMIO send */
+	/** @send_regs: GuC's FW specific registers used for sending MMIO H2G */
 	struct {
 		u32 base;
 		unsigned int count;
 		enum forcewake_domains fw_domains;
 	} send_regs;
 
-	/* register used to send interrupts to the GuC FW */
+	/** @notify_reg: register used to send interrupts to the GuC FW */
 	i915_reg_t notify_reg;
 
-	/* Store msg (e.g. log flush) that we see while CTBs are disabled */
+	/**
+	 * @mmio_msg: notification bitmask that the GuC writes in one of its
+	 * registers when the CT channel is disabled, to be processed when the
+	 * channel is back up.
+	 */
 	u32 mmio_msg;
 
-	/* To serialize the intel_guc_send actions */
+	/** @send_mutex: used to serialize the intel_guc_send actions */
 	struct mutex send_mutex;
 };
 
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 6926919bcac6..2c6ea64af7ec 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -349,6 +349,8 @@ static void fill_engine_enable_masks(struct intel_gt *gt,
 	info->engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt);
 }
 
+#define LR_HW_CONTEXT_SIZE (80 * sizeof(u32))
+#define LRC_SKIP_SIZE (LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE)
 static int guc_prep_golden_context(struct intel_guc *guc,
 				   struct __guc_ads_blob *blob)
 {
@@ -396,7 +398,18 @@ static int guc_prep_golden_context(struct intel_guc *guc,
 		if (!blob)
 			continue;
 
-		blob->ads.eng_state_size[guc_class] = real_size;
+		/*
+		 * This interface is slightly confusing. We need to pass the
+		 * base address of the full golden context and the size of just
+		 * the engine state, which is the section of the context image
+		 * that starts after the execlists context. This is required to
+		 * allow the GuC to restore just the engine state when a
+		 * watchdog reset occurs.
+		 * We calculate the engine state size by removing the size of
+		 * what comes before it in the context image (which is identical
+		 * on all engines).
+		 */
+		blob->ads.eng_state_size[guc_class] = real_size - LRC_SKIP_SIZE;
 		blob->ads.golden_context_lrca[guc_class] = addr_ggtt;
 		addr_ggtt += alloc_size;
 	}
@@ -436,11 +449,6 @@ static void guc_init_golden_context(struct intel_guc *guc)
 	u8 engine_class, guc_class;
 	u8 *ptr;
 
-	/* Skip execlist and PPGTT registers + HWSP */
-	const u32 lr_hw_context_size = 80 * sizeof(u32);
-	const u32 skip_size = LRC_PPHWSP_SZ * PAGE_SIZE +
-		lr_hw_context_size;
-
 	if (!intel_uc_uses_guc_submission(&gt->uc))
 		return;
 
@@ -476,12 +484,12 @@ static void guc_init_golden_context(struct intel_guc *guc)
 			continue;
 		}
 
-		GEM_BUG_ON(blob->ads.eng_state_size[guc_class] != real_size);
+		GEM_BUG_ON(blob->ads.eng_state_size[guc_class] !=
+			   real_size - LRC_SKIP_SIZE);
 		GEM_BUG_ON(blob->ads.golden_context_lrca[guc_class] != addr_ggtt);
 		addr_ggtt += alloc_size;
 
-		shmem_read(engine->default_state, skip_size, ptr + skip_size,
-			   real_size - skip_size);
+		shmem_read(engine->default_state, 0, ptr, real_size);
 		ptr += alloc_size;
 	}
 
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 22b4733b55e2..20c710a74498 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -1042,9 +1042,9 @@ static void ct_incoming_request_worker_func(struct work_struct *w)
 		container_of(w, struct intel_guc_ct, requests.worker);
 	bool done;
 
-	done = ct_process_incoming_requests(ct);
-	if (!done)
-		queue_work(system_unbound_wq, &ct->requests.worker);
+	do {
+		done = ct_process_incoming_requests(ct);
+	} while (!done);
 }
 
 static int ct_handle_event(struct intel_guc_ct *ct, struct ct_incoming_msg *request)
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 87d8dc8f51b9..c7a41802b448 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -28,21 +28,6 @@
 /**
  * DOC: GuC-based command submission
  *
- * IMPORTANT NOTE: GuC submission is currently not supported in i915. The GuC
- * firmware is moving to an updated submission interface and we plan to
- * turn submission back on when that lands. The below documentation (and related
- * code) matches the old submission model and will be updated as part of the
- * upgrade to the new flow.
- *
- * GuC stage descriptor:
- * During initialization, the driver allocates a static pool of 1024 such
- * descriptors, and shares them with the GuC. Currently, we only use one
- * descriptor. This stage descriptor lets the GuC know about the workqueue and
- * process descriptor. Theoretically, it also lets the GuC know about our HW
- * contexts (context ID, etc...), but we actually employ a kind of submission
- * where the GuC uses the LRCA sent via the work item instead. This is called
- * a "proxy" submission.
- *
  * The Scratch registers:
  * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
  * a value to the action register (SOFT_SCRATCH_0) along with any data. It then
@@ -51,14 +36,85 @@
  * processes the request. The kernel driver polls waiting for this update and
  * then proceeds.
  *
- * Work Items:
- * There are several types of work items that the host may place into a
- * workqueue, each with its own requirements and limitations. Currently only
- * WQ_TYPE_INORDER is needed to support legacy submission via GuC, which
- * represents in-order queue. The kernel driver packs ring tail pointer and an
- * ELSP context descriptor dword into Work Item.
- * See guc_add_request()
+ * Command Transport buffers (CTBs):
+ * Covered in detail in other sections but CTBs (Host to GuC - H2G, GuC to Host
+ * - G2H) are a message interface between the i915 and GuC.
  *
+ * Context registration:
+ * Before a context can be submitted it must be registered with the GuC via a
+ * H2G. A unique guc_id is associated with each context. The context is either
+ * registered at request creation time (normal operation) or at submission time
+ * (abnormal operation, e.g. after a reset).
+ *
+ * Context submission:
+ * The i915 updates the LRC tail value in memory. The i915 must enable the
+ * scheduling of the context within the GuC for the GuC to actually consider it.
+ * Therefore, the first time a disabled context is submitted we use a schedule
+ * enable H2G, while follow up submissions are done via the context submit H2G,
+ * which informs the GuC that a previously enabled context has new work
+ * available.
+ *
+ * Context unpin:
+ * To unpin a context a H2G is used to disable scheduling. When the
+ * corresponding G2H returns indicating the scheduling disable operation has
+ * completed it is safe to unpin the context. While a disable is in flight it
+ * isn't safe to resubmit the context so a fence is used to stall all future
+ * requests of that context until the G2H is returned.
+ *
+ * Context deregistration:
+ * Before a context can be destroyed or if we steal its guc_id we must
+ * deregister the context with the GuC via H2G. If stealing the guc_id it isn't
+ * safe to submit anything to this guc_id until the deregister completes so a
+ * fence is used to stall all requests associated with this guc_id until the
+ * corresponding G2H returns indicating the guc_id has been deregistered.
+ *
+ * guc_ids:
+ * Unique number associated with private GuC context data passed in during
+ * context registration / submission / deregistration. 64k available. Simple ida
+ * is used for allocation.
+ *
+ * Stealing guc_ids:
+ * If no guc_ids are available they can be stolen from another context at
+ * request creation time if that context is unpinned. If a guc_id can't be found
+ * we punt this problem to the user as we believe this is near impossible to hit
+ * during normal use cases.
+ *
+ * Locking:
+ * In the GuC submission code we have 3 basic spin locks which protect
+ * everything. Details about each below.
+ *
+ * sched_engine->lock
+ * This is the submission lock for all contexts that share an i915 schedule
+ * engine (sched_engine), thus only one of the contexts which share a
+ * sched_engine can be submitting at a time. Currently only one sched_engine is
+ * used for all of GuC submission but that could change in the future.
+ *
+ * guc->contexts_lock
+ * Protects guc_id allocation for the given GuC, i.e. only one context can be
+ * doing guc_id allocation operations at a time for each GuC in the system.
+ *
+ * ce->guc_state.lock
+ * Protects everything under ce->guc_state. Ensures that a context is in the
+ * correct state before issuing a H2G. e.g. We don't issue a schedule disable
+ * on a disabled context (bad idea), we don't issue a schedule enable when a
+ * schedule disable is in flight, etc... Also protects list of inflight requests
+ * on the context and the priority management state. Lock is individual to each
+ * context.
+ *
+ * Lock ordering rules:
+ * sched_engine->lock -> ce->guc_state.lock
+ * guc->contexts_lock -> ce->guc_state.lock
+ *
+ * Reset races:
+ * When a full GT reset is triggered it is assumed that some G2H responses to
+ * H2Gs can be lost as the GuC is also reset. Losing these G2H can prove to be
+ * fatal as we do certain operations upon receiving a G2H (e.g. destroy
+ * contexts, release guc_ids, etc...). When this occurs we can scrub the
+ * context state and cleanup appropriately, however this is quite racey.
+ * To avoid races, the reset code must disable submission before scrubbing for
+ * the missing G2H, while the submission code must check for submission being
+ * disabled and skip sending H2Gs and updating context states when it is. Both
+ * sides must also make sure to hold the relevant locks.
  */
 
 /* GuC Virtual Engine */
@@ -72,87 +128,36 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
 
 #define GUC_REQUEST_SIZE 64 /* bytes */
 
-/*
- * Below is a set of functions which control the GuC scheduling state which do
- * not require a lock as all state transitions are mutually exclusive. i.e. It
- * is not possible for the context pinning code and submission, for the same
- * context, to be executing simultaneously. We still need an atomic as it is
- * possible for some of the bits to changing at the same time though.
- */
-#define SCHED_STATE_NO_LOCK_ENABLED			BIT(0)
-#define SCHED_STATE_NO_LOCK_PENDING_ENABLE		BIT(1)
-#define SCHED_STATE_NO_LOCK_REGISTERED			BIT(2)
-static inline bool context_enabled(struct intel_context *ce)
-{
-	return (atomic_read(&ce->guc_sched_state_no_lock) &
-		SCHED_STATE_NO_LOCK_ENABLED);
-}
-
-static inline void set_context_enabled(struct intel_context *ce)
-{
-	atomic_or(SCHED_STATE_NO_LOCK_ENABLED, &ce->guc_sched_state_no_lock);
-}
-
-static inline void clr_context_enabled(struct intel_context *ce)
-{
-	atomic_and((u32)~SCHED_STATE_NO_LOCK_ENABLED,
-		   &ce->guc_sched_state_no_lock);
-}
-
-static inline bool context_pending_enable(struct intel_context *ce)
-{
-	return (atomic_read(&ce->guc_sched_state_no_lock) &
-		SCHED_STATE_NO_LOCK_PENDING_ENABLE);
-}
-
-static inline void set_context_pending_enable(struct intel_context *ce)
-{
-	atomic_or(SCHED_STATE_NO_LOCK_PENDING_ENABLE,
-		  &ce->guc_sched_state_no_lock);
-}
-
-static inline void clr_context_pending_enable(struct intel_context *ce)
-{
-	atomic_and((u32)~SCHED_STATE_NO_LOCK_PENDING_ENABLE,
-		   &ce->guc_sched_state_no_lock);
-}
-
-static inline bool context_registered(struct intel_context *ce)
-{
-	return (atomic_read(&ce->guc_sched_state_no_lock) &
-		SCHED_STATE_NO_LOCK_REGISTERED);
-}
-
-static inline void set_context_registered(struct intel_context *ce)
-{
-	atomic_or(SCHED_STATE_NO_LOCK_REGISTERED,
-		  &ce->guc_sched_state_no_lock);
-}
-
-static inline void clr_context_registered(struct intel_context *ce)
-{
-	atomic_and((u32)~SCHED_STATE_NO_LOCK_REGISTERED,
-		   &ce->guc_sched_state_no_lock);
-}
-
 /*
  * Below is a set of functions which control the GuC scheduling state which
- * require a lock, aside from the special case where the functions are called
- * from guc_lrc_desc_pin(). In that case it isn't possible for any other code
- * path to be executing on the context.
+ * require a lock.
  */
 #define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER	BIT(0)
 #define SCHED_STATE_DESTROYED				BIT(1)
 #define SCHED_STATE_PENDING_DISABLE			BIT(2)
 #define SCHED_STATE_BANNED				BIT(3)
-#define SCHED_STATE_BLOCKED_SHIFT			4
+#define SCHED_STATE_ENABLED				BIT(4)
+#define SCHED_STATE_PENDING_ENABLE			BIT(5)
+#define SCHED_STATE_REGISTERED				BIT(6)
+#define SCHED_STATE_BLOCKED_SHIFT			7
 #define SCHED_STATE_BLOCKED		BIT(SCHED_STATE_BLOCKED_SHIFT)
 #define SCHED_STATE_BLOCKED_MASK	(0xfff << SCHED_STATE_BLOCKED_SHIFT)
+
 static inline void init_sched_state(struct intel_context *ce)
 {
-	/* Only should be called from guc_lrc_desc_pin() */
-	atomic_set(&ce->guc_sched_state_no_lock, 0);
-	ce->guc_state.sched_state = 0;
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= SCHED_STATE_BLOCKED_MASK;
+}
+
+__maybe_unused
+static bool sched_state_is_init(struct intel_context *ce)
+{
+	/*
+	 * XXX: Kernel contexts can have SCHED_STATE_NO_LOCK_REGISTERED after
+	 * suspend.
+	 */
+	return !(ce->guc_state.sched_state &=
+		 ~(SCHED_STATE_BLOCKED_MASK | SCHED_STATE_REGISTERED));
 }
 
 static inline bool
@@ -165,7 +170,7 @@ context_wait_for_deregister_to_register(struct intel_context *ce)
 static inline void
 set_context_wait_for_deregister_to_register(struct intel_context *ce)
 {
-	/* Only should be called from guc_lrc_desc_pin() without lock */
+	lockdep_assert_held(&ce->guc_state.lock);
 	ce->guc_state.sched_state |=
 		SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER;
 }
@@ -225,6 +230,57 @@ static inline void clr_context_banned(struct intel_context *ce)
 	ce->guc_state.sched_state &= ~SCHED_STATE_BANNED;
 }
 
+static inline bool context_enabled(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_ENABLED;
+}
+
+static inline void set_context_enabled(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_ENABLED;
+}
+
+static inline void clr_context_enabled(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= ~SCHED_STATE_ENABLED;
+}
+
+static inline bool context_pending_enable(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_PENDING_ENABLE;
+}
+
+static inline void set_context_pending_enable(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_PENDING_ENABLE;
+}
+
+static inline void clr_context_pending_enable(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= ~SCHED_STATE_PENDING_ENABLE;
+}
+
+static inline bool context_registered(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_REGISTERED;
+}
+
+static inline void set_context_registered(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_REGISTERED;
+}
+
+static inline void clr_context_registered(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state &= ~SCHED_STATE_REGISTERED;
+}
+
 static inline u32 context_blocked(struct intel_context *ce)
 {
 	return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >>
@@ -233,7 +289,6 @@ static inline u32 context_blocked(struct intel_context *ce)
 
 static inline void incr_context_blocked(struct intel_context *ce)
 {
-	lockdep_assert_held(&ce->engine->sched_engine->lock);
 	lockdep_assert_held(&ce->guc_state.lock);
 
 	ce->guc_state.sched_state += SCHED_STATE_BLOCKED;
@@ -243,7 +298,6 @@ static inline void incr_context_blocked(struct intel_context *ce)
 
 static inline void decr_context_blocked(struct intel_context *ce)
 {
-	lockdep_assert_held(&ce->engine->sched_engine->lock);
 	lockdep_assert_held(&ce->guc_state.lock);
 
 	GEM_BUG_ON(!context_blocked(ce));	/* Underflow check */
@@ -251,14 +305,33 @@ static inline void decr_context_blocked(struct intel_context *ce)
 	ce->guc_state.sched_state -= SCHED_STATE_BLOCKED;
 }
 
+static inline bool context_has_committed_requests(struct intel_context *ce)
+{
+	return !!ce->guc_state.number_committed_requests;
+}
+
+static inline void incr_context_committed_requests(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	++ce->guc_state.number_committed_requests;
+	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
+}
+
+static inline void decr_context_committed_requests(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	--ce->guc_state.number_committed_requests;
+	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
+}
+
 static inline bool context_guc_id_invalid(struct intel_context *ce)
 {
-	return ce->guc_id == GUC_INVALID_LRC_ID;
+	return ce->guc_id.id == GUC_INVALID_LRC_ID;
 }
 
 static inline void set_context_guc_id_invalid(struct intel_context *ce)
 {
-	ce->guc_id = GUC_INVALID_LRC_ID;
+	ce->guc_id.id = GUC_INVALID_LRC_ID;
 }
 
 static inline struct intel_guc *ce_to_guc(struct intel_context *ce)
@@ -352,20 +425,29 @@ static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id,
 	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
+static void decr_outstanding_submission_g2h(struct intel_guc *guc)
+{
+	if (atomic_dec_and_test(&guc->outstanding_submission_g2h))
+		wake_up_all(&guc->ct.wq);
+}
+
 static int guc_submission_send_busy_loop(struct intel_guc *guc,
 					 const u32 *action,
 					 u32 len,
 					 u32 g2h_len_dw,
 					 bool loop)
 {
-	int err;
+	/*
+	 * We always loop when a send requires a reply (i.e. g2h_len_dw > 0),
+	 * so we don't handle the case where we don't get a reply because we
+	 * aborted the send due to the channel being busy.
+	 */
+	GEM_BUG_ON(g2h_len_dw && !loop);
 
-	err = intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop);
-
-	if (!err && g2h_len_dw)
+	if (g2h_len_dw)
 		atomic_inc(&guc->outstanding_submission_g2h);
 
-	return err;
+	return intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop);
 }
 
 int intel_guc_wait_for_pending_msg(struct intel_guc *guc,
@@ -430,6 +512,8 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 	u32 g2h_len_dw = 0;
 	bool enabled;
 
+	lockdep_assert_held(&rq->engine->sched_engine->lock);
+
 	/*
 	 * Corner case where requests were sitting in the priority list or a
 	 * request resubmitted after the context was banned.
@@ -437,22 +521,24 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 	if (unlikely(intel_context_is_banned(ce))) {
 		i915_request_put(i915_request_mark_eio(rq));
 		intel_engine_signal_breadcrumbs(ce->engine);
-		goto out;
+		return 0;
 	}
 
-	GEM_BUG_ON(!atomic_read(&ce->guc_id_ref));
+	GEM_BUG_ON(!atomic_read(&ce->guc_id.ref));
 	GEM_BUG_ON(context_guc_id_invalid(ce));
 
 	/*
 	 * Corner case where the GuC firmware was blown away and reloaded while
 	 * this context was pinned.
 	 */
-	if (unlikely(!lrc_desc_registered(guc, ce->guc_id))) {
+	if (unlikely(!lrc_desc_registered(guc, ce->guc_id.id))) {
 		err = guc_lrc_desc_pin(ce, false);
 		if (unlikely(err))
-			goto out;
+			return err;
 	}
 
+	spin_lock(&ce->guc_state.lock);
+
 	/*
 	 * The request / context will be run on the hardware when scheduling
 	 * gets enabled in the unblock.
@@ -464,14 +550,14 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 
 	if (!enabled) {
 		action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET;
-		action[len++] = ce->guc_id;
+		action[len++] = ce->guc_id.id;
 		action[len++] = GUC_CONTEXT_ENABLE;
 		set_context_pending_enable(ce);
 		intel_context_get(ce);
 		g2h_len_dw = G2H_LEN_DW_SCHED_CONTEXT_MODE_SET;
 	} else {
 		action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT;
-		action[len++] = ce->guc_id;
+		action[len++] = ce->guc_id.id;
 	}
 
 	err = intel_guc_send_nb(guc, action, len, g2h_len_dw);
@@ -487,6 +573,7 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 		trace_i915_request_guc_submit(rq);
 
 out:
+	spin_unlock(&ce->guc_state.lock);
 	return err;
 }
 
@@ -596,10 +683,18 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 	unsigned long index, flags;
 	bool pending_disable, pending_enable, deregister, destroyed, banned;
 
+	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
-		/* Flush context */
-		spin_lock_irqsave(&ce->guc_state.lock, flags);
-		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		/*
+		 * Corner case where the ref count on the object is zero but and
+		 * deregister G2H was lost. In this case we don't touch the ref
+		 * count and finish the destroy of the context.
+		 */
+		bool do_put = kref_get_unless_zero(&ce->ref);
+
+		xa_unlock(&guc->context_lookup);
+
+		spin_lock(&ce->guc_state.lock);
 
 		/*
 		 * Once we are at this point submission_disabled() is guaranteed
@@ -615,8 +710,12 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 		banned = context_banned(ce);
 		init_sched_state(ce);
 
+		spin_unlock(&ce->guc_state.lock);
+
+		GEM_BUG_ON(!do_put && !destroyed);
+
 		if (pending_enable || destroyed || deregister) {
-			atomic_dec(&guc->outstanding_submission_g2h);
+			decr_outstanding_submission_g2h(guc);
 			if (deregister)
 				guc_signal_context_fence(ce);
 			if (destroyed) {
@@ -635,14 +734,20 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 				intel_engine_signal_breadcrumbs(ce->engine);
 			}
 			intel_context_sched_disable_unpin(ce);
-			atomic_dec(&guc->outstanding_submission_g2h);
-			spin_lock_irqsave(&ce->guc_state.lock, flags);
+			decr_outstanding_submission_g2h(guc);
+
+			spin_lock(&ce->guc_state.lock);
 			guc_blocked_fence_complete(ce);
-			spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+			spin_unlock(&ce->guc_state.lock);
 
 			intel_context_put(ce);
 		}
+
+		if (do_put)
+			intel_context_put(ce);
+		xa_lock(&guc->context_lookup);
 	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 static inline bool
@@ -725,6 +830,7 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc)
 			wait_for_reset(guc, &guc->outstanding_submission_g2h);
 		} while (!list_empty(&guc->ct.requests.incoming));
 	}
+
 	scrub_guc_desc_for_outstanding_g2h(guc);
 }
 
@@ -796,16 +902,14 @@ __unwind_incomplete_requests(struct intel_context *ce)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sched_engine->lock, flags);
-	spin_lock(&ce->guc_active.lock);
-	list_for_each_entry_safe(rq, rn,
-				 &ce->guc_active.requests,
-				 sched.link) {
+	spin_lock(&ce->guc_state.lock);
+	list_for_each_entry_safe_reverse(rq, rn,
+					 &ce->guc_state.requests,
+					 sched.link) {
 		if (i915_request_completed(rq))
 			continue;
 
 		list_del_init(&rq->sched.link);
-		spin_unlock(&ce->guc_active.lock);
-
 		__i915_request_unsubmit(rq);
 
 		/* Push the request back into the queue for later resubmission. */
@@ -816,29 +920,43 @@ __unwind_incomplete_requests(struct intel_context *ce)
 		}
 		GEM_BUG_ON(i915_sched_engine_is_empty(sched_engine));
 
-		list_add_tail(&rq->sched.link, pl);
+		list_add(&rq->sched.link, pl);
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-
-		spin_lock(&ce->guc_active.lock);
 	}
-	spin_unlock(&ce->guc_active.lock);
+	spin_unlock(&ce->guc_state.lock);
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
 static void __guc_reset_context(struct intel_context *ce, bool stalled)
 {
 	struct i915_request *rq;
+	unsigned long flags;
 	u32 head;
+	bool skip = false;
 
 	intel_context_get(ce);
 
 	/*
-	 * 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.
+	 * 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.
 	 */
-	clr_context_enabled(ce);
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	if (likely(!context_pending_enable(ce)))
+		clr_context_enabled(ce);
+	else
+		skip = true;
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+	if (unlikely(skip))
+		goto out_put;
 
 	rq = intel_context_find_active_request(ce);
 	if (!rq) {
@@ -857,6 +975,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 out_replay:
 	guc_reset_state(ce, head, stalled);
 	__unwind_incomplete_requests(ce);
+out_put:
 	intel_context_put(ce);
 }
 
@@ -864,16 +983,29 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
 {
 	struct intel_context *ce;
 	unsigned long index;
+	unsigned long flags;
 
 	if (unlikely(!guc_submission_initialized(guc))) {
 		/* Reset called during driver load? GuC not yet initialised! */
 		return;
 	}
 
-	xa_for_each(&guc->context_lookup, index, ce)
+	xa_lock_irqsave(&guc->context_lookup, flags);
+	xa_for_each(&guc->context_lookup, index, ce) {
+		if (!kref_get_unless_zero(&ce->ref))
+			continue;
+
+		xa_unlock(&guc->context_lookup);
+
 		if (intel_context_is_pinned(ce))
 			__guc_reset_context(ce, stalled);
 
+		intel_context_put(ce);
+
+		xa_lock(&guc->context_lookup);
+	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
+
 	/* GuC is blown away, drop all references to contexts */
 	xa_destroy(&guc->context_lookup);
 }
@@ -886,10 +1018,10 @@ static void guc_cancel_context_requests(struct intel_context *ce)
 
 	/* Mark all executing requests as skipped. */
 	spin_lock_irqsave(&sched_engine->lock, flags);
-	spin_lock(&ce->guc_active.lock);
-	list_for_each_entry(rq, &ce->guc_active.requests, sched.link)
+	spin_lock(&ce->guc_state.lock);
+	list_for_each_entry(rq, &ce->guc_state.requests, sched.link)
 		i915_request_put(i915_request_mark_eio(rq));
-	spin_unlock(&ce->guc_active.lock);
+	spin_unlock(&ce->guc_state.lock);
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
@@ -948,11 +1080,24 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 {
 	struct intel_context *ce;
 	unsigned long index;
+	unsigned long flags;
+
+	xa_lock_irqsave(&guc->context_lookup, flags);
+	xa_for_each(&guc->context_lookup, index, ce) {
+		if (!kref_get_unless_zero(&ce->ref))
+			continue;
+
+		xa_unlock(&guc->context_lookup);
 
-	xa_for_each(&guc->context_lookup, index, ce)
 		if (intel_context_is_pinned(ce))
 			guc_cancel_context_requests(ce);
 
+		intel_context_put(ce);
+
+		xa_lock(&guc->context_lookup);
+	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
+
 	guc_cancel_sched_engine_requests(guc->sched_engine);
 
 	/* GuC is blown away, drop all references to contexts */
@@ -1027,6 +1172,7 @@ static inline void queue_request(struct i915_sched_engine *sched_engine,
 	list_add_tail(&rq->sched.link,
 		      i915_sched_lookup_priolist(sched_engine, prio));
 	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	tasklet_hi_schedule(&sched_engine->tasklet);
 }
 
 static int guc_bypass_tasklet_submit(struct intel_guc *guc,
@@ -1077,12 +1223,12 @@ static int new_guc_id(struct intel_guc *guc)
 static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
 {
 	if (!context_guc_id_invalid(ce)) {
-		ida_simple_remove(&guc->guc_ids, ce->guc_id);
-		reset_lrc_desc(guc, ce->guc_id);
+		ida_simple_remove(&guc->guc_ids, ce->guc_id.id);
+		reset_lrc_desc(guc, ce->guc_id.id);
 		set_context_guc_id_invalid(ce);
 	}
-	if (!list_empty(&ce->guc_id_link))
-		list_del_init(&ce->guc_id_link);
+	if (!list_empty(&ce->guc_id.link))
+		list_del_init(&ce->guc_id.link);
 }
 
 static void release_guc_id(struct intel_guc *guc, struct intel_context *ce)
@@ -1104,14 +1250,18 @@ static int steal_guc_id(struct intel_guc *guc)
 	if (!list_empty(&guc->guc_id_list)) {
 		ce = list_first_entry(&guc->guc_id_list,
 				      struct intel_context,
-				      guc_id_link);
+				      guc_id.link);
 
-		GEM_BUG_ON(atomic_read(&ce->guc_id_ref));
+		GEM_BUG_ON(atomic_read(&ce->guc_id.ref));
 		GEM_BUG_ON(context_guc_id_invalid(ce));
 
-		list_del_init(&ce->guc_id_link);
-		guc_id = ce->guc_id;
+		list_del_init(&ce->guc_id.link);
+		guc_id = ce->guc_id.id;
+
+		spin_lock(&ce->guc_state.lock);
 		clr_context_registered(ce);
+		spin_unlock(&ce->guc_state.lock);
+
 		set_context_guc_id_invalid(ce);
 		return guc_id;
 	} else {
@@ -1142,26 +1292,28 @@ static int pin_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	int ret = 0;
 	unsigned long flags, tries = PIN_GUC_ID_TRIES;
 
-	GEM_BUG_ON(atomic_read(&ce->guc_id_ref));
+	GEM_BUG_ON(atomic_read(&ce->guc_id.ref));
 
 try_again:
 	spin_lock_irqsave(&guc->contexts_lock, flags);
 
+	might_lock(&ce->guc_state.lock);
+
 	if (context_guc_id_invalid(ce)) {
-		ret = assign_guc_id(guc, &ce->guc_id);
+		ret = assign_guc_id(guc, &ce->guc_id.id);
 		if (ret)
 			goto out_unlock;
 		ret = 1;	/* Indidcates newly assigned guc_id */
 	}
-	if (!list_empty(&ce->guc_id_link))
-		list_del_init(&ce->guc_id_link);
-	atomic_inc(&ce->guc_id_ref);
+	if (!list_empty(&ce->guc_id.link))
+		list_del_init(&ce->guc_id.link);
+	atomic_inc(&ce->guc_id.ref);
 
 out_unlock:
 	spin_unlock_irqrestore(&guc->contexts_lock, flags);
 
 	/*
-	 * -EAGAIN indicates no guc_ids are available, let's retire any
+	 * -EAGAIN indicates no guc_id are available, let's retire any
 	 * outstanding requests to see if that frees up a guc_id. If the first
 	 * retire didn't help, insert a sleep with the timeslice duration before
 	 * attempting to retire more requests. Double the sleep period each
@@ -1189,15 +1341,15 @@ static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce)
 {
 	unsigned long flags;
 
-	GEM_BUG_ON(atomic_read(&ce->guc_id_ref) < 0);
+	GEM_BUG_ON(atomic_read(&ce->guc_id.ref) < 0);
 
 	if (unlikely(context_guc_id_invalid(ce)))
 		return;
 
 	spin_lock_irqsave(&guc->contexts_lock, flags);
-	if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id_link) &&
-	    !atomic_read(&ce->guc_id_ref))
-		list_add_tail(&ce->guc_id_link, &guc->guc_id_list);
+	if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id.link) &&
+	    !atomic_read(&ce->guc_id.ref))
+		list_add_tail(&ce->guc_id.link, &guc->guc_id_list);
 	spin_unlock_irqrestore(&guc->contexts_lock, flags);
 }
 
@@ -1220,21 +1372,25 @@ static int register_context(struct intel_context *ce, bool loop)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
 	u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) +
-		ce->guc_id * sizeof(struct guc_lrc_desc);
+		ce->guc_id.id * sizeof(struct guc_lrc_desc);
 	int ret;
 
 	trace_intel_context_register(ce);
 
-	ret = __guc_action_register_context(guc, ce->guc_id, offset, loop);
-	if (likely(!ret))
+	ret = __guc_action_register_context(guc, ce->guc_id.id, offset, loop);
+	if (likely(!ret)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
 		set_context_registered(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+	}
 
 	return ret;
 }
 
 static int __guc_action_deregister_context(struct intel_guc *guc,
-					   u32 guc_id,
-					   bool loop)
+					   u32 guc_id)
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_DEREGISTER_CONTEXT,
@@ -1243,16 +1399,16 @@ static int __guc_action_deregister_context(struct intel_guc *guc,
 
 	return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
 					     G2H_LEN_DW_DEREGISTER_CONTEXT,
-					     loop);
+					     true);
 }
 
-static int deregister_context(struct intel_context *ce, u32 guc_id, bool loop)
+static int deregister_context(struct intel_context *ce, u32 guc_id)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
 
 	trace_intel_context_deregister(ce);
 
-	return __guc_action_deregister_context(guc, guc_id, loop);
+	return __guc_action_deregister_context(guc, guc_id);
 }
 
 static intel_engine_mask_t adjust_engine_mask(u8 class, intel_engine_mask_t mask)
@@ -1285,22 +1441,19 @@ static void guc_context_policy_init(struct intel_engine_cs *engine,
 	desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
 }
 
-static inline u8 map_i915_prio_to_guc_prio(int prio);
-
 static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 {
 	struct intel_engine_cs *engine = ce->engine;
 	struct intel_runtime_pm *runtime_pm = engine->uncore->rpm;
 	struct intel_guc *guc = &engine->gt->uc.guc;
-	u32 desc_idx = ce->guc_id;
+	u32 desc_idx = ce->guc_id.id;
 	struct guc_lrc_desc *desc;
-	const struct i915_gem_context *ctx;
-	int prio = I915_CONTEXT_DEFAULT_PRIORITY;
 	bool context_registered;
 	intel_wakeref_t wakeref;
 	int ret = 0;
 
 	GEM_BUG_ON(!engine->mask);
+	GEM_BUG_ON(!sched_state_is_init(ce));
 
 	/*
 	 * Ensure LRC + CT vmas are is same region as write barrier is done
@@ -1311,12 +1464,6 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 
 	context_registered = lrc_desc_registered(guc, desc_idx);
 
-	rcu_read_lock();
-	ctx = rcu_dereference(ce->gem_context);
-	if (ctx)
-		prio = ctx->sched.priority;
-	rcu_read_unlock();
-
 	reset_lrc_desc(guc, desc_idx);
 	set_lrc_desc_registered(guc, desc_idx, ce);
 
@@ -1325,11 +1472,9 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 	desc->engine_submit_mask = adjust_engine_mask(engine->class,
 						      engine->mask);
 	desc->hw_context_desc = ce->lrc.lrca;
-	ce->guc_prio = map_i915_prio_to_guc_prio(prio);
-	desc->priority = ce->guc_prio;
+	desc->priority = ce->guc_state.prio;
 	desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
 	guc_context_policy_init(engine, desc);
-	init_sched_state(ce);
 
 	/*
 	 * The context_lookup xarray is used to determine if the hardware
@@ -1340,26 +1485,23 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 	 * registering this context.
 	 */
 	if (context_registered) {
+		bool disabled;
+		unsigned long flags;
+
 		trace_intel_context_steal_guc_id(ce);
-		if (!loop) {
+		GEM_BUG_ON(!loop);
+
+		/* Seal race with Reset */
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
+		disabled = submission_disabled(guc);
+		if (likely(!disabled)) {
 			set_context_wait_for_deregister_to_register(ce);
 			intel_context_get(ce);
-		} else {
-			bool disabled;
-			unsigned long flags;
-
-			/* Seal race with Reset */
-			spin_lock_irqsave(&ce->guc_state.lock, flags);
-			disabled = submission_disabled(guc);
-			if (likely(!disabled)) {
-				set_context_wait_for_deregister_to_register(ce);
-				intel_context_get(ce);
-			}
-			spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-			if (unlikely(disabled)) {
-				reset_lrc_desc(guc, desc_idx);
-				return 0;	/* Will get registered later */
-			}
+		}
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+		if (unlikely(disabled)) {
+			reset_lrc_desc(guc, desc_idx);
+			return 0;	/* Will get registered later */
 		}
 
 		/*
@@ -1367,20 +1509,18 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 		 * context whose guc_id was stolen.
 		 */
 		with_intel_runtime_pm(runtime_pm, wakeref)
-			ret = deregister_context(ce, ce->guc_id, loop);
-		if (unlikely(ret == -EBUSY)) {
-			clr_context_wait_for_deregister_to_register(ce);
-			intel_context_put(ce);
-		} else if (unlikely(ret == -ENODEV)) {
+			ret = deregister_context(ce, ce->guc_id.id);
+		if (unlikely(ret == -ENODEV))
 			ret = 0;	/* Will get registered later */
-		}
 	} else {
 		with_intel_runtime_pm(runtime_pm, wakeref)
 			ret = register_context(ce, loop);
-		if (unlikely(ret == -EBUSY))
+		if (unlikely(ret == -EBUSY)) {
+			reset_lrc_desc(guc, desc_idx);
+		} else if (unlikely(ret == -ENODEV)) {
 			reset_lrc_desc(guc, desc_idx);
-		else if (unlikely(ret == -ENODEV))
 			ret = 0;	/* Will get registered later */
+		}
 	}
 
 	return ret;
@@ -1440,7 +1580,7 @@ static void __guc_context_sched_enable(struct intel_guc *guc,
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET,
-		ce->guc_id,
+		ce->guc_id.id,
 		GUC_CONTEXT_ENABLE
 	};
 
@@ -1456,7 +1596,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc,
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET,
-		guc_id,	/* ce->guc_id not stable */
+		guc_id,	/* ce->guc_id.id not stable */
 		GUC_CONTEXT_DISABLE
 	};
 
@@ -1472,24 +1612,24 @@ static void guc_blocked_fence_complete(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->guc_state.lock);
 
-	if (!i915_sw_fence_done(&ce->guc_blocked))
-		i915_sw_fence_complete(&ce->guc_blocked);
+	if (!i915_sw_fence_done(&ce->guc_state.blocked))
+		i915_sw_fence_complete(&ce->guc_state.blocked);
 }
 
 static void guc_blocked_fence_reinit(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->guc_state.lock);
-	GEM_BUG_ON(!i915_sw_fence_done(&ce->guc_blocked));
+	GEM_BUG_ON(!i915_sw_fence_done(&ce->guc_state.blocked));
 
 	/*
 	 * This fence is always complete unless a pending schedule disable is
 	 * outstanding. We arm the fence here and complete it when we receive
 	 * the pending schedule disable complete message.
 	 */
-	i915_sw_fence_fini(&ce->guc_blocked);
-	i915_sw_fence_reinit(&ce->guc_blocked);
-	i915_sw_fence_await(&ce->guc_blocked);
-	i915_sw_fence_commit(&ce->guc_blocked);
+	i915_sw_fence_fini(&ce->guc_state.blocked);
+	i915_sw_fence_reinit(&ce->guc_state.blocked);
+	i915_sw_fence_await(&ce->guc_state.blocked);
+	i915_sw_fence_commit(&ce->guc_state.blocked);
 }
 
 static u16 prep_context_pending_disable(struct intel_context *ce)
@@ -1501,13 +1641,12 @@ static u16 prep_context_pending_disable(struct intel_context *ce)
 	guc_blocked_fence_reinit(ce);
 	intel_context_get(ce);
 
-	return ce->guc_id;
+	return ce->guc_id.id;
 }
 
 static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
-	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
 	unsigned long flags;
 	struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm;
 	intel_wakeref_t wakeref;
@@ -1516,20 +1655,14 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
 
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 
-	/*
-	 * Sync with submission path, increment before below changes to context
-	 * state.
-	 */
-	spin_lock(&sched_engine->lock);
 	incr_context_blocked(ce);
-	spin_unlock(&sched_engine->lock);
 
 	enabled = context_enabled(ce);
 	if (unlikely(!enabled || submission_disabled(guc))) {
 		if (enabled)
 			clr_context_enabled(ce);
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		return &ce->guc_blocked;
+		return &ce->guc_state.blocked;
 	}
 
 	/*
@@ -1545,13 +1678,29 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
 	with_intel_runtime_pm(runtime_pm, wakeref)
 		__guc_context_sched_disable(guc, ce, guc_id);
 
-	return &ce->guc_blocked;
+	return &ce->guc_state.blocked;
+}
+
+#define SCHED_STATE_MULTI_BLOCKED_MASK \
+	(SCHED_STATE_BLOCKED_MASK & ~SCHED_STATE_BLOCKED)
+#define SCHED_STATE_NO_UNBLOCK \
+	(SCHED_STATE_MULTI_BLOCKED_MASK | \
+	 SCHED_STATE_PENDING_DISABLE | \
+	 SCHED_STATE_BANNED)
+
+static bool context_cant_unblock(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+
+	return (ce->guc_state.sched_state & SCHED_STATE_NO_UNBLOCK) ||
+		context_guc_id_invalid(ce) ||
+		!lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id) ||
+		!intel_context_is_pinned(ce);
 }
 
 static void guc_context_unblock(struct intel_context *ce)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
-	struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
 	unsigned long flags;
 	struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm;
 	intel_wakeref_t wakeref;
@@ -1562,9 +1711,7 @@ static void guc_context_unblock(struct intel_context *ce)
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 
 	if (unlikely(submission_disabled(guc) ||
-		     !intel_context_is_pinned(ce) ||
-		     context_pending_disable(ce) ||
-		     context_blocked(ce) > 1)) {
+		     context_cant_unblock(ce))) {
 		enable = false;
 	} else {
 		enable = true;
@@ -1573,13 +1720,7 @@ static void guc_context_unblock(struct intel_context *ce)
 		intel_context_get(ce);
 	}
 
-	/*
-	 * Sync with submission path, decrement after above changes to context
-	 * state.
-	 */
-	spin_lock(&sched_engine->lock);
 	decr_context_blocked(ce);
-	spin_unlock(&sched_engine->lock);
 
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
@@ -1593,15 +1734,25 @@ static void guc_context_cancel_request(struct intel_context *ce,
 				       struct i915_request *rq)
 {
 	if (i915_sw_fence_signaled(&rq->submit)) {
-		struct i915_sw_fence *fence = guc_context_block(ce);
+		struct i915_sw_fence *fence;
 
+		intel_context_get(ce);
+		fence = guc_context_block(ce);
 		i915_sw_fence_wait(fence);
 		if (!i915_request_completed(rq)) {
 			__i915_request_skip(rq);
 			guc_reset_state(ce, intel_ring_wrap(ce->ring, rq->head),
 					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(ce);
+		intel_context_put(ce);
 	}
 }
 
@@ -1662,7 +1813,7 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
 		if (!context_guc_id_invalid(ce))
 			with_intel_runtime_pm(runtime_pm, wakeref)
 				__guc_context_set_preemption_timeout(guc,
-								     ce->guc_id,
+								     ce->guc_id.id,
 								     1);
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	}
@@ -1675,40 +1826,22 @@ static void guc_context_sched_disable(struct intel_context *ce)
 	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
 	intel_wakeref_t wakeref;
 	u16 guc_id;
-	bool enabled;
-
-	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
-	    !lrc_desc_registered(guc, ce->guc_id)) {
-		clr_context_enabled(ce);
-		goto unpin;
-	}
-
-	if (!context_enabled(ce))
-		goto unpin;
 
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 
 	/*
-	 * We have to check if the context has been disabled by another thread.
-	 * We also have to check if the context has been pinned again as another
-	 * pin operation is allowed to pass this function. Checking the pin
-	 * count, within ce->guc_state.lock, synchronizes this function with
-	 * guc_request_alloc ensuring a request doesn't slip through the
-	 * 'context_pending_disable' fence. Checking within the spin lock (can't
-	 * sleep) ensures another process doesn't pin this context and generate
-	 * a request before we set the 'context_pending_disable' flag here.
+	 * We have to check if the context has been disabled by another thread,
+	 * check if submssion has been disabled to seal a race with reset and
+	 * finally check if any more requests have been committed to the
+	 * context ensursing that a request doesn't slip through the
+	 * 'context_pending_disable' fence.
 	 */
-	enabled = context_enabled(ce);
-	if (unlikely(!enabled || submission_disabled(guc))) {
-		if (enabled)
-			clr_context_enabled(ce);
+	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
+		     context_has_committed_requests(ce))) {
+		clr_context_enabled(ce);
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 		goto unpin;
 	}
-	if (unlikely(atomic_add_unless(&ce->pin_count, -2, 2))) {
-		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		return;
-	}
 	guc_id = prep_context_pending_disable(ce);
 
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
@@ -1725,20 +1858,20 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
 
-	GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id));
-	GEM_BUG_ON(ce != __get_context(guc, ce->guc_id));
+	GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id));
+	GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id));
 	GEM_BUG_ON(context_enabled(ce));
 
-	clr_context_registered(ce);
-	deregister_context(ce, ce->guc_id, true);
+	deregister_context(ce, ce->guc_id.id);
 }
 
 static void __guc_context_destroy(struct intel_context *ce)
 {
-	GEM_BUG_ON(ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_HIGH] ||
-		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_HIGH] ||
-		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] ||
-		   ce->guc_prio_count[GUC_CLIENT_PRIORITY_NORMAL]);
+	GEM_BUG_ON(ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_KMD_HIGH] ||
+		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_HIGH] ||
+		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] ||
+		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_NORMAL]);
+	GEM_BUG_ON(ce->guc_state.number_committed_requests);
 
 	lrc_fini(ce);
 	intel_context_fini(ce);
@@ -1774,7 +1907,7 @@ static void guc_context_destroy(struct kref *kref)
 		__guc_context_destroy(ce);
 		return;
 	} else if (submission_disabled(guc) ||
-		   !lrc_desc_registered(guc, ce->guc_id)) {
+		   !lrc_desc_registered(guc, ce->guc_id.id)) {
 		release_guc_id(guc, ce);
 		__guc_context_destroy(ce);
 		return;
@@ -1783,10 +1916,10 @@ static void guc_context_destroy(struct kref *kref)
 	/*
 	 * We have to acquire the context spinlock and check guc_id again, if it
 	 * is valid it hasn't been stolen and needs to be deregistered. We
-	 * delete this context from the list of unpinned guc_ids available to
+	 * delete this context from the list of unpinned guc_id available to
 	 * steal to seal a race with guc_lrc_desc_pin(). When the G2H CTB
 	 * returns indicating this context has been deregistered the guc_id is
-	 * returned to the pool of available guc_ids.
+	 * returned to the pool of available guc_id.
 	 */
 	spin_lock_irqsave(&guc->contexts_lock, flags);
 	if (context_guc_id_invalid(ce)) {
@@ -1795,15 +1928,17 @@ static void guc_context_destroy(struct kref *kref)
 		return;
 	}
 
-	if (!list_empty(&ce->guc_id_link))
-		list_del_init(&ce->guc_id_link);
+	if (!list_empty(&ce->guc_id.link))
+		list_del_init(&ce->guc_id.link);
 	spin_unlock_irqrestore(&guc->contexts_lock, flags);
 
 	/* Seal race with Reset */
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 	disabled = submission_disabled(guc);
-	if (likely(!disabled))
+	if (likely(!disabled)) {
 		set_context_destroyed(ce);
+		clr_context_registered(ce);
+	}
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	if (unlikely(disabled)) {
 		release_guc_id(guc, ce);
@@ -1839,20 +1974,23 @@ static void guc_context_set_prio(struct intel_guc *guc,
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_SET_CONTEXT_PRIORITY,
-		ce->guc_id,
+		ce->guc_id.id,
 		prio,
 	};
 
 	GEM_BUG_ON(prio < GUC_CLIENT_PRIORITY_KMD_HIGH ||
 		   prio > GUC_CLIENT_PRIORITY_NORMAL);
+	lockdep_assert_held(&ce->guc_state.lock);
 
-	if (ce->guc_prio == prio || submission_disabled(guc) ||
-	    !context_registered(ce))
+	if (ce->guc_state.prio == prio || submission_disabled(guc) ||
+	    !context_registered(ce)) {
+		ce->guc_state.prio = prio;
 		return;
+	}
 
 	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
 
-	ce->guc_prio = prio;
+	ce->guc_state.prio = prio;
 	trace_intel_context_set_prio(ce);
 }
 
@@ -1871,25 +2009,25 @@ static inline u8 map_i915_prio_to_guc_prio(int prio)
 static inline void add_context_inflight_prio(struct intel_context *ce,
 					     u8 guc_prio)
 {
-	lockdep_assert_held(&ce->guc_active.lock);
-	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count));
+	lockdep_assert_held(&ce->guc_state.lock);
+	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_state.prio_count));
 
-	++ce->guc_prio_count[guc_prio];
+	++ce->guc_state.prio_count[guc_prio];
 
 	/* Overflow protection */
-	GEM_WARN_ON(!ce->guc_prio_count[guc_prio]);
+	GEM_WARN_ON(!ce->guc_state.prio_count[guc_prio]);
 }
 
 static inline void sub_context_inflight_prio(struct intel_context *ce,
 					     u8 guc_prio)
 {
-	lockdep_assert_held(&ce->guc_active.lock);
-	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count));
+	lockdep_assert_held(&ce->guc_state.lock);
+	GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_state.prio_count));
 
 	/* Underflow protection */
-	GEM_WARN_ON(!ce->guc_prio_count[guc_prio]);
+	GEM_WARN_ON(!ce->guc_state.prio_count[guc_prio]);
 
-	--ce->guc_prio_count[guc_prio];
+	--ce->guc_state.prio_count[guc_prio];
 }
 
 static inline void update_context_prio(struct intel_context *ce)
@@ -1900,10 +2038,10 @@ static inline void update_context_prio(struct intel_context *ce)
 	BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH != 0);
 	BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH > GUC_CLIENT_PRIORITY_NORMAL);
 
-	lockdep_assert_held(&ce->guc_active.lock);
+	lockdep_assert_held(&ce->guc_state.lock);
 
-	for (i = 0; i < ARRAY_SIZE(ce->guc_prio_count); ++i) {
-		if (ce->guc_prio_count[i]) {
+	for (i = 0; i < ARRAY_SIZE(ce->guc_state.prio_count); ++i) {
+		if (ce->guc_state.prio_count[i]) {
 			guc_context_set_prio(guc, ce, i);
 			break;
 		}
@@ -1923,8 +2061,8 @@ static void add_to_context(struct i915_request *rq)
 
 	GEM_BUG_ON(rq->guc_prio == GUC_PRIO_FINI);
 
-	spin_lock(&ce->guc_active.lock);
-	list_move_tail(&rq->sched.link, &ce->guc_active.requests);
+	spin_lock(&ce->guc_state.lock);
+	list_move_tail(&rq->sched.link, &ce->guc_state.requests);
 
 	if (rq->guc_prio == GUC_PRIO_INIT) {
 		rq->guc_prio = new_guc_prio;
@@ -1936,12 +2074,12 @@ static void add_to_context(struct i915_request *rq)
 	}
 	update_context_prio(ce);
 
-	spin_unlock(&ce->guc_active.lock);
+	spin_unlock(&ce->guc_state.lock);
 }
 
 static void guc_prio_fini(struct i915_request *rq, struct intel_context *ce)
 {
-	lockdep_assert_held(&ce->guc_active.lock);
+	lockdep_assert_held(&ce->guc_state.lock);
 
 	if (rq->guc_prio != GUC_PRIO_INIT &&
 	    rq->guc_prio != GUC_PRIO_FINI) {
@@ -1955,7 +2093,7 @@ static void remove_from_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
 
-	spin_lock_irq(&ce->guc_active.lock);
+	spin_lock_irq(&ce->guc_state.lock);
 
 	list_del_init(&rq->sched.link);
 	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
@@ -1965,9 +2103,11 @@ static void remove_from_context(struct i915_request *rq)
 
 	guc_prio_fini(rq, ce);
 
-	spin_unlock_irq(&ce->guc_active.lock);
+	decr_context_committed_requests(ce);
 
-	atomic_dec(&ce->guc_id_ref);
+	spin_unlock_irq(&ce->guc_state.lock);
+
+	atomic_dec(&ce->guc_id.ref);
 	i915_request_notify_execute_cb_imm(rq);
 }
 
@@ -1994,17 +2134,32 @@ static const struct intel_context_ops guc_context_ops = {
 	.create_virtual = guc_create_virtual,
 };
 
+static void submit_work_cb(struct irq_work *wrk)
+{
+	struct i915_request *rq = container_of(wrk, typeof(*rq), submit_work);
+
+	might_lock(&rq->engine->sched_engine->lock);
+	i915_sw_fence_complete(&rq->submit);
+}
+
 static void __guc_signal_context_fence(struct intel_context *ce)
 {
-	struct i915_request *rq;
+	struct i915_request *rq, *rn;
 
 	lockdep_assert_held(&ce->guc_state.lock);
 
 	if (!list_empty(&ce->guc_state.fences))
 		trace_intel_context_fence_release(ce);
 
-	list_for_each_entry(rq, &ce->guc_state.fences, guc_fence_link)
-		i915_sw_fence_complete(&rq->submit);
+	/*
+	 * Use an IRQ to ensure locking order of sched_engine->lock ->
+	 * ce->guc_state.lock is preserved.
+	 */
+	list_for_each_entry_safe(rq, rn, &ce->guc_state.fences,
+				 guc_fence_link) {
+		list_del(&rq->guc_fence_link);
+		irq_work_queue(&rq->submit_work);
+	}
 
 	INIT_LIST_HEAD(&ce->guc_state.fences);
 }
@@ -2022,10 +2177,25 @@ static void guc_signal_context_fence(struct intel_context *ce)
 static bool context_needs_register(struct intel_context *ce, bool new_guc_id)
 {
 	return (new_guc_id || test_bit(CONTEXT_LRCA_DIRTY, &ce->flags) ||
-		!lrc_desc_registered(ce_to_guc(ce), ce->guc_id)) &&
+		!lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id)) &&
 		!submission_disabled(ce_to_guc(ce));
 }
 
+static void guc_context_init(struct intel_context *ce)
+{
+	const struct i915_gem_context *ctx;
+	int prio = I915_CONTEXT_DEFAULT_PRIORITY;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(ce->gem_context);
+	if (ctx)
+		prio = ctx->sched.priority;
+	rcu_read_unlock();
+
+	ce->guc_state.prio = map_i915_prio_to_guc_prio(prio);
+	set_bit(CONTEXT_GUC_INIT, &ce->flags);
+}
+
 static int guc_request_alloc(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
@@ -2057,14 +2227,17 @@ static int guc_request_alloc(struct i915_request *rq)
 
 	rq->reserved_space -= GUC_REQUEST_SIZE;
 
+	if (unlikely(!test_bit(CONTEXT_GUC_INIT, &ce->flags)))
+		guc_context_init(ce);
+
 	/*
 	 * Call pin_guc_id here rather than in the pinning step as with
 	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
-	 * guc_ids and creating horrible race conditions. This is especially bad
-	 * when guc_ids are being stolen due to over subscription. By the time
+	 * guc_id and creating horrible race conditions. This is especially bad
+	 * when guc_id are being stolen due to over subscription. By the time
 	 * this function is reached, it is guaranteed that the guc_id will be
 	 * persistent until the generated request is retired. Thus, sealing these
-	 * race conditions. It is still safe to fail here if guc_ids are
+	 * race conditions. It is still safe to fail here if guc_id are
 	 * exhausted and return -EAGAIN to the user indicating that they can try
 	 * again in the future.
 	 *
@@ -2074,7 +2247,7 @@ static int guc_request_alloc(struct i915_request *rq)
 	 * decremented on each retire. When it is zero, a lock around the
 	 * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id.
 	 */
-	if (atomic_add_unless(&ce->guc_id_ref, 1, 0))
+	if (atomic_add_unless(&ce->guc_id.ref, 1, 0))
 		goto out;
 
 	ret = pin_guc_id(guc, ce);	/* returns 1 if new guc_id assigned */
@@ -2087,7 +2260,7 @@ static int guc_request_alloc(struct i915_request *rq)
 				disable_submission(guc);
 				goto out;	/* GPU will be reset */
 			}
-			atomic_dec(&ce->guc_id_ref);
+			atomic_dec(&ce->guc_id.ref);
 			unpin_guc_id(guc, ce);
 			return ret;
 		}
@@ -2102,22 +2275,16 @@ out:
 	 * schedule enable or context registration if either G2H is pending
 	 * respectfully. Once a G2H returns, the fence is released that is
 	 * blocking these requests (see guc_signal_context_fence).
-	 *
-	 * We can safely check the below fields outside of the lock as it isn't
-	 * possible for these fields to transition from being clear to set but
-	 * converse is possible, hence the need for the check within the lock.
 	 */
-	if (likely(!context_wait_for_deregister_to_register(ce) &&
-		   !context_pending_disable(ce)))
-		return 0;
-
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 	if (context_wait_for_deregister_to_register(ce) ||
 	    context_pending_disable(ce)) {
+		init_irq_work(&rq->submit_work, submit_work_cb);
 		i915_sw_fence_await(&rq->submit);
 
 		list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences);
 	}
+	incr_context_committed_requests(ce);
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
 	return 0;
@@ -2259,7 +2426,7 @@ static void guc_bump_inflight_request_prio(struct i915_request *rq,
 	     !new_guc_prio_higher(rq->guc_prio, new_guc_prio)))
 		return;
 
-	spin_lock(&ce->guc_active.lock);
+	spin_lock(&ce->guc_state.lock);
 	if (rq->guc_prio != GUC_PRIO_FINI) {
 		if (rq->guc_prio != GUC_PRIO_INIT)
 			sub_context_inflight_prio(ce, rq->guc_prio);
@@ -2267,16 +2434,16 @@ static void guc_bump_inflight_request_prio(struct i915_request *rq,
 		add_context_inflight_prio(ce, rq->guc_prio);
 		update_context_prio(ce);
 	}
-	spin_unlock(&ce->guc_active.lock);
+	spin_unlock(&ce->guc_state.lock);
 }
 
 static void guc_retire_inflight_request_prio(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
 
-	spin_lock(&ce->guc_active.lock);
+	spin_lock(&ce->guc_state.lock);
 	guc_prio_fini(rq, ce);
-	spin_unlock(&ce->guc_active.lock);
+	spin_unlock(&ce->guc_state.lock);
 }
 
 static void sanitize_hwsp(struct intel_engine_cs *engine)
@@ -2583,12 +2750,6 @@ g2h_context_lookup(struct intel_guc *guc, u32 desc_idx)
 	return ce;
 }
 
-static void decr_outstanding_submission_g2h(struct intel_guc *guc)
-{
-	if (atomic_dec_and_test(&guc->outstanding_submission_g2h))
-		wake_up_all(&guc->ct.wq);
-}
-
 int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
 					  const u32 *msg,
 					  u32 len)
@@ -2607,6 +2768,13 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
 
 	trace_intel_context_deregister_done(ce);
 
+#ifdef CONFIG_DRM_I915_SELFTEST
+	if (unlikely(ce->drop_deregister)) {
+		ce->drop_deregister = false;
+		return 0;
+	}
+#endif
+
 	if (context_wait_for_deregister_to_register(ce)) {
 		struct intel_runtime_pm *runtime_pm =
 			&ce->engine->gt->i915->runtime_pm;
@@ -2652,8 +2820,7 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,
 		     (!context_pending_enable(ce) &&
 		     !context_pending_disable(ce)))) {
 		drm_err(&guc_to_gt(guc)->i915->drm,
-			"Bad context sched_state 0x%x, 0x%x, desc_idx %u",
-			atomic_read(&ce->guc_sched_state_no_lock),
+			"Bad context sched_state 0x%x, desc_idx %u",
 			ce->guc_state.sched_state, desc_idx);
 		return -EPROTO;
 	}
@@ -2661,10 +2828,26 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,
 	trace_intel_context_sched_done(ce);
 
 	if (context_pending_enable(ce)) {
+#ifdef CONFIG_DRM_I915_SELFTEST
+		if (unlikely(ce->drop_schedule_enable)) {
+			ce->drop_schedule_enable = false;
+			return 0;
+		}
+#endif
+
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
 		clr_context_pending_enable(ce);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	} else if (context_pending_disable(ce)) {
 		bool banned;
 
+#ifdef CONFIG_DRM_I915_SELFTEST
+		if (unlikely(ce->drop_schedule_disable)) {
+			ce->drop_schedule_disable = false;
+			return 0;
+		}
+#endif
+
 		/*
 		 * Unpin must be done before __guc_signal_context_fence,
 		 * otherwise a race exists between the requests getting
@@ -2721,7 +2904,12 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	if (likely(!intel_context_is_banned(ce))) {
+	/*
+	 * XXX: Racey if request cancellation has occurred, see comment in
+	 * __guc_reset_context().
+	 */
+	if (likely(!intel_context_is_banned(ce) &&
+		   !context_blocked(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
 	}
@@ -2797,33 +2985,47 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 	struct intel_context *ce;
 	struct i915_request *rq;
 	unsigned long index;
+	unsigned long flags;
 
 	/* Reset called during driver load? GuC not yet initialised! */
 	if (unlikely(!guc_submission_initialized(guc)))
 		return;
 
+	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
-		if (!intel_context_is_pinned(ce))
+		if (!kref_get_unless_zero(&ce->ref))
 			continue;
 
+		xa_unlock(&guc->context_lookup);
+
+		if (!intel_context_is_pinned(ce))
+			goto next;
+
 		if (intel_engine_is_virtual(ce->engine)) {
 			if (!(ce->engine->mask & engine->mask))
-				continue;
+				goto next;
 		} else {
 			if (ce->engine != engine)
-				continue;
+				goto next;
 		}
 
-		list_for_each_entry(rq, &ce->guc_active.requests, sched.link) {
+		list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
 			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
 				continue;
 
 			intel_engine_set_hung_context(engine, ce);
 
 			/* Can only cope with one hang at a time... */
-			return;
+			intel_context_put(ce);
+			xa_lock(&guc->context_lookup);
+			goto done;
 		}
+next:
+		intel_context_put(ce);
+		xa_lock(&guc->context_lookup);
 	}
+done:
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
@@ -2839,23 +3041,34 @@ void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
 	if (unlikely(!guc_submission_initialized(guc)))
 		return;
 
+	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
-		if (!intel_context_is_pinned(ce))
+		if (!kref_get_unless_zero(&ce->ref))
 			continue;
 
+		xa_unlock(&guc->context_lookup);
+
+		if (!intel_context_is_pinned(ce))
+			goto next;
+
 		if (intel_engine_is_virtual(ce->engine)) {
 			if (!(ce->engine->mask & engine->mask))
-				continue;
+				goto next;
 		} else {
 			if (ce->engine != engine)
-				continue;
+				goto next;
 		}
 
-		spin_lock_irqsave(&ce->guc_active.lock, flags);
-		intel_engine_dump_active_requests(&ce->guc_active.requests,
+		spin_lock(&ce->guc_state.lock);
+		intel_engine_dump_active_requests(&ce->guc_state.requests,
 						  hung_rq, m);
-		spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+		spin_unlock(&ce->guc_state.lock);
+
+next:
+		intel_context_put(ce);
+		xa_lock(&guc->context_lookup);
 	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 void intel_guc_submission_print_info(struct intel_guc *guc,
@@ -2881,7 +3094,7 @@ void intel_guc_submission_print_info(struct intel_guc *guc,
 
 		priolist_for_each_request(rq, pl)
 			drm_printf(p, "guc_id=%u, seqno=%llu\n",
-				   rq->context->guc_id,
+				   rq->context->guc_id.id,
 				   rq->fence.seqno);
 	}
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
@@ -2893,13 +3106,12 @@ static inline void guc_log_context_priority(struct drm_printer *p,
 {
 	int i;
 
-	drm_printf(p, "\t\tPriority: %d\n",
-		   ce->guc_prio);
+	drm_printf(p, "\t\tPriority: %d\n", ce->guc_state.prio);
 	drm_printf(p, "\t\tNumber Requests (lower index == higher priority)\n");
 	for (i = GUC_CLIENT_PRIORITY_KMD_HIGH;
 	     i < GUC_CLIENT_PRIORITY_NUM; ++i) {
 		drm_printf(p, "\t\tNumber requests in priority band[%d]: %d\n",
-			   i, ce->guc_prio_count[i]);
+			   i, ce->guc_state.prio_count[i]);
 	}
 	drm_printf(p, "\n");
 }
@@ -2909,9 +3121,11 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
 {
 	struct intel_context *ce;
 	unsigned long index;
+	unsigned long flags;
 
+	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
-		drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id);
+		drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id);
 		drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
 		drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
 			   ce->ring->head,
@@ -2922,13 +3136,13 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
 		drm_printf(p, "\t\tContext Pin Count: %u\n",
 			   atomic_read(&ce->pin_count));
 		drm_printf(p, "\t\tGuC ID Ref Count: %u\n",
-			   atomic_read(&ce->guc_id_ref));
-		drm_printf(p, "\t\tSchedule State: 0x%x, 0x%x\n\n",
-			   ce->guc_state.sched_state,
-			   atomic_read(&ce->guc_sched_state_no_lock));
+			   atomic_read(&ce->guc_id.ref));
+		drm_printf(p, "\t\tSchedule State: 0x%x\n\n",
+			   ce->guc_state.sched_state);
 
 		guc_log_context_priority(p, ce);
 	}
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
 }
 
 static struct intel_context *
@@ -3036,3 +3250,7 @@ bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve)
 
 	return false;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_guc.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
new file mode 100644
index 000000000000..fb0e4a7bd8ca
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright �� 2021 Intel Corporation
+ */
+
+#include "selftests/intel_scheduler_helpers.h"
+
+static struct i915_request *nop_user_request(struct intel_context *ce,
+					     struct i915_request *from)
+{
+	struct i915_request *rq;
+	int ret;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return rq;
+
+	if (from) {
+		ret = i915_sw_fence_await_dma_fence(&rq->submit,
+						    &from->fence, 0,
+						    I915_FENCE_GFP);
+		if (ret < 0) {
+			i915_request_put(rq);
+			return ERR_PTR(ret);
+		}
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	return rq;
+}
+
+static int intel_guc_scrub_ctbs(void *arg)
+{
+	struct intel_gt *gt = arg;
+	int ret = 0;
+	int i;
+	struct i915_request *last[3] = {NULL, NULL, NULL}, *rq;
+	intel_wakeref_t wakeref;
+	struct intel_engine_cs *engine;
+	struct intel_context *ce;
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+	engine = intel_selftest_find_any_engine(gt);
+
+	/* Submit requests and inject errors forcing G2H to be dropped */
+	for (i = 0; i < 3; ++i) {
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
+			pr_err("Failed to create context, %d: %d\n", i, ret);
+			goto err;
+		}
+
+		switch (i) {
+		case 0:
+			ce->drop_schedule_enable = true;
+			break;
+		case 1:
+			ce->drop_schedule_disable = true;
+			break;
+		case 2:
+			ce->drop_deregister = true;
+			break;
+		}
+
+		rq = nop_user_request(ce, NULL);
+		intel_context_put(ce);
+
+		if (IS_ERR(rq)) {
+			ret = PTR_ERR(rq);
+			pr_err("Failed to create request, %d: %d\n", i, ret);
+			goto err;
+		}
+
+		last[i] = rq;
+	}
+
+	for (i = 0; i < 3; ++i) {
+		ret = i915_request_wait(last[i], 0, HZ);
+		if (ret < 0) {
+			pr_err("Last request failed to complete: %d\n", ret);
+			goto err;
+		}
+		i915_request_put(last[i]);
+		last[i] = NULL;
+	}
+
+	/* Force all H2G / G2H to be submitted / processed */
+	intel_gt_retire_requests(gt);
+	msleep(500);
+
+	/* Scrub missing G2H */
+	intel_gt_handle_error(engine->gt, -1, 0, "selftest reset");
+
+	/* GT will not idle if G2H are lost */
+	ret = intel_gt_wait_for_idle(gt, HZ);
+	if (ret < 0) {
+		pr_err("GT failed to idle: %d\n", ret);
+		goto err;
+	}
+
+err:
+	for (i = 0; i < 3; ++i)
+		if (last[i])
+			i915_request_put(last[i]);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+
+	return ret;
+}
+
+int intel_guc_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(intel_guc_scrub_ctbs),
+	};
+	struct intel_gt *gt = &i915->gt;
+
+	if (intel_gt_is_wedged(gt))
+		return 0;
+
+	if (!intel_uc_uses_guc_submission(&gt->uc))
+		return 0;
+
+	return intel_gt_live_subtests(tests, gt);
+}
diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
index 7b274c51cac0..6e2ad68f8f3f 100644
--- a/drivers/gpu/drm/i915/i915_buddy.c
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kmemleak.h>
+#include <linux/sizes.h>
 
 #include "i915_buddy.h"
 
@@ -82,6 +83,7 @@ int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size)
 	size = round_down(size, chunk_size);
 
 	mm->size = size;
+	mm->avail = size;
 	mm->chunk_size = chunk_size;
 	mm->max_order = ilog2(size) - ilog2(chunk_size);
 
@@ -155,6 +157,8 @@ void i915_buddy_fini(struct i915_buddy_mm *mm)
 		i915_block_free(mm, mm->roots[i]);
 	}
 
+	GEM_WARN_ON(mm->avail != mm->size);
+
 	kfree(mm->roots);
 	kfree(mm->free_list);
 }
@@ -230,6 +234,7 @@ void i915_buddy_free(struct i915_buddy_mm *mm,
 		     struct i915_buddy_block *block)
 {
 	GEM_BUG_ON(!i915_buddy_block_is_allocated(block));
+	mm->avail += i915_buddy_block_size(mm, block);
 	__i915_buddy_free(mm, block);
 }
 
@@ -283,6 +288,7 @@ i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order)
 	}
 
 	mark_allocated(block);
+	mm->avail -= i915_buddy_block_size(mm, block);
 	kmemleak_update_trace(block);
 	return block;
 
@@ -368,6 +374,7 @@ int i915_buddy_alloc_range(struct i915_buddy_mm *mm,
 			}
 
 			mark_allocated(block);
+			mm->avail -= i915_buddy_block_size(mm, block);
 			list_add_tail(&block->link, &allocated);
 			continue;
 		}
@@ -402,6 +409,44 @@ err_free:
 	return err;
 }
 
+void i915_buddy_block_print(struct i915_buddy_mm *mm,
+			    struct i915_buddy_block *block,
+			    struct drm_printer *p)
+{
+	u64 start = i915_buddy_block_offset(block);
+	u64 size = i915_buddy_block_size(mm, block);
+
+	drm_printf(p, "%#018llx-%#018llx: %llu\n", start, start + size, size);
+}
+
+void i915_buddy_print(struct i915_buddy_mm *mm, struct drm_printer *p)
+{
+	int order;
+
+	drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB\n",
+		   mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20);
+
+	for (order = mm->max_order; order >= 0; order--) {
+		struct i915_buddy_block *block;
+		u64 count = 0, free;
+
+		list_for_each_entry(block, &mm->free_list[order], link) {
+			GEM_BUG_ON(!i915_buddy_block_is_free(block));
+			count++;
+		}
+
+		drm_printf(p, "order-%d ", order);
+
+		free = count * (mm->chunk_size << order);
+		if (free < SZ_1M)
+			drm_printf(p, "free: %lluKiB", free >> 10);
+		else
+			drm_printf(p, "free: %lluMiB", free >> 20);
+
+		drm_printf(p, ", pages: %llu\n", count);
+	}
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/i915_buddy.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_buddy.h b/drivers/gpu/drm/i915/i915_buddy.h
index 3940d632f208..7077742112ac 100644
--- a/drivers/gpu/drm/i915/i915_buddy.h
+++ b/drivers/gpu/drm/i915/i915_buddy.h
@@ -10,6 +10,8 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 
+#include <drm/drm_print.h>
+
 struct i915_buddy_block {
 #define I915_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
 #define I915_BUDDY_HEADER_STATE  GENMASK_ULL(11, 10)
@@ -69,6 +71,7 @@ struct i915_buddy_mm {
 	/* Must be at least PAGE_SIZE */
 	u64 chunk_size;
 	u64 size;
+	u64 avail;
 };
 
 static inline u64
@@ -129,6 +132,11 @@ void i915_buddy_free(struct i915_buddy_mm *mm, struct i915_buddy_block *block);
 
 void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects);
 
+void i915_buddy_print(struct i915_buddy_mm *mm, struct drm_printer *p);
+void i915_buddy_block_print(struct i915_buddy_mm *mm,
+			    struct i915_buddy_block *block,
+			    struct drm_printer *p);
+
 void i915_buddy_module_exit(void);
 int i915_buddy_module_init(void);
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 44969f5dde50..04351a851586 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -238,6 +238,7 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 static int i915_gem_object_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
+	struct drm_printer p = drm_seq_file_printer(m);
 	struct intel_memory_region *mr;
 	enum intel_region_id id;
 
@@ -246,8 +247,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 		   atomic_read(&i915->mm.free_count),
 		   i915->mm.shrink_memory);
 	for_each_memory_region(mr, i915, id)
-		seq_printf(m, "%s: total:%pa, available:%pa bytes\n",
-			   mr->name, &mr->total, &mr->avail);
+		intel_memory_region_debug(mr, &p);
 
 	return 0;
 }
@@ -420,13 +420,11 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		int max_freq;
 
 		rp_state_limits = intel_uncore_read(&dev_priv->uncore, GEN6_RP_STATE_LIMITS);
-		if (IS_GEN9_LP(dev_priv)) {
-			rp_state_cap = intel_uncore_read(&dev_priv->uncore, BXT_RP_STATE_CAP);
+		rp_state_cap = intel_rps_read_state_cap(rps);
+		if (IS_GEN9_LP(dev_priv))
 			gt_perf_status = intel_uncore_read(&dev_priv->uncore, BXT_GT_PERF_STATUS);
-		} else {
-			rp_state_cap = intel_uncore_read(&dev_priv->uncore, GEN6_RP_STATE_CAP);
+		else
 			gt_perf_status = intel_uncore_read(&dev_priv->uncore, GEN6_GT_PERF_STATUS);
-		}
 
 		/* RPSTAT1 is in the GT power well */
 		intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a8129153d1db..37c1ca266bcd 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1859,11 +1859,11 @@ i915_gem_vm_lookup(struct drm_i915_file_private *file_priv, u32 id)
 {
 	struct i915_address_space *vm;
 
-	rcu_read_lock();
+	xa_lock(&file_priv->vm_xa);
 	vm = xa_load(&file_priv->vm_xa, id);
-	if (vm && !kref_get_unless_zero(&vm->ref))
-		vm = NULL;
-	rcu_read_unlock();
+	if (vm)
+		kref_get(&vm->ref);
+	xa_unlock(&file_priv->vm_xa);
 
 	return vm;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_ww.h b/drivers/gpu/drm/i915/i915_gem_ww.h
index f6b1a796667b..86f0fe343de6 100644
--- a/drivers/gpu/drm/i915/i915_gem_ww.h
+++ b/drivers/gpu/drm/i915/i915_gem_ww.h
@@ -11,8 +11,7 @@ struct i915_gem_ww_ctx {
 	struct ww_acquire_ctx ctx;
 	struct list_head obj_list;
 	struct drm_i915_gem_object *contended;
-	unsigned short intr;
-	unsigned short loop;
+	bool intr;
 };
 
 void i915_gem_ww_ctx_init(struct i915_gem_ww_ctx *ctx, bool intr);
@@ -20,31 +19,23 @@ void i915_gem_ww_ctx_fini(struct i915_gem_ww_ctx *ctx);
 int __must_check i915_gem_ww_ctx_backoff(struct i915_gem_ww_ctx *ctx);
 void i915_gem_ww_unlock_single(struct drm_i915_gem_object *obj);
 
-/* Internal functions used by the inlines! Don't use. */
+/* Internal function used by the inlines! Don't use. */
 static inline int __i915_gem_ww_fini(struct i915_gem_ww_ctx *ww, int err)
 {
-	ww->loop = 0;
 	if (err == -EDEADLK) {
 		err = i915_gem_ww_ctx_backoff(ww);
 		if (!err)
-			ww->loop = 1;
+			err = -EDEADLK;
 	}
 
-	if (!ww->loop)
+	if (err != -EDEADLK)
 		i915_gem_ww_ctx_fini(ww);
 
 	return err;
 }
 
-static inline void
-__i915_gem_ww_init(struct i915_gem_ww_ctx *ww, bool intr)
-{
-	i915_gem_ww_ctx_init(ww, intr);
-	ww->loop = 1;
-}
-
-#define for_i915_gem_ww(_ww, _err, _intr)			\
-	for (__i915_gem_ww_init(_ww, _intr); (_ww)->loop;	\
-	     _err = __i915_gem_ww_fini(_ww, _err))
-
+#define for_i915_gem_ww(_ww, _err, _intr)			  \
+	for (i915_gem_ww_ctx_init(_ww, _intr), (_err) = -EDEADLK; \
+	     (_err) == -EDEADLK;				  \
+	     (_err) = __i915_gem_ww_fini(_ww, _err))
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9cf6ac575de1..b9f66dbd46bb 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -431,6 +431,7 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 	const struct sseu_dev_info *sseu = &ee->engine->gt->info.sseu;
 	int slice;
 	int subslice;
+	int iter;
 
 	err_printf(m, "  INSTDONE: 0x%08x\n",
 		   ee->instdone.instdone);
@@ -444,19 +445,38 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 	if (GRAPHICS_VER(m->i915) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice,
-			   ee->instdone.sampler[slice][subslice]);
+	if (GRAPHICS_VER_FULL(m->i915) >= IP_VER(12, 50)) {
+		for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+			err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.sampler[slice][subslice]);
 
-	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice,
-			   ee->instdone.row[slice][subslice]);
+		for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+			err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.row[slice][subslice]);
+	} else {
+		for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+			err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.sampler[slice][subslice]);
+
+		for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+			err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.row[slice][subslice]);
+	}
 
 	if (GRAPHICS_VER(m->i915) < 12)
 		return;
 
+	if (GRAPHICS_VER_FULL(m->i915) >= IP_VER(12, 55)) {
+		for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+			err_printf(m, "  GEOM_SVGUNIT_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.geom_svg[slice][subslice]);
+	}
+
 	err_printf(m, "  SC_INSTDONE_EXTRA: 0x%08x\n",
 		   ee->instdone.slice_common_extra[0]);
 	err_printf(m, "  SC_INSTDONE_EXTRA2: 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c
index d8b4482c69d0..ab2295dd4500 100644
--- a/drivers/gpu/drm/i915/i915_module.c
+++ b/drivers/gpu/drm/i915/i915_module.c
@@ -67,8 +67,8 @@ static const struct {
 	{ .init = i915_mock_selftests },
 	{ .init = i915_pmu_init,
 	  .exit = i915_pmu_exit },
-	{ .init = i915_register_pci_driver,
-	  .exit = i915_unregister_pci_driver },
+	{ .init = i915_pci_register_driver,
+	  .exit = i915_pci_unregister_driver },
 	{ .init = i915_perf_sysctl_register,
 	  .exit = i915_perf_sysctl_unregister },
 };
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 52c04369559f..d4a6a9dcf182 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -894,7 +894,7 @@ static const struct intel_device_info rkl_info = {
 	.has_snoop = 1, \
 	.is_dgfx = 1
 
-static const struct intel_device_info dg1_info __maybe_unused = {
+static const struct intel_device_info dg1_info = {
 	GEN12_FEATURES,
 	DGFX_FEATURES,
 	.graphics_rel = 10,
@@ -912,7 +912,6 @@ static const struct intel_device_info adl_s_info = {
 	GEN12_FEATURES,
 	PLATFORM(INTEL_ALDERLAKE_S),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
-	.require_force_probe = 1,
 	.display.has_hti = 1,
 	.display.has_psr_hw_tracking = 0,
 	.platform_engine_mask =
@@ -1115,6 +1114,7 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_RKL_IDS(&rkl_info),
 	INTEL_ADLS_IDS(&adl_s_info),
 	INTEL_ADLP_IDS(&adl_p_info),
+	INTEL_DG1_IDS(&dg1_info),
 	{0, 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
@@ -1234,12 +1234,12 @@ static struct pci_driver i915_pci_driver = {
 	.driver.pm = &i915_pm_ops,
 };
 
-int i915_register_pci_driver(void)
+int i915_pci_register_driver(void)
 {
 	return pci_register_driver(&i915_pci_driver);
 }
 
-void i915_unregister_pci_driver(void)
+void i915_pci_unregister_driver(void)
 {
 	pci_unregister_driver(&i915_pci_driver);
 }
diff --git a/drivers/gpu/drm/i915/i915_pci.h b/drivers/gpu/drm/i915/i915_pci.h
index b386f319f52e..ee048c238174 100644
--- a/drivers/gpu/drm/i915/i915_pci.h
+++ b/drivers/gpu/drm/i915/i915_pci.h
@@ -1,8 +1,12 @@
+/* SPDX-License-Identifier: MIT */
 /*
- * SPDX-License-Identifier: MIT
- *
  * Copyright © 2021 Intel Corporation
  */
 
-int i915_register_pci_driver(void);
-void i915_unregister_pci_driver(void);
+#ifndef __I915_PCI_H__
+#define __I915_PCI_H__
+
+int i915_pci_register_driver(void);
+void i915_pci_unregister_driver(void);
+
+#endif /* __I915_PCI_H__ */
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index e49da36c62fb..5e2b909827f4 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -432,9 +432,6 @@ static int query_memregion_info(struct drm_i915_private *i915,
 	u32 total_length;
 	int ret, id, i;
 
-	if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM))
-		return -ENODEV;
-
 	if (query_item->flags != 0)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c8de2b4c6a9b..251d6ddebcff 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2555,6 +2555,32 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_HWS_PGA(base)	_MMIO((base) + 0x80)
 #define RING_ID(base)		_MMIO((base) + 0x8c)
 #define RING_HWS_PGA_GEN6(base)	_MMIO((base) + 0x2080)
+
+#define RING_CMD_CCTL(base)	_MMIO((base) + 0xc4)
+/*
+ * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
+ * The lsb of each can be considered a separate enabling bit for encryption.
+ * 6:0 == default MOCS value for reads  =>  6:1 == table index for reads.
+ * 13:7 == default MOCS value for writes => 13:8 == table index for writes.
+ * 15:14 == Reserved => 31:30 are set to 0.
+ */
+#define CMD_CCTL_WRITE_OVERRIDE_MASK REG_GENMASK(13, 7)
+#define CMD_CCTL_READ_OVERRIDE_MASK REG_GENMASK(6, 0)
+#define CMD_CCTL_MOCS_MASK (CMD_CCTL_WRITE_OVERRIDE_MASK | \
+			    CMD_CCTL_READ_OVERRIDE_MASK)
+#define CMD_CCTL_MOCS_OVERRIDE(write, read)				      \
+		(REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, (write) << 1) | \
+		 REG_FIELD_PREP(CMD_CCTL_READ_OVERRIDE_MASK, (read) << 1))
+
+#define BLIT_CCTL(base) _MMIO((base) + 0x204)
+#define   BLIT_CCTL_DST_MOCS_MASK       REG_GENMASK(14, 8)
+#define   BLIT_CCTL_SRC_MOCS_MASK       REG_GENMASK(6, 0)
+#define   BLIT_CCTL_MASK (BLIT_CCTL_DST_MOCS_MASK | \
+			  BLIT_CCTL_SRC_MOCS_MASK)
+#define   BLIT_CCTL_MOCS(dst, src)				       \
+		(REG_FIELD_PREP(BLIT_CCTL_DST_MOCS_MASK, (dst) << 1) | \
+		 REG_FIELD_PREP(BLIT_CCTL_SRC_MOCS_MASK, (src) << 1))
+
 #define RING_RESET_CTL(base)	_MMIO((base) + 0xd0)
 #define   RESET_CTL_CAT_ERROR	   REG_BIT(2)
 #define   RESET_CTL_READY_TO_RESET REG_BIT(1)
@@ -2690,6 +2716,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN12_SC_INSTDONE_EXTRA2	_MMIO(0x7108)
 #define GEN7_SAMPLER_INSTDONE	_MMIO(0xe160)
 #define GEN7_ROW_INSTDONE	_MMIO(0xe164)
+#define XEHPG_INSTDONE_GEOM_SVG		_MMIO(0x666c)
 #define MCFG_MCR_SELECTOR		_MMIO(0xfd0)
 #define SF_MCR_SELECTOR			_MMIO(0xfd8)
 #define GEN8_MCR_SELECTOR		_MMIO(0xfdc)
@@ -2824,6 +2851,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MI_MODE		_MMIO(0x209c)
 # define VS_TIMER_DISPATCH				(1 << 6)
 # define MI_FLUSH_ENABLE				(1 << 12)
+# define TGL_NESTED_BB_EN				(1 << 12)
 # define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
 # define MODE_IDLE					(1 << 9)
 # define STOP_RING					(1 << 8)
@@ -3154,7 +3182,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
 
-#define GEN12_GT_DSS_ENABLE _MMIO(0x913C)
+#define GEN12_GT_GEOMETRY_DSS_ENABLE _MMIO(0x913C)
+#define GEN12_GT_COMPUTE_DSS_ENABLE _MMIO(0x9144)
 
 #define XEHP_EU_ENABLE			_MMIO(0x9134)
 #define XEHP_EU_ENA_MASK		0xFF
@@ -4117,6 +4146,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RPN_CAP_MASK		REG_GENMASK(23, 16)
 #define BXT_RP_STATE_CAP        _MMIO(0x138170)
 #define GEN9_RP_STATE_LIMITS	_MMIO(0x138148)
+#define XEHPSDV_RP_STATE_CAP	_MMIO(0x250014)
 
 /*
  * Logical Context regs
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 1bc1349ba3c2..7bd9ed20623e 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -218,6 +218,11 @@ struct i915_request {
 	};
 	struct llist_head execute_cb;
 	struct i915_sw_fence semaphore;
+	/**
+	 * @submit_work: complete submit fence from an IRQ if needed for
+	 * locking hierarchy reasons.
+	 */
+	struct irq_work submit_work;
 
 	/*
 	 * A list of everyone we wait upon, and everyone who waits upon us.
@@ -285,18 +290,23 @@ struct i915_request {
 		struct hrtimer timer;
 	} watchdog;
 
-	/*
-	 * Requests may need to be stalled when using GuC submission waiting for
-	 * certain GuC operations to complete. If that is the case, stalled
-	 * requests are added to a per context list of stalled requests. The
-	 * below list_head is the link in that list.
+	/**
+	 * @guc_fence_link: Requests may need to be stalled when using GuC
+	 * submission waiting for certain GuC operations to complete. If that is
+	 * the case, stalled requests are added to a per context list of stalled
+	 * requests. The below list_head is the link in that list. Protected by
+	 * ce->guc_state.lock.
 	 */
 	struct list_head guc_fence_link;
 
 	/**
-	 * Priority level while the request is inflight. Differs from i915
-	 * scheduler priority. See comment above
-	 * I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP for details.
+	 * @guc_prio: Priority level while the request is in flight. Differs
+	 * from i915 scheduler priority. See comment above
+	 * I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP for details. Protected by
+	 * ce->guc_active.lock. Two special values (GUC_PRIO_INIT and
+	 * GUC_PRIO_FINI) outside the GuC priority range are used to indicate
+	 * if the priority has not been initialized yet or if no more updates
+	 * are possible because the request has completed.
 	 */
 #define	GUC_PRIO_INIT	0xff
 #define	GUC_PRIO_FINI	0xfe
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 63fec1c3c132..8104981a6604 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -900,23 +900,19 @@ DECLARE_EVENT_CLASS(intel_context,
 			     __field(u32, guc_id)
 			     __field(int, pin_count)
 			     __field(u32, sched_state)
-			     __field(u32, guc_sched_state_no_lock)
 			     __field(u8, guc_prio)
 			     ),
 
 		    TP_fast_assign(
-			   __entry->guc_id = ce->guc_id;
+			   __entry->guc_id = ce->guc_id.id;
 			   __entry->pin_count = atomic_read(&ce->pin_count);
 			   __entry->sched_state = ce->guc_state.sched_state;
-			   __entry->guc_sched_state_no_lock =
-			   atomic_read(&ce->guc_sched_state_no_lock);
-			   __entry->guc_prio = ce->guc_prio;
+			   __entry->guc_prio = ce->guc_state.prio;
 			   ),
 
-		    TP_printk("guc_id=%d, pin_count=%d sched_state=0x%x,0x%x, guc_prio=%u",
+		    TP_printk("guc_id=%d, pin_count=%d sched_state=0x%x, guc_prio=%u",
 			      __entry->guc_id, __entry->pin_count,
 			      __entry->sched_state,
-			      __entry->guc_sched_state_no_lock,
 			      __entry->guc_prio)
 );
 
@@ -1243,7 +1239,7 @@ DECLARE_EVENT_CLASS(i915_context,
 	TP_fast_assign(
 			__entry->dev = ctx->i915->drm.primary->index;
 			__entry->ctx = ctx;
-			__entry->vm = rcu_access_pointer(ctx->vm);
+			__entry->vm = ctx->vm;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 6877362f6b85..d59fbb019032 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -126,12 +126,30 @@ static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man,
 	kfree(bman_res);
 }
 
+static void i915_ttm_buddy_man_debug(struct ttm_resource_manager *man,
+				     struct drm_printer *printer)
+{
+	struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+	struct i915_buddy_block *block;
+
+	mutex_lock(&bman->lock);
+	drm_printf(printer, "default_page_size: %lluKiB\n",
+		   bman->default_page_size >> 10);
+
+	i915_buddy_print(&bman->mm, printer);
+
+	drm_printf(printer, "reserved:\n");
+	list_for_each_entry(block, &bman->reserved, link)
+		i915_buddy_block_print(&bman->mm, block, printer);
+	mutex_unlock(&bman->lock);
+}
+
 static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = {
 	.alloc = i915_ttm_buddy_man_alloc,
 	.free = i915_ttm_buddy_man_free,
+	.debug = i915_ttm_buddy_man_debug,
 };
 
-
 /**
  * i915_ttm_buddy_man_init - Setup buddy allocator based ttm manager
  * @bdev: The ttm device
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 779eb2fa90b6..e7f7e6627750 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -78,6 +78,18 @@ int intel_memory_region_reserve(struct intel_memory_region *mem,
 	return i915_ttm_buddy_man_reserve(man, offset, size);
 }
 
+void intel_memory_region_debug(struct intel_memory_region *mr,
+			       struct drm_printer *printer)
+{
+	drm_printf(printer, "%s: ", mr->name);
+
+	if (mr->region_private)
+		ttm_resource_manager_debug(mr->region_private, printer);
+	else
+		drm_printf(printer, "total:%pa, available:%pa bytes\n",
+			   &mr->total, &mr->avail);
+}
+
 struct intel_memory_region *
 intel_memory_region_create(struct drm_i915_private *i915,
 			   resource_size_t start,
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 1f2b96efa69d..3feae3353d33 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -15,6 +15,7 @@
 
 struct drm_i915_private;
 struct drm_i915_gem_object;
+struct drm_printer;
 struct intel_memory_region;
 struct sg_table;
 struct ttm_resource;
@@ -127,6 +128,9 @@ int intel_memory_region_reserve(struct intel_memory_region *mem,
 				resource_size_t offset,
 				resource_size_t size);
 
+void intel_memory_region_debug(struct intel_memory_region *mr,
+			       struct drm_printer *printer);
+
 struct intel_memory_region *
 i915_gem_ttm_system_setup(struct drm_i915_private *i915,
 			  u16 type, u16 instance);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 6b38bc2811c1..f9767054dbdf 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -64,7 +64,7 @@ static void mmio_debug_resume(struct intel_uncore_mmio_debug *mmio_debug)
 
 static const char * const forcewake_domain_names[] = {
 	"render",
-	"blitter",
+	"gt",
 	"media",
 	"vdbox0",
 	"vdbox1",
@@ -945,105 +945,92 @@ static const struct intel_forcewake_range __vlv_fw_ranges[] = {
 #define __gen11_fwtable_reg_read_fw_domains(uncore, offset) \
 	find_fw_domain(uncore, offset)
 
-#define __gen12_fwtable_reg_read_fw_domains(uncore, offset) \
-	find_fw_domain(uncore, offset)
-
 /* *Must* be sorted by offset! See intel_shadow_table_check(). */
-static const i915_reg_t gen8_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),	/* 0x2000 (base) */
-	GEN6_RPNSWREQ,			/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,		/* 0xA00C */
-	RING_TAIL(GEN6_BSD_RING_BASE),	/* 0x12000 (base) */
-	RING_TAIL(VEBOX_RING_BASE),	/* 0x1a000 (base) */
-	RING_TAIL(BLT_RING_BASE),	/* 0x22000 (base) */
+static const struct i915_range gen8_shadowed_regs[] = {
+	{ .start =  0x2030, .end =  0x2030 },
+	{ .start =  0xA008, .end =  0xA00C },
+	{ .start = 0x12030, .end = 0x12030 },
+	{ .start = 0x1a030, .end = 0x1a030 },
+	{ .start = 0x22030, .end = 0x22030 },
 	/* TODO: Other registers are not yet used */
 };
 
-static const i915_reg_t gen11_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
-	RING_EXECLIST_CONTROL(RENDER_RING_BASE),        /* 0x2550 */
-	GEN6_RPNSWREQ,					/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
-	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
-	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
-	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
-	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
-	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
-	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
-	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
-	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
-	/* TODO: Other registers are not yet used */
+static const struct i915_range gen11_shadowed_regs[] = {
+	{ .start =   0x2030, .end =   0x2030 },
+	{ .start =   0x2550, .end =   0x2550 },
+	{ .start =   0xA008, .end =   0xA00C },
+	{ .start =  0x22030, .end =  0x22030 },
+	{ .start =  0x22230, .end =  0x22230 },
+	{ .start =  0x22510, .end =  0x22550 },
+	{ .start = 0x1C0030, .end = 0x1C0030 },
+	{ .start = 0x1C0230, .end = 0x1C0230 },
+	{ .start = 0x1C0510, .end = 0x1C0550 },
+	{ .start = 0x1C4030, .end = 0x1C4030 },
+	{ .start = 0x1C4230, .end = 0x1C4230 },
+	{ .start = 0x1C4510, .end = 0x1C4550 },
+	{ .start = 0x1C8030, .end = 0x1C8030 },
+	{ .start = 0x1C8230, .end = 0x1C8230 },
+	{ .start = 0x1C8510, .end = 0x1C8550 },
+	{ .start = 0x1D0030, .end = 0x1D0030 },
+	{ .start = 0x1D0230, .end = 0x1D0230 },
+	{ .start = 0x1D0510, .end = 0x1D0550 },
+	{ .start = 0x1D4030, .end = 0x1D4030 },
+	{ .start = 0x1D4230, .end = 0x1D4230 },
+	{ .start = 0x1D4510, .end = 0x1D4550 },
+	{ .start = 0x1D8030, .end = 0x1D8030 },
+	{ .start = 0x1D8230, .end = 0x1D8230 },
+	{ .start = 0x1D8510, .end = 0x1D8550 },
 };
 
-static const i915_reg_t gen12_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
-	RING_EXECLIST_CONTROL(RENDER_RING_BASE),	/* 0x2550 */
-	GEN6_RPNSWREQ,					/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
-	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
-	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
-	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
-	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
-	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
-	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
-	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
-	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
-	/* TODO: Other registers are not yet used */
+static const struct i915_range gen12_shadowed_regs[] = {
+	{ .start =   0x2030, .end =   0x2030 },
+	{ .start =   0x2510, .end =   0x2550 },
+	{ .start =   0xA008, .end =   0xA00C },
+	{ .start =   0xA188, .end =   0xA188 },
+	{ .start =   0xA278, .end =   0xA278 },
+	{ .start =   0xA540, .end =   0xA56C },
+	{ .start =   0xC4C8, .end =   0xC4C8 },
+	{ .start =   0xC4D4, .end =   0xC4D4 },
+	{ .start =   0xC600, .end =   0xC600 },
+	{ .start =  0x22030, .end =  0x22030 },
+	{ .start =  0x22510, .end =  0x22550 },
+	{ .start = 0x1C0030, .end = 0x1C0030 },
+	{ .start = 0x1C0510, .end = 0x1C0550 },
+	{ .start = 0x1C4030, .end = 0x1C4030 },
+	{ .start = 0x1C4510, .end = 0x1C4550 },
+	{ .start = 0x1C8030, .end = 0x1C8030 },
+	{ .start = 0x1C8510, .end = 0x1C8550 },
+	{ .start = 0x1D0030, .end = 0x1D0030 },
+	{ .start = 0x1D0510, .end = 0x1D0550 },
+	{ .start = 0x1D4030, .end = 0x1D4030 },
+	{ .start = 0x1D4510, .end = 0x1D4550 },
+	{ .start = 0x1D8030, .end = 0x1D8030 },
+	{ .start = 0x1D8510, .end = 0x1D8550 },
+
+	/*
+	 * The rest of these ranges are specific to Xe_HP and beyond, but
+	 * are reserved/unused ranges on earlier gen12 platforms, so they can
+	 * be safely added to the gen12 table.
+	 */
+	{ .start = 0x1E0030, .end = 0x1E0030 },
+	{ .start = 0x1E0510, .end = 0x1E0550 },
+	{ .start = 0x1E4030, .end = 0x1E4030 },
+	{ .start = 0x1E4510, .end = 0x1E4550 },
+	{ .start = 0x1E8030, .end = 0x1E8030 },
+	{ .start = 0x1E8510, .end = 0x1E8550 },
+	{ .start = 0x1F0030, .end = 0x1F0030 },
+	{ .start = 0x1F0510, .end = 0x1F0550 },
+	{ .start = 0x1F4030, .end = 0x1F4030 },
+	{ .start = 0x1F4510, .end = 0x1F4550 },
+	{ .start = 0x1F8030, .end = 0x1F8030 },
+	{ .start = 0x1F8510, .end = 0x1F8550 },
 };
 
-static const i915_reg_t xehp_shadowed_regs[] = {
-	RING_TAIL(RENDER_RING_BASE),			/* 0x2000 (base) */
-	RING_EXECLIST_CONTROL(RENDER_RING_BASE),        /* 0x2550 */
-	GEN6_RPNSWREQ,					/* 0xA008 */
-	GEN6_RC_VIDEO_FREQ,				/* 0xA00C */
-	RING_TAIL(BLT_RING_BASE),			/* 0x22000 (base) */
-	RING_EXECLIST_CONTROL(BLT_RING_BASE),		/* 0x22550 */
-	RING_TAIL(GEN11_BSD_RING_BASE),			/* 0x1C0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD_RING_BASE),	/* 0x1C0550 */
-	RING_TAIL(GEN11_BSD2_RING_BASE),		/* 0x1C4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD2_RING_BASE),	/* 0x1C4550 */
-	RING_TAIL(GEN11_VEBOX_RING_BASE),		/* 0x1C8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX_RING_BASE),	/* 0x1C8550 */
-	RING_TAIL(GEN11_BSD3_RING_BASE),		/* 0x1D0000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD3_RING_BASE),	/* 0x1D0550 */
-	RING_TAIL(GEN11_BSD4_RING_BASE),		/* 0x1D4000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_BSD4_RING_BASE),	/* 0x1D4550 */
-	RING_TAIL(GEN11_VEBOX2_RING_BASE),		/* 0x1D8000 (base) */
-	RING_EXECLIST_CONTROL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8550 */
-	RING_TAIL(XEHP_BSD5_RING_BASE),			/* 0x1E0000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_BSD5_RING_BASE),	/* 0x1E0550 */
-	RING_TAIL(XEHP_BSD6_RING_BASE),			/* 0x1E4000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_BSD6_RING_BASE),	/* 0x1E4550 */
-	RING_TAIL(XEHP_VEBOX3_RING_BASE),		/* 0x1E8000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_VEBOX3_RING_BASE),	/* 0x1E8550 */
-	RING_TAIL(XEHP_BSD7_RING_BASE),			/* 0x1F0000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_BSD7_RING_BASE),	/* 0x1F0550 */
-	RING_TAIL(XEHP_BSD8_RING_BASE),			/* 0x1F4000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_BSD8_RING_BASE),	/* 0x1F4550 */
-	RING_TAIL(XEHP_VEBOX4_RING_BASE),		/* 0x1F8000 (base) */
-	RING_EXECLIST_CONTROL(XEHP_VEBOX4_RING_BASE),	/* 0x1F8550 */
-	/* TODO: Other registers are not yet used */
-};
-
-static int mmio_reg_cmp(u32 key, const i915_reg_t *reg)
+static int mmio_range_cmp(u32 key, const struct i915_range *range)
 {
-	u32 offset = i915_mmio_reg_offset(*reg);
-
-	if (key < offset)
+	if (key < range->start)
 		return -1;
-	else if (key > offset)
+	else if (key > range->end)
 		return 1;
 	else
 		return 0;
@@ -1052,15 +1039,14 @@ static int mmio_reg_cmp(u32 key, const i915_reg_t *reg)
 #define __is_X_shadowed(x) \
 static bool is_##x##_shadowed(u32 offset) \
 { \
-	const i915_reg_t *regs = x##_shadowed_regs; \
+	const struct i915_range *regs = x##_shadowed_regs; \
 	return BSEARCH(offset, regs, ARRAY_SIZE(x##_shadowed_regs), \
-		       mmio_reg_cmp); \
+		       mmio_range_cmp); \
 }
 
 __is_X_shadowed(gen8)
 __is_X_shadowed(gen11)
 __is_X_shadowed(gen12)
-__is_X_shadowed(xehp)
 
 static enum forcewake_domains
 gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg)
@@ -1124,15 +1110,6 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = {
 	__fwd; \
 })
 
-#define __xehp_fwtable_reg_write_fw_domains(uncore, offset) \
-({ \
-	enum forcewake_domains __fwd = 0; \
-	const u32 __offset = (offset); \
-	if (!is_xehp_shadowed(__offset)) \
-		__fwd = find_fw_domain(uncore, __offset); \
-	__fwd; \
-})
-
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
 static const struct intel_forcewake_range __gen9_fw_ranges[] = {
 	GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_GT),
@@ -1644,7 +1621,6 @@ __gen_read(func, 16) \
 __gen_read(func, 32) \
 __gen_read(func, 64)
 
-__gen_reg_read_funcs(gen12_fwtable);
 __gen_reg_read_funcs(gen11_fwtable);
 __gen_reg_read_funcs(fwtable);
 __gen_reg_read_funcs(gen6);
@@ -1736,7 +1712,6 @@ __gen_write(func, 8) \
 __gen_write(func, 16) \
 __gen_write(func, 32)
 
-__gen_reg_write_funcs(xehp_fwtable);
 __gen_reg_write_funcs(gen12_fwtable);
 __gen_reg_write_funcs(gen11_fwtable);
 __gen_reg_write_funcs(fwtable);
@@ -2113,16 +2088,16 @@ static int uncore_forcewake_init(struct intel_uncore *uncore)
 
 	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __dg2_fw_ranges);
-		ASSIGN_WRITE_MMIO_VFUNCS(uncore, xehp_fwtable);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
 	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __xehp_fw_ranges);
-		ASSIGN_WRITE_MMIO_VFUNCS(uncore, xehp_fwtable);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
 	} else if (GRAPHICS_VER(i915) >= 12) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen12_fw_ranges);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable);
-		ASSIGN_READ_MMIO_VFUNCS(uncore, gen12_fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
 	} else if (GRAPHICS_VER(i915) == 11) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable);
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 3c0b0a8b5250..531665b08039 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -119,6 +119,12 @@ struct intel_forcewake_range {
 	enum forcewake_domains domains;
 };
 
+/* Other register ranges (e.g., shadow tables, MCR tables, etc.) */
+struct i915_range {
+	u32 start;
+	u32 end;
+};
+
 struct intel_uncore {
 	void __iomem *regs;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index f843a5040706..2d60a5a5b065 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1300,7 +1300,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 	if (!ctx)
 		return -ENOMEM;
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
+	vm = i915_gem_context_get_eb_vm(ctx);
 	err = func(vm, 0, min(vm->total, limit), end_time);
 	i915_vm_put(vm);
 
@@ -1848,7 +1848,7 @@ static int igt_cs_tlb(void *arg)
 		goto out_unlock;
 	}
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
+	vm = i915_gem_context_get_eb_vm(ctx);
 	if (i915_is_ggtt(vm))
 		goto out_vm;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index cfa5c4165a4f..3cf6758931f9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -47,5 +47,6 @@ selftest(execlists, intel_execlists_live_selftests)
 selftest(ring_submission, intel_ring_submission_live_selftests)
 selftest(perf, i915_perf_live_selftests)
 selftest(slpc, intel_slpc_live_selftests)
+selftest(guc, intel_guc_live_selftests)
 /* Here be dragons: keep last to run last! */
 selftest(late_gt_pm, intel_gt_pm_late_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index dd0607254a95..1f10fe36619b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -39,7 +39,7 @@ static bool assert_vma(struct i915_vma *vma,
 {
 	bool ok = true;
 
-	if (vma->vm != rcu_access_pointer(ctx->vm)) {
+	if (vma->vm != ctx->vm) {
 		pr_err("VMA created with wrong VM\n");
 		ok = false;
 	}
@@ -118,7 +118,7 @@ static int create_vmas(struct drm_i915_private *i915,
 				struct i915_vma *vma;
 				int err;
 
-				vm = i915_gem_context_get_vm_rcu(ctx);
+				vm = i915_gem_context_get_eb_vm(ctx);
 				vma = checked_vma_instance(obj, vm, NULL);
 				i915_vm_put(vm);
 				if (IS_ERR(vma))
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 4b328346b48a..310fb83c527e 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -14,6 +14,18 @@
 #define REDUCED_PREEMPT		10
 #define WAIT_FOR_RESET_TIME	10000
 
+struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		return engine;
+
+	pr_err("No valid engine found!\n");
+	return NULL;
+}
+
 int intel_selftest_modify_policy(struct intel_engine_cs *engine,
 				 struct intel_selftest_saved_policy *saved,
 				 u32 modify_type)
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
index 35c098601ac0..ae60bb507f45 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
@@ -10,6 +10,7 @@
 
 struct i915_request;
 struct intel_engine_cs;
+struct intel_gt;
 
 struct intel_selftest_saved_policy {
 	u32 flags;
@@ -23,6 +24,7 @@ enum selftest_scheduler_modify {
 	SELFTEST_SCHEDULER_MODIFY_FAST_RESET,
 };
 
+struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt);
 int intel_selftest_modify_policy(struct intel_engine_cs *engine,
 				 struct intel_selftest_saved_policy *saved,
 				 enum selftest_scheduler_modify modify_type);
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 720b60853f8b..22ef2c87df1a 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -62,30 +62,39 @@ static int intel_fw_table_check(const struct intel_forcewake_range *ranges,
 static int intel_shadow_table_check(void)
 {
 	struct {
-		const i915_reg_t *regs;
+		const struct i915_range *regs;
 		unsigned int size;
-	} reg_lists[] = {
+	} range_lists[] = {
 		{ gen8_shadowed_regs, ARRAY_SIZE(gen8_shadowed_regs) },
 		{ gen11_shadowed_regs, ARRAY_SIZE(gen11_shadowed_regs) },
 		{ gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) },
-		{ xehp_shadowed_regs, ARRAY_SIZE(xehp_shadowed_regs) },
 	};
-	const i915_reg_t *reg;
+	const struct i915_range *range;
 	unsigned int i, j;
 	s32 prev;
 
-	for (j = 0; j < ARRAY_SIZE(reg_lists); ++j) {
-		reg = reg_lists[j].regs;
-		for (i = 0, prev = -1; i < reg_lists[j].size; i++, reg++) {
-			u32 offset = i915_mmio_reg_offset(*reg);
-
-			if (prev >= (s32)offset) {
-				pr_err("%s: entry[%d]:(%x) is before previous (%x)\n",
-				       __func__, i, offset, prev);
+	for (j = 0; j < ARRAY_SIZE(range_lists); ++j) {
+		range = range_lists[j].regs;
+		for (i = 0, prev = -1; i < range_lists[j].size; i++, range++) {
+			if (range->end < range->start) {
+				pr_err("%s: range[%d]:(%06x-%06x) has end before start\n",
+				       __func__, i, range->start, range->end);
 				return -EINVAL;
 			}
 
-			prev = offset;
+			if (prev >= (s32)range->start) {
+				pr_err("%s: range[%d]:(%06x-%06x) is before end of previous (%06x)\n",
+				       __func__, i, range->start, range->end, prev);
+				return -EINVAL;
+			}
+
+			if (range->start % 4) {
+				pr_err("%s: range[%d]:(%06x-%06x) has non-dword-aligned start\n",
+				       __func__, i, range->start, range->end);
+				return -EINVAL;
+			}
+
+			prev = range->end;
 		}
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index abf2d7a4fdf1..c1a6fff4135b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -78,22 +78,21 @@ void ttm_mem_io_free(struct ttm_device *bdev,
 
 /**
  * ttm_move_memcpy - Helper to perform a memcpy ttm move operation.
- * @bo: The struct ttm_buffer_object.
- * @new_mem: The struct ttm_resource we're moving to (copy destination).
- * @new_iter: A struct ttm_kmap_iter representing the destination resource.
+ * @clear: Whether to clear rather than copy.
+ * @num_pages: Number of pages of the operation.
+ * @dst_iter: A struct ttm_kmap_iter representing the destination resource.
  * @src_iter: A struct ttm_kmap_iter representing the source resource.
  *
  * This function is intended to be able to move out async under a
  * dma-fence if desired.
  */
-void ttm_move_memcpy(struct ttm_buffer_object *bo,
+void ttm_move_memcpy(bool clear,
 		     u32 num_pages,
 		     struct ttm_kmap_iter *dst_iter,
 		     struct ttm_kmap_iter *src_iter)
 {
 	const struct ttm_kmap_iter_ops *dst_ops = dst_iter->ops;
 	const struct ttm_kmap_iter_ops *src_ops = src_iter->ops;
-	struct ttm_tt *ttm = bo->ttm;
 	struct dma_buf_map src_map, dst_map;
 	pgoff_t i;
 
@@ -102,10 +101,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo,
 		return;
 
 	/* Don't move nonexistent data. Clear destination instead. */
-	if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) {
-		if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))
-			return;
-
+	if (clear) {
 		for (i = 0; i < num_pages; ++i) {
 			dst_ops->map_local(dst_iter, &dst_map, i);
 			if (dst_map.is_iomem)
@@ -148,6 +144,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		struct ttm_kmap_iter_linear_io io;
 	} _dst_iter, _src_iter;
 	struct ttm_kmap_iter *dst_iter, *src_iter;
+	bool clear;
 	int ret = 0;
 
 	if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) ||
@@ -171,7 +168,9 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		goto out_src_iter;
 	}
 
-	ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter);
+	clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm));
+	if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)))
+		ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter);
 
 	if (!src_iter->ops->maps_tt)
 		ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 68d6069572aa..5f087575194b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -322,7 +322,7 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem);
  */
 void ttm_bo_tt_destroy(struct ttm_buffer_object *bo);
 
-void ttm_move_memcpy(struct ttm_buffer_object *bo,
+void ttm_move_memcpy(bool clear,
 		     u32 num_pages,
 		     struct ttm_kmap_iter *dst_iter,
 		     struct ttm_kmap_iter *src_iter);