Merge tag 'drm-intel-gt-next-2021-10-21' of...

Merge tag 'drm-intel-gt-next-2021-10-21' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Expose multi-LRC submission interface

  Similar to the bonded submission interface but simplified.
  Comes with GuC only implementation for now. See kerneldoc
  for more details.

  Userspace changes: https://github.com/intel/media-driver/pull/1252

- Expose logical engine instance to user

  Needed by the multi-LRC submission interface for GuC

  Userspace changes: https://github.com/intel/media-driver/pull/1252

Driver Changes:

- Fix blank screen booting crashes when CONFIG_CC_OPTIMIZE_FOR_SIZE=y (Hugh)
- Add support for multi-LRC submission in the GuC backend (Matt B)
- Add extra cache flushing before making pages userspace visible (Matt A, Thomas)
- Mark internal GPU object pages dirty so they will be flushed properly (Matt A)

- Move remaining debugfs interfaces i915_wedged/i915_forcewake_user into gt (Andi)
- Replace the unconditional clflushes with drm_clflush_virt_range() (Ville)
- Remove IS_ACTIVE macro completely (Lucas)
- Improve kerneldocs for cache_dirty (Matt A)

- Add missing includes (Lucas)
- Selftest improvements (Matt R, Ran, Matt A)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YXFmLKoq8Fg9JxSd@jlahtine-mobl.ger.corp.intel.com

Documentation/gpu/rfc/i915_parallel_execbuf.h

-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2021 Intel Corporation
- */
-
-#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
-
-/**
- * struct drm_i915_context_engines_parallel_submit - Configure engine for
- * parallel submission.
- *
- * Setup a slot in the context engine map to allow multiple BBs to be submitted
- * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
- * in parallel. Multiple hardware contexts are created internally in the i915
- * run these BBs. Once a slot is configured for N BBs only N BBs can be
- * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
- * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
- * many BBs there are based on the slot's configuration. The N BBs are the last
- * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
- *
- * The default placement behavior is to create implicit bonds between each
- * context if each context maps to more than 1 physical engine (e.g. context is
- * a virtual engine). Also we only allow contexts of same engine class and these
- * contexts must be in logically contiguous order. Examples of the placement
- * behavior described below. Lastly, the default is to not allow BBs to
- * preempted mid BB rather insert coordinated preemption on all hardware
- * contexts between each set of BBs. Flags may be added in the future to change
- * both of these default behaviors.
- *
- * Returns -EINVAL if hardware context placement configuration is invalid or if
- * the placement configuration isn't supported on the platform / submission
- * interface.
- * Returns -ENODEV if extension isn't supported on the platform / submission
- * interface.
- *
- * .. code-block:: none
- *
- *	Example 1 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=1,
- *		     engines=CS[0],CS[1])
- *
- *	Results in the following valid placement:
- *	CS[0], CS[1]
- *
- *	Example 2 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=2,
- *		     engines=CS[0],CS[2],CS[1],CS[3])
- *
- *	Results in the following valid placements:
- *	CS[0], CS[1]
- *	CS[2], CS[3]
- *
- *	This can also be thought of as 2 virtual engines described by 2-D array
- *	in the engines the field with bonds placed between each index of the
- *	virtual engines. e.g. CS[0] is bonded to CS[1], CS[2] is bonded to
- *	CS[3].
- *	VE[0] = CS[0], CS[2]
- *	VE[1] = CS[1], CS[3]
- *
- *	Example 3 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=2,
- *		     engines=CS[0],CS[1],CS[1],CS[3])
- *
- *	Results in the following valid and invalid placements:
- *	CS[0], CS[1]
- *	CS[1], CS[3] - Not logical contiguous, return -EINVAL
- */
-struct drm_i915_context_engines_parallel_submit {
-	/**
-	 * @base: base user extension.
-	 */
-	struct i915_user_extension base;
-
-	/**
-	 * @engine_index: slot for parallel engine
-	 */
-	__u16 engine_index;
-
-	/**
-	 * @width: number of contexts per parallel engine
-	 */
-	__u16 width;
-
-	/**
-	 * @num_siblings: number of siblings per context
-	 */
-	__u16 num_siblings;
-
-	/**
-	 * @mbz16: reserved for future use; must be zero
-	 */
-	__u16 mbz16;
-
-	/**
-	 * @flags: all undefined flags must be zero, currently not defined flags
-	 */
-	__u64 flags;
-
-	/**
-	 * @mbz64: reserved for future use; must be zero
-	 */
-	__u64 mbz64[3];
-
-	/**
-	 * @engines: 2-d array of engine instances to configure parallel engine
-	 *
-	 * length = width (i) * num_siblings (j)
-	 * index = j + i * num_siblings
-	 */
-	struct i915_engine_class_instance engines[0];
-
-} __packed;
-

Documentation/gpu/rfc/i915_scheduler.rst

@@ -135,8 +135,8 @@ Add I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT and
 drm_i915_context_engines_parallel_submit to the uAPI to implement this
 extension.
 
-.. kernel-doc:: Documentation/gpu/rfc/i915_parallel_execbuf.h
-        :functions: drm_i915_context_engines_parallel_submit
+.. kernel-doc:: include/uapi/drm/i915_drm.h
+        :functions: i915_context_engines_parallel_submit
 
 Extend execbuf2 IOCTL to support submitting N BBs in a single IOCTL
 -------------------------------------------------------------------

drivers/gpu/drm/i915/gem/i915_gem_busy.c

@@ -4,6 +4,8 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <linux/dma-fence-array.h>
+
 #include "gt/intel_engine.h"
 
 #include "i915_gem_ioctls.h"
@@ -36,7 +38,7 @@ static __always_inline u32 __busy_write_id(u16 id)
 }
 
 static __always_inline unsigned int
-__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
+__busy_set_if_active(struct dma_fence *fence, u32 (*flag)(u16 id))
 {
 	const struct i915_request *rq;
 
@@ -46,29 +48,60 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
 	 * to eventually flush us, but to minimise latency just ask the
 	 * hardware.
 	 *
-	 * Note we only report on the status of native fences.
+	 * Note we only report on the status of native fences and we currently
+	 * have two native fences:
+	 *
+	 * 1. A composite fence (dma_fence_array) constructed of i915 requests
+	 * created during a parallel submission. In this case we deconstruct the
+	 * composite fence into individual i915 requests and check the status of
+	 * each request.
+	 *
+	 * 2. A single i915 request.
 	 */
-	if (!dma_fence_is_i915(fence))
+	if (dma_fence_is_array(fence)) {
+		struct dma_fence_array *array = to_dma_fence_array(fence);
+		struct dma_fence **child = array->fences;
+		unsigned int nchild = array->num_fences;
+
+		do {
+			struct dma_fence *current_fence = *child++;
+
+			/* Not an i915 fence, can't be busy per above */
+			if (!dma_fence_is_i915(current_fence) ||
+			    !test_bit(I915_FENCE_FLAG_COMPOSITE,
+				      &current_fence->flags)) {
+				return 0;
+			}
+
+			rq = to_request(current_fence);
+			if (!i915_request_completed(rq))
+				return flag(rq->engine->uabi_class);
+		} while (--nchild);
+
+		/* All requests in array complete, not busy */
 		return 0;
+	} else {
+		if (!dma_fence_is_i915(fence))
+			return 0;
 
-	/* opencode to_request() in order to avoid const warnings */
-	rq = container_of(fence, const struct i915_request, fence);
-	if (i915_request_completed(rq))
-		return 0;
+		rq = to_request(fence);
+		if (i915_request_completed(rq))
+			return 0;
 
-	/* Beware type-expansion follies! */
-	BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
-	return flag(rq->engine->uabi_class);
+		/* Beware type-expansion follies! */
+		BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
+		return flag(rq->engine->uabi_class);
+	}
 }
 
 static __always_inline unsigned int
-busy_check_reader(const struct dma_fence *fence)
+busy_check_reader(struct dma_fence *fence)
 {
 	return __busy_set_if_active(fence, __busy_read_flag);
 }
 
 static __always_inline unsigned int
-busy_check_writer(const struct dma_fence *fence)
+busy_check_writer(struct dma_fence *fence)
 {
 	if (!fence)
 		return 0;

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -556,9 +556,147 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
 	return 0;
 }
 
+static int
+set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
+				      void *data)
+{
+	struct i915_context_engines_parallel_submit __user *ext =
+		container_of_user(base, typeof(*ext), base);
+	const struct set_proto_ctx_engines *set = data;
+	struct drm_i915_private *i915 = set->i915;
+	u64 flags;
+	int err = 0, n, i, j;
+	u16 slot, width, num_siblings;
+	struct intel_engine_cs **siblings = NULL;
+	intel_engine_mask_t prev_mask;
+
+	/* FIXME: This is NIY for execlists */
+	if (!(intel_uc_uses_guc_submission(&i915->gt.uc)))
+		return -ENODEV;
+
+	if (get_user(slot, &ext->engine_index))
+		return -EFAULT;
+
+	if (get_user(width, &ext->width))
+		return -EFAULT;
+
+	if (get_user(num_siblings, &ext->num_siblings))
+		return -EFAULT;
+
+	if (slot >= set->num_engines) {
+		drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
+			slot, set->num_engines);
+		return -EINVAL;
+	}
+
+	if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) {
+		drm_dbg(&i915->drm,
+			"Invalid placement[%d], already occupied\n", slot);
+		return -EINVAL;
+	}
+
+	if (get_user(flags, &ext->flags))
+		return -EFAULT;
+
+	if (flags) {
+		drm_dbg(&i915->drm, "Unknown flags 0x%02llx", flags);
+		return -EINVAL;
+	}
+
+	for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
+		err = check_user_mbz(&ext->mbz64[n]);
+		if (err)
+			return err;
+	}
+
+	if (width < 2) {
+		drm_dbg(&i915->drm, "Width (%d) < 2\n", width);
+		return -EINVAL;
+	}
+
+	if (num_siblings < 1) {
+		drm_dbg(&i915->drm, "Number siblings (%d) < 1\n",
+			num_siblings);
+		return -EINVAL;
+	}
+
+	siblings = kmalloc_array(num_siblings * width,
+				 sizeof(*siblings),
+				 GFP_KERNEL);
+	if (!siblings)
+		return -ENOMEM;
+
+	/* Create contexts / engines */
+	for (i = 0; i < width; ++i) {
+		intel_engine_mask_t current_mask = 0;
+		struct i915_engine_class_instance prev_engine;
+
+		for (j = 0; j < num_siblings; ++j) {
+			struct i915_engine_class_instance ci;
+
+			n = i * num_siblings + j;
+			if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
+				err = -EFAULT;
+				goto out_err;
+			}
+
+			siblings[n] =
+				intel_engine_lookup_user(i915, ci.engine_class,
+							 ci.engine_instance);
+			if (!siblings[n]) {
+				drm_dbg(&i915->drm,
+					"Invalid sibling[%d]: { class:%d, inst:%d }\n",
+					n, ci.engine_class, ci.engine_instance);
+				err = -EINVAL;
+				goto out_err;
+			}
+
+			if (n) {
+				if (prev_engine.engine_class !=
+				    ci.engine_class) {
+					drm_dbg(&i915->drm,
+						"Mismatched class %d, %d\n",
+						prev_engine.engine_class,
+						ci.engine_class);
+					err = -EINVAL;
+					goto out_err;
+				}
+			}
+
+			prev_engine = ci;
+			current_mask |= siblings[n]->logical_mask;
+		}
+
+		if (i > 0) {
+			if (current_mask != prev_mask << 1) {
+				drm_dbg(&i915->drm,
+					"Non contiguous logical mask 0x%x, 0x%x\n",
+					prev_mask, current_mask);
+				err = -EINVAL;
+				goto out_err;
+			}
+		}
+		prev_mask = current_mask;
+	}
+
+	set->engines[slot].type = I915_GEM_ENGINE_TYPE_PARALLEL;
+	set->engines[slot].num_siblings = num_siblings;
+	set->engines[slot].width = width;
+	set->engines[slot].siblings = siblings;
+
+	return 0;
+
+out_err:
+	kfree(siblings);
+
+	return err;
+}
+
 static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = {
 	[I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance,
 	[I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond,
+	[I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT] =
+		set_proto_ctx_engines_parallel_submit,
 };
 
 static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
@@ -794,6 +932,7 @@ static int intel_context_set_gem(struct intel_context *ce,
 	GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
 	RCU_INIT_POINTER(ce->gem_context, ctx);
 
+	GEM_BUG_ON(intel_context_is_pinned(ce));
 	ce->ring_size = SZ_16K;
 
 	i915_vm_put(ce->vm);
@@ -818,6 +957,25 @@ static int intel_context_set_gem(struct intel_context *ce,
 	return ret;
 }
 
+static void __unpin_engines(struct i915_gem_engines *e, unsigned int count)
+{
+	while (count--) {
+		struct intel_context *ce = e->engines[count], *child;
+
+		if (!ce || !test_bit(CONTEXT_PERMA_PIN, &ce->flags))
+			continue;
+
+		for_each_child(ce, child)
+			intel_context_unpin(child);
+		intel_context_unpin(ce);
+	}
+}
+
+static void unpin_engines(struct i915_gem_engines *e)
+{
+	__unpin_engines(e, e->num_engines);
+}
+
 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
 {
 	while (count--) {
@@ -933,6 +1091,40 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
 	return err;
 }
 
+static int perma_pin_contexts(struct intel_context *ce)
+{
+	struct intel_context *child;
+	int i = 0, j = 0, ret;
+
+	GEM_BUG_ON(!intel_context_is_parent(ce));
+
+	ret = intel_context_pin(ce);
+	if (unlikely(ret))
+		return ret;
+
+	for_each_child(ce, child) {
+		ret = intel_context_pin(child);
+		if (unlikely(ret))
+			goto unwind;
+		++i;
+	}
+
+	set_bit(CONTEXT_PERMA_PIN, &ce->flags);
+
+	return 0;
+
+unwind:
+	intel_context_unpin(ce);
+	for_each_child(ce, child) {
+		if (j++ < i)
+			intel_context_unpin(child);
+		else
+			break;
+	}
+
+	return ret;
+}
+
 static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 					     unsigned int num_engines,
 					     struct i915_gem_proto_engine *pe)
@@ -946,7 +1138,7 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 	e->num_engines = num_engines;
 
 	for (n = 0; n < num_engines; n++) {
-		struct intel_context *ce;
+		struct intel_context *ce, *child;
 		int ret;
 
 		switch (pe[n].type) {
@@ -956,7 +1148,13 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 
 		case I915_GEM_ENGINE_TYPE_BALANCED:
 			ce = intel_engine_create_virtual(pe[n].siblings,
-							 pe[n].num_siblings);
+							 pe[n].num_siblings, 0);
+			break;
+
+		case I915_GEM_ENGINE_TYPE_PARALLEL:
+			ce = intel_engine_create_parallel(pe[n].siblings,
+							  pe[n].num_siblings,
+							  pe[n].width);
 			break;
 
 		case I915_GEM_ENGINE_TYPE_INVALID:
@@ -977,6 +1175,30 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 			err = ERR_PTR(ret);
 			goto free_engines;
 		}
+		for_each_child(ce, child) {
+			ret = intel_context_set_gem(child, ctx, pe->sseu);
+			if (ret) {
+				err = ERR_PTR(ret);
+				goto free_engines;
+			}
+		}
+
+		/*
+		 * XXX: Must be done after calling intel_context_set_gem as that
+		 * function changes the ring size. The ring is allocated when
+		 * the context is pinned. If the ring size is changed after
+		 * allocation we have a mismatch of the ring size and will cause
+		 * the context to hang. Presumably with a bit of reordering we
+		 * could move the perma-pin step to the backend function
+		 * intel_engine_create_parallel.
+		 */
+		if (pe[n].type == I915_GEM_ENGINE_TYPE_PARALLEL) {
+			ret = perma_pin_contexts(ce);
+			if (ret) {
+				err = ERR_PTR(ret);
+				goto free_engines;
+			}
+		}
 	}
 
 	return e;
@@ -1219,6 +1441,7 @@ static void context_close(struct i915_gem_context *ctx)
 
 	/* Flush any concurrent set_engines() */
 	mutex_lock(&ctx->engines_mutex);
+	unpin_engines(__context_engines_static(ctx));
 	engines_idle_release(ctx, rcu_replace_pointer(ctx->engines, NULL, 1));
 	i915_gem_context_set_closed(ctx);
 	mutex_unlock(&ctx->engines_mutex);

drivers/gpu/drm/i915/gem/i915_gem_context_types.h

@@ -78,13 +78,16 @@ enum i915_gem_engine_type {
 
 	/** @I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set */
 	I915_GEM_ENGINE_TYPE_BALANCED,
+
+	/** @I915_GEM_ENGINE_TYPE_PARALLEL: A parallel engine set */
+	I915_GEM_ENGINE_TYPE_PARALLEL,
 };
 
 /**
  * struct i915_gem_proto_engine - prototype engine
  *
  * This struct describes an engine that a context may contain.  Engines
- * have three types:
+ * have four types:
  *
  *  - I915_GEM_ENGINE_TYPE_INVALID: Invalid engines can be created but they
  *    show up as a NULL in i915_gem_engines::engines[i] and any attempt to
@@ -97,6 +100,10 @@ enum i915_gem_engine_type {
  *
  *  - I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set, described
  *    i915_gem_proto_engine::num_siblings and i915_gem_proto_engine::siblings.
+ *
+ *  - I915_GEM_ENGINE_TYPE_PARALLEL: A parallel submission engine set, described
+ *    i915_gem_proto_engine::width, i915_gem_proto_engine::num_siblings, and
+ *    i915_gem_proto_engine::siblings.
  */
 struct i915_gem_proto_engine {
 	/** @type: Type of this engine */
@@ -105,10 +112,13 @@ struct i915_gem_proto_engine {
 	/** @engine: Engine, for physical */
 	struct intel_engine_cs *engine;
 
-	/** @num_siblings: Number of balanced siblings */
+	/** @num_siblings: Number of balanced or parallel siblings */
 	unsigned int num_siblings;
 
-	/** @siblings: Balanced siblings */
+	/** @width: Width of each sibling */
+	unsigned int width;
+
+	/** @siblings: Balanced siblings or num_siblings * width for parallel */
 	struct intel_engine_cs **siblings;
 
 	/** @sseu: Client-set SSEU parameters */

drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c

@@ -232,6 +232,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
 
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct sg_table *pages;
 	unsigned int sg_page_sizes;
 
@@ -242,8 +243,11 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
-	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);
+	/* XXX: consider doing a vmap flush or something */
+	if (!HAS_LLC(i915) || i915_gem_object_can_bypass_llc(obj))
+		wbinvd_on_all_cpus();
 
+	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);
 	__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
 
 	return 0;
@@ -301,7 +305,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	}
 
 	drm_gem_private_object_init(dev, &obj->base, dma_buf->size);
-	i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops, &lock_class, 0);
+	i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops, &lock_class,
+			     I915_BO_ALLOC_USER);
 	obj->base.import_attach = attach;
 	obj->base.resv = dma_buf->resv;
 

drivers/gpu/drm/i915/gem/i915_gem_internal.c

@@ -134,6 +134,8 @@ static void i915_gem_object_put_pages_internal(struct drm_i915_gem_object *obj,
 	internal_free_pages(pages);
 
 	obj->mm.dirty = false;
+
+	__start_cpu_write(obj);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = {

drivers/gpu/drm/i915/gem/i915_gem_object.c

@@ -128,6 +128,32 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 		!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
 }
 
+bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
+	/*
+	 * This is purely from a security perspective, so we simply don't care
+	 * about non-userspace objects being able to bypass the LLC.
+	 */
+	if (!(obj->flags & I915_BO_ALLOC_USER))
+		return false;
+
+	/*
+	 * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it
+	 * possible for userspace to bypass the GTT caching bits set by the
+	 * kernel, as per the given object cache_level. This is troublesome
+	 * since the heavy flush we apply when first gathering the pages is
+	 * skipped if the kernel thinks the object is coherent with the GPU. As
+	 * a result it might be possible to bypass the cache and read the
+	 * contents of the page directly, which could be stale data. If it's
+	 * just a case of userspace shooting themselves in the foot then so be
+	 * it, but since i915 takes the stance of always zeroing memory before
+	 * handing it to userspace, we need to prevent this.
+	 */
+	return IS_JSL_EHL(i915);
+}
+
 static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem);

drivers/gpu/drm/i915/gem/i915_gem_object.h

@@ -514,6 +514,7 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj)
 
 void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 					 unsigned int cache_level);
+bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj);
 

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -427,6 +427,33 @@ struct drm_i915_gem_object {
 	 * can freely bypass the CPU cache when touching the pages with the GPU,
 	 * where the kernel is completely unaware. On such platform we need
 	 * apply the sledgehammer-on-acquire regardless of the @cache_coherent.
+	 *
+	 * Special care is taken on non-LLC platforms, to prevent potential
+	 * information leak. The driver currently ensures:
+	 *
+	 *   1. All userspace objects, by default, have @cache_level set as
+	 *   I915_CACHE_NONE. The only exception is userptr objects, where we
+	 *   instead force I915_CACHE_LLC, but we also don't allow userspace to
+	 *   ever change the @cache_level for such objects. Another special case
+	 *   is dma-buf, which doesn't rely on @cache_dirty,  but there we
+	 *   always do a forced flush when acquiring the pages, if there is a
+	 *   chance that the pages can be read directly from main memory with
+	 *   the GPU.
+	 *
+	 *   2. All I915_CACHE_NONE objects have @cache_dirty initially true.
+	 *
+	 *   3. All swapped-out objects(i.e shmem) have @cache_dirty set to
+	 *   true.
+	 *
+	 *   4. The @cache_dirty is never freely reset before the initial
+	 *   flush, even if userspace adjusts the @cache_level through the
+	 *   i915_gem_set_caching_ioctl.
+	 *
+	 *   5. All @cache_dirty objects(including swapped-in) are initially
+	 *   flushed with a synchronous call to drm_clflush_sg in
+	 *   __i915_gem_object_set_pages. The @cache_dirty can be freely reset
+	 *   at this point. All further asynchronous clfushes are never security
+	 *   critical, i.e userspace is free to race against itself.
 	 */
 	unsigned int cache_dirty:1;
 

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -182,22 +182,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj, st);
 
-	/*
-	 * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it
-	 * possible for userspace to bypass the GTT caching bits set by the
-	 * kernel, as per the given object cache_level. This is troublesome
-	 * since the heavy flush we apply when first gathering the pages is
-	 * skipped if the kernel thinks the object is coherent with the GPU. As
-	 * a result it might be possible to bypass the cache and read the
-	 * contents of the page directly, which could be stale data. If it's
-	 * just a case of userspace shooting themselves in the foot then so be
-	 * it, but since i915 takes the stance of always zeroing memory before
-	 * handing it to userspace, we need to prevent this.
-	 *
-	 * By setting cache_dirty here we make the clflush in set_pages
-	 * unconditional on such platforms.
-	 */
-	if (IS_JSL_EHL(i915) && obj->flags & I915_BO_ALLOC_USER)
+	if (i915_gem_object_can_bypass_llc(obj))
 		obj->cache_dirty = true;
 
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
@@ -301,6 +286,8 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
 				struct sg_table *pages,
 				bool needs_clflush)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
 	GEM_BUG_ON(obj->mm.madv == __I915_MADV_PURGED);
 
 	if (obj->mm.madv == I915_MADV_DONTNEED)
@@ -312,6 +299,16 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
 		drm_clflush_sg(pages);
 
 	__start_cpu_write(obj);
+	/*
+	 * On non-LLC platforms, force the flush-on-acquire if this is ever
+	 * swapped-in. Our async flush path is not trust worthy enough yet(and
+	 * happens in the wrong order), and with some tricks it's conceivable
+	 * for userspace to change the cache-level to I915_CACHE_NONE after the
+	 * pages are swapped-in, and since execbuf binds the object before doing
+	 * the async flush, we have a race window.
+	 */
+	if (!HAS_LLC(i915))
+		obj->cache_dirty = true;
 }
 
 void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages)

drivers/gpu/drm/i915/gem/i915_gem_userptr.c

@@ -165,8 +165,11 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		goto err;
 	}
 
-	sg_page_sizes = i915_sg_dma_sizes(st->sgl);
+	WARN_ON_ONCE(!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE));
+	if (i915_gem_object_can_bypass_llc(obj))
+		obj->cache_dirty = true;
 
+	sg_page_sizes = i915_sg_dma_sizes(st->sgl);
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
 	return 0;
@@ -546,7 +549,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -ENOMEM;
 
 	drm_gem_private_object_init(dev, &obj->base, args->user_size);
-	i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class, 0);
+	i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class,
+			     I915_BO_ALLOC_USER);
 	obj->mem_flags = I915_BO_FLAG_STRUCT_PAGE;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;

drivers/gpu/drm/i915/gem/selftests/huge_pages.c

@@ -136,6 +136,8 @@ static void put_huge_pages(struct drm_i915_gem_object *obj,
 	huge_pages_free_pages(pages);
 
 	obj->mm.dirty = false;
+
+	__start_cpu_write(obj);
 }
 
 static const struct drm_i915_gem_object_ops huge_page_ops = {
@@ -152,6 +154,7 @@ huge_pages_object(struct drm_i915_private *i915,
 {
 	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
+	unsigned int cache_level;
 
 	GEM_BUG_ON(!size);
 	GEM_BUG_ON(!IS_ALIGNED(size, BIT(__ffs(page_mask))));
@@ -173,7 +176,9 @@ huge_pages_object(struct drm_i915_private *i915,
 
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
-	obj->cache_level = I915_CACHE_NONE;
+
+	cache_level = HAS_LLC(i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
+	i915_gem_object_set_cache_coherency(obj, cache_level);
 
 	obj->mm.page_mask = page_mask;
 

drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c

@@ -17,13 +17,20 @@
 #include "huge_gem_object.h"
 #include "mock_context.h"
 
+enum client_tiling {
+	CLIENT_TILING_LINEAR,
+	CLIENT_TILING_X,
+	CLIENT_TILING_Y,
+	CLIENT_NUM_TILING_TYPES
+};
+
 #define WIDTH 512
 #define HEIGHT 32
 
 struct blit_buffer {
 	struct i915_vma *vma;
 	u32 start_val;
-	u32 tiling;
+	enum client_tiling tiling;
 };
 
 struct tiled_blits {
@@ -53,9 +60,9 @@ static int prepare_blit(const struct tiled_blits *t,
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(BCS_SWCTRL);
 	cmd = (BCS_SRC_Y | BCS_DST_Y) << 16;
-	if (src->tiling == I915_TILING_Y)
+	if (src->tiling == CLIENT_TILING_Y)
 		cmd |= BCS_SRC_Y;
-	if (dst->tiling == I915_TILING_Y)
+	if (dst->tiling == CLIENT_TILING_Y)
 		cmd |= BCS_DST_Y;
 	*cs++ = cmd;
 
@@ -172,7 +179,7 @@ static int tiled_blits_create_buffers(struct tiled_blits *t,
 
 		t->buffers[i].vma = vma;
 		t->buffers[i].tiling =
-			i915_prandom_u32_max_state(I915_TILING_Y + 1, prng);
+			i915_prandom_u32_max_state(CLIENT_TILING_Y + 1, prng);
 	}
 
 	return 0;
@@ -197,17 +204,17 @@ static u64 swizzle_bit(unsigned int bit, u64 offset)
 static u64 tiled_offset(const struct intel_gt *gt,
 			u64 v,
 			unsigned int stride,
-			unsigned int tiling)
+			enum client_tiling tiling)
 {
 	unsigned int swizzle;
 	u64 x, y;
 
-	if (tiling == I915_TILING_NONE)
+	if (tiling == CLIENT_TILING_LINEAR)
 		return v;
 
 	y = div64_u64_rem(v, stride, &x);
 
-	if (tiling == I915_TILING_X) {
+	if (tiling == CLIENT_TILING_X) {
 		v = div64_u64_rem(y, 8, &y) * stride * 8;
 		v += y * 512;
 		v += div64_u64_rem(x, 512, &x) << 12;
@@ -244,12 +251,12 @@ static u64 tiled_offset(const struct intel_gt *gt,
 	return v;
 }
 
-static const char *repr_tiling(int tiling)
+static const char *repr_tiling(enum client_tiling tiling)
 {
 	switch (tiling) {
-	case I915_TILING_NONE: return "linear";
-	case I915_TILING_X: return "X";
-	case I915_TILING_Y: return "Y";
+	case CLIENT_TILING_LINEAR: return "linear";
+	case CLIENT_TILING_X: return "X";
+	case CLIENT_TILING_Y: return "Y";
 	default: return "unknown";
 	}
 }

drivers/gpu/drm/i915/gt/intel_context.c

@@ -240,6 +240,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce,
 	if (err)
 		goto err_post_unpin;
 
+	intel_engine_pm_might_get(ce->engine);
+
 	if (unlikely(intel_context_is_closed(ce))) {
 		err = -ENOENT;
 		goto err_unlock;
@@ -362,8 +364,8 @@ static int __intel_context_active(struct i915_active *active)
 	return 0;
 }
 
-static int sw_fence_dummy_notify(struct i915_sw_fence *sf,
-				 enum i915_sw_fence_notify state)
+static int __i915_sw_fence_call
+sw_fence_dummy_notify(struct i915_sw_fence *sf, enum i915_sw_fence_notify state)
 {
 	return NOTIFY_DONE;
 }
@@ -399,6 +401,10 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 	ce->guc_id.id = GUC_INVALID_LRC_ID;
 	INIT_LIST_HEAD(&ce->guc_id.link);
 
+	INIT_LIST_HEAD(&ce->destroyed_link);
+
+	INIT_LIST_HEAD(&ce->parallel.child_list);
+
 	/*
 	 * Initialize fence to be complete as this is expected to be complete
 	 * unless there is a pending schedule disable outstanding.
@@ -413,10 +419,17 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 
 void intel_context_fini(struct intel_context *ce)
 {
+	struct intel_context *child, *next;
+
 	if (ce->timeline)
 		intel_timeline_put(ce->timeline);
 	i915_vm_put(ce->vm);
 
+	/* Need to put the creation ref for the children */
+	if (intel_context_is_parent(ce))
+		for_each_child_safe(ce, child, next)
+			intel_context_put(child);
+
 	mutex_destroy(&ce->pin_mutex);
 	i915_active_fini(&ce->active);
 	i915_sw_fence_fini(&ce->guc_state.blocked);
@@ -515,24 +528,53 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 
 struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 {
+	struct intel_context *parent = intel_context_to_parent(ce);
 	struct i915_request *rq, *active = NULL;
 	unsigned long flags;
 
 	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
 
-	spin_lock_irqsave(&ce->guc_state.lock, flags);
-	list_for_each_entry_reverse(rq, &ce->guc_state.requests,
+	/*
+	 * We search the parent list to find an active request on the submitted
+	 * context. The parent list contains the requests for all the contexts
+	 * in the relationship so we have to do a compare of each request's
+	 * context.
+	 */
+	spin_lock_irqsave(&parent->guc_state.lock, flags);
+	list_for_each_entry_reverse(rq, &parent->guc_state.requests,
 				    sched.link) {
+		if (rq->context != ce)
+			continue;
 		if (i915_request_completed(rq))
 			break;
 
 		active = rq;
 	}
-	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+	spin_unlock_irqrestore(&parent->guc_state.lock, flags);
 
 	return active;
 }
 
+void intel_context_bind_parent_child(struct intel_context *parent,
+				     struct intel_context *child)
+{
+	/*
+	 * Callers responsibility to validate that this function is used
+	 * correctly but we use GEM_BUG_ON here ensure that they do.
+	 */
+	GEM_BUG_ON(!intel_engine_uses_guc(parent->engine));
+	GEM_BUG_ON(intel_context_is_pinned(parent));
+	GEM_BUG_ON(intel_context_is_child(parent));
+	GEM_BUG_ON(intel_context_is_pinned(child));
+	GEM_BUG_ON(intel_context_is_child(child));
+	GEM_BUG_ON(intel_context_is_parent(child));
+
+	parent->parallel.child_index = parent->parallel.number_children++;
+	list_add_tail(&child->parallel.child_link,
+		      &parent->parallel.child_list);
+	child->parallel.parent = parent;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_context.c"
 #endif

drivers/gpu/drm/i915/gt/intel_context.h

@@ -44,6 +44,54 @@ void intel_context_free(struct intel_context *ce);
 int intel_context_reconfigure_sseu(struct intel_context *ce,
 				   const struct intel_sseu sseu);
 
+#define PARENT_SCRATCH_SIZE	PAGE_SIZE
+
+static inline bool intel_context_is_child(struct intel_context *ce)
+{
+	return !!ce->parallel.parent;
+}
+
+static inline bool intel_context_is_parent(struct intel_context *ce)
+{
+	return !!ce->parallel.number_children;
+}
+
+static inline bool intel_context_is_pinned(struct intel_context *ce);
+
+static inline struct intel_context *
+intel_context_to_parent(struct intel_context *ce)
+{
+	if (intel_context_is_child(ce)) {
+		/*
+		 * The parent holds ref count to the child so it is always safe
+		 * for the parent to access the child, but the child has a
+		 * pointer to the parent without a ref. To ensure this is safe
+		 * the child should only access the parent pointer while the
+		 * parent is pinned.
+		 */
+		GEM_BUG_ON(!intel_context_is_pinned(ce->parallel.parent));
+
+		return ce->parallel.parent;
+	} else {
+		return ce;
+	}
+}
+
+static inline bool intel_context_is_parallel(struct intel_context *ce)
+{
+	return intel_context_is_child(ce) || intel_context_is_parent(ce);
+}
+
+void intel_context_bind_parent_child(struct intel_context *parent,
+				     struct intel_context *child);
+
+#define for_each_child(parent, ce)\
+	list_for_each_entry(ce, &(parent)->parallel.child_list,\
+			    parallel.child_link)
+#define for_each_child_safe(parent, ce, cn)\
+	list_for_each_entry_safe(ce, cn, &(parent)->parallel.child_list,\
+				 parallel.child_link)
+
 /**
  * intel_context_lock_pinned - Stablises the 'pinned' status of the HW context
  * @ce - the context
@@ -193,7 +241,13 @@ intel_context_timeline_lock(struct intel_context *ce)
 	struct intel_timeline *tl = ce->timeline;
 	int err;
 
-	err = mutex_lock_interruptible(&tl->mutex);
+	if (intel_context_is_parent(ce))
+		err = mutex_lock_interruptible_nested(&tl->mutex, 0);
+	else if (intel_context_is_child(ce))
+		err = mutex_lock_interruptible_nested(&tl->mutex,
+						      ce->parallel.child_index + 1);
+	else
+		err = mutex_lock_interruptible(&tl->mutex);
 	if (err)
 		return ERR_PTR(err);
 

drivers/gpu/drm/i915/gt/intel_context_types.h

@@ -55,9 +55,13 @@ struct intel_context_ops {
 	void (*reset)(struct intel_context *ce);
 	void (*destroy)(struct kref *kref);
 
-	/* virtual engine/context interface */
+	/* virtual/parallel engine/context interface */
 	struct intel_context *(*create_virtual)(struct intel_engine_cs **engine,
-						unsigned int count);
+						unsigned int count,
+						unsigned long flags);
+	struct intel_context *(*create_parallel)(struct intel_engine_cs **engines,
+						 unsigned int num_siblings,
+						 unsigned int width);
 	struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine,
 					       unsigned int sibling);
 };
@@ -113,6 +117,7 @@ struct intel_context {
 #define CONTEXT_NOPREEMPT		8
 #define CONTEXT_LRCA_DIRTY		9
 #define CONTEXT_GUC_INIT		10
+#define CONTEXT_PERMA_PIN		11
 
 	struct {
 		u64 timeout_us;
@@ -197,22 +202,80 @@ struct intel_context {
 	struct {
 		/**
 		 * @id: handle which is used to uniquely identify this context
-		 * with the GuC, protected by guc->contexts_lock
+		 * with the GuC, protected by guc->submission_state.lock
 		 */
 		u16 id;
 		/**
 		 * @ref: the number of references to the guc_id, when
 		 * transitioning in and out of zero protected by
-		 * guc->contexts_lock
+		 * guc->submission_state.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
+		 * still valid, protected by guc->submission_state.lock
 		 */
 		struct list_head link;
 	} guc_id;
 
+	/**
+	 * @destroyed_link: link in guc->submission_state.destroyed_contexts, in
+	 * list when context is pending to be destroyed (deregistered with the
+	 * GuC), protected by guc->submission_state.lock
+	 */
+	struct list_head destroyed_link;
+
+	/** @parallel: sub-structure for parallel submission members */
+	struct {
+		union {
+			/**
+			 * @child_list: parent's list of children
+			 * contexts, no protection as immutable after context
+			 * creation
+			 */
+			struct list_head child_list;
+			/**
+			 * @child_link: child's link into parent's list of
+			 * children
+			 */
+			struct list_head child_link;
+		};
+		/** @parent: pointer to parent if child */
+		struct intel_context *parent;
+		/**
+		 * @last_rq: last request submitted on a parallel context, used
+		 * to insert submit fences between requests in the parallel
+		 * context
+		 */
+		struct i915_request *last_rq;
+		/**
+		 * @fence_context: fence context composite fence when doing
+		 * parallel submission
+		 */
+		u64 fence_context;
+		/**
+		 * @seqno: seqno for composite fence when doing parallel
+		 * submission
+		 */
+		u32 seqno;
+		/** @number_children: number of children if parent */
+		u8 number_children;
+		/** @child_index: index into child_list if child */
+		u8 child_index;
+		/** @guc: GuC specific members for parallel submission */
+		struct {
+			/** @wqi_head: head pointer in work queue */
+			u16 wqi_head;
+			/** @wqi_tail: tail pointer in work queue */
+			u16 wqi_tail;
+			/**
+			 * @parent_page: page in context state (ce->state) used
+			 * by parent for work queue, process descriptor
+			 */
+			u8 parent_page;
+		} guc;
+	} parallel;
+
 #ifdef CONFIG_DRM_I915_SELFTEST
 	/**
 	 * @drop_schedule_enable: Force drop of schedule enable G2H for selftest

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -2,6 +2,7 @@
 #ifndef _INTEL_RINGBUFFER_H_
 #define _INTEL_RINGBUFFER_H_
 
+#include <asm/cacheflush.h>
 #include <drm/drm_util.h>
 
 #include <linux/hashtable.h>
@@ -281,9 +282,19 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
+#define FORCE_VIRTUAL	BIT(0)
 struct intel_context *
 intel_engine_create_virtual(struct intel_engine_cs **siblings,
-			    unsigned int count);
+			    unsigned int count, unsigned long flags);
+
+static inline struct intel_context *
+intel_engine_create_parallel(struct intel_engine_cs **engines,
+			     unsigned int num_engines,
+			     unsigned int width)
+{
+	GEM_BUG_ON(!engines[0]->cops->create_parallel);
+	return engines[0]->cops->create_parallel(engines, num_engines, width);
+}
 
 static inline bool
 intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine)

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -290,7 +290,8 @@ static void nop_irq_handler(struct intel_engine_cs *engine, u16 iir)
 	GEM_DEBUG_WARN_ON(iir);
 }
 
-static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
+static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
+			      u8 logical_instance)
 {
 	const struct engine_info *info = &intel_engines[id];
 	struct drm_i915_private *i915 = gt->i915;
@@ -335,6 +336,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 
 	engine->class = info->class;
 	engine->instance = info->instance;
+	engine->logical_mask = BIT(logical_instance);
 	__sprint_engine_name(engine);
 
 	engine->props.heartbeat_interval_ms =
@@ -588,6 +590,37 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 	return info->engine_mask;
 }
 
+static void populate_logical_ids(struct intel_gt *gt, u8 *logical_ids,
+				 u8 class, const u8 *map, u8 num_instances)
+{
+	int i, j;
+	u8 current_logical_id = 0;
+
+	for (j = 0; j < num_instances; ++j) {
+		for (i = 0; i < ARRAY_SIZE(intel_engines); ++i) {
+			if (!HAS_ENGINE(gt, i) ||
+			    intel_engines[i].class != class)
+				continue;
+
+			if (intel_engines[i].instance == map[j]) {
+				logical_ids[intel_engines[i].instance] =
+					current_logical_id++;
+				break;
+			}
+		}
+	}
+}
+
+static void setup_logical_ids(struct intel_gt *gt, u8 *logical_ids, u8 class)
+{
+	int i;
+	u8 map[MAX_ENGINE_INSTANCE + 1];
+
+	for (i = 0; i < MAX_ENGINE_INSTANCE + 1; ++i)
+		map[i] = i;
+	populate_logical_ids(gt, logical_ids, class, map, ARRAY_SIZE(map));
+}
+
 /**
  * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
  * @gt: pointer to struct intel_gt
@@ -599,7 +632,8 @@ int intel_engines_init_mmio(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 	const unsigned int engine_mask = init_engine_mask(gt);
 	unsigned int mask = 0;
-	unsigned int i;
+	unsigned int i, class;
+	u8 logical_ids[MAX_ENGINE_INSTANCE + 1];
 	int err;
 
 	drm_WARN_ON(&i915->drm, engine_mask == 0);
@@ -609,15 +643,23 @@ int intel_engines_init_mmio(struct intel_gt *gt)
 	if (i915_inject_probe_failure(i915))
 		return -ENODEV;
 
-	for (i = 0; i < ARRAY_SIZE(intel_engines); i++) {
-		if (!HAS_ENGINE(gt, i))
-			continue;
+	for (class = 0; class < MAX_ENGINE_CLASS + 1; ++class) {
+		setup_logical_ids(gt, logical_ids, class);
 
-		err = intel_engine_setup(gt, i);
-		if (err)
-			goto cleanup;
+		for (i = 0; i < ARRAY_SIZE(intel_engines); ++i) {
+			u8 instance = intel_engines[i].instance;
+
+			if (intel_engines[i].class != class ||
+			    !HAS_ENGINE(gt, i))
+				continue;
 
-		mask |= BIT(i);
+			err = intel_engine_setup(gt, i,
+						 logical_ids[instance]);
+			if (err)
+				goto cleanup;
+
+			mask |= BIT(i);
+		}
 	}
 
 	/*
@@ -1911,16 +1953,16 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 
 struct intel_context *
 intel_engine_create_virtual(struct intel_engine_cs **siblings,
-			    unsigned int count)
+			    unsigned int count, unsigned long flags)
 {
 	if (count == 0)
 		return ERR_PTR(-EINVAL);
 
-	if (count == 1)
+	if (count == 1 && !(flags & FORCE_VIRTUAL))
 		return intel_context_create(siblings[0]);
 
 	GEM_BUG_ON(!siblings[0]->cops->create_virtual);
-	return siblings[0]->cops->create_virtual(siblings, count);
+	return siblings[0]->cops->create_virtual(siblings, count, flags);
 }
 
 struct i915_request *

drivers/gpu/drm/i915/gt/intel_engine_pm.c

@@ -162,6 +162,19 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	unsigned long flags;
 	bool result = true;
 
+	/*
+	 * This is execlist specific behaviour intended to ensure the GPU is
+	 * idle by switching to a known 'safe' context. With GuC submission, the
+	 * same idle guarantee is achieved by other means (disabling
+	 * scheduling). Further, switching to a 'safe' context has no effect
+	 * with GuC submission as the scheduler can just switch back again.
+	 *
+	 * FIXME: Move this backend scheduler specific behaviour into the
+	 * scheduler backend.
+	 */
+	if (intel_engine_uses_guc(engine))
+		return true;
+
 	/* GPU is pointing to the void, as good as in the kernel context. */
 	if (intel_gt_is_wedged(engine->gt))
 		return true;

drivers/gpu/drm/i915/gt/intel_engine_pm.h

@@ -6,9 +6,11 @@
 #ifndef INTEL_ENGINE_PM_H
 #define INTEL_ENGINE_PM_H
 
+#include "i915_drv.h"
 #include "i915_request.h"
 #include "intel_engine_types.h"
 #include "intel_wakeref.h"
+#include "intel_gt_pm.h"
 
 static inline bool
 intel_engine_pm_is_awake(const struct intel_engine_cs *engine)
@@ -16,6 +18,11 @@ intel_engine_pm_is_awake(const struct intel_engine_cs *engine)
 	return intel_wakeref_is_active(&engine->wakeref);
 }
 
+static inline void __intel_engine_pm_get(struct intel_engine_cs *engine)
+{
+	__intel_wakeref_get(&engine->wakeref);
+}
+
 static inline void intel_engine_pm_get(struct intel_engine_cs *engine)
 {
 	intel_wakeref_get(&engine->wakeref);
@@ -26,6 +33,21 @@ static inline bool intel_engine_pm_get_if_awake(struct intel_engine_cs *engine)
 	return intel_wakeref_get_if_active(&engine->wakeref);
 }
 
+static inline void intel_engine_pm_might_get(struct intel_engine_cs *engine)
+{
+	if (!intel_engine_is_virtual(engine)) {
+		intel_wakeref_might_get(&engine->wakeref);
+	} else {
+		struct intel_gt *gt = engine->gt;
+		struct intel_engine_cs *tengine;
+		intel_engine_mask_t tmp, mask = engine->mask;
+
+		for_each_engine_masked(tengine, gt, mask, tmp)
+			intel_wakeref_might_get(&tengine->wakeref);
+	}
+	intel_gt_pm_might_get(engine->gt);
+}
+
 static inline void intel_engine_pm_put(struct intel_engine_cs *engine)
 {
 	intel_wakeref_put(&engine->wakeref);
@@ -47,6 +69,21 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
 	intel_wakeref_unlock_wait(&engine->wakeref);
 }
 
+static inline void intel_engine_pm_might_put(struct intel_engine_cs *engine)
+{
+	if (!intel_engine_is_virtual(engine)) {
+		intel_wakeref_might_put(&engine->wakeref);
+	} else {
+		struct intel_gt *gt = engine->gt;
+		struct intel_engine_cs *tengine;
+		intel_engine_mask_t tmp, mask = engine->mask;
+
+		for_each_engine_masked(tengine, gt, mask, tmp)
+			intel_wakeref_might_put(&tengine->wakeref);
+	}
+	intel_gt_pm_might_put(engine->gt);
+}
+
 static inline struct i915_request *
 intel_engine_create_kernel_request(struct intel_engine_cs *engine)
 {

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -269,6 +269,13 @@ struct intel_engine_cs {
 	unsigned int guc_id;
 
 	intel_engine_mask_t mask;
+	/**
+	 * @logical_mask: logical mask of engine, reported to user space via
+	 * query IOCTL and used to communicate with the GuC in logical space.
+	 * The logical instance of a physical engine can change based on product
+	 * and fusing.
+	 */
+	intel_engine_mask_t logical_mask;
 
 	u8 class;
 	u8 instance;

drivers/gpu/drm/i915/gt/intel_execlists_submission.c

@@ -201,7 +201,8 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
 }
 
 static struct intel_context *
-execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+			 unsigned long flags);
 
 static struct i915_request *
 __active_request(const struct intel_timeline * const tl,
@@ -3784,7 +3785,8 @@ static void virtual_submit_request(struct i915_request *rq)
 }
 
 static struct intel_context *
-execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+			 unsigned long flags)
 {
 	struct virtual_engine *ve;
 	unsigned int n;
@@ -3877,6 +3879,7 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
 
 		ve->siblings[ve->num_siblings++] = sibling;
 		ve->base.mask |= sibling->mask;
+		ve->base.logical_mask |= sibling->logical_mask;
 
 		/*
 		 * All physical engines must be compatible for their emission

drivers/gpu/drm/i915/gt/intel_gt_debugfs.c

@@ -13,6 +13,59 @@
 #include "pxp/intel_pxp_debugfs.h"
 #include "uc/intel_uc_debugfs.h"
 
+int intel_gt_debugfs_reset_show(struct intel_gt *gt, u64 *val)
+{
+	int ret = intel_gt_terminally_wedged(gt);
+
+	switch (ret) {
+	case -EIO:
+		*val = 1;
+		return 0;
+	case 0:
+		*val = 0;
+		return 0;
+	default:
+		return ret;
+	}
+}
+
+int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val)
+{
+	/* Flush any previous reset before applying for a new one */
+	wait_event(gt->reset.queue,
+		   !test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
+
+	intel_gt_handle_error(gt, val, I915_ERROR_CAPTURE,
+			      "Manually reset engine mask to %llx", val);
+	return 0;
+}
+
+/*
+ * keep the interface clean where the first parameter
+ * is a 'struct intel_gt *' instead of 'void *'
+ */
+static int __intel_gt_debugfs_reset_show(void *data, u64 *val)
+{
+	return intel_gt_debugfs_reset_show(data, val);
+}
+
+static int __intel_gt_debugfs_reset_store(void *data, u64 val)
+{
+	return intel_gt_debugfs_reset_store(data, val);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(reset_fops, __intel_gt_debugfs_reset_show,
+			__intel_gt_debugfs_reset_store, "%llu\n");
+
+static void gt_debugfs_register(struct intel_gt *gt, struct dentry *root)
+{
+	static const struct intel_gt_debugfs_file files[] = {
+		{ "reset", &reset_fops, NULL },
+	};
+
+	intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
+}
+
 void intel_gt_debugfs_register(struct intel_gt *gt)
 {
 	struct dentry *root;
@@ -24,6 +77,8 @@ void intel_gt_debugfs_register(struct intel_gt *gt)
 	if (IS_ERR(root))
 		return;
 
+	gt_debugfs_register(gt, root);
+
 	intel_gt_engines_debugfs_register(gt, root);
 	intel_gt_pm_debugfs_register(gt, root);
 	intel_sseu_debugfs_register(gt, root);

drivers/gpu/drm/i915/gt/intel_gt_debugfs.h

@@ -35,4 +35,8 @@ void intel_gt_debugfs_register_files(struct dentry *root,
 				     const struct intel_gt_debugfs_file *files,
 				     unsigned long count, void *data);
 
+/* functions that need to be accessed by the upper level non-gt interfaces */
+int intel_gt_debugfs_reset_show(struct intel_gt *gt, u64 *val);
+int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val);
+
 #endif /* INTEL_GT_DEBUGFS_H */

drivers/gpu/drm/i915/gt/intel_gt_pm.h

@@ -31,6 +31,11 @@ static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt)
 	return intel_wakeref_get_if_active(&gt->wakeref);
 }
 
+static inline void intel_gt_pm_might_get(struct intel_gt *gt)
+{
+	intel_wakeref_might_get(&gt->wakeref);
+}
+
 static inline void intel_gt_pm_put(struct intel_gt *gt)
 {
 	intel_wakeref_put(&gt->wakeref);
@@ -41,6 +46,15 @@ static inline void intel_gt_pm_put_async(struct intel_gt *gt)
 	intel_wakeref_put_async(&gt->wakeref);
 }
 
+static inline void intel_gt_pm_might_put(struct intel_gt *gt)
+{
+	intel_wakeref_might_put(&gt->wakeref);
+}
+
+#define with_intel_gt_pm(gt, tmp) \
+	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
+	     intel_gt_pm_put(gt), tmp = 0)
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);

drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c

@@ -20,6 +20,46 @@
 #include "intel_uncore.h"
 #include "vlv_sideband.h"
 
+int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt)
+{
+	atomic_inc(&gt->user_wakeref);
+	intel_gt_pm_get(gt);
+	if (GRAPHICS_VER(gt->i915) >= 6)
+		intel_uncore_forcewake_user_get(gt->uncore);
+
+	return 0;
+}
+
+int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt)
+{
+	if (GRAPHICS_VER(gt->i915) >= 6)
+		intel_uncore_forcewake_user_put(gt->uncore);
+	intel_gt_pm_put(gt);
+	atomic_dec(&gt->user_wakeref);
+
+	return 0;
+}
+
+static int forcewake_user_open(struct inode *inode, struct file *file)
+{
+	struct intel_gt *gt = inode->i_private;
+
+	return intel_gt_pm_debugfs_forcewake_user_open(gt);
+}
+
+static int forcewake_user_release(struct inode *inode, struct file *file)
+{
+	struct intel_gt *gt = inode->i_private;
+
+	return intel_gt_pm_debugfs_forcewake_user_release(gt);
+}
+
+static const struct file_operations forcewake_user_fops = {
+	.owner = THIS_MODULE,
+	.open = forcewake_user_open,
+	.release = forcewake_user_release,
+};
+
 static int fw_domains_show(struct seq_file *m, void *data)
 {
 	struct intel_gt *gt = m->private;
@@ -628,6 +668,7 @@ void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root)
 		{ "drpc", &drpc_fops, NULL },
 		{ "frequency", &frequency_fops, NULL },
 		{ "forcewake", &fw_domains_fops, NULL },
+		{ "forcewake_user", &forcewake_user_fops, NULL},
 		{ "llc", &llc_fops, llc_eval },
 		{ "rps_boost", &rps_boost_fops, rps_eval },
 	};

drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.h

@@ -13,4 +13,8 @@ struct drm_printer;
 void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root);
 void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *m);
 
+/* functions that need to be accessed by the upper level non-gt interfaces */
+int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt);
+int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt);
+
 #endif /* INTEL_GT_PM_DEBUGFS_H */

drivers/gpu/drm/i915/gt/intel_llc.c

@@ -3,6 +3,7 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <asm/tsc.h>
 #include <linux/cpufreq.h>
 
 #include "i915_drv.h"

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -942,6 +942,11 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
 		context_size += PAGE_SIZE;
 	}
 
+	if (intel_context_is_parent(ce) && intel_engine_uses_guc(engine)) {
+		ce->parallel.guc.parent_page = context_size / PAGE_SIZE;
+		context_size += PARENT_SCRATCH_SIZE;
+	}
+
 	obj = i915_gem_object_create_lmem(engine->i915, context_size,
 					  I915_BO_ALLOC_PM_VOLATILE);
 	if (IS_ERR(obj))

drivers/gpu/drm/i915/gt/intel_ring_submission.c

@@ -292,7 +292,7 @@ static void xcs_sanitize(struct intel_engine_cs *engine)
 	sanitize_hwsp(engine);
 
 	/* And scrub the dirty cachelines for the HWSP */
-	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+	drm_clflush_virt_range(engine->status_page.addr, PAGE_SIZE);
 
 	intel_engine_reset_pinned_contexts(engine);
 }

drivers/gpu/drm/i915/gt/intel_timeline.c

@@ -64,7 +64,7 @@ intel_timeline_pin_map(struct intel_timeline *timeline)
 
 	timeline->hwsp_map = vaddr;
 	timeline->hwsp_seqno = memset(vaddr + ofs, 0, TIMELINE_SEQNO_BYTES);
-	clflush(vaddr + ofs);
+	drm_clflush_virt_range(vaddr + ofs, TIMELINE_SEQNO_BYTES);
 
 	return 0;
 }
@@ -225,7 +225,7 @@ void intel_timeline_reset_seqno(const struct intel_timeline *tl)
 
 	memset(hwsp_seqno + 1, 0, TIMELINE_SEQNO_BYTES - sizeof(*hwsp_seqno));
 	WRITE_ONCE(*hwsp_seqno, tl->seqno);
-	clflush(hwsp_seqno);
+	drm_clflush_virt_range(hwsp_seqno, TIMELINE_SEQNO_BYTES);
 }
 
 void intel_timeline_enter(struct intel_timeline *tl)

drivers/gpu/drm/i915/gt/selftest_execlists.c

@@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve));
 
 	for (n = 0; n < nctx; n++) {
-		ve[n] = intel_engine_create_virtual(siblings, nsibling);
+		ve[n] = intel_engine_create_virtual(siblings, nsibling, 0);
 		if (IS_ERR(ve[n])) {
 			err = PTR_ERR(ve[n]);
 			nctx = n;
@@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_close;
@@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt,
 		i915_request_add(rq);
 	}
 
-	ce = intel_engine_create_virtual(siblings, nsibling);
+	ce = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ce)) {
 		err = PTR_ERR(ce);
 		goto out;
@@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt,
 
 	/* XXX We do not handle oversubscription and fairness with normal rq */
 	for (n = 0; n < nsibling; n++) {
-		ce = intel_engine_create_virtual(siblings, nsibling);
+		ce = intel_engine_create_virtual(siblings, nsibling, 0);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			goto out;
@@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 	if (err)
 		goto out_scratch;
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_scratch;
@@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_spin;

drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h

@@ -142,6 +142,7 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505,
 	INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
 	INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600,
+	INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601,
 	INTEL_GUC_ACTION_RESET_CLIENT = 0x5507,
 	INTEL_GUC_ACTION_LIMIT
 };

drivers/gpu/drm/i915/gt/uc/intel_guc.c

@@ -756,3 +756,32 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p)
 		}
 	}
 }
+
+void intel_guc_write_barrier(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	if (i915_gem_object_is_lmem(guc->ct.vma->obj)) {
+		/*
+		 * Ensure intel_uncore_write_fw can be used rather than
+		 * intel_uncore_write.
+		 */
+		GEM_BUG_ON(guc->send_regs.fw_domains);
+
+		/*
+		 * This register is used by the i915 and GuC for MMIO based
+		 * communication. Once we are in this code CTBs are the only
+		 * method the i915 uses to communicate with the GuC so it is
+		 * safe to write to this register (a value of 0 is NOP for MMIO
+		 * communication). If we ever start mixing CTBs and MMIOs a new
+		 * register will have to be chosen. This function is also used
+		 * to enforce ordering of a work queue item write and an update
+		 * to the process descriptor. When a work queue is being used,
+		 * CTBs are also the only mechanism of communication.
+		 */
+		intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0);
+	} else {
+		/* wmb() sufficient for a barrier if in smem */
+		wmb();
+	}
+}

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -46,6 +46,15 @@ struct intel_guc {
 	 * submitted until the stalled request is processed.
 	 */
 	struct i915_request *stalled_request;
+	/**
+	 * @submission_stall_reason: reason why submission is stalled
+	 */
+	enum {
+		STALL_NONE,
+		STALL_REGISTER_CONTEXT,
+		STALL_MOVE_LRC_TAIL,
+		STALL_ADD_REQUEST,
+	} submission_stall_reason;
 
 	/* intel_guc_recv interrupt related state */
 	/** @irq_lock: protects GuC irq state */
@@ -71,16 +80,41 @@ struct intel_guc {
 	} interrupts;
 
 	/**
-	 * @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
+	 * @submission_state: sub-structure for submission state protected by
+	 * single lock
 	 */
-	struct list_head guc_id_list;
+	struct {
+		/**
+		 * @lock: protects everything in submission_state,
+		 * ce->guc_id.id, and ce->guc_id.ref when transitioning in and
+		 * out of zero
+		 */
+		spinlock_t lock;
+		/**
+		 * @guc_ids: used to allocate new guc_ids, single-lrc
+		 */
+		struct ida guc_ids;
+		/**
+		 * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc
+		 */
+		unsigned long *guc_ids_bitmap;
+		/**
+		 * @guc_id_list: list of intel_context with valid guc_ids but no
+		 * refs
+		 */
+		struct list_head guc_id_list;
+		/**
+		 * @destroyed_contexts: list of contexts waiting to be destroyed
+		 * (deregistered with the GuC)
+		 */
+		struct list_head destroyed_contexts;
+		/**
+		 * @destroyed_worker: worker to deregister contexts, need as we
+		 * need to take a GT PM reference and can't from destroy
+		 * function as it might be in an atomic context (no sleeping)
+		 */
+		struct work_struct destroyed_worker;
+	} submission_state;
 
 	/**
 	 * @submission_supported: tracks whether we support GuC submission on
@@ -342,4 +376,6 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc);
 
 void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
 
+void intel_guc_write_barrier(struct intel_guc *guc);
+
 #endif

drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c

@@ -176,7 +176,7 @@ static void guc_mapping_table_init(struct intel_gt *gt,
 	for_each_engine(engine, gt, id) {
 		u8 guc_class = engine_class_to_guc_class(engine->class);
 
-		system_info->mapping_table[guc_class][engine->instance] =
+		system_info->mapping_table[guc_class][ilog2(engine->logical_mask)] =
 			engine->instance;
 	}
 }

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -383,28 +383,6 @@ static u32 ct_get_next_fence(struct intel_guc_ct *ct)
 	return ++ct->requests.last_fence;
 }
 
-static void write_barrier(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	if (i915_gem_object_is_lmem(guc->ct.vma->obj)) {
-		GEM_BUG_ON(guc->send_regs.fw_domains);
-		/*
-		 * This register is used by the i915 and GuC for MMIO based
-		 * communication. Once we are in this code CTBs are the only
-		 * method the i915 uses to communicate with the GuC so it is
-		 * safe to write to this register (a value of 0 is NOP for MMIO
-		 * communication). If we ever start mixing CTBs and MMIOs a new
-		 * register will have to be chosen.
-		 */
-		intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0);
-	} else {
-		/* wmb() sufficient for a barrier if in smem */
-		wmb();
-	}
-}
-
 static int ct_write(struct intel_guc_ct *ct,
 		    const u32 *action,
 		    u32 len /* in dwords */,
@@ -474,7 +452,7 @@ static int ct_write(struct intel_guc_ct *ct,
 	 * make sure H2G buffer update and LRC tail update (if this triggering a
 	 * submission) are visible before updating the descriptor tail
 	 */
-	write_barrier(ct);
+	intel_guc_write_barrier(ct_to_guc(ct));
 
 	/* update local copies */
 	ctb->tail = tail;

drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h

@@ -52,27 +52,27 @@
 
 #define GUC_DOORBELL_INVALID		256
 
-#define GUC_WQ_SIZE			(PAGE_SIZE * 2)
-
-/* Work queue item header definitions */
+/*
+ * Work queue item header definitions
+ *
+ * Work queue is circular buffer used to submit complex (multi-lrc) submissions
+ * to the GuC. A work queue item is an entry in the circular buffer.
+ */
 #define WQ_STATUS_ACTIVE		1
 #define WQ_STATUS_SUSPENDED		2
 #define WQ_STATUS_CMD_ERROR		3
 #define WQ_STATUS_ENGINE_ID_NOT_USED	4
 #define WQ_STATUS_SUSPENDED_FROM_RESET	5
-#define WQ_TYPE_SHIFT			0
-#define   WQ_TYPE_BATCH_BUF		(0x1 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_PSEUDO		(0x2 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_INORDER		(0x3 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_NOOP			(0x4 << WQ_TYPE_SHIFT)
-#define WQ_TARGET_SHIFT			10
-#define WQ_LEN_SHIFT			16
-#define WQ_NO_WCFLUSH_WAIT		(1 << 27)
-#define WQ_PRESENT_WORKLOAD		(1 << 28)
-
-#define WQ_RING_TAIL_SHIFT		20
-#define WQ_RING_TAIL_MAX		0x7FF	/* 2^11 QWords */
-#define WQ_RING_TAIL_MASK		(WQ_RING_TAIL_MAX << WQ_RING_TAIL_SHIFT)
+#define WQ_TYPE_BATCH_BUF		0x1
+#define WQ_TYPE_PSEUDO			0x2
+#define WQ_TYPE_INORDER			0x3
+#define WQ_TYPE_NOOP			0x4
+#define WQ_TYPE_MULTI_LRC		0x5
+#define WQ_TYPE_MASK			GENMASK(7, 0)
+#define WQ_LEN_MASK			GENMASK(26, 16)
+
+#define WQ_GUC_ID_MASK			GENMASK(15, 0)
+#define WQ_RING_TAIL_MASK		GENMASK(28, 18)
 
 #define GUC_STAGE_DESC_ATTR_ACTIVE	BIT(0)
 #define GUC_STAGE_DESC_ATTR_PENDING_DB	BIT(1)
@@ -186,7 +186,7 @@ struct guc_process_desc {
 	u32 wq_status;
 	u32 engine_presence;
 	u32 priority;
-	u32 reserved[30];
+	u32 reserved[36];
 } __packed;
 
 #define CONTEXT_REGISTRATION_FLAG_KMD	BIT(0)

drivers/gpu/drm/i915/i915_query.c

@@ -124,7 +124,9 @@ query_engine_info(struct drm_i915_private *i915,
 	for_each_uabi_engine(engine, i915) {
 		info.engine.engine_class = engine->uabi_class;
 		info.engine.engine_instance = engine->uabi_instance;
+		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;
 		info.capabilities = engine->uabi_capabilities;
+		info.logical_instance = ilog2(engine->logical_mask);
 
 		if (copy_to_user(info_ptr, &info, sizeof(info)))
 			return -EFAULT;

drivers/gpu/drm/i915/i915_vma.h

@@ -57,9 +57,16 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma)
 
 int __must_check __i915_vma_move_to_active(struct i915_vma *vma,
 					   struct i915_request *rq);
-int __must_check i915_vma_move_to_active(struct i915_vma *vma,
-					 struct i915_request *rq,
-					 unsigned int flags);
+int __must_check _i915_vma_move_to_active(struct i915_vma *vma,
+					  struct i915_request *rq,
+					  struct dma_fence *fence,
+					  unsigned int flags);
+static inline int __must_check
+i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq,
+			unsigned int flags)
+{
+	return _i915_vma_move_to_active(vma, rq, &rq->fence, flags);
+}
 
 #define __i915_vma_flags(v) ((unsigned long *)&(v)->flags.counter)