[Intel-gfx] [PATCH 21/28] drm/i915: Coordinate i915_active with its own mutex

Chris Wilson chris at chris-wilson.co.uk
Mon Jun 10 07:21:19 UTC 2019


Forgo the struct_mutex serialisation for i915_active, and interpose its
own mutex handling for active/retire.

This is a multi-layered sleight-of-hand. First, we had to ensure that no
active/retire callbacks accidentally inverted the mutex ordering rules,
nor assumed that they were themselves serialised by struct_mutex. More
challenging though, is the rule over updating elements of the active
rbtree. Instead of the whole i915_active now being serialised by
struct_mutex, allocations/rotations of the tree are serialised by the
i915_active.mutex and individual nodes are serialised by the caller
using the i915_timeline.mutex (we need to use nested spinlocks to
interact with the dma_fence callback lists).

The pain point here is that instead of a single mutex around execbuf, we
now have to take a mutex for active tracker (one for each vma, context,
etc) and a couple of spinlocks for each fence update. The improvement in
fine grained locking allowing for multiple concurrent clients
(eventually!) should be worth it in typical loads.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  12 +-
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |   2 +-
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |   2 +
 drivers/gpu/drm/i915/gem/i915_gem_pm.c        |   9 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |   2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c         |  10 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |   5 +-
 drivers/gpu/drm/i915/gvt/scheduler.c          |   3 -
 drivers/gpu/drm/i915/i915_active.c            | 165 +++++++-------
 drivers/gpu/drm/i915/i915_active.h            | 204 +++++-------------
 drivers/gpu/drm/i915/i915_active_types.h      |  17 +-
 drivers/gpu/drm/i915/i915_gem.c               |  50 +++--
 drivers/gpu/drm/i915/i915_gem_gtt.c           |   2 +-
 drivers/gpu/drm/i915/i915_request.c           |  56 +----
 drivers/gpu/drm/i915/i915_request.h           |   1 -
 drivers/gpu/drm/i915/i915_timeline.c          |   9 +-
 drivers/gpu/drm/i915/i915_timeline_types.h    |   2 +-
 drivers/gpu/drm/i915/i915_vma.c               |  36 +---
 drivers/gpu/drm/i915/intel_frontbuffer.c      |   3 +-
 drivers/gpu/drm/i915/intel_overlay.c          |   6 +-
 drivers/gpu/drm/i915/selftests/i915_active.c  |   5 +-
 .../gpu/drm/i915/selftests/mock_timeline.c    |   2 +-
 22 files changed, 229 insertions(+), 374 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 837cad233cc6..2e684f8151d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -909,20 +909,18 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 				void (*task)(void *data),
 				void *data)
 {
-	struct drm_i915_private *i915 = ctx->i915;
 	struct context_barrier_task *cb;
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
 	int err = 0;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!task);
 
 	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
 	if (!cb)
 		return -ENOMEM;
 
-	i915_active_init(i915, &cb->base, NULL, cb_retire);
+	i915_active_init(&cb->base, NULL, cb_retire);
 	err = i915_active_acquire(&cb->base);
 	if (err) {
 		kfree(cb);
@@ -954,7 +952,9 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 		if (emit)
 			err = emit(rq, data);
 		if (err == 0)
-			err = i915_active_ref(&cb->base, rq->fence.context, rq);
+			err = i915_active_ref(&cb->base,
+					      rq->fence.context,
+					      &rq->fence);
 
 		i915_request_add(rq);
 		if (err)
@@ -1188,7 +1188,7 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 		return PTR_ERR(rq);
 
 	/* Queue this switch after all other activity by this context. */
-	ret = i915_active_request_set(&ce->ring->timeline->last_request, rq);
+	ret = i915_active_fence_set(&ce->ring->timeline->last_request, rq);
 	if (ret)
 		goto out_add;
 
@@ -1200,7 +1200,7 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	 * words transfer the pinned ce object to tracked active request.
 	 */
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
-	ret = i915_active_ref(&ce->active, rq->fence.context, rq);
+	ret = i915_active_ref(&ce->active, rq->fence.context, &rq->fence);
 	if (ret)
 		goto out_add;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 2c4f3229361d..6193c81ebbed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1316,7 +1316,7 @@ relocate_entry(struct i915_vma *vma,
 
 	if (!eb->reloc_cache.vaddr &&
 	    (DBG_FORCE_RELOC == FORCE_GPU_RELOC ||
-	     !reservation_object_test_signaled_rcu(vma->resv, true))) {
+	     i915_vma_is_active(vma))) {
 		const unsigned int gen = eb->reloc_cache.gen;
 		unsigned int len;
 		u32 *batch;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 21bfb7bd0f57..e87fca4d8194 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -11,6 +11,8 @@
 
 #include <drm/drm_gem.h>
 
+#include <uapi/drm/i915_drm.h>
+
 #include "i915_active.h"
 #include "i915_selftest.h"
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index b0f37621de9f..283092ac13fe 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -15,14 +15,11 @@ static void call_idle_barriers(struct intel_engine_cs *engine)
 	struct llist_node *node, *next;
 
 	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
-		struct i915_active_request *active =
+		struct i915_active_fence *active =
 			container_of((struct list_head *)node,
-				     typeof(*active), link);
+				     typeof(*active), cb.node);
 
-		INIT_LIST_HEAD(&active->link);
-		RCU_INIT_POINTER(active->request, NULL);
-
-		active->retire(active, NULL);
+		active->cb.func(NULL, &active->cb);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index b9fea31cf9ec..a32698f7645f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -182,7 +182,7 @@ intel_context_init(struct intel_context *ce,
 
 	mutex_init(&ce->pin_mutex);
 
-	i915_active_init(ctx->i915, &ce->active,
+	i915_active_init(&ce->active,
 			 __intel_context_active, __intel_context_retire);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 1f831fe759a5..c5a772889ea5 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -881,10 +881,10 @@ static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
 	 */
 	mutex_lock(&i915->gt.timelines.mutex);
 	list_for_each_entry(tl, &i915->gt.timelines.active_list, link) {
-		struct i915_request *rq;
+		struct dma_fence *fence;
 
-		rq = i915_active_request_get_unlocked(&tl->last_request);
-		if (!rq)
+		fence = i915_active_fence_get(&tl->last_request);
+		if (!fence)
 			continue;
 
 		/*
@@ -894,8 +894,8 @@ static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
 		 * (I915_FENCE_TIMEOUT) so this wait should not be unbounded
 		 * in the worst case.
 		 */
-		dma_fence_default_wait(&rq->fence, false, MAX_SCHEDULE_TIMEOUT);
-		i915_request_put(rq);
+		dma_fence_default_wait(fence, false, MAX_SCHEDULE_TIMEOUT);
+		dma_fence_put(fence);
 	}
 	mutex_unlock(&i915->gt.timelines.mutex);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 338111d690ac..9fc03a400685 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -854,7 +854,6 @@ static struct i915_request *dummy_request(struct intel_engine_cs *engine)
 	if (!rq)
 		return NULL;
 
-	INIT_LIST_HEAD(&rq->active_list);
 	rq->engine = engine;
 
 	i915_sched_node_init(&rq->sched);
@@ -945,8 +944,8 @@ static int live_suppress_wait_preempt(void *arg)
 				}
 
 				/* Disable NEWCLIENT promotion */
-				__i915_active_request_set(&rq[i]->timeline->last_request,
-							  dummy);
+				__i915_active_fence_set(&rq[i]->timeline->last_request,
+							&dummy->fence);
 				i915_request_add(rq[i]);
 			}
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 6cd72dd96a4b..31752b7ebff5 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -391,11 +391,8 @@ intel_gvt_workload_req_alloc(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct i915_request *rq;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	if (workload->req)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index f7ffa6e7bd9a..65a9ad2fc9c7 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -8,8 +8,6 @@
 #include "i915_active.h"
 #include "i915_globals.h"
 
-#define BKL(ref) (&(ref)->i915->drm.struct_mutex)
-
 /*
  * Active refs memory management
  *
@@ -23,7 +21,7 @@ static struct i915_global_active {
 } global;
 
 struct active_node {
-	struct i915_active_request base;
+	struct i915_active_fence base;
 	struct i915_active *ref;
 	struct rb_node node;
 	u64 timeline;
@@ -32,11 +30,12 @@ struct active_node {
 static void
 __active_retire(struct i915_active *ref)
 {
-	struct rb_root root = RB_ROOT;
 	struct active_node *it, *n;
+	struct rb_root root;
 	bool retire = false;
 
 	lockdep_assert_held(&ref->mutex);
+	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	/* return the unused nodes to our slabcache -- flushing the allocator */
 	if (atomic_dec_and_test(&ref->count)) {
@@ -47,12 +46,13 @@ __active_retire(struct i915_active *ref)
 	}
 
 	mutex_unlock(&ref->mutex);
+	if (!retire)
+		return;
 
-	if (retire)
-		ref->retire(ref);
+	ref->retire(ref);
 
 	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
-		GEM_BUG_ON(i915_active_request_isset(&it->base));
+		GEM_BUG_ON(i915_active_fence_isset(&it->base));
 		kmem_cache_free(global.slab_cache, it);
 	}
 }
@@ -86,12 +86,13 @@ active_retire(struct i915_active *ref)
 }
 
 static void
-node_retire(struct i915_active_request *base, struct i915_request *rq)
+node_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	active_retire(container_of(base, struct active_node, base)->ref);
+	i915_active_fence_cb(fence, cb);
+	active_retire(container_of(cb, struct active_node, base.cb)->ref);
 }
 
-static struct i915_active_request *
+static struct i915_active_fence *
 active_instance(struct i915_active *ref, u64 idx)
 {
 	struct active_node *node, *prealloc;
@@ -114,6 +115,7 @@ active_instance(struct i915_active *ref, u64 idx)
 		return NULL;
 
 	mutex_lock(&ref->mutex);
+	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	parent = NULL;
 	p = &ref->tree.rb_node;
@@ -121,7 +123,7 @@ active_instance(struct i915_active *ref, u64 idx)
 		parent = *p;
 
 		node = rb_entry(parent, struct active_node, node);
-		if (node->timeline == idx && !IS_ERR(node->base.request)) {
+		if (node->timeline == idx && !IS_ERR(node->base.fence)) {
 			kmem_cache_free(global.slab_cache, prealloc);
 			goto out;
 		}
@@ -133,7 +135,8 @@ active_instance(struct i915_active *ref, u64 idx)
 	}
 
 	node = prealloc;
-	i915_active_request_init(&node->base, NULL, node_retire);
+	RCU_INIT_POINTER(node->base.fence, NULL);
+	node->base.cb.func = node_retire;
 	node->ref = ref;
 	node->timeline = idx;
 
@@ -147,13 +150,11 @@ active_instance(struct i915_active *ref, u64 idx)
 	return &node->base;
 }
 
-void __i915_active_init(struct drm_i915_private *i915,
-			struct i915_active *ref,
+void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
 			struct lock_class_key *key)
 {
-	ref->i915 = i915;
 	ref->active = active;
 	ref->retire = retire;
 	ref->tree = RB_ROOT;
@@ -166,9 +167,9 @@ void __i915_active_init(struct drm_i915_private *i915,
 
 int i915_active_ref(struct i915_active *ref,
 		    u64 timeline,
-		    struct i915_request *rq)
+		    struct dma_fence *fence)
 {
-	struct i915_active_request *active;
+	struct i915_active_fence *active;
 	int err;
 
 	/* Prevent reaping in case we malloc/wait while building the tree */
@@ -182,9 +183,9 @@ int i915_active_ref(struct i915_active *ref,
 		goto out;
 	}
 
-	if (!i915_active_request_isset(active))
+	GEM_BUG_ON(!atomic_read(&ref->count));
+	if (!__i915_active_fence_set(active, fence))
 		atomic_inc(&ref->count);
-	__i915_active_request_set(active, rq);
 
 out:
 	i915_active_release(ref);
@@ -222,60 +223,33 @@ int i915_active_wait(struct i915_active *ref)
 	struct active_node *it, *n;
 	int err;
 
+	might_sleep();
 	if (RB_EMPTY_ROOT(&ref->tree))
 		return 0;
 
-	err = i915_active_acquire(ref); /* Avoid retiring ourselves */
+	err = mutex_lock_interruptible(&ref->mutex);
 	if (err)
 		return err;
 
-	err = mutex_lock_interruptible(&ref->mutex);
-	if (err)
-		goto out;
+	if (!atomic_add_unless(&ref->count, 1, 0))
+		goto unlock;
 
 	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		err = i915_active_request_retire(&it->base, BKL(ref));
-		if (err)
-			break;
-	}
-	mutex_unlock(&ref->mutex);
+		struct dma_fence *fence;
 
-out:
-	i915_active_release(ref);
-	return err;
-}
-
-int i915_request_await_active_request(struct i915_request *rq,
-				      struct i915_active_request *active)
-{
-	struct i915_request *barrier =
-		i915_active_request_raw(active, &rq->i915->drm.struct_mutex);
-
-	return barrier ? i915_request_await_dma_fence(rq, &barrier->fence) : 0;
-}
+		fence = i915_active_fence_get(&it->base);
+		if (!fence)
+			continue;
 
-int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
-{
-	struct active_node *it, *n;
-	int err;
-
-	if (RB_EMPTY_ROOT(&ref->tree))
-		return 0;
-
-	/* await allocates and so we need to avoid hitting the shrinker */
-	err = i915_active_acquire(ref);
-	if (err)
-		return err;
-
-	mutex_lock(&ref->mutex);
-	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		err = i915_request_await_active_request(rq, &it->base);
+		err = dma_fence_wait(fence, true);
+		dma_fence_put(fence);
 		if (err)
 			break;
 	}
-	mutex_unlock(&ref->mutex);
+	__active_retire(ref);
 
-	i915_active_release(ref);
+unlock:
+	mutex_unlock(&ref->mutex);
 	return err;
 }
 
@@ -306,13 +280,13 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			break;
 		}
 
-		i915_active_request_init(&node->base,
-					 (void *)engine, node_retire);
+		RCU_INIT_POINTER(node->base.fence, (void *)engine);
+		node->base.cb.func = node_retire;
 		node->timeline = kctx->ring->timeline->fence_context;
 		node->ref = ref;
 		atomic_inc(&ref->count);
 
-		llist_add((struct llist_node *)&node->base.link,
+		llist_add((struct llist_node *)&node->base.cb.node,
 			  &ref->barriers);
 	}
 
@@ -332,10 +306,10 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 		struct rb_node **p, *parent;
 
 		node = container_of((struct list_head *)pos,
-				    typeof(*node), base.link);
+				    typeof(*node), base.cb.node);
 
-		engine = (void *)rcu_access_pointer(node->base.request);
-		RCU_INIT_POINTER(node->base.request, ERR_PTR(-EAGAIN));
+		engine = (void *)rcu_access_pointer(node->base.fence);
+		RCU_INIT_POINTER(node->base.fence, ERR_PTR(-EAGAIN));
 
 		parent = NULL;
 		p = &ref->tree.rb_node;
@@ -351,7 +325,7 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 		rb_link_node(&node->node, parent, p);
 		rb_insert_color(&node->node, &ref->tree);
 
-		llist_add((struct llist_node *)&node->base.link,
+		llist_add((struct llist_node *)&node->base.cb.node,
 			  &engine->barrier_tasks);
 	}
 	mutex_unlock(&ref->mutex);
@@ -361,29 +335,66 @@ void i915_request_add_barriers(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct llist_node *node, *next;
+	unsigned long flags;
+
+	GEM_BUG_ON(intel_engine_is_virtual(engine));
+	node = llist_del_all(&engine->barrier_tasks);
+	if (!node)
+		return;
 
-	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks))
-		list_add_tail((struct list_head *)node, &rq->active_list);
+	spin_lock_irqsave(&rq->lock, flags);
+	llist_for_each_safe(node, next, node)
+		list_add_tail((struct list_head *)node, &rq->fence.cb_list);
+	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
-int i915_active_request_set(struct i915_active_request *active,
-			    struct i915_request *rq)
+struct dma_fence *
+__i915_active_fence_set(struct i915_active_fence *active,
+			struct dma_fence *fence)
 {
+	struct dma_fence *old;
+	unsigned long flags;
+
+	spin_lock_irqsave(fence->lock, flags);
+	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
+
+	old = rcu_dereference_protected(active->fence, 1);
+	if (old) {
+		spin_lock_nested(old->lock, SINGLE_DEPTH_NESTING);
+		__list_del_entry(&active->cb.node);
+		spin_unlock(old->lock);
+	}
+
+	rcu_assign_pointer(active->fence, fence);
+	list_add_tail(&active->cb.node, &fence->cb_list);
+
+	spin_unlock_irqrestore(fence->lock, flags);
+
+	return old;
+}
+
+int i915_active_fence_set(struct i915_active_fence *active,
+			  struct i915_request *rq)
+{
+	struct dma_fence *fence;
 	int err;
 
 	/* Must maintain ordering wrt previous active requests */
-	err = i915_request_await_active_request(rq, active);
-	if (err)
-		return err;
+	fence = i915_active_fence_get(active);
+	if (fence) {
+		err = i915_request_await_dma_fence(rq, fence);
+		dma_fence_put(fence);
+		if (err)
+			return err;
+	}
 
-	__i915_active_request_set(active, rq);
+	__i915_active_fence_set(active, &rq->fence);
 	return 0;
 }
 
-void i915_active_retire_noop(struct i915_active_request *active,
-			     struct i915_request *request)
+void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	/* Space left intentionally blank */
+	i915_active_fence_cb(fence, cb);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index bdec4f81b6e8..21a9ce6fa461 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -10,7 +10,9 @@
 #include <linux/lockdep.h>
 
 #include "i915_active_types.h"
-#include "i915_request.h"
+
+struct i915_request;
+struct intel_engine_cs;
 
 /*
  * We treat requests as fences. This is not be to confused with our
@@ -28,128 +30,62 @@
  * write access so that we can perform concurrent read operations between
  * the CPU and GPU engines, as well as waiting for all rendering to
  * complete, or waiting for the last GPU user of a "fence register". The
- * object then embeds a #i915_active_request to track the most recent (in
+ * object then embeds a #i915_active_fence to track the most recent (in
  * retirement order) request relevant for the desired mode of access.
- * The #i915_active_request is updated with i915_active_request_set() to
+ * The #i915_active_fence is updated with i915_active_fence_set() to
  * track the most recent fence request, typically this is done as part of
  * i915_vma_move_to_active().
  *
- * When the #i915_active_request completes (is retired), it will
+ * When the #i915_active_fence completes (is retired), it will
  * signal its completion to the owner through a callback as well as mark
- * itself as idle (i915_active_request.request == NULL). The owner
+ * itself as idle (i915_active_fence.request == NULL). The owner
  * can then perform any action, such as delayed freeing of an active
  * resource including itself.
  */
 
-void i915_active_retire_noop(struct i915_active_request *active,
-			     struct i915_request *request);
+void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb);
 
 /**
- * i915_active_request_init - prepares the activity tracker for use
+ * i915_active_fence_init - prepares the activity tracker for use
  * @active - the active tracker
  * @rq - initial request to track, can be NULL
  * @func - a callback when then the tracker is retired (becomes idle),
  *         can be NULL
  *
- * i915_active_request_init() prepares the embedded @active struct for use as
+ * i915_active_fence_init() prepares the embedded @active struct for use as
  * an activity tracker, that is for tracking the last known active request
  * associated with it. When the last request becomes idle, when it is retired
  * after completion, the optional callback @func is invoked.
  */
 static inline void
-i915_active_request_init(struct i915_active_request *active,
-			 struct i915_request *rq,
-			 i915_active_retire_fn retire)
+i915_active_fence_init(struct i915_active_fence *active,
+		       struct dma_fence *fence,
+		       dma_fence_func_t fn)
 {
-	RCU_INIT_POINTER(active->request, rq);
-	INIT_LIST_HEAD(&active->link);
-	active->retire = retire ?: i915_active_retire_noop;
+	RCU_INIT_POINTER(active->fence, fence);
+	active->cb.func = fn ?: i915_active_noop;
 }
 
-#define INIT_ACTIVE_REQUEST(name) i915_active_request_init((name), NULL, NULL)
+#define INIT_ACTIVE_FENCE(A) i915_active_fence_init(A, NULL, NULL)
 
-/**
- * i915_active_request_set - updates the tracker to watch the current request
- * @active - the active tracker
- * @request - the request to watch
- *
- * __i915_active_request_set() watches the given @request for completion. Whilst
- * that @request is busy, the @active reports busy. When that @request is
- * retired, the @active tracker is updated to report idle.
- */
-static inline void
-__i915_active_request_set(struct i915_active_request *active,
-			  struct i915_request *request)
-{
-	list_move(&active->link, &request->active_list);
-	rcu_assign_pointer(active->request, request);
-}
+struct dma_fence *
+__i915_active_fence_set(struct i915_active_fence *active,
+			struct dma_fence *fence);
 
 int __must_check
-i915_active_request_set(struct i915_active_request *active,
-			struct i915_request *rq);
-
-/**
- * i915_active_request_raw - return the active request
- * @active - the active tracker
- *
- * i915_active_request_raw() returns the current request being tracked, or NULL.
- * It does not obtain a reference on the request for the caller, so the caller
- * must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_active_request_raw(const struct i915_active_request *active,
-			struct mutex *mutex)
-{
-	return rcu_dereference_protected(active->request,
-					 lockdep_is_held(mutex));
-}
+i915_active_fence_set(struct i915_active_fence *active,
+		      struct i915_request *rq);
 
 /**
- * i915_active_request_peek - report the active request being monitored
+ * __i915_active_fence_get_rcu - return a reference to the active request
  * @active - the active tracker
  *
- * i915_active_request_peek() returns the current request being tracked if
- * still active, or NULL. It does not obtain a reference on the request
- * for the caller, so the caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_active_request_peek(const struct i915_active_request *active,
-			 struct mutex *mutex)
-{
-	struct i915_request *request;
-
-	request = i915_active_request_raw(active, mutex);
-	if (!request || i915_request_completed(request))
-		return NULL;
-
-	return request;
-}
-
-/**
- * i915_active_request_get - return a reference to the active request
- * @active - the active tracker
- *
- * i915_active_request_get() returns a reference to the active request, or NULL
- * if the active tracker is idle. The caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_active_request_get(const struct i915_active_request *active,
-			struct mutex *mutex)
-{
-	return i915_request_get(i915_active_request_peek(active, mutex));
-}
-
-/**
- * __i915_active_request_get_rcu - return a reference to the active request
- * @active - the active tracker
- *
- * __i915_active_request_get() returns a reference to the active request,
+ * __i915_active_fence_get() returns a reference to the active request,
  * or NULL if the active tracker is idle. The caller must hold the RCU read
  * lock, but the returned pointer is safe to use outside of RCU.
  */
-static inline struct i915_request *
-__i915_active_request_get_rcu(const struct i915_active_request *active)
+static inline struct dma_fence *
+__i915_active_fence_get_rcu(const struct i915_active_fence *active)
 {
 	/*
 	 * Performing a lockless retrieval of the active request is super
@@ -198,10 +134,11 @@ __i915_active_request_get_rcu(const struct i915_active_request *active)
 	 * See i915_request_alloc().
 	 */
 	do {
-		struct i915_request *request;
+		struct dma_fence *fence;
 
-		request = rcu_dereference(active->request);
-		if (!request || i915_request_completed(request))
+		fence = rcu_dereference(active->fence);
+		if (!fence ||
+		    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 			return NULL;
 
 		/*
@@ -218,7 +155,7 @@ __i915_active_request_get_rcu(const struct i915_active_request *active)
 		 */
 		barrier();
 
-		request = i915_request_get_rcu(request);
+		fence = dma_fence_get_rcu(fence);
 
 		/*
 		 * What stops the following rcu_access_pointer() from occurring
@@ -247,81 +184,58 @@ __i915_active_request_get_rcu(const struct i915_active_request *active)
 		 * The corresponding write barrier is part of
 		 * rcu_assign_pointer().
 		 */
-		if (!request || request == rcu_access_pointer(active->request))
-			return rcu_pointer_handoff(request);
+		if (!fence || fence == rcu_access_pointer(active->fence))
+			return rcu_pointer_handoff(fence);
 
-		i915_request_put(request);
+		dma_fence_put(fence);
 	} while (1);
 }
 
 /**
- * i915_active_request_get_unlocked - return a reference to the active request
+ * i915_active_fence_get - return a reference to the active request
  * @active - the active tracker
  *
- * i915_active_request_get_unlocked() returns a reference to the active request,
+ * i915_active_fence_get() returns a reference to the active request,
  * or NULL if the active tracker is idle. The reference is obtained under RCU,
  * so no locking is required by the caller.
  *
- * The reference should be freed with i915_request_put().
+ * The reference should be freed with dma_fence_put().
  */
-static inline struct i915_request *
-i915_active_request_get_unlocked(const struct i915_active_request *active)
+static inline struct dma_fence *
+i915_active_fence_get(const struct i915_active_fence *active)
 {
-	struct i915_request *request;
+	struct dma_fence *fence;
 
 	rcu_read_lock();
-	request = __i915_active_request_get_rcu(active);
+	fence = __i915_active_fence_get_rcu(active);
 	rcu_read_unlock();
 
-	return request;
+	return fence;
 }
 
 /**
- * i915_active_request_isset - report whether the active tracker is assigned
+ * i915_active_fence_isset - report whether the active tracker is assigned
  * @active - the active tracker
  *
- * i915_active_request_isset() returns true if the active tracker is currently
+ * i915_active_fence_isset() returns true if the active tracker is currently
  * assigned to a request. Due to the lazy retiring, that request may be idle
  * and this may report stale information.
  */
 static inline bool
-i915_active_request_isset(const struct i915_active_request *active)
+i915_active_fence_isset(const struct i915_active_fence *active)
 {
-	return rcu_access_pointer(active->request);
+	return rcu_access_pointer(active->fence);
 }
 
-/**
- * i915_active_request_retire - waits until the request is retired
- * @active - the active request on which to wait
- *
- * i915_active_request_retire() waits until the request is completed,
- * and then ensures that at least the retirement handler for this
- * @active tracker is called before returning. If the @active
- * tracker is idle, the function returns immediately.
- */
-static inline int __must_check
-i915_active_request_retire(struct i915_active_request *active,
-			   struct mutex *mutex)
+static inline void
+i915_active_fence_cb(struct dma_fence *fence,
+		     struct dma_fence_cb *cb)
 {
-	struct i915_request *request;
-	long ret;
-
-	request = i915_active_request_raw(active, mutex);
-	if (!request)
-		return 0;
-
-	ret = i915_request_wait(request,
-				I915_WAIT_INTERRUPTIBLE | I915_WAIT_LOCKED,
-				MAX_SCHEDULE_TIMEOUT);
-	if (ret < 0)
-		return ret;
-
-	list_del_init(&active->link);
-	RCU_INIT_POINTER(active->request, NULL);
-
-	active->retire(active, request);
+	struct i915_active_fence *active =
+		container_of(cb, typeof(*active), cb);
 
-	return 0;
+	//GEM_BUG_ON(rcu_access_pointer(active->fence) != fence);
+	RCU_INIT_POINTER(active->fence, NULL);
 }
 
 /*
@@ -350,31 +264,29 @@ i915_active_request_retire(struct i915_active_request *active,
  * synchronisation.
  */
 
-void __i915_active_init(struct drm_i915_private *i915,
-			struct i915_active *ref,
+void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
 			struct lock_class_key *key);
-#define i915_active_init(i915, ref, active, retire) do {		\
+#define i915_active_init(ref, active, retire) do {		\
 	static struct lock_class_key __key;				\
 									\
-	__i915_active_init(i915, ref, active, retire, &__key);		\
+	__i915_active_init(ref, active, retire, &__key);		\
 } while (0)
 
 int i915_active_ref(struct i915_active *ref,
 		    u64 timeline,
-		    struct i915_request *rq);
+		    struct dma_fence *fence);
 
 int i915_active_wait(struct i915_active *ref);
 
 int i915_request_await_active(struct i915_request *rq,
 			      struct i915_active *ref);
-int i915_request_await_active_request(struct i915_request *rq,
-				      struct i915_active_request *active);
+int i915_request_await_active_fence(struct i915_request *rq,
+				    struct i915_active_fence *active);
 
 int i915_active_acquire(struct i915_active *ref);
 void i915_active_release(struct i915_active *ref);
-void __i915_active_release_nested(struct i915_active *ref, int subclass);
 
 static inline bool
 i915_active_is_idle(const struct i915_active *ref)
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 06acdffe0f6d..9519b6523801 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -8,30 +8,21 @@
 #define _I915_ACTIVE_TYPES_H_
 
 #include <linux/atomic.h>
+#include <linux/dma-fence.h>
 #include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-struct drm_i915_private;
-struct i915_active_request;
-struct i915_request;
-
-typedef void (*i915_active_retire_fn)(struct i915_active_request *,
-				      struct i915_request *);
-
-struct i915_active_request {
-	struct i915_request __rcu *request;
-	struct list_head link;
-	i915_active_retire_fn retire;
+struct i915_active_fence {
+	struct dma_fence __rcu *fence;
+	struct dma_fence_cb cb;
 };
 
 struct active_node;
 
 struct i915_active {
-	struct drm_i915_private *i915;
-
 	struct active_node *cache;
 	struct rb_root tree;
 	struct mutex mutex;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e097f7fcce6f..d74fcddd863e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -951,34 +951,38 @@ wait_for_timelines(struct drm_i915_private *i915,
 
 	mutex_lock(&gt->mutex);
 	list_for_each_entry(tl, &gt->active_list, link) {
-		struct i915_request *rq;
+		struct dma_fence *fence;
 
-		rq = i915_active_request_get_unlocked(&tl->last_request);
-		if (!rq)
+		fence = i915_active_fence_get(&tl->last_request);
+		if (!fence)
 			continue;
 
-		mutex_unlock(&gt->mutex);
-
-		/*
-		 * "Race-to-idle".
-		 *
-		 * Switching to the kernel context is often used a synchronous
-		 * step prior to idling, e.g. in suspend for flushing all
-		 * current operations to memory before sleeping. These we
-		 * want to complete as quickly as possible to avoid prolonged
-		 * stalls, so allow the gpu to boost to maximum clocks.
-		 */
-		if (flags & I915_WAIT_FOR_IDLE_BOOST)
-			gen6_rps_boost(rq);
+		if (!dma_fence_is_i915(fence)) {
+			timeout = dma_fence_wait_timeout(fence,
+							 flags & I915_WAIT_INTERRUPTIBLE,
+							 timeout);
+		} else {
+			struct i915_request *rq = to_request(fence);
+
+			/*
+			 * "Race-to-idle".
+			 *
+			 * Switching to the kernel context is often used as
+			 * a synchronous step prior to idling, e.g. in suspend
+			 * for flushing all current operations to memory before
+			 * sleeping. These we want to complete as quickly as
+			 * possible to avoid prolonged stalls, so allow the gpu
+			 * to boost to maximum clocks.
+			 */
+			if (flags & I915_WAIT_FOR_IDLE_BOOST)
+				gen6_rps_boost(rq);
+
+			timeout = i915_request_wait(rq, flags, timeout);
+		}
 
-		timeout = i915_request_wait(rq, flags, timeout);
-		i915_request_put(rq);
+		dma_fence_put(fence);
 		if (timeout < 0)
-			return timeout;
-
-		/* restart after reacquiring the lock */
-		mutex_lock(&gt->mutex);
-		tl = list_entry(&gt->active_list, typeof(*tl), link);
+			break;
 	}
 	mutex_unlock(&gt->mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 05fef1d3579d..60f754292a64 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2062,7 +2062,7 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	i915_active_init(i915, &vma->active, NULL, NULL);
+	i915_active_init(&vma->active, NULL, NULL);
 
 	vma->vm = &ggtt->vm;
 	vma->ops = &pd_vma_ops;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index c71edd6ea873..cbdf71e80616 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -229,9 +229,8 @@ static void free_capture_list(struct i915_request *request)
 
 static bool i915_request_retire(struct i915_request *rq)
 {
-	struct i915_active_request *active, *next;
+	lockdep_assert_held(&rq->timeline->mutex);
 
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	if (!i915_request_completed(rq))
 		return false;
 
@@ -245,35 +244,6 @@ static bool i915_request_retire(struct i915_request *rq)
 
 	advance_ring(rq);
 
-	/*
-	 * Walk through the active list, calling retire on each. This allows
-	 * objects to track their GPU activity and mark themselves as idle
-	 * when their *last* active request is completed (updating state
-	 * tracking lists for eviction, active references for GEM, etc).
-	 *
-	 * As the ->retire() may free the node, we decouple it first and
-	 * pass along the auxiliary information (to avoid dereferencing
-	 * the node after the callback).
-	 */
-	list_for_each_entry_safe(active, next, &rq->active_list, link) {
-		/*
-		 * In microbenchmarks or focusing upon time inside the kernel,
-		 * we may spend an inordinate amount of time simply handling
-		 * the retirement of requests and processing their callbacks.
-		 * Of which, this loop itself is particularly hot due to the
-		 * cache misses when jumping around the list of
-		 * i915_active_request.  So we try to keep this loop as
-		 * streamlined as possible and also prefetch the next
-		 * i915_active_request to try and hide the likely cache miss.
-		 */
-		prefetchw(next);
-
-		INIT_LIST_HEAD(&active->link);
-		RCU_INIT_POINTER(active->request, NULL);
-
-		active->retire(active, rq);
-	}
-
 	local_irq_disable();
 
 	/*
@@ -288,8 +258,7 @@ static bool i915_request_retire(struct i915_request *rq)
 
 	spin_lock(&rq->lock);
 	i915_request_mark_complete(rq);
-	if (!i915_request_signaled(rq))
-		dma_fence_signal_locked(&rq->fence);
+	dma_fence_signal_locked(&rq->fence);
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
 		i915_request_cancel_breadcrumb(rq);
 	if (rq->waitboost) {
@@ -328,11 +297,9 @@ void i915_request_retire_upto(struct i915_request *rq)
 		  rq->fence.context, rq->fence.seqno,
 		  hwsp_seqno(rq));
 
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
+	lockdep_assert_held(&rq->timeline->mutex);
 	GEM_BUG_ON(!i915_request_completed(rq));
-
-	if (list_empty(&rq->ring_link))
-		return;
+	GEM_BUG_ON(list_empty(&rq->ring_link));
 
 	do {
 		tmp = list_first_entry(&ring->request_list,
@@ -567,6 +534,7 @@ static void ring_retire_requests(struct intel_ring *ring)
 {
 	struct i915_request *rq, *rn;
 
+	lockdep_assert_held(&ring->timeline->mutex);
 	list_for_each_entry_safe(rq, rn, &ring->request_list, ring_link)
 		if (!i915_request_retire(rq))
 			break;
@@ -687,7 +655,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->waitboost = false;
 	rq->execution_mask = ALL_ENGINES;
 
-	INIT_LIST_HEAD(&rq->active_list);
 	INIT_LIST_HEAD(&rq->execute_cb);
 
 	/*
@@ -726,7 +693,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	ce->ring->emit = rq->head;
 
 	/* Make sure we didn't add ourselves to external state before freeing */
-	GEM_BUG_ON(!list_empty(&rq->active_list));
 	GEM_BUG_ON(!list_empty(&rq->sched.signalers_list));
 	GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
 
@@ -1113,7 +1079,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	 * precludes optimising to use semaphores serialisation of a single
 	 * timeline across engines.
 	 */
-	prev = rcu_dereference_protected(timeline->last_request.request, 1);
+	prev = to_request(__i915_active_fence_set(&timeline->last_request,
+						  &rq->fence));
 	if (prev && !i915_request_completed(prev)) {
 		if (is_power_of_2(prev->engine->mask | rq->engine->mask))
 			i915_sw_fence_await_sw_fence(&rq->submit,
@@ -1138,7 +1105,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	 * us, the timeline will hold its seqno which is later than ours.
 	 */
 	GEM_BUG_ON(timeline->seqno != rq->fence.seqno);
-	__i915_active_request_set(&timeline->last_request, rq);
 
 	return prev;
 }
@@ -1369,10 +1335,6 @@ static void request_wait_wake(struct dma_fence *fence, struct dma_fence_cb *cb)
  * maximum of @timeout jiffies (with MAX_SCHEDULE_TIMEOUT implying an
  * unbounded wait).
  *
- * If the caller holds the struct_mutex, the caller must pass I915_WAIT_LOCKED
- * in via the flags, and vice versa if the struct_mutex is not held, the caller
- * must not specify that the wait is locked.
- *
  * Returns the remaining time (in jiffies) if the request completed, which may
  * be zero or -ETIME if the request is unfinished after the timeout expires.
  * May return -EINTR is called with I915_WAIT_INTERRUPTIBLE and a signal is
@@ -1482,7 +1444,11 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 	list_for_each_entry_safe(ring, tmp,
 				 &i915->gt.active_rings, active_link) {
 		intel_ring_get(ring); /* last rq holds reference! */
+		mutex_lock(&ring->timeline->mutex);
+
 		ring_retire_requests(ring);
+
+		mutex_unlock(&ring->timeline->mutex);
 		intel_ring_put(ring);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index bebc1e9b4a5e..8277cff0df70 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -211,7 +211,6 @@ struct i915_request {
 	 * on the active_list (of their final request).
 	 */
 	struct i915_capture_list *capture_list;
-	struct list_head active_list;
 
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
index e2f9336bab83..4ffb61991768 100644
--- a/drivers/gpu/drm/i915/i915_timeline.c
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -179,8 +179,7 @@ cacheline_alloc(struct i915_timeline_hwsp *hwsp, unsigned int cacheline)
 	cl->hwsp = hwsp;
 	cl->vaddr = page_pack_bits(vaddr, cacheline);
 
-	i915_active_init(hwsp_to_i915(hwsp), &cl->active,
-			 __cacheline_active, __cacheline_retire);
+	i915_active_init(&cl->active, __cacheline_active, __cacheline_retire);
 
 	return cl;
 }
@@ -263,7 +262,7 @@ int i915_timeline_init(struct drm_i915_private *i915,
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_REQUEST(&timeline->last_request);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
@@ -463,7 +462,7 @@ __i915_timeline_get_seqno(struct i915_timeline *tl,
 	 * all writes into the cacheline from previous requests are complete.
 	 */
 	err = i915_active_ref(&tl->hwsp_cacheline->active,
-			      tl->fence_context, rq);
+			      tl->fence_context, &rq->fence);
 	if (err)
 		goto err_cacheline;
 
@@ -514,7 +513,7 @@ int i915_timeline_get_seqno(struct i915_timeline *tl,
 static int cacheline_ref(struct i915_timeline_cacheline *cl,
 			 struct i915_request *rq)
 {
-	return i915_active_ref(&cl->active, rq->fence.context, rq);
+	return i915_active_ref(&cl->active, rq->fence.context, &rq->fence);
 }
 
 int i915_timeline_read_hwsp(struct i915_request *from,
diff --git a/drivers/gpu/drm/i915/i915_timeline_types.h b/drivers/gpu/drm/i915/i915_timeline_types.h
index fce5cb4f1090..5af6d185d70c 100644
--- a/drivers/gpu/drm/i915/i915_timeline_types.h
+++ b/drivers/gpu/drm/i915/i915_timeline_types.h
@@ -45,7 +45,7 @@ struct i915_timeline {
 	 * the request using i915_active_request_get_request_rcu(), or hold the
 	 * struct_mutex.
 	 */
-	struct i915_active_request last_request;
+	struct i915_active_fence last_request;
 
 	/**
 	 * We track the most recent seqno that we wait on in every context so
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 5bc58d0baf73..b8b8a9ca1ac7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -114,8 +114,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	vma->size = obj->base.size;
 	vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
 
-	i915_active_init(vm->i915, &vma->active,
-			 __i915_vma_active, __i915_vma_retire);
+	i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire);
 
 	INIT_LIST_HEAD(&vma->closed_link);
 
@@ -909,7 +908,7 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	err = i915_active_ref(&vma->active, rq->fence.context, rq);
+	err = i915_active_ref(&vma->active, rq->fence.context, &rq->fence);
 	if (err)
 		return err;
 
@@ -920,7 +919,7 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 		if (intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CS))
 			i915_active_ref(&obj->frontbuffer->write,
 					rq->fence.context,
-					rq);
+					&rq->fence);
 
 		obj->read_domains = 0;
 	}
@@ -939,31 +938,10 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
-	/*
-	 * First wait upon any activity as retiring the request may
-	 * have side-effects such as unpinning or even unbinding this vma.
-	 */
-	might_sleep();
-	if (i915_vma_is_active(vma)) {
-		/*
-		 * When a closed VMA is retired, it is unbound - eek.
-		 * In order to prevent it from being recursively closed,
-		 * take a pin on the vma so that the second unbind is
-		 * aborted.
-		 *
-		 * Even more scary is that the retire callback may free
-		 * the object (last active vma). To prevent the explosion
-		 * we defer the actual object free to a worker that can
-		 * only proceed once it acquires the struct_mutex (which
-		 * we currently hold, therefore it cannot free this object
-		 * before we are finished).
-		 */
-		__i915_vma_pin(vma);
-		ret = i915_active_wait(&vma->active);
-		__i915_vma_unpin(vma);
-		if (ret)
-			return ret;
-	}
+	ret = i915_active_wait(&vma->active);
+	if (ret)
+		return ret;
+
 	flush_work(&vma->active.work);
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 4fcec413f405..e8a1bb20f548 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -253,8 +253,7 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj)
 	fb->obj = obj;
 	kref_init(&fb->ref);
 	atomic_set(&fb->bits, 0);
-	i915_active_init(i915, &fb->write,
-			 frontbuffer_active, frontbuffer_retire);
+	i915_active_init(&fb->write, frontbuffer_active, frontbuffer_retire);
 
 	spin_lock(&i915->fb_tracking.lock);
 	if (obj->frontbuffer) {
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 38495df60f7b..dc7b66c94f74 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -230,7 +230,8 @@ alloc_request(struct intel_overlay *overlay, void (*fn)(struct intel_overlay *))
 	if (IS_ERR(rq))
 		return rq;
 
-	err = i915_active_ref(&overlay->last_flip, rq->fence.context, rq);
+	err = i915_active_ref(&overlay->last_flip,
+			      rq->fence.context, &rq->fence);
 	if (err) {
 		i915_request_add(rq);
 		return ERR_PTR(err);
@@ -1366,8 +1367,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	overlay->contrast = 75;
 	overlay->saturation = 146;
 
-	i915_active_init(dev_priv,
-			 &overlay->last_flip,
+	i915_active_init(&overlay->last_flip,
 			 NULL, intel_overlay_last_flip_retire);
 
 	ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv));
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 3b3ca5658122..376ea04350b1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -36,7 +36,7 @@ static int __live_active_setup(struct drm_i915_private *i915,
 	if (!submit)
 		return -ENOMEM;
 
-	i915_active_init(i915, &active->base, NULL, __live_active_retire);
+	i915_active_init(&active->base, NULL, __live_active_retire);
 	active->retired = false;
 
 	err = i915_active_acquire(&active->base);
@@ -57,7 +57,8 @@ static int __live_active_setup(struct drm_i915_private *i915,
 						       GFP_KERNEL);
 		if (err >= 0)
 			err = i915_active_ref(&active->base,
-					      rq->fence.context, rq);
+					      rq->fence.context,
+					      &rq->fence);
 		i915_request_add(rq);
 		if (err) {
 			pr_err("Failed to track active ref!\n");
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c
index 65b52be23d42..024de718f66f 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c
@@ -15,7 +15,7 @@ void mock_timeline_init(struct i915_timeline *timeline, u64 context)
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_REQUEST(&timeline->last_request);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
-- 
2.20.1



More information about the Intel-gfx mailing list