[PATCH 14/19] object-active-nope

Chris Wilson chris at chris-wilson.co.uk
Sat Jun 8 14:00:55 UTC 2019


---
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  1 -
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  6 ---
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  1 -
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c  |  5 +-
 .../drm/i915/gem/selftests/i915_gem_mman.c    |  1 -
 drivers/gpu/drm/i915/gt/intel_lrc.c           |  4 +-
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c    |  1 -
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  | 32 +++++------
 drivers/gpu/drm/i915/i915_debugfs.c           |  8 +--
 drivers/gpu/drm/i915/i915_gem_batch_pool.c    | 42 ++++++---------
 drivers/gpu/drm/i915/i915_vma.c               | 53 ++++---------------
 11 files changed, 47 insertions(+), 107 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 7a07e726ec83..fab943062517 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -189,7 +189,6 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 		mutex_lock(&i915->drm.struct_mutex);
 
-		GEM_BUG_ON(i915_gem_object_is_active(obj));
 		list_for_each_entry_safe(vma, vn, &obj->vma.list, obj_link) {
 			GEM_BUG_ON(i915_vma_is_active(vma));
 			vma->flags &= ~I915_VMA_PIN_MASK;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 7cb1871d7128..454bfb498001 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -158,12 +158,6 @@ i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
 }
 
-static inline bool
-i915_gem_object_is_active(const struct drm_i915_gem_object *obj)
-{
-	return READ_ONCE(obj->active_count);
-}
-
 static inline bool
 i915_gem_object_is_framebuffer(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 5b05698619ce..c299fed2c6b1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -156,7 +156,6 @@ struct drm_i915_gem_object {
 
 	/** Count of VMA actually bound by this object */
 	atomic_t bind_count;
-	unsigned int active_count;
 	/** Count of how many global VMA are currently pinned for use by HW */
 	unsigned int pin_global;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 1e7f48db7b3e..a4c75305e159 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -234,8 +234,9 @@ i915_gem_shrink(struct drm_i915_private *i915,
 				continue;
 
 			if (!(flags & I915_SHRINK_ACTIVE) &&
-			    (i915_gem_object_is_active(obj) ||
-			     i915_gem_object_is_framebuffer(obj)))
+			    (i915_gem_object_is_framebuffer(obj) ||
+			     reservation_object_test_signaled_rcu(obj->resv,
+								  true)))
 				continue;
 
 			if (!(flags & I915_SHRINK_BOUND) &&
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index b92809418729..b0ba1680ede6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -476,7 +476,6 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		}
 
 		/* NB we rely on the _active_ reference to access obj now */
-		GEM_BUG_ON(!i915_gem_object_is_active(obj));
 		err = create_mmap_offset(obj);
 		if (err) {
 			pr_err("[loop %d] create_mmap_offset failed with err=%d\n",
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 40246ebd223f..0ab3d1377e92 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1502,9 +1502,7 @@ static void execlists_submit_request(struct i915_request *request)
 static void __execlists_context_fini(struct intel_context *ce)
 {
 	intel_ring_put(ce->ring);
-
-	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
-	i915_gem_object_put(ce->state->obj);
+	i915_vma_put(ce->state);
 }
 
 static void execlists_context_destroy(struct kref *kref)
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 93b0893c736b..aa4c9e82138e 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1309,7 +1309,6 @@ void intel_ring_free(struct kref *ref)
 
 static void __ring_context_fini(struct intel_context *ce)
 {
-	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
 	i915_gem_object_put(ce->state->obj);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 127faef8d8c2..c6016398c7e9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -130,33 +130,29 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	struct drm_i915_private *i915 = h->i915;
 	struct i915_address_space *vm =
 		h->ctx->ppgtt ? &h->ctx->ppgtt->vm : &i915->ggtt.vm;
+	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
 	unsigned int flags;
+	void *vaddr;
 	u32 *batch;
 	int err;
 
-	if (i915_gem_object_is_active(h->obj)) {
-		struct drm_i915_gem_object *obj;
-		void *vaddr;
-
-		obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE);
-		if (IS_ERR(obj))
-			return ERR_CAST(obj);
+	obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
 
-		vaddr = i915_gem_object_pin_map(obj,
-						i915_coherent_map_type(h->i915));
-		if (IS_ERR(vaddr)) {
-			i915_gem_object_put(obj);
-			return ERR_CAST(vaddr);
-		}
+	vaddr = i915_gem_object_pin_map(obj, i915_coherent_map_type(h->i915));
+	if (IS_ERR(vaddr)) {
+		i915_gem_object_put(obj);
+		return ERR_CAST(vaddr);
+	}
 
-		i915_gem_object_unpin_map(h->obj);
-		i915_gem_object_put(h->obj);
+	i915_gem_object_unpin_map(h->obj);
+	i915_gem_object_put(h->obj);
 
-		h->obj = obj;
-		h->batch = vaddr;
-	}
+	h->obj = obj;
+	h->batch = vaddr;
 
 	vma = i915_vma_instance(h->obj, vm, NULL);
 	if (IS_ERR(vma))
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 326a56a97247..fec5fdeca07f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -74,11 +74,6 @@ static int i915_capabilities(struct seq_file *m, void *data)
 	return 0;
 }
 
-static char get_active_flag(struct drm_i915_gem_object *obj)
-{
-	return i915_gem_object_is_active(obj) ? '*' : ' ';
-}
-
 static char get_pin_flag(struct drm_i915_gem_object *obj)
 {
 	return obj->pin_global ? 'p' : ' ';
@@ -143,9 +138,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	unsigned int frontbuffer_bits;
 	int pin_count = 0;
 
-	seq_printf(m, "%pK: %c%c%c%c%c %8zdKiB %02x %02x %s%s%s",
+	seq_printf(m, "%pK: %c%c%c%c %8zdKiB %02x %02x %s%s%s",
 		   &obj->base,
-		   get_active_flag(obj),
 		   get_pin_flag(obj),
 		   get_tiling_flag(obj),
 		   get_global_flag(obj),
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.c b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
index 56adfdcaed3e..1b7595e2ac21 100644
--- a/drivers/gpu/drm/i915/i915_gem_batch_pool.c
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
@@ -94,34 +94,26 @@ i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool,
 	list = &pool->cache_list[n];
 
 	list_for_each_entry(obj, list, batch_pool_link) {
+		struct reservation_object *resv = obj->resv;
+
 		/* The batches are strictly LRU ordered */
-		if (i915_gem_object_is_active(obj)) {
-			struct reservation_object *resv = obj->resv;
-
-			if (!reservation_object_test_signaled_rcu(resv, true))
-				break;
-
-			i915_retire_requests(pool->engine->i915);
-			GEM_BUG_ON(i915_gem_object_is_active(obj));
-
-			/*
-			 * The object is now idle, clear the array of shared
-			 * fences before we add a new request. Although, we
-			 * remain on the same engine, we may be on a different
-			 * timeline and so may continually grow the array,
-			 * trapping a reference to all the old fences, rather
-			 * than replace the existing fence.
-			 */
-			if (rcu_access_pointer(resv->fence)) {
-				reservation_object_lock(resv, NULL);
-				reservation_object_add_excl_fence(resv, NULL);
-				reservation_object_unlock(resv);
-			}
+		if (!reservation_object_test_signaled_rcu(resv, true))
+			break;
+
+		/*
+		 * The object is now idle, clear the array of shared
+		 * fences before we add a new request. Although, we
+		 * remain on the same engine, we may be on a different
+		 * timeline and so may continually grow the array,
+		 * trapping a reference to all the old fences, rather
+		 * than replace the existing fence.
+		 */
+		if (rcu_access_pointer(resv->fence)) {
+			reservation_object_lock(resv, NULL);
+			reservation_object_add_excl_fence(resv, NULL);
+			reservation_object_unlock(resv);
 		}
 
-		GEM_BUG_ON(!reservation_object_test_signaled_rcu(obj->resv,
-								 true));
-
 		if (obj->base.size >= size)
 			goto found;
 	}
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index a3cb08f602f9..6e04b4489ad2 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -77,42 +77,11 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 
 #endif
 
-static void obj_bump_mru(struct drm_i915_gem_object *obj)
-{
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-
-	spin_lock(&i915->mm.obj_lock);
-	list_move_tail(&obj->mm.link, &i915->mm.shrink_list);
-	spin_unlock(&i915->mm.obj_lock);
-
-	obj->mm.dirty = true; /* be paranoid  */
-}
-
 static void __i915_vma_retire(struct i915_active *ref)
 {
 	struct i915_vma *vma = container_of(ref, typeof(*vma), active);
-	struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(!i915_gem_object_is_active(obj));
-	if (--obj->active_count)
-		return;
-
-	/* Prune the shared fence arrays iff completely idle (inc. external) */
-	if (reservation_object_trylock(obj->resv)) {
-		if (reservation_object_test_signaled_rcu(obj->resv, true))
-			reservation_object_add_excl_fence(obj->resv, NULL);
-		reservation_object_unlock(obj->resv);
-	}
-
-	/*
-	 * Bump our place on the bound list to keep it roughly in LRU order
-	 * so that we don't steal from recently used but inactive objects
-	 * (unless we are forced to ofc!)
-	 */
-	if (i915_gem_object_is_shrinkable(obj))
-		obj_bump_mru(obj);
-
-	i915_gem_object_put(obj); /* and drop the active reference */
+	i915_vma_put(vma);
 }
 
 static struct i915_vma *
@@ -920,6 +889,7 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 			    unsigned int flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
+	int err;
 
 	assert_vma_held(vma);
 	assert_object_held(obj);
@@ -933,17 +903,13 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	if (!vma->active.count && !obj->active_count++)
-		i915_gem_object_get(obj); /* once more for the active ref */
-
-	if (unlikely(i915_active_ref(&vma->active, rq->fence.context, rq))) {
-		if (!vma->active.count && !--obj->active_count)
-			i915_gem_object_put(obj);
-		return -ENOMEM;
-	}
+	if (i915_active_acquire(&vma->active))
+		i915_vma_get(vma);
 
-	GEM_BUG_ON(!i915_vma_is_active(vma));
-	GEM_BUG_ON(!obj->active_count);
+	err = i915_active_ref(&vma->active, rq->fence.context, rq);
+	i915_active_release(&vma->active);
+	if (err)
+		return err;
 
 	obj->write_domain = 0;
 	if (flags & EXEC_OBJECT_WRITE) {
@@ -955,11 +921,14 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 		obj->read_domains = 0;
 	}
 	obj->read_domains |= I915_GEM_GPU_DOMAINS;
+	obj->mm.dirty = true;
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
 		__i915_active_request_set(&vma->last_fence, rq);
 
 	export_fence(vma, rq, flags);
+
+	GEM_BUG_ON(!i915_vma_is_active(vma));
 	return 0;
 }
 
-- 
2.20.1



More information about the Intel-gfx-trybot mailing list