1 files changed, 215 insertions, 106 deletions

diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 293e5bcc4b6c..d32db8a4db5c 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -4,6 +4,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/debugobjects.h>
+
 #include "gt/intel_engine_pm.h"
 
 #include "i915_drv.h"
@@ -31,49 +33,108 @@ struct active_node {
 	u64 timeline;
 };
 
-static void
-__active_park(struct i915_active *ref)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && IS_ENABLED(CONFIG_DEBUG_OBJECTS)
+
+static void *active_debug_hint(void *addr)
 {
-	struct active_node *it, *n;
+	struct i915_active *ref = addr;
 
-	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		GEM_BUG_ON(i915_active_request_isset(&it->base));
-		kmem_cache_free(global.slab_cache, it);
-	}
-	ref->tree = RB_ROOT;
+	return (void *)ref->active ?: (void *)ref->retire ?: (void *)ref;
+}
+
+static struct debug_obj_descr active_debug_desc = {
+	.name = "i915_active",
+	.debug_hint = active_debug_hint,
+};
+
+static void debug_active_init(struct i915_active *ref)
+{
+	debug_object_init(ref, &active_debug_desc);
 }
 
+static void debug_active_activate(struct i915_active *ref)
+{
+	debug_object_activate(ref, &active_debug_desc);
+}
+
+static void debug_active_deactivate(struct i915_active *ref)
+{
+	debug_object_deactivate(ref, &active_debug_desc);
+}
+
+static void debug_active_fini(struct i915_active *ref)
+{
+	debug_object_free(ref, &active_debug_desc);
+}
+
+static void debug_active_assert(struct i915_active *ref)
+{
+	debug_object_assert_init(ref, &active_debug_desc);
+}
+
+#else
+
+static inline void debug_active_init(struct i915_active *ref) { }
+static inline void debug_active_activate(struct i915_active *ref) { }
+static inline void debug_active_deactivate(struct i915_active *ref) { }
+static inline void debug_active_fini(struct i915_active *ref) { }
+static inline void debug_active_assert(struct i915_active *ref) { }
+
+#endif
+
 static void
 __active_retire(struct i915_active *ref)
 {
-	GEM_BUG_ON(!ref->count);
-	if (--ref->count)
-		return;
+	struct active_node *it, *n;
+	struct rb_root root;
+	bool retire = false;
+
+	lockdep_assert_held(&ref->mutex);
+
+	/* return the unused nodes to our slabcache -- flushing the allocator */
+	if (atomic_dec_and_test(&ref->count)) {
+		debug_active_deactivate(ref);
+		root = ref->tree;
+		ref->tree = RB_ROOT;
+		ref->cache = NULL;
+		retire = true;
+	}
 
-	/* return the unused nodes to our slabcache */
-	__active_park(ref);
+	mutex_unlock(&ref->mutex);
+	if (!retire)
+		return;
 
 	ref->retire(ref);
+
+	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
+		GEM_BUG_ON(i915_active_request_isset(&it->base));
+		kmem_cache_free(global.slab_cache, it);
+	}
 }
 
 static void
-node_retire(struct i915_active_request *base, struct i915_request *rq)
+active_retire(struct i915_active *ref)
 {
-	__active_retire(container_of(base, struct active_node, base)->ref);
+	GEM_BUG_ON(!atomic_read(&ref->count));
+	if (atomic_add_unless(&ref->count, -1, 1))
+		return;
+
+	/* One active may be flushed from inside the acquire of another */
+	mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
+	__active_retire(ref);
 }
 
 static void
-last_retire(struct i915_active_request *base, struct i915_request *rq)
+node_retire(struct i915_active_request *base, struct i915_request *rq)
 {
-	__active_retire(container_of(base, struct i915_active, last));
+	active_retire(container_of(base, struct active_node, base)->ref);
 }
 
 static struct i915_active_request *
 active_instance(struct i915_active *ref, u64 idx)
 {
-	struct active_node *node;
+	struct active_node *node, *prealloc;
 	struct rb_node **p, *parent;
-	struct i915_request *old;
 
 	/*
 	 * We track the most recently used timeline to skip a rbtree search
@@ -81,20 +142,18 @@ active_instance(struct i915_active *ref, u64 idx)
 	 * at all. We can reuse the last slot if it is empty, that is
 	 * after the previous activity has been retired, or if it matches the
 	 * current timeline.
-	 *
-	 * Note that we allow the timeline to be active simultaneously in
-	 * the rbtree and the last cache. We do this to avoid having
-	 * to search and replace the rbtree element for a new timeline, with
-	 * the cost being that we must be aware that the ref may be retired
-	 * twice for the same timeline (as the older rbtree element will be
-	 * retired before the new request added to last).
 	 */
-	old = i915_active_request_raw(&ref->last, BKL(ref));
-	if (!old || old->fence.context == idx)
-		goto out;
+	node = READ_ONCE(ref->cache);
+	if (node && node->timeline == idx)
+		return &node->base;
 
-	/* Move the currently active fence into the rbtree */
-	idx = old->fence.context;
+	/* Preallocate a replacement, just in case */
+	prealloc = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
+	if (!prealloc)
+		return NULL;
+
+	mutex_lock(&ref->mutex);
+	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	parent = NULL;
 	p = &ref->tree.rb_node;
@@ -102,8 +161,10 @@ active_instance(struct i915_active *ref, u64 idx)
 		parent = *p;
 
 		node = rb_entry(parent, struct active_node, node);
-		if (node->timeline == idx)
-			goto replace;
+		if (node->timeline == idx) {
+			kmem_cache_free(global.slab_cache, prealloc);
+			goto out;
+		}
 
 		if (node->timeline < idx)
 			p = &parent->rb_right;
@@ -111,17 +172,7 @@ active_instance(struct i915_active *ref, u64 idx)
 			p = &parent->rb_left;
 	}
 
-	node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
-
-	/* kmalloc may retire the ref->last (thanks shrinker)! */
-	if (unlikely(!i915_active_request_raw(&ref->last, BKL(ref)))) {
-		kmem_cache_free(global.slab_cache, node);
-		goto out;
-	}
-
-	if (unlikely(!node))
-		return ERR_PTR(-ENOMEM);
-
+	node = prealloc;
 	i915_active_request_init(&node->base, NULL, node_retire);
 	node->ref = ref;
 	node->timeline = idx;
@@ -129,38 +180,30 @@ active_instance(struct i915_active *ref, u64 idx)
 	rb_link_node(&node->node, parent, p);
 	rb_insert_color(&node->node, &ref->tree);
 
-replace:
-	/*
-	 * Overwrite the previous active slot in the rbtree with last,
-	 * leaving last zeroed. If the previous slot is still active,
-	 * we must be careful as we now only expect to receive one retire
-	 * callback not two, and so much undo the active counting for the
-	 * overwritten slot.
-	 */
-	if (i915_active_request_isset(&node->base)) {
-		/* Retire ourselves from the old rq->active_list */
-		__list_del_entry(&node->base.link);
-		ref->count--;
-		GEM_BUG_ON(!ref->count);
-	}
-	GEM_BUG_ON(list_empty(&ref->last.link));
-	list_replace_init(&ref->last.link, &node->base.link);
-	node->base.request = fetch_and_zero(&ref->last.request);
-
 out:
-	return &ref->last;
+	ref->cache = node;
+	mutex_unlock(&ref->mutex);
+
+	return &node->base;
 }
 
-void i915_active_init(struct drm_i915_private *i915,
-		      struct i915_active *ref,
-		      void (*retire)(struct i915_active *ref))
+void __i915_active_init(struct drm_i915_private *i915,
+			struct i915_active *ref,
+			int (*active)(struct i915_active *ref),
+			void (*retire)(struct i915_active *ref),
+			struct lock_class_key *key)
 {
+	debug_active_init(ref);
+
 	ref->i915 = i915;
+	ref->flags = 0;
+	ref->active = active;
 	ref->retire = retire;
 	ref->tree = RB_ROOT;
-	i915_active_request_init(&ref->last, NULL, last_retire);
+	ref->cache = NULL;
 	init_llist_head(&ref->barriers);
-	ref->count = 0;
+	atomic_set(&ref->count, 0);
+	__mutex_init(&ref->mutex, "i915_active", key);
 }
 
 int i915_active_ref(struct i915_active *ref,
@@ -168,60 +211,123 @@ int i915_active_ref(struct i915_active *ref,
 		    struct i915_request *rq)
 {
 	struct i915_active_request *active;
-	int err = 0;
+	int err;
 
 	/* Prevent reaping in case we malloc/wait while building the tree */
-	i915_active_acquire(ref);
+	err = i915_active_acquire(ref);
+	if (err)
+		return err;
 
 	active = active_instance(ref, timeline);
-	if (IS_ERR(active)) {
-		err = PTR_ERR(active);
+	if (!active) {
+		err = -ENOMEM;
 		goto out;
 	}
 
 	if (!i915_active_request_isset(active))
-		ref->count++;
+		atomic_inc(&ref->count);
 	__i915_active_request_set(active, rq);
 
-	GEM_BUG_ON(!ref->count);
 out:
 	i915_active_release(ref);
 	return err;
 }
 
-bool i915_active_acquire(struct i915_active *ref)
+int i915_active_acquire(struct i915_active *ref)
 {
-	lockdep_assert_held(BKL(ref));
-	return !ref->count++;
+	int err;
+
+	debug_active_assert(ref);
+	if (atomic_add_unless(&ref->count, 1, 0))
+		return 0;
+
+	err = mutex_lock_interruptible(&ref->mutex);
+	if (err)
+		return err;
+
+	if (!atomic_read(&ref->count) && ref->active)
+		err = ref->active(ref);
+	if (!err) {
+		debug_active_activate(ref);
+		atomic_inc(&ref->count);
+	}
+
+	mutex_unlock(&ref->mutex);
+
+	return err;
 }
 
 void i915_active_release(struct i915_active *ref)
 {
-	lockdep_assert_held(BKL(ref));
-	__active_retire(ref);
+	debug_active_assert(ref);
+	active_retire(ref);
+}
+
+static void __active_ungrab(struct i915_active *ref)
+{
+	clear_and_wake_up_bit(I915_ACTIVE_GRAB_BIT, &ref->flags);
+}
+
+bool i915_active_trygrab(struct i915_active *ref)
+{
+	debug_active_assert(ref);
+
+	if (test_and_set_bit(I915_ACTIVE_GRAB_BIT, &ref->flags))
+		return false;
+
+	if (!atomic_add_unless(&ref->count, 1, 0)) {
+		__active_ungrab(ref);
+		return false;
+	}
+
+	return true;
+}
+
+void i915_active_ungrab(struct i915_active *ref)
+{
+	GEM_BUG_ON(!test_bit(I915_ACTIVE_GRAB_BIT, &ref->flags));
+
+	active_retire(ref);
+	__active_ungrab(ref);
 }
 
 int i915_active_wait(struct i915_active *ref)
 {
 	struct active_node *it, *n;
-	int ret = 0;
+	int err;
 
-	if (i915_active_acquire(ref))
-		goto out_release;
+	might_sleep();
+	might_lock(&ref->mutex);
+
+	if (i915_active_is_idle(ref))
+		return 0;
+
+	err = mutex_lock_interruptible(&ref->mutex);
+	if (err)
+		return err;
 
-	ret = i915_active_request_retire(&ref->last, BKL(ref));
-	if (ret)
-		goto out_release;
+	if (!atomic_add_unless(&ref->count, 1, 0)) {
+		mutex_unlock(&ref->mutex);
+		return 0;
+	}
 
 	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		ret = i915_active_request_retire(&it->base, BKL(ref));
-		if (ret)
+		err = i915_active_request_retire(&it->base, BKL(ref));
+		if (err)
 			break;
 	}
 
-out_release:
-	i915_active_release(ref);
-	return ret;
+	__active_retire(ref);
+	if (err)
+		return err;
+
+	if (wait_on_bit(&ref->flags, I915_ACTIVE_GRAB_BIT, TASK_KILLABLE))
+		return -EINTR;
+
+	if (!i915_active_is_idle(ref))
+		return -EBUSY;
+
+	return 0;
 }
 
 int i915_request_await_active_request(struct i915_request *rq,
@@ -236,23 +342,24 @@ int i915_request_await_active_request(struct i915_request *rq,
 int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
 {
 	struct active_node *it, *n;
-	int err = 0;
+	int err;
 
-	/* await allocates and so we need to avoid hitting the shrinker */
-	if (i915_active_acquire(ref))
-		goto out; /* was idle */
+	if (RB_EMPTY_ROOT(&ref->tree))
+		return 0;
 
-	err = i915_request_await_active_request(rq, &ref->last);
+	/* await allocates and so we need to avoid hitting the shrinker */
+	err = i915_active_acquire(ref);
 	if (err)
-		goto out;
+		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);
 		if (err)
-			goto out;
+			break;
 	}
+	mutex_unlock(&ref->mutex);
 
-out:
 	i915_active_release(ref);
 	return err;
 }
@@ -260,9 +367,10 @@ out:
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 void i915_active_fini(struct i915_active *ref)
 {
-	GEM_BUG_ON(i915_active_request_isset(&ref->last));
+	debug_active_fini(ref);
 	GEM_BUG_ON(!RB_EMPTY_ROOT(&ref->tree));
-	GEM_BUG_ON(ref->count);
+	GEM_BUG_ON(atomic_read(&ref->count));
+	mutex_destroy(&ref->mutex);
 }
 #endif
 
@@ -270,12 +378,12 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
+	intel_engine_mask_t tmp, mask = engine->mask;
 	struct llist_node *pos, *next;
-	unsigned long tmp;
 	int err;
 
-	GEM_BUG_ON(!engine->mask);
-	for_each_engine_masked(engine, i915, engine->mask, tmp) {
+	GEM_BUG_ON(!mask);
+	for_each_engine_masked(engine, i915, mask, tmp) {
 		struct intel_context *kctx = engine->kernel_context;
 		struct active_node *node;
 
@@ -289,7 +397,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					 (void *)engine, node_retire);
 		node->timeline = kctx->ring->timeline->fence_context;
 		node->ref = ref;
-		ref->count++;
+		atomic_inc(&ref->count);
 
 		intel_engine_pm_get(engine);
 		llist_add((struct llist_node *)&node->base.link,
@@ -316,8 +424,9 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 {
 	struct llist_node *pos, *next;
 
-	i915_active_acquire(ref);
+	GEM_BUG_ON(i915_active_is_idle(ref));
 
+	mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
 	llist_for_each_safe(pos, next, llist_del_all(&ref->barriers)) {
 		struct intel_engine_cs *engine;
 		struct active_node *node;
@@ -347,7 +456,7 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 			  &engine->barrier_tasks);
 		intel_engine_pm_put(engine);
 	}
-	i915_active_release(ref);
+	mutex_unlock(&ref->mutex);
 }
 
 void i915_request_add_barriers(struct i915_request *rq)