[Intel-gfx] [PATCH 3/6] drm/i915: Export a preallocate variant of i915_active_acquire()

[Chris Wilson <chris@chris-wilson.co.uk>]

Sometimes we have to be very careful not to allocate underneath a mutex
(or spinlock) and yet still want to track activity. Enter
i915_active_acquire_for_context(). This raises the activity counter on
i915_active prior to use and ensures that the fence-tree contains a slot
for the context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |   2 +-
 drivers/gpu/drm/i915/gt/intel_timeline.c      |   4 +-
 drivers/gpu/drm/i915/i915_active.c            | 111 ++++++++++++++----
 drivers/gpu/drm/i915/i915_active.h            |  12 +-
 4 files changed, 103 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..719ba9fe3e85 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1729,7 +1729,7 @@ __parser_mark_active(struct i915_vma *vma,
 {
 	struct intel_gt_buffer_pool_node *node = vma->private;
 
-	return i915_active_ref(&node->active, tl, fence);
+	return i915_active_ref(&node->active, tl->fence_context, fence);
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 4546284fede1..e4a5326633b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -479,7 +479,9 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 	 * free it after the current request is retired, which ensures that
 	 * all writes into the cacheline from previous requests are complete.
 	 */
-	err = i915_active_ref(&tl->hwsp_cacheline->active, tl, &rq->fence);
+	err = i915_active_ref(&tl->hwsp_cacheline->active,
+			      tl->fence_context,
+			      &rq->fence);
 	if (err)
 		goto err_cacheline;
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 841b5c30950a..a3a9295b22f7 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -28,12 +28,14 @@ static struct i915_global_active {
 } global;
 
 struct active_node {
+	struct rb_node node;
 	struct i915_active_fence base;
 	struct i915_active *ref;
-	struct rb_node node;
 	u64 timeline;
 };
 
+#define fetch_node(x) rb_entry(READ_ONCE(x), typeof(struct active_node), node)
+
 static inline struct active_node *
 node_from_active(struct i915_active_fence *active)
 {
@@ -216,12 +218,39 @@ excl_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 		active_retire(container_of(cb, struct i915_active, excl.cb));
 }
 
+static struct active_node *__active_lookup(struct i915_active *ref, u64 idx)
+{
+	struct active_node *it;
+
+	it = READ_ONCE(ref->cache);
+	if (it && it->timeline == idx)
+		return it;
+
+	BUILD_BUG_ON(offsetof(typeof(*it), node));
+
+	/* While active, the tree can only be built; not destroyed */
+	GEM_BUG_ON(i915_active_is_idle(ref));
+
+	it = fetch_node(ref->tree.rb_node);
+	while (it) {
+		if (it->timeline < idx) {
+			it = fetch_node(it->node.rb_right);
+		} else if (it->timeline > idx) {
+			it = fetch_node(it->node.rb_left);
+		} else {
+			WRITE_ONCE(ref->cache, it);
+			break;
+		}
+	}
+
+	return it;
+}
+
 static struct i915_active_fence *
-active_instance(struct i915_active *ref, struct intel_timeline *tl)
+active_instance(struct i915_active *ref, u64 idx)
 {
 	struct active_node *node, *prealloc;
 	struct rb_node **p, *parent;
-	u64 idx = tl->fence_context;
 
 	/*
 	 * We track the most recently used timeline to skip a rbtree search
@@ -230,8 +259,8 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	 * after the previous activity has been retired, or if it matches the
 	 * current timeline.
 	 */
-	node = READ_ONCE(ref->cache);
-	if (node && node->timeline == idx)
+	node = __active_lookup(ref, idx);
+	if (likely(node))
 		return &node->base;
 
 	/* Preallocate a replacement, just in case */
@@ -268,10 +297,9 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	rb_insert_color(&node->node, &ref->tree);
 
 out:
-	ref->cache = node;
+	WRITE_ONCE(ref->cache, node);
 	spin_unlock_irq(&ref->tree_lock);
 
-	BUILD_BUG_ON(offsetof(typeof(*node), base));
 	return &node->base;
 }
 
@@ -353,21 +381,17 @@ __active_del_barrier(struct i915_active *ref, struct active_node *node)
 	return ____active_del_barrier(ref, node, barrier_to_engine(node));
 }
 
-int i915_active_ref(struct i915_active *ref,
-		    struct intel_timeline *tl,
-		    struct dma_fence *fence)
+int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
 {
 	struct i915_active_fence *active;
 	int err;
 
-	lockdep_assert_held(&tl->mutex);
-
 	/* Prevent reaping in case we malloc/wait while building the tree */
 	err = i915_active_acquire(ref);
 	if (err)
 		return err;
 
-	active = active_instance(ref, tl);
+	active = active_instance(ref, idx);
 	if (!active) {
 		err = -ENOMEM;
 		goto out;
@@ -384,32 +408,61 @@ int i915_active_ref(struct i915_active *ref,
 		atomic_dec(&ref->count);
 	}
 	if (!__i915_active_fence_set(active, fence))
-		atomic_inc(&ref->count);
+		__i915_active_acquire(ref);
 
 out:
 	i915_active_release(ref);
 	return err;
 }
 
-struct dma_fence *
-i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
+static struct dma_fence *
+__i915_active_set_fence(struct i915_active *ref,
+			struct i915_active_fence *active,
+			struct dma_fence *fence)
 {
 	struct dma_fence *prev;
 
 	/* We expect the caller to manage the exclusive timeline ordering */
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
+	if (is_barrier(active)) { /* proto-node used by our idle barrier */
+		/*
+		 * This request is on the kernel_context timeline, and so
+		 * we can use it to substitute for the pending idle-barrer
+		 * request that we want to emit on the kernel_context.
+		 */
+		__active_del_barrier(ref, node_from_active(active));
+		RCU_INIT_POINTER(active->fence, fence);
+		return NULL;
+	}
+
 	rcu_read_lock();
-	prev = __i915_active_fence_set(&ref->excl, f);
+	prev = __i915_active_fence_set(active, fence);
 	if (prev)
 		prev = dma_fence_get_rcu(prev);
 	else
-		atomic_inc(&ref->count);
+		__i915_active_acquire(ref);
 	rcu_read_unlock();
 
 	return prev;
 }
 
+struct dma_fence *
+__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
+{
+	/* Only valid while active, see i915_active_acquire_for_context() */
+	return __i915_active_set_fence(ref,
+				       &__active_lookup(ref, idx)->base,
+				       fence);
+}
+
+struct dma_fence *
+i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
+{
+	/* We expect the caller to manage the exclusive timeline ordering */
+	return __i915_active_set_fence(ref, &ref->excl, f);
+}
+
 bool i915_active_acquire_if_busy(struct i915_active *ref)
 {
 	debug_active_assert(ref);
@@ -450,6 +503,24 @@ int i915_active_acquire(struct i915_active *ref)
 	return err;
 }
 
+int i915_active_acquire_for_context(struct i915_active *ref, u64 idx)
+{
+	struct i915_active_fence *active;
+	int err;
+
+	err = i915_active_acquire(ref);
+	if (err)
+		return err;
+
+	active = active_instance(ref, idx);
+	if (!active) {
+		i915_active_release(ref);
+		return -ENOMEM;
+	}
+
+	return 0; /* return with active ref */
+}
+
 void i915_active_release(struct i915_active *ref)
 {
 	debug_active_assert(ref);
@@ -753,7 +824,7 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 match:
 	rb_erase(p, &ref->tree); /* Hide from waits and sibling allocations */
 	if (p == &ref->cache->node)
-		ref->cache = NULL;
+		WRITE_ONCE(ref->cache, NULL);
 	spin_unlock_irq(&ref->tree_lock);
 
 	return rb_entry(p, struct active_node, node);
@@ -811,7 +882,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			 */
 			RCU_INIT_POINTER(node->base.fence, ERR_PTR(-EAGAIN));
 			node->base.cb.node.prev = (void *)engine;
-			atomic_inc(&ref->count);
+			__i915_active_acquire(ref);
 		}
 		GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN));
 
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index cf4058150966..73ded3c52a04 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -163,14 +163,16 @@ void __i915_active_init(struct i915_active *ref,
 	__i915_active_init(ref, active, retire, &__mkey, &__wkey);	\
 } while (0)
 
-int i915_active_ref(struct i915_active *ref,
-		    struct intel_timeline *tl,
-		    struct dma_fence *fence);
+struct dma_fence *
+__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence);
+int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence);
 
 static inline int
 i915_active_add_request(struct i915_active *ref, struct i915_request *rq)
 {
-	return i915_active_ref(ref, i915_request_timeline(rq), &rq->fence);
+	return i915_active_ref(ref,
+			       i915_request_timeline(rq)->fence_context,
+			       &rq->fence);
 }
 
 struct dma_fence *
@@ -198,7 +200,9 @@ int i915_request_await_active(struct i915_request *rq,
 #define I915_ACTIVE_AWAIT_BARRIER BIT(2)
 
 int i915_active_acquire(struct i915_active *ref);
+int i915_active_acquire_for_context(struct i915_active *ref, u64 idx);
 bool i915_active_acquire_if_busy(struct i915_active *ref);
+
 void i915_active_release(struct i915_active *ref);
 
 static inline void __i915_active_acquire(struct i915_active *ref)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx