DONOTMERGE: dma-buf: Get rid of dma_fence_get_rcu_safe

This helper existed to handle the weird corner-cases caused by using
SLAB_TYPESAFE_BY_RCU for backing dma_fence.  Now that no one is using
that anymore (i915 was the only real user), dma_fence_get_rcu is
sufficient.  The one slightly annoying thing we have to deal with here
is that dma_fence_get_rcu_safe did an rcu_dereference as well as a
SLAB_TYPESAFE_BY_RCU-safe dma_fence_get_rcu.  This means each call site
ends up being 3 lines instead of 1.

Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Christian König <christian.koenig@amd.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

drivers/dma-buf/dma-fence-chain.c

@@ -15,15 +15,17 @@ static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
  * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
  * @chain: chain node to get the previous node from
  *
- * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
- * chain node.
+ * Use rcu_dereference and dma_fence_get_rcu to get a reference to the
+ * previous fence of the chain node.
  */
 static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
 {
 	struct dma_fence *prev;
 
 	rcu_read_lock();
-	prev = dma_fence_get_rcu_safe(&chain->prev);
+	prev = rcu_dereference(chain->prev);
+	if (prev)
+		prev = dma_fence_get_rcu(prev);
 	rcu_read_unlock();
 	return prev;
 }

drivers/dma-buf/dma-resv.c

@@ -376,7 +376,9 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
 		dst_list = NULL;
 	}
 
-	new = dma_fence_get_rcu_safe(&src->fence_excl);
+	new = rcu_dereference(src->fence_excl);
+	if (new)
+		new = dma_fence_get_rcu(new);
 	rcu_read_unlock();
 
 	src_list = dma_resv_shared_list(dst);

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -161,7 +161,9 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 		struct dma_fence *old;
 
 		rcu_read_lock();
-		old = dma_fence_get_rcu_safe(ptr);
+		old = rcu_dereference(*ptr);
+		if (old)
+			old = dma_fence_get_rcu(old);
 		rcu_read_unlock();
 
 		if (old) {

drivers/gpu/drm/i915/i915_active.h

@@ -103,7 +103,9 @@ i915_active_fence_get(struct i915_active_fence *active)
 	struct dma_fence *fence;
 
 	rcu_read_lock();
-	fence = dma_fence_get_rcu_safe(&active->fence);
+	fence = rcu_dereference(active->fence);
+	if (fence)
+		fence = dma_fence_get_rcu(fence);
 	rcu_read_unlock();
 
 	return fence;

drivers/gpu/drm/i915/i915_vma.c

@@ -351,7 +351,9 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
 		struct dma_fence *fence;
 
 		rcu_read_lock();
-		fence = dma_fence_get_rcu_safe(&vma->active.excl.fence);
+		fence = rcu_dereference(vma->active.excl.fence);
+		if (fence)
+			fence = dma_fence_get_rcu(fence);
 		rcu_read_unlock();
 		if (fence) {
 			err = dma_fence_wait(fence, MAX_SCHEDULE_TIMEOUT);

include/drm/drm_syncobj.h

@@ -105,7 +105,9 @@ drm_syncobj_fence_get(struct drm_syncobj *syncobj)
 	struct dma_fence *fence;
 
 	rcu_read_lock();
-	fence = dma_fence_get_rcu_safe(&syncobj->fence);
+	fence = rcu_dereference(syncobj->fence);
+	if (fence)
+		fence = dma_fence_get_rcu(syncobj->fence);
 	rcu_read_unlock();
 
 	return fence;

include/linux/dma-fence.h

@@ -307,56 +307,6 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
 		return NULL;
 }
 
-/**
- * dma_fence_get_rcu_safe  - acquire a reference to an RCU tracked fence
- * @fencep: pointer to fence to increase refcount of
- *
- * Function returns NULL if no refcount could be obtained, or the fence.
- * This function handles acquiring a reference to a fence that may be
- * reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU),
- * so long as the caller is using RCU on the pointer to the fence.
- *
- * An alternative mechanism is to employ a seqlock to protect a bunch of
- * fences, such as used by struct dma_resv. When using a seqlock,
- * the seqlock must be taken before and checked after a reference to the
- * fence is acquired (as shown here).
- *
- * The caller is required to hold the RCU read lock.
- */
-static inline struct dma_fence *
-dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep)
-{
-	do {
-		struct dma_fence *fence;
-
-		fence = rcu_dereference(*fencep);
-		if (!fence)
-			return NULL;
-
-		if (!dma_fence_get_rcu(fence))
-			continue;
-
-		/* The atomic_inc_not_zero() inside dma_fence_get_rcu()
-		 * provides a full memory barrier upon success (such as now).
-		 * This is paired with the write barrier from assigning
-		 * to the __rcu protected fence pointer so that if that
-		 * pointer still matches the current fence, we know we
-		 * have successfully acquire a reference to it. If it no
-		 * longer matches, we are holding a reference to some other
-		 * reallocated pointer. This is possible if the allocator
-		 * is using a freelist like SLAB_TYPESAFE_BY_RCU where the
-		 * fence remains valid for the RCU grace period, but it
-		 * may be reallocated. When using such allocators, we are
-		 * responsible for ensuring the reference we get is to
-		 * the right fence, as below.
-		 */
-		if (fence == rcu_access_pointer(*fencep))
-			return rcu_pointer_handoff(fence);
-
-		dma_fence_put(fence);
-	} while (1);
-}
-
 #ifdef CONFIG_LOCKDEP
 bool dma_fence_begin_signalling(void);
 void dma_fence_end_signalling(bool cookie);

include/linux/dma-resv.h

@@ -248,7 +248,9 @@ dma_resv_get_excl_unlocked(struct dma_resv *obj)
 		return NULL;
 
 	rcu_read_lock();
-	fence = dma_fence_get_rcu_safe(&obj->fence_excl);
+	fence = rcu_dereference(obj->fence_excl);
+	if (fence)
+		fence = dma_fence_get_rcu(fence);
 	rcu_read_unlock();
 
 	return fence;