drm/ttm: remove lru_lock around ttm_bo_reserve

There should no longer be assumptions that reserve will always succeed
with the lru lock held, so we can safely break the whole atomic
reserve/lru thing. As a bonus this fixes most lockdep annotations for
reservations.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>

2 files changed, 36 insertions, 20 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 33d20be87db5..e8e4814b1295 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -213,14 +213,13 @@ int ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 	return put_count;
 }
 
-int ttm_bo_reserve_locked(struct ttm_buffer_object *bo,
+int ttm_bo_reserve_nolru(struct ttm_buffer_object *bo,
 			  bool interruptible,
 			  bool no_wait, bool use_sequence, uint32_t sequence)
 {
-	struct ttm_bo_global *glob = bo->glob;
 	int ret;
 
-	while (unlikely(atomic_read(&bo->reserved) != 0)) {
+	while (unlikely(atomic_xchg(&bo->reserved, 1) != 0)) {
 		/**
 		 * Deadlock avoidance for multi-bo reserving.
 		 */
@@ -241,26 +240,36 @@ int ttm_bo_reserve_locked(struct ttm_buffer_object *bo,
 		if (no_wait)
 			return -EBUSY;
 
-		spin_unlock(&glob->lru_lock);
 		ret = ttm_bo_wait_unreserved(bo, interruptible);
-		spin_lock(&glob->lru_lock);
 
 		if (unlikely(ret))
 			return ret;
 	}
 
-	atomic_set(&bo->reserved, 1);
 	if (use_sequence) {
+		bool wake_up = false;
 		/**
 		 * Wake up waiters that may need to recheck for deadlock,
 		 * if we decreased the sequence number.
 		 */
 		if (unlikely((bo->val_seq - sequence < (1 << 31))
 			     || !bo->seq_valid))
-			wake_up_all(&bo->event_queue);
+			wake_up = true;
 
+		/*
+		 * In the worst case with memory ordering these values can be
+		 * seen in the wrong order. However since we call wake_up_all
+		 * in that case, this will hopefully not pose a problem,
+		 * and the worst case would only cause someone to accidentally
+		 * hit -EAGAIN in ttm_bo_reserve when they see old value of
+		 * val_seq. However this would only happen if seq_valid was
+		 * written before val_seq was, and just means some slightly
+		 * increased cpu usage
+		 */
 		bo->val_seq = sequence;
 		bo->seq_valid = true;
+		if (wake_up)
+			wake_up_all(&bo->event_queue);
 	} else {
 		bo->seq_valid = false;
 	}
@@ -289,14 +298,14 @@ int ttm_bo_reserve(struct ttm_buffer_object *bo,
 	int put_count = 0;
 	int ret;
 
-	spin_lock(&glob->lru_lock);
-	ret = ttm_bo_reserve_locked(bo, interruptible, no_wait, use_sequence,
-				    sequence);
-	if (likely(ret == 0))
+	ret = ttm_bo_reserve_nolru(bo, interruptible, no_wait, use_sequence,
+				   sequence);
+	if (likely(ret == 0)) {
+		spin_lock(&glob->lru_lock);
 		put_count = ttm_bo_del_from_lru(bo);
-	spin_unlock(&glob->lru_lock);
-
-	ttm_bo_list_ref_sub(bo, put_count, true);
+		spin_unlock(&glob->lru_lock);
+		ttm_bo_list_ref_sub(bo, put_count, true);
+	}
 
 	return ret;
 }
@@ -510,7 +519,7 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	int ret;
 
 	spin_lock(&glob->lru_lock);
-	ret = ttm_bo_reserve_locked(bo, false, true, false, 0);
+	ret = ttm_bo_reserve_nolru(bo, false, true, false, 0);
 
 	spin_lock(&bdev->fence_lock);
 	(void) ttm_bo_wait(bo, false, false, true);
@@ -603,7 +612,7 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 			return ret;
 
 		spin_lock(&glob->lru_lock);
-		ret = ttm_bo_reserve_locked(bo, false, true, false, 0);
+		ret = ttm_bo_reserve_nolru(bo, false, true, false, 0);
 
 		/*
 		 * We raced, and lost, someone else holds the reservation now,
@@ -667,7 +676,14 @@ static int ttm_bo_delayed_delete(struct ttm_bo_device *bdev, bool remove_all)
 			kref_get(&nentry->list_kref);
 		}
 
-		ret = ttm_bo_reserve_locked(entry, false, !remove_all, false, 0);
+		ret = ttm_bo_reserve_nolru(entry, false, true, false, 0);
+		if (remove_all && ret) {
+			spin_unlock(&glob->lru_lock);
+			ret = ttm_bo_reserve_nolru(entry, false, false,
+						   false, 0);
+			spin_lock(&glob->lru_lock);
+		}
+
 		if (!ret)
 			ret = ttm_bo_cleanup_refs_and_unlock(entry, false,
 							     !remove_all);
@@ -815,7 +831,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
-		ret = ttm_bo_reserve_locked(bo, false, true, false, 0);
+		ret = ttm_bo_reserve_nolru(bo, false, true, false, 0);
 		if (!ret)
 			break;
 	}
@@ -1796,7 +1812,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &glob->swap_lru, swap) {
-		ret = ttm_bo_reserve_locked(bo, false, true, false, 0);
+		ret = ttm_bo_reserve_nolru(bo, false, true, false, 0);
 		if (!ret)
 			break;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index cd9e4523dc56..bd37b5cb8553 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -153,7 +153,7 @@ retry:
 		struct ttm_buffer_object *bo = entry->bo;
 
 retry_this_bo:
-		ret = ttm_bo_reserve_locked(bo, true, true, true, val_seq);
+		ret = ttm_bo_reserve_nolru(bo, true, true, true, val_seq);
 		switch (ret) {
 		case 0:
 			break;