When a background request completes via the io_uring path, the
background queue gets flushed to dispatch pending background requests,
but this is done before the connection-level background counters
(fc->num_background, fc->active_background) are properly accounted,
which can leave pending background requests stuck in the per-queue
background queue.

The connection-level counters are decremented in fuse_request_end(), but
flush_bg_queue() flushes the /dev/fuse path queue (fc->bg_queue), not
the io_uring per-queue bg one, which means pending uring background
requests on the queue are never dispatched.

Fix this by accounting the connection-level background counters first
before flushing the queue's background queue. Since
fuse_request_bg_finish() clears FR_BACKGROUND, fuse_request_end() will
skip the background cleanup branch entirely, which avoids any
double-decrements; it will call the wake_up(&req->waitq) branch but this
is effectively a no-op as background requests have no waiters on
req->waitq.

Fixes: 857b0263f30e ("fuse: Allow to queue bg requests through io-uring")
Cc: stable@vger.kernel.org
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
---
 fs/fuse/dev.c        | 41 ++++++++++++++++++++++++-----------------
 fs/fuse/dev_uring.c  |  1 +
 fs/fuse/fuse_dev_i.h |  1 +
 3 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index b212565a78cf..35cdfc162ba5 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -447,6 +447,29 @@ static void flush_bg_queue(struct fuse_conn *fc)
 	}
 }
 
+void fuse_request_bg_finish(struct fuse_conn *fc, struct fuse_req *req)
+{
+	lockdep_assert_held(&fc->bg_lock);
+
+	clear_bit(FR_BACKGROUND, &req->flags);
+	if (fc->num_background == fc->max_background) {
+		fc->blocked = 0;
+		wake_up(&fc->blocked_waitq);
+	} else if (!fc->blocked) {
+		/*
+		 * Wake up next waiter, if any.  It's okay to use
+		 * waitqueue_active(), as we've already synced up
+		 * fc->blocked with waiters with the wake_up() call
+		 * above.
+		 */
+		if (waitqueue_active(&fc->blocked_waitq))
+			wake_up(&fc->blocked_waitq);
+	}
+
+	fc->num_background--;
+	fc->active_background--;
+}
+
 /*
  * This function is called when a request is finished.  Either a reply
  * has arrived or it was aborted (and not yet sent) or some error
@@ -479,23 +502,7 @@ void fuse_request_end(struct fuse_req *req)
 	WARN_ON(test_bit(FR_SENT, &req->flags));
 	if (test_bit(FR_BACKGROUND, &req->flags)) {
 		spin_lock(&fc->bg_lock);
-		clear_bit(FR_BACKGROUND, &req->flags);
-		if (fc->num_background == fc->max_background) {
-			fc->blocked = 0;
-			wake_up(&fc->blocked_waitq);
-		} else if (!fc->blocked) {
-			/*
-			 * Wake up next waiter, if any.  It's okay to use
-			 * waitqueue_active(), as we've already synced up
-			 * fc->blocked with waiters with the wake_up() call
-			 * above.
-			 */
-			if (waitqueue_active(&fc->blocked_waitq))
-				wake_up(&fc->blocked_waitq);
-		}
-
-		fc->num_background--;
-		fc->active_background--;
+		fuse_request_bg_finish(fc, req);
 		flush_bg_queue(fc);
 		spin_unlock(&fc->bg_lock);
 	} else {
diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index 7b9822e8837b..ae916733f18a 100644
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -90,6 +90,7 @@ static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req,
 	if (test_bit(FR_BACKGROUND, &req->flags)) {
 		queue->active_background--;
 		spin_lock(&fc->bg_lock);
+		fuse_request_bg_finish(fc, req);
 		fuse_uring_flush_bg(queue);
 		spin_unlock(&fc->bg_lock);
 	}
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
index 134bf44aff0d..7da505af6d35 100644
--- a/fs/fuse/fuse_dev_i.h
+++ b/fs/fuse/fuse_dev_i.h
@@ -59,6 +59,7 @@ unsigned int fuse_req_hash(u64 unique);
 struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique);
 
 void fuse_dev_end_requests(struct list_head *head);
+void fuse_request_bg_finish(struct fuse_conn *fc, struct fuse_req *req);
 
 void fuse_copy_init(struct fuse_copy_state *cs, bool write,
 			   struct iov_iter *iter);
-- 
2.52.0