fuse-uring: fix race between registration and connection abortion

This fixes this race:
- thread a: io_uring_enter -> register sqe ->
  fuse_uring_create_ring_ent -> allocate ent but doesn't grab queue_ref
  yet
- thread b: fuse_conn_destroy() -> fuse_chan_abort() ->
  fuse_uring_abort() is a no-op due to queue ref being 0
- thread a: grabs the queue_ref, queue_ref is now 1, rest of
  fuse_uring_do_register() logic executes
- thread b: fuse_chan_abort() returns, fuse_chan_wait_aborted() now runs
  and calls
  "wait_event(ring->stop_waitq, atomic_read(&ring->queue_refs) == 0);"
The abort/unmount thread will hang indefinitely in unkillable state as
nothing will decrement queue_refs or wake stop_waitq, and the ring,
queue, and ent are leaked.

Fix this by checking fch->connected under fch->lock after the created
ent has grabbed a ref count on the queue. This ensures that in the
scenario above, it is guaranteed that we either release the queue ref
and wake up stop_waitq (in case fuse_chan_wait_aborted() is already
waiting) in fuse_uring_do_register() when we detect !fch->connected, or
if the connection is aborted after the check, it is guaranteed that the
async teardown worker will be running in the background cleaning up ents
and decrementing the ent's ref on the queue, which will unblock the
eventual queue and ring teardown.

Fixes: 24fe962c86f5 ("fuse: {io-uring} Handle SQEs - register commands")
Cc: stable@vger.kernel.org
Reviewed-by: Bernd Schubert <bernd@bsbernd.com>
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index 33b9fcee4fc372333459b4736493f8b41ed85fff..16b9229c2dbdf8a95686a3248a45e26259606b74 100644 (file)
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -972,15 +972,26 @@ static bool is_ring_ready(struct fuse_ring *ring, int current_qid)
 /*
  * fuse_uring_req_fetch command handling
  */
-static void fuse_uring_do_register(struct fuse_ring_ent *ent,
-                                  struct io_uring_cmd *cmd,
-                                  unsigned int issue_flags)
+static int fuse_uring_do_register(struct fuse_ring_ent *ent,
+                                 struct io_uring_cmd *cmd,
+                                 unsigned int issue_flags)
 {
        struct fuse_ring_queue *queue = ent->queue;
        struct fuse_ring *ring = queue->ring;
        struct fuse_conn *fc = ring->fc;
        struct fuse_iqueue *fiq = &fc->iq;
 
+       spin_lock(&fch->lock);
+       /* abort teardown path is running or has run */
+       if (!fch->connected) {
+               spin_unlock(&fch->lock);
+               if (atomic_dec_and_test(&ring->queue_refs))
+                       wake_up_all(&ring->stop_waitq);
+               kfree(ent);
+               return -ECONNABORTED;
+       }
+       spin_unlock(&fch->lock);
+
        fuse_uring_prepare_cancel(cmd, issue_flags, ent);
 
        spin_lock(&queue->lock);
@@ -997,6 +1008,7 @@ static void fuse_uring_do_register(struct fuse_ring_ent *ent,
                        wake_up_all(&fc->blocked_waitq);
                }
        }
+       return 0;
 }
 
 /*
@@ -1113,9 +1125,7 @@ static int fuse_uring_register(struct io_uring_cmd *cmd,
        if (IS_ERR(ent))
                return PTR_ERR(ent);
 
-       fuse_uring_do_register(ent, cmd, issue_flags);
-
-       return 0;
+       return fuse_uring_do_register(ent, cmd, issue_flags);
 }
 
 /*