io_uring: fix mutex_unlock with unreferenced ctx

commit f7b32e785042d2357c5abc23ca6db1b92c91a070 upstream.

Callers of mutex_unlock() have to make sure that the mutex stays alive
for the whole duration of the function call. For io_uring that means
that the following pattern is not valid unless we ensure that the
context outlives the mutex_unlock() call.

mutex_lock(&ctx->uring_lock);
req_put(req); // typically via io_req_task_submit()
mutex_unlock(&ctx->uring_lock);

Most contexts are fine: io-wq pins requests, syscalls hold the file,
task works are taking ctx references and so on. However, the task work
fallback path doesn't follow the rule.

Cc:  <stable@vger.kernel.org>
Fixes: 04fc6c802d ("io_uring: save ctx put/get for task_work submit")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/io-uring/CAG48ez3xSoYb+45f1RLtktROJrpiDQ1otNvdR+YLQf7m+Krj5Q@mail.gmail.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index f09e3ee..bb8880d 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -269,6 +269,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
        struct io_kiocb *req, *tmp;
        struct io_tw_state ts = { .locked = true, };
 
+       percpu_ref_get(&ctx->refs);
        mutex_lock(&ctx->uring_lock);
        llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
                req->io_task_work.func(req, &ts);
@@ -276,6 +277,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
                return;
        io_submit_flush_completions(ctx);
        mutex_unlock(&ctx->uring_lock);
+       percpu_ref_put(&ctx->refs);
 }
 
 static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
@@ -3138,12 +3140,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
        init_completion(&exit.completion);
        init_task_work(&exit.task_work, io_tctx_exit_cb);
        exit.ctx = ctx;
-       /*
-        * Some may use context even when all refs and requests have been put,
-        * and they are free to do so while still holding uring_lock or
-        * completion_lock, see io_req_task_submit(). Apart from other work,
-        * this lock/unlock section also waits them to finish.
-        */
+
        mutex_lock(&ctx->uring_lock);
        while (!list_empty(&ctx->tctx_list)) {
                WARN_ON_ONCE(time_after(jiffies, timeout));