io_uring: handle TIF_NOTIFY_RESUME when checking for task_work

If TIF_NOTIFY_RESUME is set, then we need to call resume_user_mode_work()
for PF_IO_WORKER threads. They never return to usermode, hence never get
a chance to process any items that are marked by this flag. Most notably
this includes the final put of files, but also any throttling markers set
by block cgroups.

Cc: stable@vger.kernel.org # 5.10+
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index c68edf9872a53f9f513a9427d0613c7fc03a8a23..d58cfe062da90b522cc3d3b0038c3c47f313143d 100644 (file)
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -3,6 +3,7 @@
 
 #include <linux/errno.h>
 #include <linux/lockdep.h>
+#include <linux/resume_user_mode.h>
 #include <linux/io_uring_types.h>
 #include <uapi/linux/eventpoll.h>
 #include "io-wq.h"
@@ -274,6 +275,13 @@ static inline int io_run_task_work(void)
         */
        if (test_thread_flag(TIF_NOTIFY_SIGNAL))
                clear_notify_signal();
+       /*
+        * PF_IO_WORKER never returns to userspace, so check here if we have
+        * notify work that needs processing.
+        */
+       if (current->flags & PF_IO_WORKER &&
+           test_thread_flag(TIF_NOTIFY_RESUME))
+               resume_user_mode_work(NULL);
        if (task_work_pending(current)) {
                __set_current_state(TASK_RUNNING);
                task_work_run();