On Sat, 2021-08-07 at 17:13 -0700, Nadav Amit wrote:
> From: Nadav Amit <namit@xxxxxxxxxx>
>
> When using SQPOLL, the submission queue polling thread calls
> task_work_run() to run queued work. However, when work is added with
> TWA_SIGNAL - as done by io_uring itself - the TIF_NOTIFY_SIGNAL remains
> set afterwards and is never cleared.
>
> Consequently, when the submission queue polling thread checks whether
> signal_pending(), it may always find a pending signal, if
> task_work_add() was ever called before.
>
> The impact of this bug might be different on different kernel versions.
> It appears that on 5.14 it would only cause unnecessary calculation and
> prevent the polling thread from sleeping. On 5.13, where the bug was
> found, it stops the polling thread from finding newly submitted work.
>
> Instead of task_work_run(), use tracehook_notify_signal() that clears
> TIF_NOTIFY_SIGNAL. Test for TIF_NOTIFY_SIGNAL in addition to
> current->task_works to avoid a race in which task_works is cleared but
> the TIF_NOTIFY_SIGNAL is set.
>
> Fixes: 685fe7feedb96 ("io-wq: eliminate the need for a manager thread")
> Cc: Jens Axboe <axboe@xxxxxxxxx>
> Cc: Pavel Begunkov <asml.silence@xxxxxxxxx>
> Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
> ---
> fs/io_uring.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 5a0fd6bcd318..f39244d35f90 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -78,6 +78,7 @@
> #include <linux/task_work.h>
> #include <linux/pagemap.h>
> #include <linux/io_uring.h>
> +#include <linux/tracehook.h>
>
> #define CREATE_TRACE_POINTS
> #include <trace/events/io_uring.h>
> @@ -2203,9 +2204,9 @@ static inline unsigned int io_put_rw_kbuf(struct
> io_kiocb *req)
>
> static inline bool io_run_task_work(void)
> {
> - if (current->task_works) {
> + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works)
> {
> __set_current_state(TASK_RUNNING);
> - task_work_run();
> + tracehook_notify_signal();
> return true;
> }
>
thx a lot for this patch!
This explains what I am seeing here:
https://lore.kernel.org/io-uring/4d93d0600e4a9590a48d320c5a7dd4c54d66f095.camel@xxxxxxxxxxxxxx/
I was under the impression that task_work_run() was clearing
TIF_NOTIFY_SIGNAL.
your patch made me realize that it does not...
