io_uring: fix racy IOPOLL flush overflow

It's not safe to call io_cqring_overflow_flush() for IOPOLL mode without
hodling uring_lock, because it does synchronisation differently. Make
sure we have it.

As for io_ring_exit_work(), we don't even need it there because
io_ring_ctx_wait_and_kill() already set force flag making all overflowed
requests to be dropped.

Cc: <stable@vger.kernel.org> # 5.5+
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d030a44..c0306f7 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8654,8 +8654,6 @@ static void io_ring_exit_work(struct work_struct *work)
         * as nobody else will be looking for them.
         */
        do {
-               if (ctx->rings)
-                       io_cqring_overflow_flush(ctx, true, NULL, NULL);
                io_iopoll_try_reap_events(ctx);
        } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
        io_ring_ctx_free(ctx);
@@ -8665,6 +8663,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
        mutex_lock(&ctx->uring_lock);
        percpu_ref_kill(&ctx->refs);
+       if (ctx->rings)
+               io_cqring_overflow_flush(ctx, true, NULL, NULL);
        mutex_unlock(&ctx->uring_lock);
 
        io_kill_timeouts(ctx, NULL, NULL);
@@ -8674,8 +8674,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
                io_wq_cancel_all(ctx->io_wq);
 
        /* if we failed setting up the ctx, we might not have any rings */
-       if (ctx->rings)
-               io_cqring_overflow_flush(ctx, true, NULL, NULL);
        io_iopoll_try_reap_events(ctx);
        idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
 
@@ -8840,7 +8838,9 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
        }
 
        io_cancel_defer_files(ctx, task, files);
+       io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
        io_cqring_overflow_flush(ctx, true, task, files);
+       io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
 
        if (!files)
                __io_uring_cancel_task_requests(ctx, task);
@@ -9172,8 +9172,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
         */
        ret = 0;
        if (ctx->flags & IORING_SETUP_SQPOLL) {
+               io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
                if (!list_empty_careful(&ctx->cq_overflow_list))
                        io_cqring_overflow_flush(ctx, false, NULL, NULL);
+               io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
                if (flags & IORING_ENTER_SQ_WAKEUP)
                        wake_up(&ctx->sq_data->wait);
                if (flags & IORING_ENTER_SQ_WAIT)