io_uring/poll: allow some retries for poll triggering spuriously

If we get woken spuriously when polling and fail the operation with
-EAGAIN again, then we generally only allow polling again if data
had been transferred at some point. This is indicated with
REQ_F_PARTIAL_IO. However, if the spurious poll triggers when the socket
was originally empty, then we haven't transferred data yet and we will
fail the poll re-arm. This either punts the socket to io-wq if it's
blocking, or it fails the request with -EAGAIN if not. Neither condition
is desirable, as the former will slow things down, while the latter
will make the application confused.

We want to ensure that a repeated poll trigger doesn't lead to infinite
work making no progress, that's what the REQ_F_PARTIAL_IO check was
for. But it doesn't protect against a loop post the first receive, and
it's unnecessarily strict if we started out with an empty socket.

Add a somewhat random retry count, just to put an upper limit on the
potential number of retries that will be done. This should be high enough
that we won't really hit it in practice, unless something needs to be
aborted anyway.

Cc: stable@vger.kernel.org # v5.10+
Link: https://github.com/axboe/liburing/issues/364
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/poll.c b/io_uring/poll.c
index 8339a92b451079b993359fee37aef449fba52d21..a82d6830bdfdde132baa18dabf1e180522fefdde 100644 (file)
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -650,6 +650,14 @@ static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
        __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
 }
 
+/*
+ * We can't reliably detect loops in repeated poll triggers and issue
+ * subsequently failing. But rather than fail these immediately, allow a
+ * certain amount of retries before we give up. Given that this condition
+ * should _rarely_ trigger even once, we should be fine with a larger value.
+ */
+#define APOLL_MAX_RETRY                128
+
 static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
                                             unsigned issue_flags)
 {
@@ -665,14 +673,18 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
                if (entry == NULL)
                        goto alloc_apoll;
                apoll = container_of(entry, struct async_poll, cache);
+               apoll->poll.retries = APOLL_MAX_RETRY;
        } else {
 alloc_apoll:
                apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
                if (unlikely(!apoll))
                        return NULL;
+               apoll->poll.retries = APOLL_MAX_RETRY;
        }
        apoll->double_poll = NULL;
        req->apoll = apoll;
+       if (unlikely(!--apoll->poll.retries))
+               return NULL;
        return apoll;
 }
 
@@ -694,8 +706,6 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
                return IO_APOLL_ABORTED;
        if (!file_can_poll(req->file))
                return IO_APOLL_ABORTED;
-       if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
-               return IO_APOLL_ABORTED;
        if (!(req->flags & REQ_F_APOLL_MULTISHOT))
                mask |= EPOLLONESHOT;
 

diff --git a/io_uring/poll.h b/io_uring/poll.h
index 5f3bae50fc81a03e2c79c3d2a15652a67c39a98f..b2393b403a2c21014d5c648cc244a707748cb02a 100644 (file)
--- a/io_uring/poll.h
+++ b/io_uring/poll.h
@@ -12,6 +12,7 @@ struct io_poll {
        struct file                     *file;
        struct wait_queue_head          *head;
        __poll_t                        events;
+       int                             retries;
        struct wait_queue_entry         wait;
 };