io_uring: add memory barrier to synchronize io_kiocb's result and iopoll_completed
In io_complete_rw_iopoll(), stores to io_kiocb's result and iopoll
completed are two independent store operations, to ensure that once
iopoll_completed is ture and then req->result must been perceived by
the cpu executing io_do_iopoll(), proper memory barrier should be used.
And in io_do_iopoll(), we check whether req->result is EAGAIN, if it is,
we'll need to issue this io request using io-wq again. In order to just
issue a single smp_rmb() on the completion side, move the re-submit work
to io_iopoll_complete().
Cc: stable@vger.kernel.org
Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
[axboe: don't set ->iopoll_completed for -EAGAIN retry]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index eb37977..9d2ae9a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1742,6 +1742,18 @@ static int io_put_kbuf(struct io_kiocb *req)
return cflags;
}
+static void io_iopoll_queue(struct list_head *again)
+{
+ struct io_kiocb *req;
+
+ do {
+ req = list_first_entry(again, struct io_kiocb, list);
+ list_del(&req->list);
+ refcount_inc(&req->refs);
+ io_queue_async_work(req);
+ } while (!list_empty(again));
+}
+
/*
* Find and free completed poll iocbs
*/
@@ -1750,12 +1762,21 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
{
struct req_batch rb;
struct io_kiocb *req;
+ LIST_HEAD(again);
+
+ /* order with ->result store in io_complete_rw_iopoll() */
+ smp_rmb();
rb.to_free = rb.need_iter = 0;
while (!list_empty(done)) {
int cflags = 0;
req = list_first_entry(done, struct io_kiocb, list);
+ if (READ_ONCE(req->result) == -EAGAIN) {
+ req->iopoll_completed = 0;
+ list_move_tail(&req->list, &again);
+ continue;
+ }
list_del(&req->list);
if (req->flags & REQ_F_BUFFER_SELECTED)
@@ -1773,18 +1794,9 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
if (ctx->flags & IORING_SETUP_SQPOLL)
io_cqring_ev_posted(ctx);
io_free_req_many(ctx, &rb);
-}
-static void io_iopoll_queue(struct list_head *again)
-{
- struct io_kiocb *req;
-
- do {
- req = list_first_entry(again, struct io_kiocb, list);
- list_del(&req->list);
- refcount_inc(&req->refs);
- io_queue_async_work(req);
- } while (!list_empty(again));
+ if (!list_empty(&again))
+ io_iopoll_queue(&again);
}
static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
@@ -1792,7 +1804,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
{
struct io_kiocb *req, *tmp;
LIST_HEAD(done);
- LIST_HEAD(again);
bool spin;
int ret;
@@ -1818,13 +1829,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
if (!list_empty(&done))
break;
- if (req->result == -EAGAIN) {
- list_move_tail(&req->list, &again);
- continue;
- }
- if (!list_empty(&again))
- break;
-
ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
if (ret < 0)
break;
@@ -1837,9 +1841,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
if (!list_empty(&done))
io_iopoll_complete(ctx, nr_events, &done);
- if (!list_empty(&again))
- io_iopoll_queue(&again);
-
return ret;
}
@@ -1990,9 +1991,13 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
if (res != -EAGAIN && res != req->result)
req_set_fail_links(req);
- req->result = res;
- if (res != -EAGAIN)
+
+ WRITE_ONCE(req->result, res);
+ /* order with io_poll_complete() checking ->result */
+ if (res != -EAGAIN) {
+ smp_wmb();
WRITE_ONCE(req->iopoll_completed, 1);
+ }
}
/*