From: Jens Axboe axboe@kernel.dk
commit 2b2ed9750fc9d040b9f6d076afcef6f00b6f1f7c upstream.
We currently assume that submissions from the sqthread are successful, and if IO polling is enabled, we use that value for knowing how many completions to look for. But if we overflowed the CQ ring or some requests simply got errored and already completed, they won't be available for polling.
For the case of IO polling and SQTHREAD usage, look at the pending poll list. If it ever hits empty then we know that we don't have anymore pollable requests inflight. For that case, simply reset the inflight count to zero.
Reported-by: Pavel Begunkov asml.silence@gmail.com Reviewed-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- fs/io_uring.c | 44 ++++++++++++++++++++++++++++++++------------ 1 file changed, 32 insertions(+), 12 deletions(-)
--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -816,19 +816,11 @@ static void io_iopoll_reap_events(struct mutex_unlock(&ctx->uring_lock); }
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) +static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) { - int iters, ret = 0; + int iters = 0, ret = 0;
- /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - - iters = 0; do { int tmin = 0;
@@ -864,6 +856,21 @@ static int io_iopoll_check(struct io_rin ret = 0; } while (min && !*nr_events && !need_resched());
+ return ret; +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) +{ + int ret; + + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); + ret = __io_iopoll_check(ctx, nr_events, min); mutex_unlock(&ctx->uring_lock); return ret; } @@ -2327,7 +2334,20 @@ static int io_sq_thread(void *data) unsigned nr_events = 0;
if (ctx->flags & IORING_SETUP_IOPOLL) { - io_iopoll_check(ctx, &nr_events, 0); + /* + * inflight is the count of the maximum possible + * entries we submitted, but it can be smaller + * if we dropped some of them. If we don't have + * poll entries available, then we know that we + * have nothing left to poll for. Reset the + * inflight count to zero in that case. + */ + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->poll_list)) + __io_iopoll_check(ctx, &nr_events, 0); + else + inflight = 0; + mutex_unlock(&ctx->uring_lock); } else { /* * Normal IO, just pretend everything completed.