IOPOLL users should care more about getting completions for requests
they submitted, but not in "device did/completed something". Currently,
io_do_iopoll() may return a positive number, which will instruct
io_iopoll_check() to break the loop and end the syscall, even if there
is not enough CQEs or none at all.
Don't return positive numbers, so io_iopoll_check() exits only when it
gets an actual error, need reschedule or got enough CQEs.
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
fs/io_uring.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6dca33fdb012..87d9a5d54464 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2276,7 +2276,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
struct io_kiocb *req, *tmp;
LIST_HEAD(done);
bool spin;
- int ret;
/*
* Only spin for completions if we don't have multiple devices hanging
@@ -2284,9 +2283,9 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
*/
spin = !ctx->poll_multi_queue && *nr_events < min;
- ret = 0;
list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) {
struct kiocb *kiocb = &req->rw.kiocb;
+ int ret;
/*
* Move completed and retryable entries to our local lists.
@@ -2301,22 +2300,20 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
break;
ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
- if (ret < 0)
- break;
+ if (unlikely(ret < 0))
+ return ret;
+ else if (ret)
+ spin = false;
/* iopoll may have completed current req */
if (READ_ONCE(req->iopoll_completed))
list_move_tail(&req->inflight_entry, &done);
-
- if (ret && spin)
- spin = false;
- ret = 0;
}
if (!list_empty(&done))
io_iopoll_complete(ctx, nr_events, &done, resubmit);
- return ret;
+ return 0;
}
/*
--
2.32.0
