From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>,
[email protected], [email protected]
Subject: [PATCH 2/4] io_uring: handle EAGAIN iopoll
Date: Tue, 23 Jun 2020 01:16:33 +0300 [thread overview]
Message-ID: <d9ab20194c0189c2d585a9e9173a147d156f129c.1592863245.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
req->iopoll() is not necessarily called by a task that submitted a
request. Because of that, it's dangerous to grab_env() and punt async
on -EGAIN, potentially grabbinf another task's mm and corrupting its
memory.
Do resubmit from the submitter task context.
Signed-off-by: Pavel Begunkov <[email protected]>
---
fs/io_uring.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index bb0dfc450db5..595d2bbb31b1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -884,6 +884,8 @@ enum io_mem_account {
ACCT_PINNED,
};
+static void io_complete_rw_common(struct kiocb *kiocb, long res);
+static bool io_rw_reissue(struct io_kiocb *req, long res);
static void io_wq_submit_work(struct io_wq_work **workptr);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
static void io_put_req(struct io_kiocb *req);
@@ -1756,8 +1758,11 @@ static void io_iopoll_queue(struct list_head *again)
do {
req = list_first_entry(again, struct io_kiocb, list);
list_del(&req->list);
- refcount_inc(&req->refs);
- io_queue_async_work(req);
+
+ if (!io_rw_reissue(req, -EAGAIN)) {
+ io_complete_rw_common(&req->rw.kiocb, -EAGAIN);
+ io_put_req(req);
+ }
} while (!list_empty(again));
}
@@ -1930,6 +1935,8 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
*/
if (!(++iters & 7)) {
mutex_unlock(&ctx->uring_lock);
+ if (current->task_works)
+ task_work_run();
mutex_lock(&ctx->uring_lock);
}
@@ -2288,6 +2295,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_complete = io_complete_rw_iopoll;
req->result = 0;
req->iopoll_completed = 0;
+ io_get_req_task(req);
} else {
if (kiocb->ki_flags & IOCB_HIPRI)
return -EINVAL;
--
2.24.0
next prev parent reply other threads:[~2020-06-22 22:18 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-22 22:16 [PATCH 0/4] iopoll fixes + cleanups Pavel Begunkov
2020-06-22 22:16 ` [PATCH 1/4] io_uring: fix hanging iopoll in case of -EAGAIN Pavel Begunkov
2020-06-23 2:07 ` Jens Axboe
2020-06-23 2:18 ` Jens Axboe
2020-06-23 11:57 ` Pavel Begunkov
2020-06-23 19:01 ` Jens Axboe
2020-06-24 16:56 ` Pavel Begunkov
2020-06-22 22:16 ` Pavel Begunkov [this message]
2020-06-30 4:01 ` [PATCH 2/4] io_uring: handle EAGAIN iopoll kernel test robot
2020-06-22 22:16 ` [PATCH 3/4] io-wq: compact io-wq flags numbers Pavel Begunkov
2020-06-22 22:16 ` [PATCH 4/4] io-wq: return next work from ->do_work() directly Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d9ab20194c0189c2d585a9e9173a147d156f129c.1592863245.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox