io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: io-uring@vger.kernel.org
Cc: Jackie Liu <liuyun01@kylinos.cn>
Subject: [PATCH] io_uring: fix race with shadow drain deferrals
Date: Wed, 20 Nov 2019 16:07:41 -0700	[thread overview]
Message-ID: <27c153ee-cfc8-3251-a874-df85a033429a@kernel.dk> (raw)

When we go and queue requests with drain, we check if we need to defer
based on sequence. This is done safely under the lock, but then we drop
the lock before actually inserting the shadow. If the original request
is found on the deferred list by another completion in the mean time,
it could have been started AND completed by the time we insert the
shadow, which will stall the queue.

After re-grabbing the completion lock, check if the original request is
still in the deferred list. If it isn't, then we know that someone else
already found and issued it. If that happened, then our job is done, we
can simply free the shadow.

Cc: Jackie Liu <liuyun01@kylinos.cn>
Fixes: 4fe2c963154c ("io_uring: add support for link with drain")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6175e2e195c0..6fb25ae53817 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2973,6 +2973,7 @@ static void io_queue_link_head(struct io_kiocb *req, struct io_kiocb *shadow)
 	int ret;
 	int need_submit = false;
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_kiocb *tmp;
 
 	if (unlikely(req->flags & REQ_F_FAIL_LINK)) {
 		ret = -ECANCELED;
@@ -3011,8 +3012,30 @@ static void io_queue_link_head(struct io_kiocb *req, struct io_kiocb *shadow)
 
 	/* Insert shadow req to defer_list, blocking next IOs */
 	spin_lock_irq(&ctx->completion_lock);
-	trace_io_uring_defer(ctx, shadow, true);
-	list_add_tail(&shadow->list, &ctx->defer_list);
+	if (ret) {
+		/*
+		 * We dropped the lock since deciding we needed to defer this
+		 * request. We must re-check under the lock, if it's now gone
+		 * from the list, that means that another completion came in
+		 * and submitted it since we decided we needed to defer. If
+		 * that's the case, simply drop the shadow, there's nothing
+		 * more we need to do here.
+		 */
+		list_for_each_entry(tmp, &ctx->defer_list, list) {
+			if (tmp == req)
+				break;
+		}
+		if (tmp != req) {
+			__io_free_req(shadow);
+			shadow = NULL;
+		}
+	}
+	if (shadow) {
+		trace_io_uring_defer(ctx, shadow, true);
+		list_add_tail(&shadow->list, &ctx->defer_list);
+	} else {
+		need_submit = false;
+	}
 	spin_unlock_irq(&ctx->completion_lock);
 
 	if (need_submit)

-- 
Jens Axboe


             reply	other threads:[~2019-11-20 23:07 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-20 23:07 Jens Axboe [this message]
2019-11-20 23:58 ` [PATCH] io_uring: fix race with shadow drain deferrals Jens Axboe
2019-11-21  1:32   ` Jackie Liu
2019-11-21  1:35     ` Jackie Liu
2019-11-21  1:40       ` Jens Axboe
2019-11-21  1:49         ` Jens Axboe
2019-11-21  1:57           ` Jackie Liu
2019-11-20 23:14             ` Jens Axboe
     [not found]               ` <57EF3B0C-A6D3-45D5-A689-B8090F750C1E@kylinos.cn>
2019-11-20 23:03                 ` Jens Axboe
2019-11-21  8:54           ` [PATCH] io_uring: drain next sqe instead of shadowing Pavel Begunkov
     [not found]             ` <A12FD0FF-3C4F-46BE-8ABB-AA732002A9CA@kylinos.cn>
2019-11-21  9:43               ` Pavel Begunkov
     [not found]                 ` <5dd68282.1c69fb81.110a.43a7SMTPIN_ADDED_BROKEN@mx.google.com>
2019-11-21 12:40                   ` Pavel Begunkov
     [not found]                     ` <5dd68820.1c69fb81.64e0b.4340SMTPIN_ADDED_BROKEN@mx.google.com>
2019-11-21 13:47                       ` Jens Axboe
     [not found]                         ` <5dd69c7f.1c69fb81.8868.e3c2SMTPIN_ADDED_BROKEN@mx.google.com>
2019-11-21 13:54                           ` Jens Axboe
     [not found]                         ` <5dd69c43.1c69fb81.6589a.b4f1SMTPIN_ADDED_BROKEN@mx.google.com>
2019-11-21 14:28                           ` Pavel Begunkov
2019-11-21 13:53                             ` Jens Axboe
2019-11-21 15:23                               ` Pavel Begunkov
2019-11-21 13:50                                 ` Jens Axboe
2019-11-21  1:39     ` [PATCH] io_uring: fix race with shadow drain deferrals Jens Axboe

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=27c153ee-cfc8-3251-a874-df85a033429a@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    --cc=liuyun01@kylinos.cn \
    /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;
as well as URLs for NNTP newsgroup(s).