public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: [email protected]
Cc: [email protected], Jens Axboe <[email protected]>
Subject: [PATCH 2/2] io_uring: add flag for disabling provided buffer recycling
Date: Wed, 23 Mar 2022 16:41:31 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

If we need to continue doing this IO, then we don't want a potentially
selected buffer recycled. Add a flag for that.

Set this for recv/recvmsg if they do partial IO.

Signed-off-by: Jens Axboe <[email protected]>
---
 fs/io_uring.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a70de170aea1..88556e654c5a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -783,6 +783,7 @@ enum {
 	REQ_F_SKIP_LINK_CQES_BIT,
 	REQ_F_SINGLE_POLL_BIT,
 	REQ_F_DOUBLE_POLL_BIT,
+	REQ_F_PARTIAL_IO_BIT,
 	/* keep async read/write and isreg together and in order */
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
@@ -845,6 +846,8 @@ enum {
 	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
 	/* double poll may active */
 	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
+	/* request has already done partial IO */
+	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
 };
 
 struct async_poll {
@@ -1392,6 +1395,9 @@ static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 
 	if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
 		return;
+	/* don't recycle if we already did IO to this buffer */
+	if (req->flags & REQ_F_PARTIAL_IO)
+		return;
 
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		mutex_lock(&ctx->uring_lock);
@@ -5477,6 +5483,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 			ret = -EINTR;
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
+			req->flags |= REQ_F_PARTIAL_IO;
 			return io_setup_async_msg(req, kmsg);
 		}
 		req_set_fail(req);
@@ -5546,6 +5553,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
+			req->flags |= REQ_F_PARTIAL_IO;
 			return -EAGAIN;
 		}
 		req_set_fail(req);
-- 
2.35.1


  parent reply	other threads:[~2022-03-23 22:41 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-23 22:41 [PATCHSET v2 0/2] Fix MSG_WAITALL for IORING_OP_RECV/RECVMSG Jens Axboe
2022-03-23 22:41 ` [PATCH 1/2] io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly Jens Axboe
2022-03-24  0:32   ` Stefan Metzmacher
2022-03-24  0:35     ` Jens Axboe
2022-03-23 22:41 ` Jens Axboe [this message]
2022-03-25  3:16 ` [PATCHSET v2 0/2] Fix MSG_WAITALL for IORING_OP_RECV/RECVMSG Constantine Gavrilov
2022-03-25 14:50   ` Jens Axboe
  -- strict thread matches above, loose matches on Subject: below --
2022-03-23 15:39 [PATCHSET " Jens Axboe
2022-03-23 15:39 ` [PATCH 2/2] io_uring: add flag for disabling provided buffer recycling 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 \
    [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