All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org, Jason Wang <jasowang@redhat.com>,
	John Fastabend <john.fastabend@gmail.com>,
	David Miller <davem@davemloft.net>
Subject: [PATCH net-next 03/12] ptr_ring: READ/WRITE_ONCE for __ptr_ring_empty
Date: Fri, 26 Jan 2018 01:36:29 +0200	[thread overview]
Message-ID: <1516923320-16959-4-git-send-email-mst@redhat.com> (raw)
In-Reply-To: <1516923320-16959-1-git-send-email-mst@redhat.com>

Lockless __ptr_ring_empty requires that consumer head is read and
written at once, atomically. Annotate accordingly to make sure compiler
does it correctly.  Switch locked callers to __ptr_ring_peek which does
not support the lockless operation.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/ptr_ring.h | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 8594c7b..9a72d8f 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -196,7 +196,9 @@ static inline void *__ptr_ring_peek(struct ptr_ring *r)
  */
 static inline bool __ptr_ring_empty(struct ptr_ring *r)
 {
-	return !__ptr_ring_peek(r);
+	if (likely(r->size))
+		return !r->queue[READ_ONCE(r->consumer_head)];
+	return true;
 }
 
 static inline bool ptr_ring_empty(struct ptr_ring *r)
@@ -285,7 +287,8 @@ static inline void __ptr_ring_discard_one(struct ptr_ring *r)
 		consumer_head = 0;
 		r->consumer_tail = 0;
 	}
-	r->consumer_head = consumer_head;
+	/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
+	WRITE_ONCE(r->consumer_head, consumer_head);
 }
 
 static inline void *__ptr_ring_consume(struct ptr_ring *r)
@@ -541,7 +544,9 @@ static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n,
 			goto done;
 		}
 		r->queue[head] = batch[--n];
-		r->consumer_tail = r->consumer_head = head;
+		r->consumer_tail = head;
+		/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
+		WRITE_ONCE(r->consumer_head, head);
 	}
 
 done:
-- 
MST

  parent reply	other threads:[~2018-01-25 23:39 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-25 23:36 [PATCH net-next 00/12] ptr_ring fixes Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 01/12] ptr_ring: keep consumer_head valid at all times Michael S. Tsirkin
2018-01-26  0:11   ` John Fastabend
2018-01-25 23:36 ` [PATCH net-next 02/12] ptr_ring: clean up documentation Michael S. Tsirkin
2018-01-25 23:36 ` Michael S. Tsirkin [this message]
2018-01-26  2:37   ` [PATCH net-next 03/12] ptr_ring: READ/WRITE_ONCE for __ptr_ring_empty Jason Wang
2018-01-26  2:44     ` Michael S. Tsirkin
2018-01-26  3:19       ` Jason Wang
2018-01-26 13:44         ` Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 04/12] tap: fix use-after-free Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 05/12] ptr_ring: disallow lockless __ptr_ring_full Michael S. Tsirkin
2018-01-26  2:38   ` Jason Wang
2018-01-26  2:46     ` Michael S. Tsirkin
2018-01-29  3:36       ` Jason Wang
2018-01-29  4:41         ` Michael S. Tsirkin
2018-01-29  7:09           ` Jason Wang
2018-01-25 23:36 ` [PATCH net-next 06/12] Revert "net: ptr_ring: otherwise safe empty checks can overrun array bounds" Michael S. Tsirkin
2018-01-26  0:12   ` John Fastabend
2018-01-25 23:36 ` [PATCH net-next 07/12] skb_array: use __ptr_ring_empty Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 08/12] ptr_ring: prevent queue load/store tearing Michael S. Tsirkin
2018-01-26  2:38   ` Jason Wang
2018-01-26  2:49     ` Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 09/12] tools/virtio: switch to __ptr_ring_empty Michael S. Tsirkin
2018-01-25 23:36 ` Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 10/12] tools/virtio: more stubs to fix tools build Michael S. Tsirkin
2018-01-25 23:36   ` Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 11/12] tools/virtio: copy READ/WRITE_ONCE Michael S. Tsirkin
2018-01-25 23:36 ` Michael S. Tsirkin
2018-01-25 23:36 ` [PATCH net-next 12/12] tools/virtio: fix smp_mb on x86 Michael S. Tsirkin
2018-01-26  3:56   ` Jason Wang
2018-01-26  3:56     ` Jason Wang
2018-01-26 13:45     ` Michael S. Tsirkin
2018-01-26 13:45     ` Michael S. Tsirkin
2018-01-25 23:36 ` Michael S. Tsirkin
2018-01-26  3:20 ` [PATCH net-next 00/12] ptr_ring fixes Jason Wang
2018-01-29  7:10 ` Jason Wang
2018-01-29 17:03   ` David Miller

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=1516923320-16959-4-git-send-email-mst@redhat.com \
    --to=mst@redhat.com \
    --cc=davem@davemloft.net \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.