netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
To: davem@davemloft.net
Cc: Alexander Duyck <alexander.h.duyck@intel.com>,
	netdev@vger.kernel.org, gospo@redhat.com, sassmann@redhat.com,
	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Subject: [net-next 05/14] net: Add memory barriers to prevent possible race in byte queue limits
Date: Mon, 12 Mar 2012 21:03:43 -0700	[thread overview]
Message-ID: <1331611432-30109-6-git-send-email-jeffrey.t.kirsher@intel.com> (raw)
In-Reply-To: <1331611432-30109-1-git-send-email-jeffrey.t.kirsher@intel.com>

From: Alexander Duyck <alexander.h.duyck@intel.com>

This change adds a memory barrier to the byte queue limit code to address a
possible race as has been seen in the past with the
netif_stop_queue/netif_wake_queue logic.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Stephen Ko <stephen.s.ko@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h |   49 ++++++++++++++++++++++++++++++--------------
 1 files changed, 33 insertions(+), 16 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4bf314f..4535a4e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1899,12 +1899,22 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 {
 #ifdef CONFIG_BQL
 	dql_queued(&dev_queue->dql, bytes);
-	if (unlikely(dql_avail(&dev_queue->dql) < 0)) {
-		set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
-		if (unlikely(dql_avail(&dev_queue->dql) >= 0))
-			clear_bit(__QUEUE_STATE_STACK_XOFF,
-			    &dev_queue->state);
-	}
+
+	if (likely(dql_avail(&dev_queue->dql) >= 0))
+		return;
+
+	set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
+
+	/*
+	 * The XOFF flag must be set before checking the dql_avail below,
+	 * because in netdev_tx_completed_queue we update the dql_completed
+	 * before checking the XOFF flag.
+	 */
+	smp_mb();
+
+	/* check again in case another CPU has just made room avail */
+	if (unlikely(dql_avail(&dev_queue->dql) >= 0))
+		clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
 #endif
 }
 
@@ -1917,16 +1927,23 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 					     unsigned pkts, unsigned bytes)
 {
 #ifdef CONFIG_BQL
-	if (likely(bytes)) {
-		dql_completed(&dev_queue->dql, bytes);
-		if (unlikely(test_bit(__QUEUE_STATE_STACK_XOFF,
-		    &dev_queue->state) &&
-		    dql_avail(&dev_queue->dql) >= 0)) {
-			if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF,
-			     &dev_queue->state))
-				netif_schedule_queue(dev_queue);
-		}
-	}
+	if (unlikely(!bytes))
+		return;
+
+	dql_completed(&dev_queue->dql, bytes);
+
+	/*
+	 * Without the memory barrier there is a small possiblity that
+	 * netdev_tx_sent_queue will miss the update and cause the queue to
+	 * be stopped forever
+	 */
+	smp_mb();
+
+	if (dql_avail(&dev_queue->dql) < 0)
+		return;
+
+	if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state))
+		netif_schedule_queue(dev_queue);
 #endif
 }
 
-- 
1.7.7.6

  parent reply	other threads:[~2012-03-13  4:03 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-03-13  4:03 [net-next 00/14][pull request] Intel Wired LAN Driver Updates Jeff Kirsher
2012-03-13  4:03 ` [net-next 01/14] igb: fix ethtool offline test Jeff Kirsher
2012-03-13  4:03 ` [net-next 02/14] ixgbe: remove tie between NAPI work limits and interrupt moderation Jeff Kirsher
2012-03-13  4:03 ` [net-next 03/14] ixgbe: add support for byte queue limits Jeff Kirsher
2012-03-13  4:03 ` [net-next 04/14] net: Fix issue with netdev_tx_reset_queue not resetting queue from XOFF state Jeff Kirsher
2012-04-20 21:19   ` Tom Herbert
2012-04-20 21:31     ` John Fastabend
2012-04-21  3:24       ` Alexander Duyck
2012-04-21  6:01         ` Tom Herbert
2012-04-21 16:27           ` John Fastabend
2012-04-21 20:18             ` David Miller
2012-04-23  3:21               ` John Fastabend
2012-03-13  4:03 ` Jeff Kirsher [this message]
2012-03-13  4:03 ` [net-next 06/14] ixgbe: Do no clear Tx status bits since eop_desc provides enough info Jeff Kirsher
2012-03-13  4:03 ` [net-next 07/14] ixgbe: Reorder adapter contents for better cache utilization Jeff Kirsher
2012-03-13  4:03 ` [net-next 08/14] ixgbe: Address issues with Tx WHTRESH value not being set correctly Jeff Kirsher
2012-03-13  4:03 ` [net-next 09/14] ixgbe: Correct Adaptive Interrupt Moderation so that it will change values Jeff Kirsher
2012-03-13  4:03 ` [net-next 10/14] ixgbe: Default to queue pairs when number of queues is less than CPUs Jeff Kirsher
2012-03-13  4:03 ` [net-next 11/14] ixgbe: Drop unnecessary napi_schedule_prep and spare blank line from ixgbe_intr Jeff Kirsher
2012-03-13  4:03 ` [net-next 12/14] ixgbe: Allocate rings as part of the q_vector Jeff Kirsher
2012-03-13  4:03 ` [net-next 13/14] ixgbe: Add iterator for cycling through rings on a q_vector Jeff Kirsher
2012-03-13  4:03 ` [net-next 14/14] ixgbe: Simplify logic for ethtool loopback frame creation and testing Jeff Kirsher
2012-03-13  5:55 ` [net-next 00/14][pull request] Intel Wired LAN Driver Updates 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=1331611432-30109-6-git-send-email-jeffrey.t.kirsher@intel.com \
    --to=jeffrey.t.kirsher@intel.com \
    --cc=alexander.h.duyck@intel.com \
    --cc=davem@davemloft.net \
    --cc=gospo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=sassmann@redhat.com \
    /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).