Patchwork net-rps: Fix brokeness causing OOO packets

login
register
mail settings
Submitter Eric Dumazet
Date Nov. 16, 2012, 7:04 p.m.
Message ID <1353092655.10798.44.camel@edumazet-glaptop>
Download mbox | patch
Permalink /patch/199716/
State Accepted
Delegated to: David Miller
Headers show

Comments

Eric Dumazet - Nov. 16, 2012, 7:04 p.m.
From: Tom Herbert <therbert@google.com>

In commit c445477d74ab3779 which adds aRFS to the kernel, the CPU
selected for RFS is not set correctly when CPU is changing.
This is causing OOO packets and probably other issues.

Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Ben Hutchings <bhutchings@solarflare.com>
---
 net/core/dev.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
David Miller - Nov. 16, 2012, 7:36 p.m.
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 16 Nov 2012 11:04:15 -0800

> From: Tom Herbert <therbert@google.com>
> 
> In commit c445477d74ab3779 which adds aRFS to the kernel, the CPU
> selected for RFS is not set correctly when CPU is changing.
> This is causing OOO packets and probably other issues.
> 
> Signed-off-by: Tom Herbert <therbert@google.com>
> Acked-by: Eric Dumazet <edumazet@google.com>
> Acked-by: Ben Hutchings <bhutchings@solarflare.com>

Applied and queued up for -stable, thanks everyone.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/net/core/dev.c b/net/core/dev.c
index bda6d00..c0946cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2818,8 +2818,10 @@  static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (unlikely(tcpu != next_cpu) &&
 		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
-		      rflow->last_qtail)) >= 0))
+		      rflow->last_qtail)) >= 0)) {
+			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+		}
 
 		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
 			*rflowp = rflow;