diff options
author | Priyanka Jain <Priyanka.Jain@freescale.com> | 2012-05-17 09:35:11 +0530 |
---|---|---|
committer | Steven Rostedt <rostedt@rostedt.homelinux.com> | 2012-10-26 14:42:50 -0400 |
commit | f93560c2eebf395e3e18b2200a2746b7df9bb29d (patch) | |
tree | 0f6d7e5b97b19d59a351061f3c0e205d91d4019c | |
parent | 338a46a8c428eb6e3f7d71c7d7fdaa8226bf39a8 (diff) |
net,RT:REmove preemption disabling in netif_rx()
1)enqueue_to_backlog() (called from netif_rx) should be
bind to a particluar CPU. This can be achieved by
disabling migration. No need to disable preemption
2)Fixes crash "BUG: scheduling while atomic: ksoftirqd"
in case of RT.
If preemption is disabled, enqueue_to_backog() is called
in atomic context. And if backlog exceeds its count,
kfree_skb() is called. But in RT, kfree_skb() might
gets scheduled out, so it expects non atomic context.
3)When CONFIG_PREEMPT_RT_FULL is not defined,
migrate_enable(), migrate_disable() maps to
preempt_enable() and preempt_disable(), so no
change in functionality in case of non-RT.
-Replace preempt_enable(), preempt_disable() with
migrate_enable(), migrate_disable() respectively
-Replace get_cpu(), put_cpu() with get_cpu_light(),
put_cpu_light() respectively
Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com>
Acked-by: Rajan Srivastava <Rajan.Srivastava@freescale.com>
Cc: <rostedt@goodmis.orgn>
Link: http://lkml.kernel.org/r/1337227511-2271-1-git-send-email-Priyanka.Jain@freescale.com
Cc: stable-rt@vger.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
-rw-r--r-- | net/core/dev.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 875cf67112f1..338608df7116 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2881,7 +2881,7 @@ int netif_rx(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); + migrate_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -2891,13 +2891,13 @@ int netif_rx(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); + migrate_enable(); } #else { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); + put_cpu_light(); } #endif return ret; |