From 49c6f4a2ba104ce198c61445edbff78ce1508a65 Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Thu, 10 Feb 2011 10:23:26 +0100 Subject: sched: Fix softirq time accounting Commit: 75e1056f5c57050415b64cb761a3acc35d91f013 upstream Peter Zijlstra found a bug in the way softirq time is accounted in VIRT_CPU_ACCOUNTING on this thread: http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/01366.html The problem is, softirq processing uses local_bh_disable internally. There is no way, later in the flow, to differentiate between whether softirq is being processed or is it just that bh has been disabled. So, a hardirq when bh is disabled results in time being wrongly accounted as softirq. Looking at the code a bit more, the problem exists in !VIRT_CPU_ACCOUNTING as well. As account_system_time() in normal tick based accouting also uses softirq_count, which will be set even when not in softirq with bh disabled. Peter also suggested solution of using 2*SOFTIRQ_OFFSET as irq count for local_bh_{disable,enable} and using just SOFTIRQ_OFFSET while softirq processing. The patch below does that and adds API in_serving_softirq() which returns whether we are currently processing softirq or not. Also changes one of the usages of softirq_count in net/sched/cls_cgroup.c to in_serving_softirq. Looks like many usages of in_softirq really want in_serving_softirq. Those changes can be made individually on a case by case basis. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Peter Zijlstra LKML-Reference: <1286237003-12406-2-git-send-email-venki@google.com> Signed-off-by: Ingo Molnar Signed-off-by: Mike Galbraith Acked-by: Peter Zijlstra Signed-off-by: Greg Kroah-Hartman --- include/linux/hardirq.h | 5 +++++ include/linux/sched.h | 6 +++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 6d527ee82b2..fa20e7673e5 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -64,6 +64,8 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + #ifndef PREEMPT_ACTIVE #define PREEMPT_ACTIVE_BITS 1 #define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) @@ -82,10 +84,13 @@ /* * Are we doing bottom half or hardware interrupt processing? * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) /* * Are we in NMI context? diff --git a/include/linux/sched.h b/include/linux/sched.h index c1b6ab912d5..c43d86bdc90 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2401,9 +2401,9 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_softirq(void); -#define cond_resched_softirq() ({ \ - __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \ - __cond_resched_softirq(); \ +#define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ }) /* -- cgit v1.2.3-18-g5258