summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorVenkatesh Pallipadi <venki@google.com>2011-02-10 10:23:26 +0100
committerGreg Kroah-Hartman <gregkh@suse.de>2011-02-17 15:37:24 -0800
commit49c6f4a2ba104ce198c61445edbff78ce1508a65 (patch)
tree87db2d6d963ca83b7699e98b06a593697118548b /kernel
parent1d3d2371a682f9905153bf28cc21ee1d2184bb44 (diff)
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 <venki@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1286237003-12406-2-git-send-email-venki@google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Mike Galbraith <efault@gmx.de> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched.c2
-rw-r--r--kernel/softirq.c51
2 files changed, 35 insertions, 18 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index 7619287a44f7..fc1840961145 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5178,7 +5178,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
tmp = cputime_to_cputime64(cputime);
if (hardirq_count() - hardirq_offset)
cpustat->irq = cputime64_add(cpustat->irq, tmp);
- else if (softirq_count())
+ else if (in_serving_softirq())
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
else
cpustat->system = cputime64_add(cpustat->system, tmp);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f8749e5216e0..0ed83430b077 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -77,11 +77,21 @@ void wakeup_softirqd(void)
}
/*
+ * preempt_count and SOFTIRQ_OFFSET usage:
+ * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
+ * softirq processing.
+ * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * on local_bh_disable or local_bh_enable.
+ * This lets us distinguish between whether we are currently processing
+ * softirq and whether we just have bh disabled.
+ */
+
+/*
* This one is for softirq.c-internal use,
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip)
+static void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -95,32 +105,43 @@ static void __local_bh_disable(unsigned long ip)
* We must manually increment preempt_count here and manually
* call the trace_preempt_off later.
*/
- preempt_count() += SOFTIRQ_OFFSET;
+ preempt_count() += cnt;
/*
* Were softirqs turned off above:
*/
- if (softirq_count() == SOFTIRQ_OFFSET)
+ if (softirq_count() == cnt)
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
- if (preempt_count() == SOFTIRQ_OFFSET)
+ if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip)
+static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
- add_preempt_count(SOFTIRQ_OFFSET);
+ add_preempt_count(cnt);
barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */
void local_bh_disable(void)
{
- __local_bh_disable((unsigned long)__builtin_return_address(0));
+ __local_bh_disable((unsigned long)__builtin_return_address(0),
+ SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(local_bh_disable);
+static void __local_bh_enable(unsigned int cnt)
+{
+ WARN_ON_ONCE(in_irq());
+ WARN_ON_ONCE(!irqs_disabled());
+
+ if (softirq_count() == cnt)
+ trace_softirqs_on((unsigned long)__builtin_return_address(0));
+ sub_preempt_count(cnt);
+}
+
/*
* Special-case - softirqs can safely be enabled in
* cond_resched_softirq(), or by __do_softirq(),
@@ -128,12 +149,7 @@ EXPORT_SYMBOL(local_bh_disable);
*/
void _local_bh_enable(void)
{
- WARN_ON_ONCE(in_irq());
- WARN_ON_ONCE(!irqs_disabled());
-
- if (softirq_count() == SOFTIRQ_OFFSET)
- trace_softirqs_on((unsigned long)__builtin_return_address(0));
- sub_preempt_count(SOFTIRQ_OFFSET);
+ __local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
@@ -147,13 +163,13 @@ static inline void _local_bh_enable_ip(unsigned long ip)
/*
* Are softirqs going to be turned on now:
*/
- if (softirq_count() == SOFTIRQ_OFFSET)
+ if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
trace_softirqs_on(ip);
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
- sub_preempt_count(SOFTIRQ_OFFSET - 1);
+ sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
@@ -198,7 +214,8 @@ asmlinkage void __do_softirq(void)
pending = local_softirq_pending();
account_system_vtime(current);
- __local_bh_disable((unsigned long)__builtin_return_address(0));
+ __local_bh_disable((unsigned long)__builtin_return_address(0),
+ SOFTIRQ_OFFSET);
lockdep_softirq_enter();
cpu = smp_processor_id();
@@ -245,7 +262,7 @@ restart:
lockdep_softirq_exit();
account_system_vtime(current);
- _local_bh_enable();
+ __local_bh_enable(SOFTIRQ_OFFSET);
}
#ifndef __ARCH_HAS_DO_SOFTIRQ