perf/x86: Push the duration-logging printk() to IRQ context
Calling printk() from NMI context is bad (TM), so move it to IRQ
context.
This also avoids the problem where the printk() time is measured by
the generic NMI duration goo and triggers a second warning.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-75dv35xf6dhhmeb7nq6fua31@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..2067cbb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -231,11 +231,29 @@
#define NR_ACCUMULATED_SAMPLES 128
static DEFINE_PER_CPU(u64, running_sample_length);
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
{
+ u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
u64 avg_local_sample_len;
u64 local_samples_len;
+
+ local_samples_len = __get_cpu_var(running_sample_length);
+ avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+ printk_ratelimited(KERN_WARNING
+ "perf interrupt took too long (%lld > %lld), lowering "
+ "kernel.perf_event_max_sample_rate to %d\n",
+ avg_local_sample_len, allowed_ns,
+ sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+ u64 avg_local_sample_len;
+ u64 local_samples_len;
if (allowed_ns == 0)
return;
@@ -263,13 +281,9 @@
sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
- printk_ratelimited(KERN_WARNING
- "perf samples too long (%lld > %lld), lowering "
- "kernel.perf_event_max_sample_rate to %d\n",
- avg_local_sample_len, allowed_ns,
- sysctl_perf_event_sample_rate);
-
update_perf_cpu_limits();
+
+ irq_work_queue(&perf_duration_work);
}
static atomic64_t perf_event_id;