[PATCH 2/2] perf/x86/intel, watchdog: Switch NMI watchdog to ref cycles on x86

[kan . liang]

From: Kan Liang <Kan.liang@xxxxxxxxx>

The NMI watchdog uses either the fixed cycles or a generic cycles
counter. This causes a lot of conflicts with users of the PMU who want
to run a full group including the cycles fixed counter, for example the
--topdown support recently added to perf stat. The code needs to fall
back to not use groups, which can cause measurement inaccuracy due to
multiplexing errors.

This patch switches the NMI watchdog to use reference cycles on Intel
systems. This is actually more accurate than cycles, because cycles can
tick faster than the measured CPU Frequency due to Turbo mode.

The ref cycles always tick at their frequency, or slower when the system
is idling. That means the NMI watchdog can never expire too early,
unlike with cycles.

The reference cycles tick roughly at the frequency of the TSC, so the
same period computation can be used.

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---

This patch was once merged, but reverted later.
Because ref-cycles can not be used anymore when watchdog is enabled.
The commit is 44530d588e142a96cf0cd345a7cb8911c4f88720

The patch 1/2 has extended the ref-cycles to GP counter. The concern
should be gone.

Rebased the patch and repost.


 arch/x86/kernel/apic/hw_nmi.c | 8 ++++++++
 include/linux/nmi.h           | 1 +
 kernel/watchdog_hld.c         | 7 +++++++
 3 files changed, 16 insertions(+)

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c73c9fb..acd21dc 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -18,8 +18,16 @@
 #include <linux/nmi.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/perf_event.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+int hw_nmi_get_event(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		return PERF_COUNT_HW_REF_CPU_CYCLES;
+	return PERF_COUNT_HW_CPU_CYCLES;
+}
+
 u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
 	return (u64)(cpu_khz) * 1000 * watchdog_thresh;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index aa3cd08..b2fa444 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -141,6 +141,7 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
+int hw_nmi_get_event(void);
 extern int nmi_watchdog_enabled;
 extern int soft_watchdog_enabled;
 extern int watchdog_user_enabled;
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 54a427d..f899766 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -70,6 +70,12 @@ void touch_nmi_watchdog(void)
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
 
+/* Can be overridden by architecture */
+__weak int hw_nmi_get_event(void)
+{
+	return PERF_COUNT_HW_CPU_CYCLES;
+}
+
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES,
@@ -165,6 +171,7 @@ int watchdog_nmi_enable(unsigned int cpu)
 
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
+	wd_attr->config = hw_nmi_get_event();
 
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
-- 
2.7.4