[PATCH V6 1/6] perf, x86: use the PEBS auto reload mechanism when possible

[Kan Liang <kan.liang@intel.com>]

From: Yan, Zheng <zheng.z.yan@intel.com>

When a fixed period is specified, this patch make perf use the PEBS
auto reload mechanism. This makes normal profiling faster, because
it avoids one costly MSR write in the PMI handler.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c          | 15 +++++++++------
 arch/x86/kernel/cpu/perf_event.h          |  2 +-
 arch/x86/kernel/cpu/perf_event_intel.c    |  8 ++++++--
 arch/x86/kernel/cpu/perf_event_intel_ds.c |  7 +++++++
 4 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87848eb..8cc1153 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1058,13 +1058,16 @@ int x86_perf_event_set_period(struct perf_event *event)
 
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
-	/*
-	 * The hw event starts counting from this event offset,
-	 * mark it to be able to extra future deltas:
-	 */
-	local64_set(&hwc->prev_count, (u64)-left);
+	if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+	    local64_read(&hwc->prev_count) != (u64)-left) {
+		/*
+		 * The hw event starts counting from this event offset,
+		 * mark it to be able to extra future deltas:
+		 */
+		local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	/*
 	 * Due to erratum on certan cpu we need
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 329f035..1290bb6 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -74,7 +74,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_EXCL		0x40 /* HT exclusivity on counter */
 #define PERF_X86_EVENT_DYNAMIC		0x80 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x40 /* grant rdpmc permission */
-
+#define PERF_X86_EVENT_AUTO_RELOAD	0x80 /* use PEBS auto-reload */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9da2400..0a7b5ca 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2305,8 +2305,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if (!event->attr.freq)
+			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ca69ea5..7c6dd8e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -680,6 +680,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
@@ -689,6 +690,12 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
+
+	/* Use auto-reload if possible to save a MSR write in the PMI */
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		ds->pebs_event_reset[hwc->idx] =
+			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	}
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
-- 
1.7.11.7