[PATCH v2 10/16] perf/x86: add support for PEBS Precise Store

[Stephane Eranian <eranian@google.com>]

This patch adds support for PEBS Precise Store
which is available on Intel Sandy Bridge and
Ivy Bridge processors.

To use Precise store, the proper PEBS event
must be used: mem_trans_retired:precise_stores.
For the perf tool, the generic mem-stores event
exported via sysfs can be used directly.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 arch/x86/kernel/cpu/perf_event.h          |    5 +++
 arch/x86/kernel/cpu/perf_event_intel.c    |    2 ++
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   49 +++++++++++++++++++++++++++--
 3 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3c5aa72..4e95c90 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -66,6 +66,7 @@ struct event_constraint {
  * struct event_constraint flags
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -242,6 +243,10 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
 
+#define INTEL_PST_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
+
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index cbfb252..4176be3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -150,6 +150,7 @@ EVENT_ATTR(ref-cycles,			REF_CPU_CYCLES		);
 
 EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
 
 struct attribute *nhm_events_attrs[] = {
 	EVENT_PTR(CPU_CYCLES),
@@ -178,6 +179,7 @@ struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(STALLED_CYCLES_BACKEND),
 	EVENT_PTR(REF_CPU_CYCLES),
 	EVENT_PTR(mem_ld_snb),
+	EVENT_PTR(mem_st_snb),
 	NULL,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 759b0c0..ed0ca3e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -69,6 +69,44 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL,UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+static u64 precise_store_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
+
+	dse.val = status;
+
+	/*
+	 * bit 4: TLB access
+	 * 1 = stored missed 2nd level TLB
+	 *
+	 * so it either hit the walker or the OS
+	 * otherwise hit 2nd level TLB
+	 */
+	if (dse.st_stlb_miss)
+		val |= P(TLB, MISS);
+	else
+		val |= P(TLB, HIT);
+
+	/*
+	 * bit 0: hit L1 data cache
+	 * if not set, then all we know is that
+	 * it missed L1D
+	 */
+	if (dse.st_l1d_hit)
+		val |= P(LVL, HIT);
+	else
+		val |= P(LVL, MISS);
+
+	/*
+	 * bit 5: Locked prefix
+	 */
+	if (dse.st_locked)
+		val |= P(LOCK, LOCKED);
+
+	return val;
+}
+
 static u64 load_latency_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -486,6 +524,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -500,6 +539,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -537,6 +577,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
+		cpuc->pebs_enabled |= 1ULL << 63;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -657,12 +699,13 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	struct perf_sample_data data;
 	struct pt_regs regs;
 	u64 sample_type;
-	int fll;
+	int fll, fst;
 
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
 	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
+	fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST;
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
@@ -672,7 +715,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	/*
 	 * if PEBS-LL or PreciseStore
 	 */
-	if (fll) {
+	if (fll || fst) {
 		if (sample_type & PERF_SAMPLE_ADDR)
 			data.addr = pebs->dla;
 
@@ -688,6 +731,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		if (sample_type & PERF_SAMPLE_DSRC) {
 			if (fll)
 				data.dsrc.val = load_latency_data(pebs->dse);
+			else
+				data.dsrc.val = precise_store_data(pebs->dse);
 		}
 	}
 
-- 
1.7.9.5