Merge branch 'perf/urgent' into perf/core, to pick up dependent patches and fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 93 insertions, 14 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ceb37ef96bfa..5a8d6e1a9334 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
@@ -4001,6 +3995,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -4012,6 +4085,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 46aaaeae0c8d..1f7e1a692a7a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */