1 files changed, 351 insertions, 19 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 50963472ee85..f1926e9f2143 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -243,10 +243,14 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 
 static struct event_constraint intel_icl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
-	INTEL_UEVENT_CONSTRAINT(0x1c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x01c0, 0),	/* INST_RETIRED.PREC_DIST */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
 	INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
 	INTEL_EVENT_CONSTRAINT(0x32, 0xf),	/* SW_PREFETCH_ACCESS.* */
@@ -309,6 +313,12 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
 EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
 	"4", "2");
 
+EVENT_ATTR_STR(slots,			slots,		"event=0x00,umask=0x4");
+EVENT_ATTR_STR(topdown-retiring,	td_retiring,	"event=0x00,umask=0x80");
+EVENT_ATTR_STR(topdown-bad-spec,	td_bad_spec,	"event=0x00,umask=0x81");
+EVENT_ATTR_STR(topdown-fe-bound,	td_fe_bound,	"event=0x00,umask=0x82");
+EVENT_ATTR_STR(topdown-be-bound,	td_be_bound,	"event=0x00,umask=0x83");
+
 static struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(td_slots_issued),
 	EVENT_PTR(td_slots_retired),
@@ -2165,11 +2175,24 @@ static inline void intel_clear_masks(struct perf_event *event, int idx)
 static void intel_pmu_disable_fixed(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
+	int idx = hwc->idx;
 
-	mask = 0xfULL << (idx * 4);
+	if (is_topdown_idx(idx)) {
+		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+		/*
+		 * When there are other active TopDown events,
+		 * don't disable the fixed counter 3.
+		 */
+		if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+			return;
+		idx = INTEL_PMC_IDX_FIXED_SLOTS;
+	}
 
+	intel_clear_masks(event, idx);
+
+	mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4);
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	wrmsrl(hwc->config_base, ctrl_val);
@@ -2180,17 +2203,28 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	if (idx < INTEL_PMC_IDX_FIXED) {
+	switch (idx) {
+	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		intel_clear_masks(event, idx);
 		x86_pmu_disable_event(event);
-	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
-		intel_clear_masks(event, idx);
+		break;
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_disable_fixed(event);
-	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		break;
+	case INTEL_PMC_IDX_FIXED_BTS:
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		return;
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		intel_clear_masks(event, idx);
+		break;
+	default:
+		intel_clear_masks(event, idx);
+		pr_warn("Failed to disable the event with invalid index %d\n",
+			idx);
+		return;
+	}
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2208,10 +2242,189 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_pebs_del(event);
 }
 
+static int icl_set_topdown_event_period(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	s64 left = local64_read(&hwc->period_left);
+
+	/*
+	 * The values in PERF_METRICS MSR are derived from fixed counter 3.
+	 * Software should start both registers, PERF_METRICS and fixed
+	 * counter 3, from zero.
+	 * Clear PERF_METRICS and Fixed counter 3 in initialization.
+	 * After that, both MSRs will be cleared for each read.
+	 * Don't need to clear them again.
+	 */
+	if (left == x86_pmu.max_period) {
+		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
+		wrmsrl(MSR_PERF_METRICS, 0);
+		hwc->saved_slots = 0;
+		hwc->saved_metric = 0;
+	}
+
+	if ((hwc->saved_slots) && is_slots_event(event)) {
+		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
+		wrmsrl(MSR_PERF_METRICS, hwc->saved_metric);
+	}
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx)
+{
+	u32 val;
+
+	/*
+	 * The metric is reported as an 8bit integer fraction
+	 * suming up to 0xff.
+	 * slots-in-metric = (Metric / 0xff) * slots
+	 */
+	val = (metric >> ((idx - INTEL_PMC_IDX_METRIC_BASE) * 8)) & 0xff;
+	return  mul_u64_u32_div(slots, val, 0xff);
+}
+
+static u64 icl_get_topdown_value(struct perf_event *event,
+				       u64 slots, u64 metrics)
+{
+	int idx = event->hw.idx;
+	u64 delta;
+
+	if (is_metric_idx(idx))
+		delta = icl_get_metrics_event_value(metrics, slots, idx);
+	else
+		delta = slots;
+
+	return delta;
+}
+
+static void __icl_update_topdown_event(struct perf_event *event,
+				       u64 slots, u64 metrics,
+				       u64 last_slots, u64 last_metrics)
+{
+	u64 delta, last = 0;
+
+	delta = icl_get_topdown_value(event, slots, metrics);
+	if (last_slots)
+		last = icl_get_topdown_value(event, last_slots, last_metrics);
+
+	/*
+	 * The 8bit integer fraction of metric may be not accurate,
+	 * especially when the changes is very small.
+	 * For example, if only a few bad_spec happens, the fraction
+	 * may be reduced from 1 to 0. If so, the bad_spec event value
+	 * will be 0 which is definitely less than the last value.
+	 * Avoid update event->count for this case.
+	 */
+	if (delta > last) {
+		delta -= last;
+		local64_add(delta, &event->count);
+	}
+}
+
+static void update_saved_topdown_regs(struct perf_event *event,
+				      u64 slots, u64 metrics)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *other;
+	int idx;
+
+	event->hw.saved_slots = slots;
+	event->hw.saved_metric = metrics;
+
+	for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+		if (!is_topdown_idx(idx))
+			continue;
+		other = cpuc->events[idx];
+		other->hw.saved_slots = slots;
+		other->hw.saved_metric = metrics;
+	}
+}
+
+/*
+ * Update all active Topdown events.
+ *
+ * The PERF_METRICS and Fixed counter 3 are read separately. The values may be
+ * modify by a NMI. PMU has to be disabled before calling this function.
+ */
+static u64 icl_update_topdown_event(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *other;
+	u64 slots, metrics;
+	bool reset = true;
+	int idx;
+
+	/* read Fixed counter 3 */
+	rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
+	if (!slots)
+		return 0;
+
+	/* read PERF_METRICS */
+	rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+
+	for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+		if (!is_topdown_idx(idx))
+			continue;
+		other = cpuc->events[idx];
+		__icl_update_topdown_event(other, slots, metrics,
+					   event ? event->hw.saved_slots : 0,
+					   event ? event->hw.saved_metric : 0);
+	}
+
+	/*
+	 * Check and update this event, which may have been cleared
+	 * in active_mask e.g. x86_pmu_stop()
+	 */
+	if (event && !test_bit(event->hw.idx, cpuc->active_mask)) {
+		__icl_update_topdown_event(event, slots, metrics,
+					   event->hw.saved_slots,
+					   event->hw.saved_metric);
+
+		/*
+		 * In x86_pmu_stop(), the event is cleared in active_mask first,
+		 * then drain the delta, which indicates context switch for
+		 * counting.
+		 * Save metric and slots for context switch.
+		 * Don't need to reset the PERF_METRICS and Fixed counter 3.
+		 * Because the values will be restored in next schedule in.
+		 */
+		update_saved_topdown_regs(event, slots, metrics);
+		reset = false;
+	}
+
+	if (reset) {
+		/* The fixed counter 3 has to be written before the PERF_METRICS. */
+		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
+		wrmsrl(MSR_PERF_METRICS, 0);
+		if (event)
+			update_saved_topdown_regs(event, 0, 0);
+	}
+
+	return slots;
+}
+
+static void intel_pmu_read_topdown_event(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/* Only need to call update_topdown_event() once for group read. */
+	if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
+	    !is_slots_event(event))
+		return;
+
+	perf_pmu_disable(event->pmu);
+	x86_pmu.update_topdown_event(event);
+	perf_pmu_enable(event->pmu);
+}
+
 static void intel_pmu_read_event(struct perf_event *event)
 {
 	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 		intel_pmu_auto_reload_read(event);
+	else if (is_topdown_count(event) && x86_pmu.update_topdown_event)
+		intel_pmu_read_topdown_event(event);
 	else
 		x86_perf_event_update(event);
 }
@@ -2219,8 +2432,22 @@ static void intel_pmu_read_event(struct perf_event *event)
 static void intel_pmu_enable_fixed(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask, bits = 0;
+	int idx = hwc->idx;
+
+	if (is_topdown_idx(idx)) {
+		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+		/*
+		 * When there are other active TopDown events,
+		 * don't enable the fixed counter 3 again.
+		 */
+		if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+			return;
+
+		idx = INTEL_PMC_IDX_FIXED_SLOTS;
+	}
+
+	intel_set_masks(event, idx);
 
 	/*
 	 * Enable IRQ generation (0x8), if not PEBS,
@@ -2240,6 +2467,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
 		bits |= 0x4;
 
+	idx -= INTEL_PMC_IDX_FIXED;
 	bits <<= (idx * 4);
 	mask = 0xfULL << (idx * 4);
 
@@ -2262,18 +2490,27 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (idx < INTEL_PMC_IDX_FIXED) {
+	switch (idx) {
+	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		intel_set_masks(event, idx);
 		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
-	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
-		intel_set_masks(event, idx);
+		break;
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
-	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		break;
+	case INTEL_PMC_IDX_FIXED_BTS:
 		if (!__this_cpu_read(cpu_hw_events.enabled))
 			return;
 		intel_pmu_enable_bts(hwc->config);
-	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		break;
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		intel_set_masks(event, idx);
+		break;
+	default:
+		pr_warn("Failed to enable the event with invalid index %d\n",
+			idx);
+	}
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2389,7 +2626,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
-	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+	if (__test_and_clear_bit(GLOBAL_STATUS_BUFFER_OVF_BIT, (unsigned long *)&status)) {
 		u64 pebs_enabled = cpuc->pebs_enabled;
 
 		handled++;
@@ -2410,7 +2647,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	/*
 	 * Intel PT
 	 */
-	if (__test_and_clear_bit(55, (unsigned long *)&status)) {
+	if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
 		handled++;
 		if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() &&
 			perf_guest_cbs->handle_intel_pt_intr))
@@ -2420,6 +2657,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	}
 
 	/*
+	 * Intel Perf mertrics
+	 */
+	if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
+		handled++;
+		if (x86_pmu.update_topdown_event)
+			x86_pmu.update_topdown_event(NULL);
+	}
+
+	/*
 	 * Checkpointed counters can lead to 'spurious' PMIs because the
 	 * rollback caused by the PMI will have cleared the overflow status
 	 * bit. Therefore always force probe these counters.
@@ -3355,6 +3601,56 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
+	/*
+	 * Config Topdown slots and metric events
+	 *
+	 * The slots event on Fixed Counter 3 can support sampling,
+	 * which will be handled normally in x86_perf_event_update().
+	 *
+	 * Metric events don't support sampling and require being paired
+	 * with a slots event as group leader. When the slots event
+	 * is used in a metrics group, it too cannot support sampling.
+	 */
+	if (x86_pmu.intel_cap.perf_metrics && is_topdown_event(event)) {
+		if (event->attr.config1 || event->attr.config2)
+			return -EINVAL;
+
+		/*
+		 * The TopDown metrics events and slots event don't
+		 * support any filters.
+		 */
+		if (event->attr.config & X86_ALL_EVENT_FLAGS)
+			return -EINVAL;
+
+		if (is_metric_event(event)) {
+			struct perf_event *leader = event->group_leader;
+
+			/* The metric events don't support sampling. */
+			if (is_sampling_event(event))
+				return -EINVAL;
+
+			/* The metric events require a slots group leader. */
+			if (!is_slots_event(leader))
+				return -EINVAL;
+
+			/*
+			 * The leader/SLOTS must not be a sampling event for
+			 * metric use; hardware requires it starts at 0 when used
+			 * in conjunction with MSR_PERF_METRICS.
+			 */
+			if (is_sampling_event(leader))
+				return -EINVAL;
+
+			event->event_caps |= PERF_EV_CAP_SIBLING;
+			/*
+			 * Only once we have a METRICs sibling do we
+			 * need TopDown magic.
+			 */
+			leader->hw.flags |= PERF_X86_EVENT_TOPDOWN;
+			event->hw.flags  |= PERF_X86_EVENT_TOPDOWN;
+		}
+	}
+
 	if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
 		return 0;
 
@@ -3787,6 +4083,17 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (x86_pmu.counter_freezing)
 		enable_counter_freeze();
 
+	/* Disable perf metrics if any added CPU doesn't support it. */
+	if (x86_pmu.intel_cap.perf_metrics) {
+		union perf_capabilities perf_cap;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
+		if (!perf_cap.perf_metrics) {
+			x86_pmu.intel_cap.perf_metrics = 0;
+			x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+		}
+	}
+
 	if (!cpuc->shared_regs)
 		return;
 
@@ -4355,6 +4662,15 @@ static struct attribute *icl_events_attrs[] = {
 	NULL,
 };
 
+static struct attribute *icl_td_events_attrs[] = {
+	EVENT_PTR(slots),
+	EVENT_PTR(td_retiring),
+	EVENT_PTR(td_bad_spec),
+	EVENT_PTR(td_fe_bound),
+	EVENT_PTR(td_be_bound),
+	NULL,
+};
+
 static struct attribute *icl_tsx_events_attrs[] = {
 	EVENT_PTR(tx_start),
 	EVENT_PTR(tx_abort),
@@ -4682,7 +4998,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
-		/* fall through */
+		fallthrough;
 
 	case INTEL_FAM6_CORE2_MEROM_L:
 	case INTEL_FAM6_CORE2_PENRYN:
@@ -4830,6 +5146,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ATOM_TREMONT_D:
 	case INTEL_FAM6_ATOM_TREMONT:
+	case INTEL_FAM6_ATOM_TREMONT_L:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -5062,7 +5379,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_SKYLAKE_X:
 		pmem = true;
-		/* fall through */
+		fallthrough;
 	case INTEL_FAM6_SKYLAKE_L:
 	case INTEL_FAM6_SKYLAKE:
 	case INTEL_FAM6_KABYLAKE_L:
@@ -5114,7 +5431,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_ICELAKE_D:
 		pmem = true;
-		/* fall through */
+		fallthrough;
 	case INTEL_FAM6_ICELAKE_L:
 	case INTEL_FAM6_ICELAKE:
 	case INTEL_FAM6_TIGERLAKE_L:
@@ -5139,10 +5456,13 @@ __init int intel_pmu_init(void)
 			hsw_format_attr : nhm_format_attr;
 		extra_skl_attr = skl_format_attr;
 		mem_attr = icl_events_attrs;
+		td_attr = icl_td_events_attrs;
 		tsx_attr = icl_tsx_events_attrs;
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
 		x86_pmu.lbr_pt_coexist = true;
 		intel_pmu_pebs_data_source_skl(pmem);
+		x86_pmu.update_topdown_event = icl_update_topdown_event;
+		x86_pmu.set_topdown_event_period = icl_set_topdown_event_period;
 		pr_cont("Icelake events, ");
 		name = "icelake";
 		break;
@@ -5198,6 +5518,15 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			/*
+			 * Don't extend the topdown slots and metrics
+			 * events to the generic counters.
+			 */
+			if (c->idxmsk64 & INTEL_PMC_MSK_TOPDOWN) {
+				c->weight = hweight64(c->idxmsk64);
+				continue;
+			}
+
 			if (c->cmask == FIXED_EVENT_FLAGS
 			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
@@ -5253,6 +5582,9 @@ __init int intel_pmu_init(void)
 	if (x86_pmu.counter_freezing)
 		x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
 
+	if (x86_pmu.intel_cap.perf_metrics)
+		x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+
 	return 0;
 }