Add top down metrics to perf stat

index b597bcc..0d228d1 100644
@@ -284,13 +284,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int ret = 0;
 
 	event_dir = opendir(dir);
 	if (!event_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(event_dir))) {
+	while ((evt_ent = readdir(event_dir))) {
 		char path[PATH_MAX];
 		char *name = evt_ent->d_name;
 		FILE *file;

@@ -306,17 +305,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
-		ret = -EINVAL;
 		file = fopen(path, "r");
-		if (!file)
-			break;
+		if (!file) {
+			pr_warning("Cannot open %s\n", path);
+			continue;
+		}
 
-		ret = perf_pmu__new_alias(head, dir, name, file);
+		if (perf_pmu__new_alias(head, dir, name, file) < 0)
+			pr_warning("Cannot set up %s\n", name);
 		fclose(file);
 	}
 
 	closedir(event_dir);
-	return ret;
+	return 0;
 }
 
 /*

index 8e75434..239a666 100644
@@ -114,6 +114,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			aggr_per_core;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

index 4f7b0ef..9dff8c5 100644
@@ -1027,6 +1027,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
 		evsel->per_pkg = info.per_pkg;
+		evsel->aggr_per_core = info.aggr_per_core;
 		evsel->snapshot = info.snapshot;
 	}
 

index 0d228d1..c5eb1ce 100644
@@ -189,6 +189,24 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
 	return 0;
 }
 
+static void
+perf_pmu__parse_aggr_per_core(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	FILE *f;
+	int flag;
+
+	snprintf(path, PATH_MAX, "%s/%s.aggr-per-core", dir, name);
+
+	f = fopen(path, "r");
+	if (f) {
+		if (fscanf(f, "%d", &flag) == 1)
+			alias->aggr_per_core = flag != 0;
+		fclose(f);
+	}
+}
+
+
 static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 				    char *dir, char *name)
 {

@@ -238,6 +256,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		perf_pmu__parse_scale(alias, dir, name);
 		perf_pmu__parse_per_pkg(alias, dir, name);
 		perf_pmu__parse_snapshot(alias, dir, name);
+		perf_pmu__parse_aggr_per_core(alias, dir, name);
 	}
 
 	list_add_tail(&alias->list, list);

@@ -272,6 +291,8 @@ static inline bool pmu_alias_info_file(char *name)
 		return true;
 	if (len > 9 && !strcmp(name + len - 9, ".snapshot"))
 		return true;
+	if (len > 14 && !strcmp(name + len - 14, ".aggr-per-core"))
+		return true;
 
 	return false;
 }

@@ -851,6 +872,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	int ret;
 
 	info->per_pkg = false;
+	info->aggr_per_core = false;
 
 	/*
 	 * Mark unit and scale as not set

@@ -874,6 +896,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 
 		if (alias->per_pkg)
 			info->per_pkg = true;
+		if (alias->aggr_per_core)
+			info->aggr_per_core = true;
 
 		list_del(&term->list);
 		free(term);

index 5d7e844..e9dde6c 100644
@@ -32,6 +32,7 @@ struct perf_pmu_info {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	bool aggr_per_core;
 };
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */

@@ -44,6 +45,7 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	bool aggr_per_core;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);

index 5a02870..d20cf3e 100644
@@ -2086,6 +2086,7 @@ static int __cmd_report(int argc, const char **argv)
 
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	struct perf_evsel *counter;
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
 		NULL

@@ -2232,6 +2233,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (add_default_attributes())
 		goto out;
 
+	evlist__for_each (evsel_list, counter) {
+		/* Enable per core mode if only a single event requires it. */
+		if (counter->aggr_per_core) {
+			if (stat_config.aggr_mode != AGGR_GLOBAL &&
+			    stat_config.aggr_mode != AGGR_CORE) {
+				pr_err("per core event configuration requires per core mode\n");
+				goto out;
+			}
+			stat_config.aggr_mode = AGGR_CORE;
+			if (nr_cgroups || !target__has_cpu(&target)) {
+				pr_err("per core event configuration requires system-wide mode (-a)\n");
+				goto out;
+			}
+			break;
+		}
+	}
+
 	target__validate(&target);
 
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {

index d20cf3e..dca4f0d 100644
@@ -66,6 +66,7 @@
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
+#include <math.h>
 
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"

@@ -967,12 +968,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	const char *fmt;
 
 	if (csv_output) {
-		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
 	} else {
 		if (big_num)
-			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
 		else
-			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
 	}
 
 	aggr_printout(evsel, id, nr);

index 2f901d1..f3217b3 100644
@@ -307,6 +307,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat_evsel *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
+	u64 val;
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;

@@ -337,7 +338,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	perf_stat__update_shadow_stats(counter, count, 0);
+	val = counter->scale * *count;
+	perf_stat__update_shadow_stats(counter, &val, 0);
 
 	return 0;
 }

new file mode 100644
index 0000000..f3039b5
@@ -0,0 +1,27 @@
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/group.h"
+
+/*
+ * Check whether we can use a group for top down.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool check_group(bool *warn)
+{
+	int n;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+		return false;
+	if (n > 0) {
+		*warn = true;
+		return false;
+	}
+	return true;
+}
+
+void group_warn(void)
+{
+	fprintf(stderr,
+		"nmi_watchdog enabled with topdown. May give wrong results.\n"
+		"Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}

171 lines not on this page · raw message

new file mode 100644
index 0000000..daad3ff
@@ -0,0 +1,7 @@
+#ifndef GROUP_H
+#define GROUP_H 1
+
+bool check_group(bool *warn);
+void group_warn(void);
+
+#endif

index 4d8f185..4b853c3 100644
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,

@@ -28,6 +29,11 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
 
 struct stats walltime_nsecs_stats;
 

@@ -68,6 +74,11 @@ void perf_stat__reset_shadow_stats(void)
 		sizeof(runtime_transaction_stats));
 	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
 	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+	memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots));
+	memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired));
+	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
+	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
+	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
 }
 
 /*

@@ -90,6 +101,16 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
 		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
+		update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
+		update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
+		update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
+		update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
+		update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))

@@ -289,6 +310,104 @@ static void print_ll_cache_misses(int cpu,
 	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
+/*
+ * High level "TopDown" CPU core pipe line bottleneck break down.
+ *
+ * Basic concept following
+ * Yasin, A Top Down Method for Performance analysis and Counter architecture
+ * ISPASS14
+ *
+ * The CPU pipeline is divided into 4 areas that can be bottlenecks:
+ *
+ * Frontend -> Backend -> Retiring
+ * BadSpeculation in addition means out of order execution that is thrown away
+ * (for example branch mispredictions)
+ * Frontend is instruction decoding.
+ * Backend is execution, like computation and accessing data in memory
+ * Retiring is good execution that is not directly bottlenecked
+ *
+ * The formulas are computed in slots.
+ * A slot is an entry in the pipeline each for the pipeline width
+ * (for example a 4-wide pipeline has 4 slots for each cycle)
+ *
+ * Formulas:
+ * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) /
+ *			TotalSlots
+ * Retiring = SlotsRetired / TotalSlots
+ * FrontendBound = FetchBubbles / TotalSlots
+ * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound
+ *
+ * The kernel provides the mapping to the low level CPU events and any scaling
+ * needed for the CPU pipeline width, for example:
+ *
+ * TotalSlots = Cycles * 4
+ *
+ * The scaling factor is communicated in the sysfs unit.
+ *
+ * In some cases the CPU may not be able to measure all the formulas due to
+ * missing events. In this case multiple formulas are combined, as possible.
+ *
+ * With SMT the slots of thread siblings need to be combined to get meaningful
+ * results. This is implemented by the kernel forcing per-core mode with
+ * the .aggr-per-core sysfs attribute.
+ *
+ * Full TopDown supports more levels to sub-divide each area: for example
+ * BackendBound into computing bound and memory bound. For now we only
+ * support Level 1 TopDown.
+ */
+
+static double td_total_slots(int ctx, int cpu)
+{
+	return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+}
+
+static double td_bad_spec(int ctx, int cpu)
+{
+	double bad_spec = 0;
+	double total_slots;
+	double total;
+
+	total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) -
+		avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) +
+		avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]);
+	total_slots = td_total_slots(ctx, cpu);
+	if (total_slots)
+		bad_spec = total / total_slots;
+	return bad_spec;
+}
+
+static double td_retiring(int ctx, int cpu)
+{
+	double retiring = 0;
+	double total_slots = td_total_slots(ctx, cpu);
+	double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]);
+
+	if (total_slots)
+		retiring = ret_slots / total_slots;
+	return retiring;
+}
+
+static double td_fe_bound(int ctx, int cpu)
+{
+	double fe_bound = 0;
+	double total_slots = td_total_slots(ctx, cpu);
+	double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]);
+
+	if (total_slots)
+		fe_bound = fetch_bub / total_slots;
+	return fe_bound;
+}
+
+static double td_be_bound(int ctx, int cpu)
+{
+	double sum = (td_fe_bound(ctx, cpu) +
+		      td_bad_spec(ctx, cpu) +
+		      td_retiring(ctx, cpu));
+	if (sum == 0)
+		return 0;
+	return 1.0 - sum;
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out)

@@ -296,6 +415,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
+	const char *color = NULL;
 	int ctx = evsel_context(evsel);
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {

@@ -438,6 +558,46 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				     avg / ratio);
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
+		double fe_bound = td_fe_bound(ctx, cpu);
+
+		if (fe_bound > 0.2)
+			color = PERF_COLOR_RED;
+		print_metric(ctxp, color, "%8.2f%%", "frontend bound",
+				fe_bound * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
+		double retiring = td_retiring(ctx, cpu);
+
+		if (retiring > 0.7)
+			color = PERF_COLOR_RED;
+		print_metric(ctxp, color, "%8.2f%%", "retiring",
+				retiring * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
+		double bad_spec = td_bad_spec(ctx, cpu);
+
+		if (bad_spec > 0.1)
+			color = PERF_COLOR_RED;
+		print_metric(ctxp, color, "%8.2f%%", "bad speculation",
+				bad_spec * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
+		double be_bound = td_be_bound(ctx, cpu);
+		const char *name = "backend bound";
+		static int have_recovery_bubbles = -1;
+
+		/* In case the CPU does not support topdown-recovery-bubbles */
+		if (have_recovery_bubbles < 0)
+			have_recovery_bubbles = pmu_have_event("cpu",
+					"topdown-recovery-bubbles");
+		if (!have_recovery_bubbles)
+			name = "backend bound/bad spec";
+
+		if (be_bound > 0.2)
+			color = PERF_COLOR_RED;
+		if (td_total_slots(ctx, cpu) > 0)
+			print_metric(ctxp, NULL, "%8.2f%%", name,
+					be_bound * 100.);
+		else
+			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];

index f3217b3..fc6039c 100644
@@ -79,6 +79,11 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 	ID(TRANSACTION_START,	cpu/tx-start/),
 	ID(ELISION_START,	cpu/el-start/),
 	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
+	ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
+	ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
+	ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
+	ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
+	ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
 };
 #undef ID
 

index f14c0f4..4866240 100644
@@ -17,6 +17,11 @@ enum perf_stat_evsel_id {
 	PERF_STAT_EVSEL_ID__TRANSACTION_START,
 	PERF_STAT_EVSEL_ID__ELISION_START,
 	PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+	PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS,
+	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED,
+	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
+	PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
+	PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
 	PERF_STAT_EVSEL_ID__MAX,
 };
 

index afea25d..3930ee3 100644
@@ -309,6 +309,14 @@ static int read_counter(struct perf_evsel *counter)
 					return -1;
 				}
 			}
+
+			if (verbose) {
+				fprintf(stat_config.output,
+					"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+						perf_evsel__name(counter),
+						cpu,
+						count->val, count->ena, count->run);
+			}
 		}
 	}
 

index 1b443db..7379eb9 100644
@@ -1463,6 +1463,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 	unsigned int cpu = (long)hcpu;
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	int i, ret = NOTIFY_OK;
+	bool ht_on;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:

@@ -1482,6 +1483,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 			kfree(cpuc->kfree_on_online[i]);
 			cpuc->kfree_on_online[i] = NULL;
 		}
+		x86_pmu.ht_on = cpumask_weight(topology_sibling_cpumask(cpu)) > 1;
 		break;
 
 	case CPU_DYING:

@@ -1493,6 +1495,15 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 	case CPU_DEAD:
 		if (x86_pmu.cpu_dead)
 			x86_pmu.cpu_dead(cpu);
+		/* Recompute HT state for all CPUs on offline */
+		ht_on = false;
+		for_each_online_cpu (cpu) {
+			if (cpumask_weight(topology_sibling_cpumask(cpu)) > 1) {
+				ht_on = true;
+				break;
+			}
+		}
+		x86_pmu.ht_on = ht_on;
 		break;
 
 	default:

@@ -1602,6 +1613,30 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 	return x86_pmu.events_sysfs_show(page, config);
 }
 
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct perf_pmu_events_ht_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_ht_attr, attr);
+
+	/*
+	 * Report conditional events depending on Hyper-Threading.
+	 *
+	 * This is overly conservative as usually the HT special
+	 * handling is not needed if the other CPU thread is idle.
+	 *
+	 * Note this does not (cannot) handle the case when thread
+	 * siblings are invisible, for example with virtualization
+	 * if they are owned by some other guest.  The user tool
+	 * has to re-read when a thread sibling gets onlined later.
+	 */
+
+	return sprintf(page, "%s",
+			x86_pmu.ht_on ?
+			pmu_attr->event_str_ht :
+			pmu_attr->event_str_noht);
+}
+
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);

index 7bb61e3..a7e0148 100644
@@ -616,6 +616,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Hyper Threading on?
+	 */
+	bool ht_on;
 };
 
 struct x86_perf_task_context {

@@ -661,6 +666,14 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 	.event_str	= str,						\
 };
 
+#define EVENT_ATTR_STR_HT(_name, v, noht, ht)				\
+static struct perf_pmu_events_ht_attr event_attr_##v = {		\
+	.attr		= __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
+	.id		= 0,						\
+	.event_str_noht	= noht,						\
+	.event_str_ht	= ht,						\
+}
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 static inline bool x86_pmu_has_lbr_callstack(void)

@@ -922,6 +935,8 @@ int knc_pmu_init(void);
 
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
 
 static inline int is_ht_workaround_enabled(void)
 {

index f9828a4..ea2d830 100644
@@ -1166,6 +1166,13 @@ struct perf_pmu_events_attr {
 	const char *event_str;
 };
 
+struct perf_pmu_events_ht_attr {
+	struct device_attribute attr;
+	u64 id;
+	const char *event_str_ht;
+	const char *event_str_noht;
+};
+
 ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
 			      char *page);
 

index a667078..c5a512e 100644
@@ -230,9 +230,59 @@ struct attribute *nhm_events_attrs[] = {
 	NULL,
 };
 
+/*
+ * TopDown events for Core.
+ *
+ * The events are all in slots, which is a free slot in a 4 wide
+ * pipeline. Some events are already reported in slots, for cycle
+ * events we multiply by the pipeline width (4).
+ *
+ * With Hyper Threading on, TopDown metrics are either summed or averaged
+ * between the threads of a core: (count_t0 + count_t1).
+ *
+ * For the average case the metric is always scaled to pipeline width,
+ * so we use factor 2 ((count_t0 + count_t1) / 2 * 4)
+ *
+ * We tell perf to aggregate per core by setting the .aggr-per-core
+ * attribute for the alias to 1.
+ */
+
+EVENT_ATTR_STR_HT(topdown-total-slots, td_total_slots,
+	"event=0x3c,umask=0x0",			/* cpu_clk_unhalted.thread */
+	"event=0x3c,umask=0x0,any=1");		/* cpu_clk_unhalted.thread_any */
+EVENT_ATTR_STR_HT(topdown-total-slots.scale, td_total_slots_scale, "4", "2");
+EVENT_ATTR_STR(topdown-total-slots.aggr-per-core, td_total_slots_pc, "1");
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued,
+	"event=0xe,umask=0x1");			/* uops_issued.any */
+EVENT_ATTR_STR(topdown-slots-issued.aggr-per-core, td_slots_issued_pc, "1");
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired,
+	"event=0xc2,umask=0x2");		/* uops_retired.retire_slots */
+EVENT_ATTR_STR(topdown-slots-retired.aggr-per-core, td_slots_retired_pc, "1");
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles,
+	"event=0x9c,umask=0x1");		/* idq_uops_not_delivered_core */
+EVENT_ATTR_STR(topdown-fetch-bubbles.aggr-per-core, td_fetch_bubbles_pc, "1");
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
+	"event=0xd,umask=0x3,cmask=1",		/* int_misc.recovery_cycles */
+	"event=0xd,umask=0x3,cmask=1,any=1");	/* int_misc.recovery_cycles_any */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
+	"4", "2");
+EVENT_ATTR_STR(topdown-recovery-bubbles.aggr-per-core, td_recovery_bubbles_pc, "1");
+
 struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(mem_ld_snb),
 	EVENT_PTR(mem_st_snb),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_issued_pc),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_slots_retired_pc),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_fetch_bubbles_pc),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_total_slots_pc),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	EVENT_PTR(td_recovery_bubbles_pc),
 	NULL,
 };
 

@@ -3283,6 +3333,18 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_issued_pc),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_slots_retired_pc),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_fetch_bubbles_pc),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_total_slots_pc),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	EVENT_PTR(td_recovery_bubbles_pc),
 	NULL
 };
 

@@ -3622,6 +3684,12 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 		intel_pmu_lbr_init_skl();
 
+		/* INT_MISC.RECOVERY_CYCLES has umask 1 in Skylake */
+		event_attr_td_recovery_bubbles.event_str_noht =
+			"event=0xd,umask=0x1,cmask=1";
+		event_attr_td_recovery_bubbles.event_str_ht =
+			"event=0xd,umask=0x1,cmask=1,any=1";
+
 		x86_pmu.event_constraints = intel_skl_event_constraints;
 		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_skl_extra_regs;

index c5a512e..51a0f4c 100644
@@ -1382,6 +1382,29 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+EVENT_ATTR_STR(topdown-total-slots, td_total_slots_slm, "event=0x3c");
+EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_slm, "2");
+/* no_alloc_cycles.not_delivered */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_slm,
+	       "event=0xca,umask=0x50");
+EVENT_ATTR_STR(topdown-fetch-bubbles.scale, td_fetch_bubbles_scale_slm, "2");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_slm,
+	       "event=0xc2,umask=0x10");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_slm,
+	       "event=0xc2,umask=0x10");
+
+static struct attribute *slm_events_attrs[] = {
+	EVENT_PTR(td_total_slots_slm),
+	EVENT_PTR(td_total_slots_scale_slm),
+	EVENT_PTR(td_fetch_bubbles_slm),
+	EVENT_PTR(td_fetch_bubbles_scale_slm),
+	EVENT_PTR(td_slots_issued_slm),
+	EVENT_PTR(td_slots_retired_slm),
+	NULL
+};
+
 static struct extra_reg intel_slm_extra_regs[] __read_mostly =
 {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */

@@ -3494,6 +3517,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_slm_extra_regs;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.cpu_events = slm_events_attrs;
 		pr_cont("Silvermont events, ");
 		break;