Merge tag 'perf-core-for-mingo-4.21-20181122' of...

Merge tag 'perf-core-for-mingo-4.21-20181122' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Start using BPF maps in 'perf trace' for filters in the augmented syscalls
  code, keeping the existing code for tracepoint filters so that we can switch
  back and forth while getting everything BPFied (Arnaldo Carvalho de Melo)

- Suppress potential format-truncation warning in the PMU code (Ben Hutchings)

- Introduce 'perf bench epoll', with "wait" and "ctl" benchmarks (Davidlohr Bueso)

- Fix slowness due to -ffunction-section, do it by sorting the maps by name, so
  avoiding the using rb_first/next to traverse all entries looking for a map name,
  that with --ffunction-section gets to thousands of maps (Eric Saint-Etienne)

- Separate jvmti cmlr check (Jiri Olsa)

- Allow using the stepping when figuring out which JSON files to use for a x86
  processor, so that Cascadelake server can be support, which has the same
  cpuid as some other processor, being different only in the stepping (Kan Liang)

- Share code and output format for uregs and iregs 'perf script' output (Milian Wolff)

- Use perf_evsel__is_clocki() for clock events in 'perf stat' (Ravi Bangoria)
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

tools/build/Makefile.feature

@@ -31,6 +31,7 @@ FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         dwarf                           \
         dwarf_getlocations              \
+        eventfd                         \
         fortify-source                  \
         sync-compare-and-swap           \
         get_current_dir_name            \

tools/build/feature/Makefile

@@ -5,6 +5,7 @@ FILES=                                          \
          test-bionic.bin                        \
          test-dwarf.bin                         \
          test-dwarf_getlocations.bin            \
+         test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
          test-get_current_dir_name.bin          \
@@ -54,6 +55,7 @@ FILES=                                          \
          test-sdt.bin                           \
          test-cxx.bin                           \
          test-jvmti.bin				\
+         test-jvmti-cmlr.bin			\
          test-sched_getcpu.bin			\
          test-setns.bin				\
          test-libopencsd.bin			\
@@ -102,6 +104,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-eventfd.bin:
+	$(BUILD)
+
 $(OUTPUT)test-get_current_dir_name.bin:
 	$(BUILD)
 
@@ -263,6 +268,9 @@ $(OUTPUT)test-cxx.bin:
 $(OUTPUT)test-jvmti.bin:
 	$(BUILD)
 
+$(OUTPUT)test-jvmti-cmlr.bin:
+	$(BUILD)
+
 $(OUTPUT)test-llvm.bin:
 	$(BUILDXX) -std=gnu++11 				\
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\

tools/build/feature/test-all.c

@@ -50,6 +50,10 @@
 # include "test-dwarf_getlocations.c"
 #undef main
 
+#define main main_test_eventfd
+# include "test-eventfd.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main
@@ -182,6 +186,7 @@ int main(int argc, char *argv[])
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
+	main_test_eventfd();
 	main_test_libelf_getphdrnum();
 	main_test_libelf_gelf_getnote();
 	main_test_libelf_getshdrstrndx();

tools/build/feature/test-eventfd.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include <sys/eventfd.h>
+
+int main(void)
+{
+	return eventfd(0, EFD_NONBLOCK);
+}

tools/build/feature/test-jvmti-cmlr.c

+// SPDX-License-Identifier: GPL-2.0
+#include <jvmti.h>
+#include <jvmticmlr.h>
+
+int main(void)
+{
+	jvmtiCompiledMethodLoadInlineRecord	rec __attribute__((unused));
+	jvmtiCompiledMethodLoadRecordHeader	hdr __attribute__((unused));
+	PCStackInfo				p   __attribute__((unused));
+	return 0;
+}

tools/build/feature/test-jvmti.c

 // SPDX-License-Identifier: GPL-2.0
 #include <jvmti.h>
-#include <jvmticmlr.h>
 
 int main(void)
 {

tools/perf/Documentation/perf-bench.txt

@@ -58,6 +58,9 @@ SUBSYSTEM
 'futex'::
 	Futex stressing benchmarks.
 
+'epoll'::
+	Eventpoll (epoll) stressing benchmarks.
+
 'all'::
 	All benchmark subsystems.
 
@@ -203,6 +206,13 @@ Suite for evaluating requeue calls.
 *lock-pi*::
 Suite for evaluating futex lock_pi calls.
 
+SUITES FOR 'epoll'
+~~~~~~~~~~~~~~~~~~
+*wait*::
+Suite for evaluating concurrent epoll_wait calls.
+
+*ctl*::
+Suite for evaluating multiple epoll_ctl calls.
 
 SEE ALSO
 --------

tools/perf/Makefile.config

@@ -299,11 +299,14 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-eventfd), 1)
+  CFLAGS += -DHAVE_EVENTFD
+endif
+
 ifeq ($(feature-get_current_dir_name), 1)
   CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
 endif
 
-
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1
@@ -852,6 +855,13 @@ ifndef NO_JVMTI
   $(call feature_check,jvmti)
   ifeq ($(feature-jvmti), 1)
     $(call detected_var,JDIR)
+    ifndef NO_JVMTI_CMLR
+      FEATURE_CHECK_CFLAGS-jvmti-cmlr := $(FEATURE_CHECK_CFLAGS-jvmti)
+      $(call feature_check,jvmti-cmlr)
+      ifeq ($(feature-jvmti-cmlr), 1)
+        CFLAGS += -DHAVE_JVMTI_CMLR
+      endif
+    endif # NO_JVMTI_CMLR
   else
     $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel)
     NO_JVMTI := 1

tools/perf/Makefile.perf

@@ -95,6 +95,9 @@ include ../scripts/utilities.mak
 #
 # Define NO_JVMTI if you do not want jvmti agent built
 #
+# Define NO_JVMTI_CMLR (debug only) if you do not want to process CMLR
+# data for java source lines.
+#
 # Define LIBCLANGLLVM if you DO want builtin clang and llvm support.
 # When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
 # llvm-config is not in $PATH.

tools/perf/arch/x86/util/header.c

@@ -4,6 +4,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <regex.h>
 
 #include "../../util/header.h"
 
@@ -70,9 +71,72 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
-	if (buf && __get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
+	if (buf && __get_cpuid(buf, 128, "%s-%u-%X-%X$") < 0) {
 		free(buf);
 		return NULL;
 	}
 	return buf;
 }
+
+/* Full CPUID format for x86 is vendor-family-model-stepping */
+static bool is_full_cpuid(const char *id)
+{
+	const char *tmp = id;
+	int count = 0;
+
+	while ((tmp = strchr(tmp, '-')) != NULL) {
+		count++;
+		tmp++;
+	}
+
+	if (count == 3)
+		return true;
+
+	return false;
+}
+
+int strcmp_cpuid_str(const char *mapcpuid, const char *id)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+	bool full_mapcpuid = is_full_cpuid(mapcpuid);
+	bool full_cpuid = is_full_cpuid(id);
+
+	/*
+	 * Full CPUID format is required to identify a platform.
+	 * Error out if the cpuid string is incomplete.
+	 */
+	if (full_mapcpuid && !full_cpuid) {
+		pr_info("Invalid CPUID %s. Full CPUID is required, "
+			"vendor-family-model-stepping\n", id);
+		return 1;
+	}
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, id, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+		size_t cpuid_len;
+
+		/* If the full CPUID format isn't required,
+		 * ignoring the stepping.
+		 */
+		if (!full_mapcpuid && full_cpuid)
+			cpuid_len = strrchr(id, '-') - id;
+		else
+			cpuid_len = strlen(id);
+
+		/* Verify the entire string matched. */
+		if (match_len == cpuid_len)
+			return 0;
+	}
+
+	return 1;
+}

tools/perf/arch/x86/util/kvm-stat.c

@@ -156,7 +156,7 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 	if (strstr(cpuid, "Intel")) {
 		kvm->exit_reasons = vmx_exit_reasons;
 		kvm->exit_reasons_isa = "VMX";
-	} else if (strstr(cpuid, "AMD")) {
+	} else if (strstr(cpuid, "AMD") || strstr(cpuid, "Hygon")) {
 		kvm->exit_reasons = svm_exit_reasons;
 		kvm->exit_reasons_isa = "SVM";
 	} else

tools/perf/bench/Build

@@ -7,6 +7,9 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-y += epoll-wait.o
+perf-y += epoll-ctl.o
+
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o

tools/perf/bench/bench.h

@@ -38,6 +38,9 @@ int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
 int bench_futex_lock_pi(int argc, const char **argv);
 
+int bench_epoll_wait(int argc, const char **argv);
+int bench_epoll_ctl(int argc, const char **argv);
+
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
 #define BENCH_FORMAT_SIMPLE_STR		"simple"
@@ -48,4 +51,15 @@ int bench_futex_lock_pi(int argc, const char **argv);
 extern int bench_format;
 extern unsigned int bench_repeat;
 
+#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
+#include <pthread.h>
+#include <linux/compiler.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
+					      size_t cpusetsize __maybe_unused,
+					      cpu_set_t *cpuset __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 #endif

tools/perf/bench/epoll-ctl.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Davidlohr Bueso.
+ *
+ * Benchmark the various operations allowed for epoll_ctl(2).
+ * The idea is to concurrently stress a single epoll instance
+ */
+#ifdef HAVE_EVENTFD
+/* For the CLR_() macros */
+#include <string.h>
+#include <pthread.h>
+
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/epoll.h>
+#include <sys/eventfd.h>
+
+#include "../util/stat.h"
+#include <subcmd/parse-options.h>
+#include "bench.h"
+#include "cpumap.h"
+
+#include <err.h>
+
+#define printinfo(fmt, arg...) \
+	do { if (__verbose) printf(fmt, ## arg); } while (0)
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs    = 8;
+struct timeval start, end, runtime;
+static bool done, __verbose, randomize;
+
+/*
+ * epoll related shared variables.
+ */
+
+/* Maximum number of nesting allowed inside epoll sets */
+#define EPOLL_MAXNESTS 4
+
+enum {
+	OP_EPOLL_ADD,
+	OP_EPOLL_MOD,
+	OP_EPOLL_DEL,
+	EPOLL_NR_OPS,
+};
+
+static int epollfd;
+static int *epollfdp;
+static bool noaffinity;
+static unsigned int nested = 0;
+
+/* amount of fds to monitor, per thread */
+static unsigned int nfds = 64;
+
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats all_stats[EPOLL_NR_OPS];
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+	int tid;
+	pthread_t thread;
+	unsigned long ops[EPOLL_NR_OPS];
+	int *fdmap;
+};
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs,    "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "nfds", &nfds, "Specify amount of file descriptors to monitor for each thread"),
+	OPT_BOOLEAN( 'n', "noaffinity",  &noaffinity,   "Disables CPU affinity"),
+	OPT_UINTEGER( 'N', "nested",  &nested,   "Nesting level epoll hierarchy (default is 0, no nesting)"),
+	OPT_BOOLEAN( 'R', "randomize", &randomize,   "Perform random operations on random fds"),
+	OPT_BOOLEAN( 'v', "verbose",  &__verbose,   "Verbose mode"),
+	OPT_END()
+};
+
+static const char * const bench_epoll_ctl_usage[] = {
+	"perf bench epoll ctl <options>",
+	NULL
+};
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void nest_epollfd(void)
+{
+	unsigned int i;
+	struct epoll_event ev;
+
+	if (nested > EPOLL_MAXNESTS)
+		nested = EPOLL_MAXNESTS;
+	printinfo("Nesting level(s): %d\n", nested);
+
+	epollfdp = calloc(nested, sizeof(int));
+	if (!epollfd)
+		err(EXIT_FAILURE, "calloc");
+
+	for (i = 0; i < nested; i++) {
+		epollfdp[i] = epoll_create(1);
+		if (epollfd < 0)
+			err(EXIT_FAILURE, "epoll_create");
+	}
+
+	ev.events = EPOLLHUP; /* anything */
+	ev.data.u64 = i; /* any number */
+
+	for (i = nested - 1; i; i--) {
+		if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD,
+			      epollfdp[i], &ev) < 0)
+			err(EXIT_FAILURE, "epoll_ctl");
+	}
+
+	if (epoll_ctl(epollfd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0)
+		err(EXIT_FAILURE, "epoll_ctl");
+}
+
+static inline void do_epoll_op(struct worker *w, int op, int fd)
+{
+	int error;
+	struct epoll_event ev;
+
+	ev.events = EPOLLIN;
+	ev.data.u64 = fd;
+
+	switch (op) {
+	case OP_EPOLL_ADD:
+		error = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev);
+		break;
+	case OP_EPOLL_MOD:
+		ev.events = EPOLLOUT;
+		error = epoll_ctl(epollfd, EPOLL_CTL_MOD, fd, &ev);
+		break;
+	case OP_EPOLL_DEL:
+		error = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL);
+		break;
+	default:
+		error = 1;
+		break;
+	}
+
+	if (!error)
+		w->ops[op]++;
+}
+
+static inline void do_random_epoll_op(struct worker *w)
+{
+	unsigned long rnd1 = random(), rnd2 = random();
+	int op, fd;
+
+	fd = w->fdmap[rnd1 % nfds];
+	op = rnd2 % EPOLL_NR_OPS;
+
+	do_epoll_op(w, op, fd);
+}
+
+static void *workerfn(void *arg)
+{
+	unsigned int i;
+	struct worker *w = (struct worker *) arg;
+	struct timespec ts = { .tv_sec = 0,
+			       .tv_nsec = 250 };
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	/* Let 'em loose */
+	do {
+		/* random */
+		if (randomize) {
+			do_random_epoll_op(w);
+		} else {
+			for (i = 0; i < nfds; i++) {
+				do_epoll_op(w, OP_EPOLL_ADD, w->fdmap[i]);
+				do_epoll_op(w, OP_EPOLL_MOD, w->fdmap[i]);
+				do_epoll_op(w, OP_EPOLL_DEL, w->fdmap[i]);
+			}
+		}
+
+		nanosleep(&ts, NULL);
+	}  while (!done);
+
+	return NULL;
+}
+
+static void init_fdmaps(struct worker *w, int pct)
+{
+	unsigned int i;
+	int inc;
+	struct epoll_event ev;
+
+	if (!pct)
+		return;
+
+	inc = 100/pct;
+	for (i = 0; i < nfds; i+=inc) {
+		ev.data.fd = w->fdmap[i];
+		ev.events = EPOLLIN;
+
+		if (epoll_ctl(epollfd, EPOLL_CTL_ADD, w->fdmap[i], &ev) < 0)
+			err(EXIT_FAILURE, "epoll_ct");
+	}
+}
+
+static int do_threads(struct worker *worker, struct cpu_map *cpu)
+{
+	pthread_attr_t thread_attr, *attrp = NULL;
+	cpu_set_t cpuset;
+	unsigned int i, j;
+	int ret;
+
+	if (!noaffinity)
+		pthread_attr_init(&thread_attr);
+
+	for (i = 0; i < nthreads; i++) {
+		struct worker *w = &worker[i];
+
+		w->tid = i;
+		w->fdmap = calloc(nfds, sizeof(int));
+		if (!w->fdmap)
+			return 1;
+
+		for (j = 0; j < nfds; j++) {
+			w->fdmap[j] = eventfd(0, EFD_NONBLOCK);
+			if (w->fdmap[j] < 0)
+				err(EXIT_FAILURE, "eventfd");
+		}
+
+		/*
+		 * Lets add 50% of the fdmap to the epoll instance, and
+		 * do it before any threads are started; otherwise there is
+		 * an initial bias of the call failing  (mod and del ops).
+		 */
+		if (randomize)
+			init_fdmaps(w, 50);
+
+		if (!noaffinity) {
+			CPU_ZERO(&cpuset);
+			CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+
+			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+			attrp = &thread_attr;
+		}
+
+		ret = pthread_create(&w->thread, attrp, workerfn,
+				     (void *)(struct worker *) w);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_create");
+	}
+
+	if (!noaffinity)
+		pthread_attr_destroy(&thread_attr);
+
+	return ret;
+}
+
+static void print_summary(void)
+{
+	int i;
+	unsigned long avg[EPOLL_NR_OPS];
+	double stddev[EPOLL_NR_OPS];
+
+	for (i = 0; i < EPOLL_NR_OPS; i++) {
+		avg[i] = avg_stats(&all_stats[i]);
+		stddev[i] = stddev_stats(&all_stats[i]);
+	}
+
+	printf("\nAveraged %ld ADD operations (+- %.2f%%)\n",
+	       avg[OP_EPOLL_ADD], rel_stddev_stats(stddev[OP_EPOLL_ADD],
+						   avg[OP_EPOLL_ADD]));
+	printf("Averaged %ld MOD operations (+- %.2f%%)\n",
+	       avg[OP_EPOLL_MOD], rel_stddev_stats(stddev[OP_EPOLL_MOD],
+						   avg[OP_EPOLL_MOD]));
+	printf("Averaged %ld DEL operations (+- %.2f%%)\n",
+	       avg[OP_EPOLL_DEL], rel_stddev_stats(stddev[OP_EPOLL_DEL],
+						   avg[OP_EPOLL_DEL]));
+}
+
+int bench_epoll_ctl(int argc, const char **argv)
+{
+	int j, ret = 0;
+	struct sigaction act;
+	struct worker *worker = NULL;
+	struct cpu_map *cpu;
+	struct rlimit rl, prevrl;
+	unsigned int i;
+
+	argc = parse_options(argc, argv, options, bench_epoll_ctl_usage, 0);
+	if (argc) {
+		usage_with_options(bench_epoll_ctl_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		goto errmem;
+
+	/* a single, main epoll instance */
+	epollfd = epoll_create(1);
+	if (epollfd < 0)
+		err(EXIT_FAILURE, "epoll_create");
+
+	/*
+	 * Deal with nested epolls, if any.
+	 */
+	if (nested)
+		nest_epollfd();
+
+	/* default to the number of CPUs */
+	if (!nthreads)
+		nthreads = cpu->nr;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		goto errmem;
+
+	if (getrlimit(RLIMIT_NOFILE, &prevrl))
+	    err(EXIT_FAILURE, "getrlimit");
+	rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50;
+	printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n",
+		  (uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max);
+	if (setrlimit(RLIMIT_NOFILE, &rl) < 0)
+		err(EXIT_FAILURE, "setrlimit");
+
+	printf("Run summary [PID %d]: %d threads doing epoll_ctl ops "
+	       "%d file-descriptors for %d secs.\n\n",
+	       getpid(), nthreads, nfds, nsecs);
+
+	for (i = 0; i < EPOLL_NR_OPS; i++)
+		init_stats(&all_stats[i]);
+
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+
+	gettimeofday(&start, NULL);
+
+	do_threads(worker, cpu);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+	printinfo("main thread: toggling done\n");
+
+	for (i = 0; i < nthreads; i++) {
+		ret = pthread_join(worker[i].thread, NULL);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_join");
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t[EPOLL_NR_OPS];
+
+		for (j = 0; j < EPOLL_NR_OPS; j++) {
+			t[j] = worker[i].ops[j];
+			update_stats(&all_stats[j], t[j]);
+		}
+
+		if (nfds == 1)
+			printf("[thread %2d] fdmap: %p [ add: %04ld; mod: %04ld; del: %04lds ops ]\n",
+			       worker[i].tid, &worker[i].fdmap[0],
+			       t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
+		else
+			printf("[thread %2d] fdmap: %p ... %p [ add: %04ld ops; mod: %04ld ops; del: %04ld ops ]\n",
+			       worker[i].tid, &worker[i].fdmap[0],
+			       &worker[i].fdmap[nfds-1],
+			       t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
+	}
+
+	print_summary();
+
+	close(epollfd);
+	return ret;
+errmem:
+	err(EXIT_FAILURE, "calloc");
+}
+#endif // HAVE_EVENTFD

tools/perf/bench/epoll-wait.c

+// SPDX-License-Identifier: GPL-2.0
+#ifdef HAVE_EVENTFD
+/*
+ * Copyright (C) 2018 Davidlohr Bueso.
+ *
+ * This program benchmarks concurrent epoll_wait(2) monitoring multiple
+ * file descriptors under one or two load balancing models. The first,
+ * and default, is the single/combined queueing (which refers to a single
+ * epoll instance for N worker threads):
+ *
+ *                          |---> [worker A]
+ *                          |---> [worker B]
+ *        [combined queue]  .---> [worker C]
+ *                          |---> [worker D]
+ *                          |---> [worker E]
+ *
+ * While the second model, enabled via --multiq option, uses multiple
+ * queueing (which refers to one epoll instance per worker). For example,
+ * short lived tcp connections in a high throughput httpd server will
+ * ditribute the accept()'ing  connections across CPUs. In this case each
+ * worker does a limited  amount of processing.
+ *
+ *             [queue A]  ---> [worker]
+ *             [queue B]  ---> [worker]
+ *             [queue C]  ---> [worker]
+ *             [queue D]  ---> [worker]
+ *             [queue E]  ---> [worker]
+ *
+ * Naturally, the single queue will enforce more concurrency on the epoll
+ * instance, and can therefore scale poorly compared to multiple queues.
+ * However, this is a benchmark raw data and must be taken with a grain of
+ * salt when choosing how to make use of sys_epoll.
+
+ * Each thread has a number of private, nonblocking file descriptors,
+ * referred to as fdmap. A writer thread will constantly be writing to
+ * the fdmaps of all threads, minimizing each threads's chances of
+ * epoll_wait not finding any ready read events and blocking as this
+ * is not what we want to stress. The size of the fdmap can be adjusted
+ * by the user; enlarging the value will increase the chances of
+ * epoll_wait(2) blocking as the lineal writer thread will take "longer",
+ * at least at a high level.
+ *
+ * Note that because fds are private to each thread, this workload does
+ * not stress scenarios where multiple tasks are awoken per ready IO; ie:
+ * EPOLLEXCLUSIVE semantics.
+ *
+ * The end result/metric is throughput: number of ops/second where an
+ * operation consists of:
+ *
+ *   epoll_wait(2) + [others]
+ *
+ *        ... where [others] is the cost of re-adding the fd (EPOLLET),
+ *            or rearming it (EPOLLONESHOT).
+ *
+ *
+ * The purpose of this is program is that it be useful for measuring
+ * kernel related changes to the sys_epoll, and not comparing different
+ * IO polling methods, for example. Hence everything is very adhoc and
+ * outputs raw microbenchmark numbers. Also this uses eventfd, similar
+ * tools tend to use pipes or sockets, but the result is the same.
+ */
+
+/* For the CLR_() macros */
+#include <string.h>
+#include <pthread.h>
+
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/epoll.h>
+#include <sys/eventfd.h>
+#include <sys/types.h>
+
+#include "../util/stat.h"
+#include <subcmd/parse-options.h>
+#include "bench.h"
+#include "cpumap.h"
+
+#include <err.h>
+
+#define printinfo(fmt, arg...) \
+	do { if (__verbose) { printf(fmt, ## arg); fflush(stdout); } } while (0)
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs    = 8;
+struct timeval start, end, runtime;
+static bool wdone, done, __verbose, randomize, nonblocking;
+
+/*
+ * epoll related shared variables.
+ */
+
+/* Maximum number of nesting allowed inside epoll sets */
+#define EPOLL_MAXNESTS 4
+
+static int epollfd;
+static int *epollfdp;
+static bool noaffinity;
+static unsigned int nested = 0;
+static bool et; /* edge-trigger */
+static bool oneshot;
+static bool multiq; /* use an epoll instance per thread */
+
+/* amount of fds to monitor, per thread */
+static unsigned int nfds = 64;
+
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+	int tid;
+	int epollfd; /* for --multiq */
+	pthread_t thread;
+	unsigned long ops;
+	int *fdmap;
+};
+
+static const struct option options[] = {
+	/* general benchmark options */
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "nfds",    &nfds,  "Specify amount of file descriptors to monitor for each thread"),
+	OPT_BOOLEAN( 'n', "noaffinity",  &noaffinity,   "Disables CPU affinity"),
+	OPT_BOOLEAN('R', "randomize", &randomize,   "Enable random write behaviour (default is lineal)"),
+	OPT_BOOLEAN( 'v', "verbose", &__verbose, "Verbose mode"),
+
+	/* epoll specific options */
+	OPT_BOOLEAN( 'm', "multiq",  &multiq,   "Use multiple epoll instances (one per thread)"),
+	OPT_BOOLEAN( 'B', "nonblocking", &nonblocking, "Nonblocking epoll_wait(2) behaviour"),
+	OPT_UINTEGER( 'N', "nested",  &nested,   "Nesting level epoll hierarchy (default is 0, no nesting)"),
+	OPT_BOOLEAN( 'S', "oneshot",  &oneshot,   "Use EPOLLONESHOT semantics"),
+	OPT_BOOLEAN( 'E', "edge",  &et,   "Use Edge-triggered interface (default is LT)"),
+
+	OPT_END()
+};
+
+static const char * const bench_epoll_wait_usage[] = {
+	"perf bench epoll wait <options>",
+	NULL
+};
+
+
+/*
+ * Arrange the N elements of ARRAY in random order.
+ * Only effective if N is much smaller than RAND_MAX;
+ * if this may not be the case, use a better random
+ * number generator. -- Ben Pfaff.
+ */
+static void shuffle(void *array, size_t n, size_t size)
+{
+	char *carray = array;
+	void *aux;
+	size_t i;
+
+	if (n <= 1)
+		return;
+
+	aux = calloc(1, size);
+	if (!aux)
+		err(EXIT_FAILURE, "calloc");
+
+	for (i = 1; i < n; ++i) {
+		size_t j =   i + rand() / (RAND_MAX / (n - i) + 1);
+		j *= size;
+
+		memcpy(aux, &carray[j], size);
+		memcpy(&carray[j], &carray[i*size], size);
+		memcpy(&carray[i*size], aux, size);
+	}
+
+	free(aux);
+}
+
+
+static void *workerfn(void *arg)
+{
+	int fd, ret, r;
+	struct worker *w = (struct worker *) arg;
+	unsigned long ops = w->ops;
+	struct epoll_event ev;
+	uint64_t val;
+	int to = nonblocking? 0 : -1;
+	int efd = multiq ? w->epollfd : epollfd;
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	do {
+		/*
+		 * Block undefinitely waiting for the IN event.
+		 * In order to stress the epoll_wait(2) syscall,
+		 * call it event per event, instead of a larger
+		 * batch (max)limit.
+		 */
+		do {
+			ret = epoll_wait(efd, &ev, 1, to);
+		} while (ret < 0 && errno == EINTR);
+		if (ret < 0)
+			err(EXIT_FAILURE, "epoll_wait");
+
+		fd = ev.data.fd;
+
+		do {
+			r = read(fd, &val, sizeof(val));
+		} while (!done && (r < 0 && errno == EAGAIN));
+
+		if (et) {
+			ev.events = EPOLLIN | EPOLLET;
+			ret = epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev);
+		}
+
+		if (oneshot) {
+			/* rearm the file descriptor with a new event mask */
+			ev.events |= EPOLLIN | EPOLLONESHOT;
+			ret = epoll_ctl(efd, EPOLL_CTL_MOD, fd, &ev);
+		}
+
+		ops++;
+	}  while (!done);
+
+	if (multiq)
+		close(w->epollfd);
+
+	w->ops = ops;
+	return NULL;
+}
+
+static void nest_epollfd(struct worker *w)
+{
+	unsigned int i;
+	struct epoll_event ev;
+	int efd = multiq ? w->epollfd : epollfd;
+
+	if (nested > EPOLL_MAXNESTS)
+		nested = EPOLL_MAXNESTS;
+
+	epollfdp = calloc(nested, sizeof(*epollfdp));
+	if (!epollfdp)
+		err(EXIT_FAILURE, "calloc");
+
+	for (i = 0; i < nested; i++) {
+		epollfdp[i] = epoll_create(1);
+		if (epollfdp[i] < 0)
+			err(EXIT_FAILURE, "epoll_create");
+	}
+
+	ev.events = EPOLLHUP; /* anything */
+	ev.data.u64 = i; /* any number */
+
+	for (i = nested - 1; i; i--) {
+		if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD,
+			      epollfdp[i], &ev) < 0)
+			err(EXIT_FAILURE, "epoll_ctl");
+	}
+
+	if (epoll_ctl(efd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0)
+		err(EXIT_FAILURE, "epoll_ctl");
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void print_summary(void)
+{
+	unsigned long avg = avg_stats(&throughput_stats);
+	double stddev = stddev_stats(&throughput_stats);
+
+	printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+	       avg, rel_stddev_stats(stddev, avg),
+	       (int) runtime.tv_sec);
+}
+
+static int do_threads(struct worker *worker, struct cpu_map *cpu)
+{
+	pthread_attr_t thread_attr, *attrp = NULL;
+	cpu_set_t cpuset;
+	unsigned int i, j;
+	int ret, events = EPOLLIN;
+
+	if (oneshot)
+		events |= EPOLLONESHOT;
+	if (et)
+		events |= EPOLLET;
+
+	printinfo("starting worker/consumer %sthreads%s\n",
+		  noaffinity ?  "":"CPU affinity ",
+		  nonblocking ? " (nonblocking)":"");
+	if (!noaffinity)
+		pthread_attr_init(&thread_attr);
+
+	for (i = 0; i < nthreads; i++) {
+		struct worker *w = &worker[i];
+
+		if (multiq) {
+			w->epollfd = epoll_create(1);
+			if (w->epollfd < 0)
+				err(EXIT_FAILURE, "epoll_create");
+
+			if (nested)
+				nest_epollfd(w);
+		}
+
+		w->tid = i;
+		w->fdmap = calloc(nfds, sizeof(int));
+		if (!w->fdmap)
+			return 1;
+
+		for (j = 0; j < nfds; j++) {
+			int efd = multiq ? w->epollfd : epollfd;
+			struct epoll_event ev;
+
+			w->fdmap[j] = eventfd(0, EFD_NONBLOCK);
+			if (w->fdmap[j] < 0)
+				err(EXIT_FAILURE, "eventfd");
+
+			ev.data.fd = w->fdmap[j];
+			ev.events = events;
+
+			ret = epoll_ctl(efd, EPOLL_CTL_ADD,
+					w->fdmap[j], &ev);
+			if (ret < 0)
+				err(EXIT_FAILURE, "epoll_ctl");
+		}
+
+		if (!noaffinity) {
+			CPU_ZERO(&cpuset);
+			CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+
+			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+			attrp = &thread_attr;
+		}
+
+		ret = pthread_create(&w->thread, attrp, workerfn,
+				     (void *)(struct worker *) w);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_create");
+	}
+
+	if (!noaffinity)
+		pthread_attr_destroy(&thread_attr);
+
+	return ret;
+}
+
+static void *writerfn(void *p)
+{
+	struct worker *worker = p;
+	size_t i, j, iter;
+	const uint64_t val = 1;
+	ssize_t sz;
+	struct timespec ts = { .tv_sec = 0,
+			       .tv_nsec = 500 };
+
+	printinfo("starting writer-thread: doing %s writes ...\n",
+		  randomize? "random":"lineal");
+
+	for (iter = 0; !wdone; iter++) {
+		if (randomize) {
+			shuffle((void *)worker, nthreads, sizeof(*worker));
+		}
+
+		for (i = 0; i < nthreads; i++) {
+			struct worker *w = &worker[i];
+
+			if (randomize) {
+				shuffle((void *)w->fdmap, nfds, sizeof(int));
+			}
+
+			for (j = 0; j < nfds; j++) {
+				do {
+					sz = write(w->fdmap[j], &val, sizeof(val));
+				} while (!wdone && (sz < 0 && errno == EAGAIN));
+			}
+		}
+
+		nanosleep(&ts, NULL);
+	}
+
+	printinfo("exiting writer-thread (total full-loops: %zd)\n", iter);
+	return NULL;
+}
+
+static int cmpworker(const void *p1, const void *p2)
+{
+
+	struct worker *w1 = (struct worker *) p1;
+	struct worker *w2 = (struct worker *) p2;
+	return w1->tid > w2->tid;
+}
+
+int bench_epoll_wait(int argc, const char **argv)
+{
+	int ret = 0;
+	struct sigaction act;
+	unsigned int i;
+	struct worker *worker = NULL;
+	struct cpu_map *cpu;
+	pthread_t wthread;
+	struct rlimit rl, prevrl;
+
+	argc = parse_options(argc, argv, options, bench_epoll_wait_usage, 0);
+	if (argc) {
+		usage_with_options(bench_epoll_wait_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	cpu = cpu_map__new(NULL);
+	if (!cpu)
+		goto errmem;
+
+	/* a single, main epoll instance */
+	if (!multiq) {
+		epollfd = epoll_create(1);
+		if (epollfd < 0)
+			err(EXIT_FAILURE, "epoll_create");
+
+		/*
+		 * Deal with nested epolls, if any.
+		 */
+		if (nested)
+			nest_epollfd(NULL);
+	}
+
+	printinfo("Using %s queue model\n", multiq ? "multi" : "single");
+	printinfo("Nesting level(s): %d\n", nested);
+
+	/* default to the number of CPUs and leave one for the writer pthread */
+	if (!nthreads)
+		nthreads = cpu->nr - 1;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker) {
+		goto errmem;
+	}
+
+	if (getrlimit(RLIMIT_NOFILE, &prevrl))
+		err(EXIT_FAILURE, "getrlimit");
+	rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50;
+	printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n",
+		  (uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max);
+	if (setrlimit(RLIMIT_NOFILE, &rl) < 0)
+		err(EXIT_FAILURE, "setrlimit");
+
+	printf("Run summary [PID %d]: %d threads monitoring%s on "
+	       "%d file-descriptors for %d secs.\n\n",
+	       getpid(), nthreads, oneshot ? " (EPOLLONESHOT semantics)": "", nfds, nsecs);
+
+	init_stats(&throughput_stats);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+
+	gettimeofday(&start, NULL);
+
+	do_threads(worker, cpu);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	/*
+	 * At this point the workers should be blocked waiting for read events
+	 * to become ready. Launch the writer which will constantly be writing
+	 * to each thread's fdmap.
+	 */
+	ret = pthread_create(&wthread, NULL, writerfn,
+			     (void *)(struct worker *) worker);
+	if (ret)
+		err(EXIT_FAILURE, "pthread_create");
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+	printinfo("main thread: toggling done\n");
+
+	sleep(1); /* meh */
+	wdone = true;
+	ret = pthread_join(wthread, NULL);
+	if (ret)
+		err(EXIT_FAILURE, "pthread_join");
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	/* sort the array back before reporting */
+	if (randomize)
+		qsort(worker, nthreads, sizeof(struct worker), cmpworker);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t = worker[i].ops/runtime.tv_sec;
+
+		update_stats(&throughput_stats, t);
+
+		if (nfds == 1)
+			printf("[thread %2d] fdmap: %p [ %04ld ops/sec ]\n",
+			       worker[i].tid, &worker[i].fdmap[0], t);
+		else
+			printf("[thread %2d] fdmap: %p ... %p [ %04ld ops/sec ]\n",
+			       worker[i].tid, &worker[i].fdmap[0],
+			       &worker[i].fdmap[nfds-1], t);
+	}
+
+	print_summary();
+
+	close(epollfd);
+	return ret;
+errmem:
+	err(EXIT_FAILURE, "calloc");
+}
+#endif // HAVE_EVENTFD

tools/perf/bench/futex.h

@@ -86,16 +86,4 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
 		 val, opflags);
 }
-
-#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
-#include <pthread.h>
-#include <linux/compiler.h>
-static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
-					      size_t cpusetsize __maybe_unused,
-					      cpu_set_t *cpuset __maybe_unused)
-{
-	return 0;
-}
-#endif
-
 #endif /* _FUTEX_H */

tools/perf/builtin-bench.c

@@ -14,6 +14,7 @@
  *  mem   ... memory access performance
  *  numa  ... NUMA scheduling and MM performance
  *  futex ... Futex performance
+ *  epoll ... Event poll performance
  */
 #include "perf.h"
 #include "util/util.h"
@@ -67,6 +68,15 @@ static struct bench futex_benchmarks[] = {
 	{ NULL,		NULL,						NULL			}
 };
 
+#ifdef HAVE_EVENTFD
+static struct bench epoll_benchmarks[] = {
+	{ "wait",	"Benchmark epoll concurrent epoll_waits",       bench_epoll_wait	},
+	{ "ctl",	"Benchmark epoll concurrent epoll_ctls",        bench_epoll_ctl		},
+	{ "all",	"Run all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+#endif // HAVE_EVENTFD
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -80,6 +90,9 @@ static struct collection collections[] = {
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
 #endif
 	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
+#ifdef HAVE_EVENTFD
+	{"epoll",       "Epoll stressing benchmarks",                   epoll_benchmarks        },
+#endif
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };

tools/perf/builtin-script.c

@@ -566,44 +566,40 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	return 0;
 }
 
-static int perf_sample__fprintf_iregs(struct perf_sample *sample,
-				      struct perf_event_attr *attr, FILE *fp)
+static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
+				     FILE *fp
+)
 {
-	struct regs_dump *regs = &sample->intr_regs;
-	uint64_t mask = attr->sample_regs_intr;
 	unsigned i = 0, r;
 	int printed = 0;
 
-	if (!regs)
+	if (!regs || !regs->regs)
 		return 0;
 
+	printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi);
+
 	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
 		u64 val = regs->regs[i++];
 		printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
 	}
 
+	fprintf(fp, "\n");
+
 	return printed;
 }
 
-static int perf_sample__fprintf_uregs(struct perf_sample *sample,
+static int perf_sample__fprintf_iregs(struct perf_sample *sample,
 				      struct perf_event_attr *attr, FILE *fp)
 {
-	struct regs_dump *regs = &sample->user_regs;
-	uint64_t mask = attr->sample_regs_user;
-	unsigned i = 0, r;
-	int printed = 0;
-
-	if (!regs || !regs->regs)
-		return 0;
-
-	printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi);
-
-	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
-		u64 val = regs->regs[i++];
-		printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
-	}
+	return perf_sample__fprintf_regs(&sample->intr_regs,
+					 attr->sample_regs_intr, fp);
+}
 
-	return printed;
+static int perf_sample__fprintf_uregs(struct perf_sample *sample,
+				      struct perf_event_attr *attr, FILE *fp)
+{
+	return perf_sample__fprintf_regs(&sample->user_regs,
+					 attr->sample_regs_user, fp);
 }
 
 static int perf_sample__fprintf_start(struct perf_sample *sample,

tools/perf/builtin-trace.c

@@ -18,6 +18,7 @@
 
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <bpf/bpf.h>
 #include "builtin.h"
 #include "util/cgroup.h"
 #include "util/color.h"
@@ -99,6 +100,7 @@ struct trace {
 	struct {
 		size_t		nr;
 		pid_t		*entries;
+		struct bpf_map  *map;
 	}			filter_pids;
 	double			duration_filter;
 	double			runtime_ms;
@@ -2565,9 +2567,27 @@ static int trace__set_ev_qualifier_filter(struct trace *trace)
 	goto out;
 }
 
+static int bpf_map__set_filter_pids(struct bpf_map *map __maybe_unused,
+				    size_t npids __maybe_unused, pid_t *pids __maybe_unused)
+{
+	int err = 0;
+#ifdef HAVE_LIBBPF_SUPPORT
+	bool value = true;
+	int map_fd = bpf_map__fd(map);
+	size_t i;
+
+	for (i = 0; i < npids; ++i) {
+		err = bpf_map_update_elem(map_fd, &pids[i], &value, BPF_ANY);
+		if (err)
+			break;
+	}
+#endif
+	return err;
+}
+
 static int trace__set_filter_loop_pids(struct trace *trace)
 {
-	unsigned int nr = 1;
+	unsigned int nr = 1, err;
 	pid_t pids[32] = {
 		getpid(),
 	};
@@ -2586,7 +2606,34 @@ static int trace__set_filter_loop_pids(struct trace *trace)
 		thread = parent;
 	}
 
-	return perf_evlist__set_filter_pids(trace->evlist, nr, pids);
+	err = perf_evlist__set_tp_filter_pids(trace->evlist, nr, pids);
+	if (!err && trace->filter_pids.map)
+		err = bpf_map__set_filter_pids(trace->filter_pids.map, nr, pids);
+
+	return err;
+}
+
+static int trace__set_filter_pids(struct trace *trace)
+{
+	int err = 0;
+	/*
+	 * Better not use !target__has_task() here because we need to cover the
+	 * case where no threads were specified in the command line, but a
+	 * workload was, and in that case we will fill in the thread_map when
+	 * we fork the workload in perf_evlist__prepare_workload.
+	 */
+	if (trace->filter_pids.nr > 0) {
+		err = perf_evlist__set_tp_filter_pids(trace->evlist, trace->filter_pids.nr,
+						      trace->filter_pids.entries);
+		if (!err && trace->filter_pids.map) {
+			err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr,
+						       trace->filter_pids.entries);
+		}
+	} else if (thread_map__pid(trace->evlist->threads, 0) == -1) {
+		err = trace__set_filter_loop_pids(trace);
+	}
+
+	return err;
 }
 
 static int trace__run(struct trace *trace, int argc, const char **argv)
@@ -2695,17 +2742,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_error_open;
 	}
 
-	/*
-	 * Better not use !target__has_task() here because we need to cover the
-	 * case where no threads were specified in the command line, but a
-	 * workload was, and in that case we will fill in the thread_map when
-	 * we fork the workload in perf_evlist__prepare_workload.
-	 */
-	if (trace->filter_pids.nr > 0)
-		err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
-	else if (thread_map__pid(evlist->threads, 0) == -1)
-		err = trace__set_filter_loop_pids(trace);
-
+	err = trace__set_filter_pids(trace);
 	if (err < 0)
 		goto out_error_mem;
 
@@ -3104,8 +3141,8 @@ static int trace__set_duration(const struct option *opt, const char *str,
 	return 0;
 }
 
-static int trace__set_filter_pids(const struct option *opt, const char *str,
-				  int unset __maybe_unused)
+static int trace__set_filter_pids_from_option(const struct option *opt, const char *str,
+					      int unset __maybe_unused)
 {
 	int ret = -1;
 	size_t i;
@@ -3315,6 +3352,25 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u
 	return 0;
 }
 
+static struct bpf_map *bpf__find_map_by_name(const char *name)
+{
+	struct bpf_object *obj, *tmp;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		struct bpf_map *map = bpf_object__find_map_by_name(obj, name);
+		if (map)
+			return map;
+
+	}
+
+	return NULL;
+}
+
+static void trace__set_bpf_map_filtered_pids(struct trace *trace)
+{
+	trace->filter_pids.map = bpf__find_map_by_name("pids_filtered");
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -3363,7 +3419,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
 		    "trace events on existing thread id"),
 	OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
-		     "pids to filter (by the kernel)", trace__set_filter_pids),
+		     "pids to filter (by the kernel)", trace__set_filter_pids_from_option),
 	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
@@ -3451,8 +3507,10 @@ int cmd_trace(int argc, const char **argv)
 		goto out;
 	}
 
-	if (evsel)
+	if (evsel) {
 		trace.syscalls.events.augmented = evsel;
+		trace__set_bpf_map_filtered_pids(&trace);
+	}
 
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {

tools/perf/examples/bpf/augmented_raw_syscalls.c

@@ -15,7 +15,8 @@
  */
 
 #include <stdio.h>
-#include <linux/socket.h>
+#include <unistd.h>
+#include <pid_filter.h>
 
 /* bpf-output associated map */
 struct bpf_map SEC("maps") __augmented_syscalls__ = {
@@ -46,6 +47,8 @@ struct augmented_filename {
 #define SYS_OPEN 2
 #define SYS_OPENAT 257
 
+pid_filter(pids_filtered);
+
 SEC("raw_syscalls:sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
@@ -56,6 +59,9 @@ int sys_enter(struct syscall_enter_args *args)
 	unsigned int len = sizeof(augmented_args);
 	const void *filename_arg = NULL;
 
+	if (pid_filter__has(&pids_filtered, getpid()))
+		return 0;
+
 	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
 	/*
 	 * Yonghong and Edward Cree sayz:
@@ -125,7 +131,7 @@ int sys_enter(struct syscall_enter_args *args)
 SEC("raw_syscalls:sys_exit")
 int sys_exit(struct syscall_exit_args *args)
 {
-	return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */
+	return !pid_filter__has(&pids_filtered, getpid());
 }
 
 license(GPL);

tools/perf/include/bpf/bpf.h

@@ -18,6 +18,25 @@ struct bpf_map {
         unsigned int numa_node;
 };
 
+/*
+ * FIXME: this should receive .max_entries as a parameter, as careful
+ *	  tuning of these limits is needed to avoid hitting limits that
+ *	  prevents other BPF constructs, such as tracepoint handlers,
+ *	  to get installed, with cryptic messages from libbpf, etc.
+ *	  For the current need, 'perf trace --filter-pids', 64 should
+ *	  be good enough, but this surely needs to be revisited.
+ */
+#define pid_map(name, value_type)		\
+struct bpf_map SEC("maps") name = {		\
+	.type	     = BPF_MAP_TYPE_HASH,	\
+	.key_size    = sizeof(pid_t),		\
+	.value_size  = sizeof(value_type),	\
+	.max_entries = 64,			\
+}
+
+static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem;
+static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem;
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \

tools/perf/include/bpf/pid_filter.h

+// SPDX-License-Identifier: LGPL-2.1
+
+#ifndef _PERF_BPF_PID_FILTER_
+#define _PERF_BPF_PID_FILTER_
+
+#include <bpf.h>
+
+#define pid_filter(name) pid_map(name, bool)
+
+static int pid_filter__add(struct bpf_map *pids, pid_t pid)
+{
+	bool value = true;
+	return bpf_map_update_elem(pids, &pid, &value, BPF_NOEXIST);
+}
+
+static bool pid_filter__has(struct bpf_map *pids, pid_t pid)
+{
+	return bpf_map_lookup_elem(pids, &pid) != NULL;
+}
+
+#endif // _PERF_BPF_PID_FILTER_

tools/perf/include/bpf/unistd.h

+// SPDX-License-Identifier: LGPL-2.1
+
+#include <bpf.h>
+
+static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
+
+static pid_t getpid(void)
+{
+	return bpf_get_current_pid_tgid();
+}

tools/perf/jvmti/libjvmti.c

@@ -6,7 +6,9 @@
 #include <stdlib.h>
 #include <err.h>
 #include <jvmti.h>
+#ifdef HAVE_JVMTI_CMLR
 #include <jvmticmlr.h>
+#endif
 #include <limits.h>
 
 #include "jvmti_agent.h"
@@ -27,6 +29,7 @@ static void print_error(jvmtiEnv *jvmti, const char *msg, jvmtiError ret)
 	}
 }
 
+#ifdef HAVE_JVMTI_CMLR
 static jvmtiError
 do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
 		    jvmti_line_info_t *tab, jint *nr)
@@ -125,6 +128,15 @@ get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **
 	*nr_lines = lines_total;
 	return JVMTI_ERROR_NONE;
 }
+#else /* HAVE_JVMTI_CMLR */
+
+static jvmtiError
+get_line_numbers(jvmtiEnv *jvmti __maybe_unused, const void *compile_info __maybe_unused,
+		 jvmti_line_info_t **tab __maybe_unused, int *nr_lines __maybe_unused)
+{
+	return JVMTI_ERROR_NONE;
+}
+#endif /* HAVE_JVMTI_CMLR */
 
 static void
 copy_class_filename(const char * class_sign, const char * file_name, char * result, size_t max_length)

tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json

+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]

tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json

+[
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x1",
+        "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x2",
+        "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x4",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x8",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x10",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x20",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x40",
+        "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x80",
+        "BriefDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "UMask": "0x1e",
+        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ASSIST.ANY",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json

+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode+C37",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB/sec). Derived from unc_m_pmm_rpq_inserts",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xE3",
+        "EventName": "UNC_M_PMM_BANDWIDTH.READ",
+        "PerPkg": "1",
+        "ScaleUnit": "6.103515625E-5MB/sec",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec). Derived from unc_m_pmm_wpq_inserts",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xE7",
+        "EventName": "UNC_M_PMM_BANDWIDTH.WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "6.103515625E-5MB/sec",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec). Derived from unc_m_pmm_rpq_inserts",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xE3",
+        "EventName": "UNC_M_PMM_BANDWIDTH.TOTAL",
+        "MetricExpr": "UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS",
+        "MetricName": "UNC_M_PMM_BANDWIDTH.TOTAL",
+        "PerPkg": "1",
+        "ScaleUnit": "6.103515625E-5MB/sec",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xE0",
+        "EventName": "UNC_M_PMM_READ_LATENCY",
+        "MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
+        "MetricName": "UNC_M_PMM_READ_LATENCY",
+        "PerPkg": "1",
+        "ScaleUnit": "6000000000ns",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    }
+]

tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json

+[
+    {
+        "BriefDescription": "Uncore cache clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_CHA_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "config1=0x40e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "config1=0x40040e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "config1=0x40041e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "config1=0x41833",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "config1=0x41a33",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x03",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0x0C",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UPI_DATA_BANDWIDTH_TX",
+        "PerPkg": "1",
+        "ScaleUnit": "7.11E-06Bytes",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    }
+]

tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json

+[
+    {
+        "EventCode": "0x08",
+        "UMask": "0x1",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x2",
+        "BriefDescription": "Page walk completed due to a demand data load to a 4K page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x4",
+        "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x8",
+        "BriefDescription": "Page walk completed due to a demand data load to a 1G page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x20",
+        "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x1",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x2",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x4",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x8",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1G page",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages.  The page walks can end with or without a page fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x20",
+        "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x4F",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
+        "Counter": "0,1,2,3",
+        "EventName": "EPT.WALK_PENDING",
+        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x1",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x2",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x4",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x8",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
+        "MSRValue": "0x00",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x20",
+        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAE",
+        "UMask": "0x1",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x1",
+        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.DTLB_THREAD",
+        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x20",
+        "BriefDescription": "STLB flush attempts",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.STLB_ANY",
+        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -31,4 +31,5 @@ GenuineIntel-6-2A,v15,sandybridge,core
 GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
-GenuineIntel-6-55,v1,skylakex,core
+GenuineIntel-6-55-[01234],v1,skylakex,core
+GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core

tools/perf/util/evlist.c

@@ -1176,7 +1176,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 	return err;
 }
 
-int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
+int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter)
 {
 	struct perf_evsel *evsel;
 	int err = 0;
@@ -1193,7 +1193,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	return err;
 }
 
-int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids)
+int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids)
 {
 	char *filter;
 	int ret = -1;
@@ -1214,15 +1214,15 @@ int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t
 		}
 	}
 
-	ret = perf_evlist__set_filter(evlist, filter);
+	ret = perf_evlist__set_tp_filter(evlist, filter);
 out_free:
 	free(filter);
 	return ret;
 }
 
-int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid)
+int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid)
 {
-	return perf_evlist__set_filter_pids(evlist, 1, &pid);
+	return perf_evlist__set_tp_filter_pids(evlist, 1, &pid);
 }
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)

tools/perf/util/evlist.h

@@ -98,9 +98,9 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
 #define perf_evlist__reset_sample_bit(evlist, bit) \
 	__perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit)
 
-int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
-int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid);
-int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids);
+int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter);
+int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid);
+int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids);
 
 struct perf_evsel *
 perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);

tools/perf/util/header.c

@@ -987,6 +987,45 @@ static int write_group_desc(struct feat_fd *ff,
 	return 0;
 }
 
+/*
+ * Return the CPU id as a raw string.
+ *
+ * Each architecture should provide a more precise id string that
+ * can be use to match the architecture's "mapfile".
+ */
+char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
+/* Return zero when the cpuid from the mapfile.csv matches the
+ * cpuid string generated on this platform.
+ * Otherwise return non-zero.
+ */
+int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, cpuid, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+		/* Verify the entire string matched. */
+		if (match_len == strlen(cpuid))
+			return 0;
+	}
+	return 1;
+}
+
 /*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(SRCARCH)/util/header.c

tools/perf/util/map.c

@@ -21,6 +21,7 @@
 #include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
+static void __maps__insert_name(struct maps *maps, struct map *map);
 
 static inline int is_anon_memory(const char *filename, u32 flags)
 {
@@ -496,6 +497,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 static void maps__init(struct maps *maps)
 {
 	maps->entries = RB_ROOT;
+	maps->names = RB_ROOT;
 	init_rwsem(&maps->lock);
 }
 
@@ -664,6 +666,7 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 static void __map_groups__insert(struct map_groups *mg, struct map *map)
 {
 	__maps__insert(&mg->maps, map);
+	__maps__insert_name(&mg->maps, map);
 	map->groups = mg;
 }
 
@@ -824,10 +827,34 @@ static void __maps__insert(struct maps *maps, struct map *map)
 	map__get(map);
 }
 
+static void __maps__insert_name(struct maps *maps, struct map *map)
+{
+	struct rb_node **p = &maps->names.rb_node;
+	struct rb_node *parent = NULL;
+	struct map *m;
+	int rc;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node_name);
+		rc = strcmp(m->dso->short_name, map->dso->short_name);
+		if (rc < 0)
+			p = &(*p)->rb_left;
+		else if (rc  > 0)
+			p = &(*p)->rb_right;
+		else
+			return;
+	}
+	rb_link_node(&map->rb_node_name, parent, p);
+	rb_insert_color(&map->rb_node_name, &maps->names);
+	map__get(map);
+}
+
 void maps__insert(struct maps *maps, struct map *map)
 {
 	down_write(&maps->lock);
 	__maps__insert(maps, map);
+	__maps__insert_name(maps, map);
 	up_write(&maps->lock);
 }
 

tools/perf/util/map.h

@@ -25,6 +25,7 @@ struct map {
 		struct rb_node	rb_node;
 		struct list_head node;
 	};
+	struct rb_node          rb_node_name;
 	u64			start;
 	u64			end;
 	bool			erange_warned;
@@ -57,6 +58,7 @@ struct kmap {
 
 struct maps {
 	struct rb_root	 entries;
+	struct rb_root	 names;
 	struct rw_semaphore lock;
 };
 

tools/perf/util/pmu.c

@@ -145,7 +145,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	int fd, ret = -1;
 	char path[PATH_MAX];
 
-	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -175,7 +175,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	ssize_t sret;
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -205,7 +205,7 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
 	char path[PATH_MAX];
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -223,7 +223,7 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	char path[PATH_MAX];
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -655,45 +655,6 @@ static int is_arm_pmu_core(const char *name)
 	return 0;
 }
 
-/*
- * Return the CPU id as a raw string.
- *
- * Each architecture should provide a more precise id string that
- * can be use to match the architecture's "mapfile".
- */
-char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
-{
-	return NULL;
-}
-
-/* Return zero when the cpuid from the mapfile.csv matches the
- * cpuid string generated on this platform.
- * Otherwise return non-zero.
- */
-int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
-{
-	regex_t re;
-	regmatch_t pmatch[1];
-	int match;
-
-	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
-		/* Warn unable to generate match particular string. */
-		pr_info("Invalid regular expression %s\n", mapcpuid);
-		return 1;
-	}
-
-	match = !regexec(&re, cpuid, 1, pmatch, 0);
-	regfree(&re);
-	if (match) {
-		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
-
-		/* Verify the entire string matched. */
-		if (match_len == strlen(cpuid))
-			return 0;
-	}
-	return 1;
-}
-
 static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;

tools/perf/util/stat-shadow.c

@@ -212,8 +212,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
 
 	count *= counter->scale;
 
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
-	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
+	if (perf_evsel__is_clock(counter))
 		update_runtime_stat(st, STAT_NSECS, 0, cpu, count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);

tools/perf/util/symbol.c

@@ -1680,11 +1680,22 @@ struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
 {
 	struct maps *maps = &mg->maps;
 	struct map *map;
+	struct rb_node *node;
 
 	down_read(&maps->lock);
 
-	for (map = maps__first(maps); map; map = map__next(map)) {
-		if (map->dso && strcmp(map->dso->short_name, name) == 0)
+	for (node = maps->names.rb_node; node; ) {
+		int rc;
+
+		map = rb_entry(node, struct map, rb_node_name);
+
+		rc = strcmp(map->dso->short_name, name);
+		if (rc < 0)
+			node = node->rb_left;
+		else if (rc > 0)
+			node = node->rb_right;
+		else
+
 			goto out_unlock;
 	}