Merge tag 'perf-core-for-mingo-4.15-20170922' 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:

- Support direct --user-regs arguments in 'perf record', previously the
  only way to sample PERF_SAMPLE_REGS_USER was implicitly selecting it
  when recording callchains (Andi Kleen)

- Support showing sampled user regs in 'perf script' (Andi Kleen)

- Introduce the concept of weak groups in 'perf stat': try to set up a
  group, but if it's not schedulable fallback to not using a group. That
  gives us the best of both worlds: groups if they work, but still a
  usable fallback if they don't. E.g: (Andi Kleen)

  % perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1

    125,366,055  branches                                    (80.02%)
      9,208,402  branch-misses       # 7.35% of all branches (80.01%)
     24,560,249  l1d.replacement                             (80.00%)
     43,174,971  l2_lines_in.all                             (80.05%)
     31,891,457  l2_rqsts.all_code_rd                        (79.92%)

- Support metrics in 'stat' and 'list'. A metric is a formula that
  uses multiple events to compute a higher level result (e.g. IPC). (Andi Kleen)

- Add Intel processors vendor event metrics JSON files (Andi Kleen)

- Add 'pid' and 'tid' options to 'perf sched timehist' (David Ahern)

- Generate 'behavior' string table from kernel headers, helps getting
  new parameters when synchronizing kernel headers, like MADV_WIPEONFORK
  and MADV_KEEPONFORK, that are now beautied (Arnaldo Carvalho de Melo)

- Improve TUI progress bar by showing how many bytes from a total were
  processed (Jiri Olsa)

- Use scandir() to replace readdir(), prep work to have the synthesizing
  of PERF_RECORD_ entries for existing threads be multithreaded, making
  'perf top' bearable on high core count systems such as Intel's Knights
  Landing/Mill  (Kan Liang)

- Allow creating a ~/.perfconfig file when setting a variable to its
  default value, previously it would bail out and not write such a
  file (Taeung Song)

- Introduce wrapper for allowing purely single threaded apps to avoid
  the costs of locking (Arnaldo Carvalho de Melo)

- Introduce hashtable to reduce the cost of thread lookup

- Fix build C++ build wrt poison.h using void pointer arithmetic,
  affects only the embedded clang/llvm case, that is disabled by
  default (Arnaldo Carvalho de Melo)

- Fix leaking rec_argv in error cases (Martin Kepplinger)

- Remove Intel CQM perf test, that infrastructure was nuked (Xiaochen Shen)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/include/linux/poison.h

@@ -14,6 +14,10 @@
 # define POISON_POINTER_DELTA 0
 #endif
 
+#ifdef __cplusplus
+#define LIST_POISON1  NULL
+#define LIST_POISON2  NULL
+#else
 /*
  * These are non-NULL pointers that will result in page faults
  * under normal circumstances, used to verify that nobody uses
@@ -21,6 +25,7 @@
  */
 #define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
 #define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
+#endif
 
 /********** include/linux/timer.h **********/
 /*

tools/include/uapi/asm-generic/mman-common.h

@@ -58,20 +58,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_DONTDUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

tools/perf/Documentation/perf-list.txt

@@ -8,7 +8,8 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
+'perf list' [--no-desc] [--long-desc]
+            [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob]
 
 DESCRIPTION
 -----------
@@ -47,6 +48,8 @@ counted. The following modifiers exist:
  P - use maximum detected precise level
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
+ W - group is weak and will fallback to non-group if not schedulable,
+     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
@@ -246,6 +249,10 @@ To limit the list use:
 
 . 'sdt' to list all Statically Defined Tracepoint events.
 
+. 'metric' to list metrics
+
+. 'metricgroup' to list metricgroups with metrics.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 

tools/perf/Documentation/perf-record.txt

@@ -377,6 +377,8 @@ symbolic names, e.g. on x86, ax, si. To list the available registers use
 --intr-regs=\?. To name registers, pass a comma separated list such as
 --intr-regs=ax,bx. The list of register is architecture dependent.
 
+--user-regs::
+Capture user registers at sample time. Same arguments as -I.
 
 --running-time::
 Record running and enabled time for read events (:S)

tools/perf/Documentation/perf-sched.txt

@@ -106,6 +106,14 @@ OPTIONS for 'perf sched timehist'
 --max-stack::
 	Maximum number of functions to display in backtrace, default 5.
 
+-p=::
+--pid=::
+	Only show events for given process ID (comma separated list).
+
+-t=::
+--tid=::
+	Only show events for given thread ID (comma separated list).
+
 -s::
 --summary::
     Show only a summary of scheduling by thread with min, max, and average

tools/perf/Documentation/perf-script.txt

@@ -116,8 +116,8 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth, phys_addr.
+        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
+        brstackoff, callindent, insn, insnlen, synth, phys_addr.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace

tools/perf/Documentation/perf-stat.txt

@@ -199,6 +199,13 @@ Aggregate counts per processor socket for system-wide mode measurements.
 --per-core::
 Aggregate counts per physical processor for system-wide mode measurements.
 
+-M::
+--metrics::
+Print metrics or metricgroups specified in a comma separated list.
+For a group all metrics from the group are added.
+The events from the metrics are automatically measured.
+See perf list output for the possble metrics and metricgroups.
+
 -A::
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.

tools/perf/MANIFEST

@@ -1,34 +1,8 @@
 tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
 tools/scripts
 tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
 tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
@@ -42,60 +16,3 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-tools/include/asm-generic/bitops.h
-tools/include/linux/atomic.h
-tools/include/linux/bitops.h
-tools/include/linux/compiler.h
-tools/include/linux/compiler-gcc.h
-tools/include/linux/coresight-pmu.h
-tools/include/linux/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/fcntl.h
-tools/include/uapi/asm-generic/ioctls.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/drm/drm.h
-tools/include/uapi/drm/i915_drm.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/kvm.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/sched.h
-tools/include/uapi/linux/stat.h
-tools/include/uapi/linux/vhost.h
-tools/include/uapi/sound/asound.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h

tools/perf/Makefile.perf

@@ -173,7 +173,7 @@ AWK     = awk
 # non-config cases
 config := 1
 
-NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
+NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -441,6 +441,13 @@ perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh
 $(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl)
 	$(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@
 
+madvise_behavior_array := $(beauty_outdir)/madvise_behavior_array.c
+madvise_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
+
+$(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
+	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
+
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
@@ -541,6 +548,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kvm_ioctl_array) \
 	$(vhost_virtio_ioctl_array) \
+	$(madvise_behavior_array) \
 	$(perf_ioctl_array)
 
 $(OUTPUT)%.o: %.c prepare FORCE
@@ -802,7 +810,10 @@ config-clean:
 	$(call QUIET_CLEAN, config)
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
+python-clean:
+	$(python-clean)
+
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
@@ -811,6 +822,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)util/intel-pt-decoder/inat-tables.c \
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
+		$(OUTPUT)$(madvise_behavior_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \
@@ -819,7 +831,6 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array)
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
-	$(python-clean)
 
 #
 # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)

tools/perf/arch/x86/include/arch-tests.h

@@ -8,7 +8,6 @@ struct test;
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
-int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;

tools/perf/arch/x86/tests/Build

@@ -5,4 +5,3 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
-libperf-y += intel-cqm.o

tools/perf/arch/x86/tests/arch-tests.c

@@ -23,10 +23,6 @@ struct test arch_tests[] = {
 		.func = test__insn_x86,
 	},
 #endif
-	{
-		.desc = "Intel cqm nmi context read",
-		.func = test__intel_cqm_count_nmi_context,
-	},
 	{
 		.func = NULL,
 	},

tools/perf/arch/x86/tests/intel-cqm.c

@@ -1,127 +0,0 @@
-#include "tests/tests.h"
-#include "perf.h"
-#include "cloexec.h"
-#include "debug.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "arch-tests.h"
-
-#include <signal.h>
-#include <sys/mman.h>
-#include <sys/wait.h>
-#include <errno.h>
-#include <string.h>
-
-static pid_t spawn(void)
-{
-	pid_t pid;
-
-	pid = fork();
-	if (pid)
-		return pid;
-
-	while(1)
-		sleep(5);
-	return 0;
-}
-
-/*
- * Create an event group that contains both a sampled hardware
- * (cpu-cycles) and software (intel_cqm/llc_occupancy/) event. We then
- * wait for the hardware perf counter to overflow and generate a PMI,
- * which triggers an event read for both of the events in the group.
- *
- * Since reading Intel CQM event counters requires sending SMP IPIs, the
- * CQM pmu needs to handle the above situation gracefully, and return
- * the last read counter value to avoid triggering a WARN_ON_ONCE() in
- * smp_call_function_many() caused by sending IPIs from NMI context.
- */
-int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused)
-{
-	struct perf_evlist *evlist = NULL;
-	struct perf_evsel *evsel = NULL;
-	struct perf_event_attr pe;
-	int i, fd[2], flag, ret;
-	size_t mmap_len;
-	void *event;
-	pid_t pid;
-	int err = TEST_FAIL;
-
-	flag = perf_event_open_cloexec_flag();
-
-	evlist = perf_evlist__new();
-	if (!evlist) {
-		pr_debug("perf_evlist__new failed\n");
-		return TEST_FAIL;
-	}
-
-	ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL);
-	if (ret) {
-		pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n");
-		err = TEST_SKIP;
-		goto out;
-	}
-
-	evsel = perf_evlist__first(evlist);
-	if (!evsel) {
-		pr_debug("perf_evlist__first failed\n");
-		goto out;
-	}
-
-	memset(&pe, 0, sizeof(pe));
-	pe.size = sizeof(pe);
-
-	pe.type = PERF_TYPE_HARDWARE;
-	pe.config = PERF_COUNT_HW_CPU_CYCLES;
-	pe.read_format = PERF_FORMAT_GROUP;
-
-	pe.sample_period = 128;
-	pe.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_READ;
-
-	pid = spawn();
-
-	fd[0] = sys_perf_event_open(&pe, pid, -1, -1, flag);
-	if (fd[0] < 0) {
-		pr_debug("failed to open event\n");
-		goto out;
-	}
-
-	memset(&pe, 0, sizeof(pe));
-	pe.size = sizeof(pe);
-
-	pe.type = evsel->attr.type;
-	pe.config = evsel->attr.config;
-
-	fd[1] = sys_perf_event_open(&pe, pid, -1, fd[0], flag);
-	if (fd[1] < 0) {
-		pr_debug("failed to open event\n");
-		goto out;
-	}
-
-	/*
-	 * Pick a power-of-two number of pages + 1 for the meta-data
-	 * page (struct perf_event_mmap_page). See tools/perf/design.txt.
-	 */
-	mmap_len = page_size * 65;
-
-	event = mmap(NULL, mmap_len, PROT_READ, MAP_SHARED, fd[0], 0);
-	if (event == (void *)(-1)) {
-		pr_debug("failed to mmap %d\n", errno);
-		goto out;
-	}
-
-	sleep(1);
-
-	err = TEST_OK;
-
-	munmap(event, mmap_len);
-
-	for (i = 0; i < 2; i++)
-		close(fd[i]);
-
-	kill(pid, SIGKILL);
-	wait(NULL);
-out:
-	perf_evlist__delete(evlist);
-	return err;
-}

tools/perf/builtin-c2c.c

@@ -2732,6 +2732,7 @@ static int perf_c2c__record(int argc, const char **argv)
 		if (!perf_mem_events[j].supported) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events[j].name);
+			free(rec_argv);
 			return -1;
 		}
 

tools/perf/builtin-config.c

@@ -34,8 +34,7 @@ static struct option config_options[] = {
 	OPT_END()
 };
 
-static int set_config(struct perf_config_set *set, const char *file_name,
-		      const char *var, const char *value)
+static int set_config(struct perf_config_set *set, const char *file_name)
 {
 	struct perf_config_section *section = NULL;
 	struct perf_config_item *item = NULL;
@@ -49,7 +48,6 @@ static int set_config(struct perf_config_set *set, const char *file_name,
 	if (!fp)
 		return -1;
 
-	perf_config_set__collect(set, file_name, var, value);
 	fprintf(fp, "%s\n", first_line);
 
 	/* overwrite configvariables */
@@ -161,6 +159,7 @@ int cmd_config(int argc, const char **argv)
 	struct perf_config_set *set;
 	char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 	const char *config_filename;
+	bool changed = false;
 
 	argc = parse_options(argc, argv, config_options, config_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
@@ -231,15 +230,26 @@ int cmd_config(int argc, const char **argv)
 					goto out_err;
 				}
 			} else {
-				if (set_config(set, config_filename, var, value) < 0) {
-					pr_err("Failed to set '%s=%s' on %s\n",
-					       var, value, config_filename);
+				if (perf_config_set__collect(set, config_filename,
+							     var, value) < 0) {
+					pr_err("Failed to add '%s=%s'\n",
+					       var, value);
 					free(arg);
 					goto out_err;
 				}
+				changed = true;
 			}
 			free(arg);
 		}
+
+		if (!changed)
+			break;
+
+		if (set_config(set, config_filename) < 0) {
+			pr_err("Failed to set the configs on %s\n",
+			       config_filename);
+			goto out_err;
+		}
 	}
 
 	ret = 0;

tools/perf/builtin-kvm.c

@@ -34,7 +34,6 @@
 #include <termios.h>
 #include <semaphore.h>
 #include <signal.h>
-#include <pthread.h>
 #include <math.h>
 
 static const char *get_filename_for_perf_kvm(void)

tools/perf/builtin-list.c

@@ -15,6 +15,7 @@
 #include "util/cache.h"
 #include "util/pmu.h"
 #include "util/debug.h"
+#include "util/metricgroup.h"
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
@@ -79,6 +80,10 @@ int cmd_list(int argc, const char **argv)
 						long_desc_flag, details_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
+		else if (strcmp(argv[i], "metric") == 0)
+			metricgroup__print(true, false, NULL, raw_dump);
+		else if (strcmp(argv[i], "metricgroup") == 0)
+			metricgroup__print(false, true, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;
 
@@ -96,6 +101,7 @@ int cmd_list(int argc, const char **argv)
 			s[sep_idx] = '\0';
 			print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
 			print_sdt_events(s, s + sep_idx + 1, raw_dump);
+			metricgroup__print(true, true, s, raw_dump);
 			free(s);
 		} else {
 			if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -112,6 +118,7 @@ int cmd_list(int argc, const char **argv)
 						details_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
+			metricgroup__print(true, true, NULL, raw_dump);
 			free(s);
 		}
 	}

tools/perf/builtin-mem.c

@@ -112,6 +112,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		if (!perf_mem_events[j].supported) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(j));
+			free(rec_argv);
 			return -1;
 		}
 

tools/perf/builtin-record.c

@@ -1643,6 +1643,9 @@ static struct option __record_options[] = {
 	OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
 		    "sample selected machine registers on interrupt,"
 		    " use -I ? to list register names", parse_regs),
+	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
+		    "sample selected machine registers on interrupt,"
+		    " use -I ? to list register names", parse_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
 	OPT_CALLBACK('k', "clockid", &record.opts,

tools/perf/builtin-sched.c

@@ -3363,6 +3363,10 @@ int cmd_sched(int argc, const char **argv)
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
 	OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
+	OPT_STRING('p', "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
+		   "analyze events only for given process id(s)"),
+	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
+		   "analyze events only for given thread id(s)"),
 	OPT_PARENT(sched_options)
 	};
 

tools/perf/builtin-script.c

@@ -88,6 +88,7 @@ enum perf_output_field {
 	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
 	PERF_OUTPUT_SYNTH           = 1U << 25,
 	PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+	PERF_OUTPUT_UREGS	    = 1U << 27,
 };
 
 struct output_option {
@@ -109,6 +110,7 @@ struct output_option {
 	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 	{.str = "period", .field = PERF_OUTPUT_PERIOD},
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
+	{.str = "uregs", .field = PERF_OUTPUT_UREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
@@ -385,6 +387,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_IREGS))
 		return -EINVAL;
 
+	if (PRINT_FIELD(UREGS) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
+					PERF_OUTPUT_UREGS))
+		return -EINVAL;
+
 	if (PRINT_FIELD(PHYS_ADDR) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
 					PERF_OUTPUT_PHYS_ADDR))
@@ -509,6 +516,24 @@ static void print_sample_iregs(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_uregs(struct perf_sample *sample,
+			  struct perf_event_attr *attr)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	uint64_t mask = attr->sample_regs_user;
+	unsigned i = 0, r;
+
+	if (!regs || !regs->regs)
+		return;
+
+	printf(" ABI:%" PRIu64 " ", regs->abi);
+
+	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs->regs[i++];
+		printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+	}
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)
@@ -1444,6 +1469,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(IREGS))
 		print_sample_iregs(sample, attr);
 
+	if (PRINT_FIELD(UREGS))
+		print_sample_uregs(sample, attr);
+
 	if (PRINT_FIELD(BRSTACK))
 		print_sample_brstack(sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))
@@ -2739,7 +2767,7 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
 		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
@@ -2801,6 +2829,8 @@ int cmd_script(int argc, const char **argv)
 		NULL
 	};
 
+	perf_set_singlethreaded();
+
 	setup_scripting();
 
 	argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,

tools/perf/builtin-stat.c

@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/group.h"
 #include "util/string2.h"
+#include "util/metricgroup.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -133,6 +134,8 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
+static struct rblist		 metric_events;
+
 static struct target target = {
 	.uid	= UINT_MAX,
 };
@@ -192,6 +195,11 @@ static struct perf_stat_config stat_config = {
 	.scale		= true,
 };
 
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -407,6 +415,8 @@ static void process_interval(void)
 			pr_err("failed to write stat round event\n");
 	}
 
+	init_stats(&walltime_nsecs_stats);
+	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
 	print_counters(&rs, 0, NULL);
 }
 
@@ -582,6 +592,32 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
+static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
+{
+	struct perf_evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(c2);
+			c2->leader = c2;
+			c2->nr_members = 0;
+		}
+	}
+	return leader;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
@@ -618,6 +654,15 @@ static int __run_perf_stat(int argc, const char **argv)
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
 		if (create_perf_stat_counter(counter) < 0) {
+
+			/* Weak group failed. Reset the group. */
+			if ((errno == EINVAL || errno == EBADF) &&
+			    counter->leader != counter &&
+			    counter->weak_group) {
+				counter = perf_evsel__reset_weak_group(counter);
+				goto try_again;
+			}
+
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
 			 * (behavior changed with commit b0a873e).
@@ -1199,7 +1244,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
-				&out);
+				&out, &metric_events);
 	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
@@ -1325,6 +1370,9 @@ static void print_aggr(char *prefix)
 		ad.id = id = aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
+
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
 			if (!collect_data(counter, aggr_cb, &ad))
@@ -1468,6 +1516,8 @@ static void print_no_aggr_metric(char *prefix)
 		if (prefix)
 			fputs(prefix, stat_config.output);
 		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			if (first) {
 				aggr_printout(counter, cpu, 0);
 				first = false;
@@ -1522,6 +1572,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evsel_list, counter) {
+		if (is_duration_time(counter))
+			continue;
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
@@ -1530,7 +1582,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
-					      &out);
+					      &out,
+					      &metric_events);
 	}
 	fputc('\n', stat_config.output);
 }
@@ -1668,12 +1721,18 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		print_aggr(prefix);
 		break;
 	case AGGR_THREAD:
-		evlist__for_each_entry(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			print_aggr_thread(counter, prefix);
+		}
 		break;
 	case AGGR_GLOBAL:
-		evlist__for_each_entry(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			print_counter_aggr(counter, prefix);
+		}
 		if (metric_only)
 			fputc('\n', stat_config.output);
 		break;
@@ -1681,8 +1740,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		if (metric_only)
 			print_no_aggr_metric(prefix);
 		else {
-			evlist__for_each_entry(evsel_list, counter)
+			evlist__for_each_entry(evsel_list, counter) {
+				if (is_duration_time(counter))
+					continue;
 				print_counter(counter, prefix);
+			}
 		}
 		break;
 	case AGGR_UNSET:
@@ -1754,6 +1816,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_metric_groups(const struct option *opt,
+			       const char *str,
+			       int unset __maybe_unused)
+{
+	return metricgroup__parse_groups(opt, str, &metric_events);
+}
+
 static const struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1819,6 +1888,9 @@ static const struct option stat_options[] = {
 			"measure topdown level 1 statistics"),
 	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
 			"measure SMI cost"),
+	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
+		     "monitor specified metrics or metric groups (separated by ,)",
+		     parse_metric_groups),
 	OPT_END()
 };
 

tools/perf/builtin-timechart.c

@@ -1732,8 +1732,10 @@ static int timechart__io_record(int argc, const char **argv)
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
-	if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+	if (asprintf(&filter, "common_pid != %d", getpid()) < 0) {
+		free(rec_argv);
 		return -ENOMEM;
+	}
 
 	p = rec_argv;
 	for (i = 0; i < common_args_nr; i++)

tools/perf/builtin-trace.c

@@ -2078,6 +2078,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 			rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
 		else {
 			pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+			free(rec_argv);
 			return -1;
 		}
 	}
@@ -2730,20 +2731,23 @@ DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_event
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 {
-	DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
 	size_t printed = trace__fprintf_threads_header(fp);
 	struct rb_node *nd;
+	int i;
 
-	if (threads == NULL) {
-		fprintf(fp, "%s", "Error sorting output by nr_events!\n");
-		return 0;
-	}
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
 
-	resort_rb__for_each_entry(nd, threads)
-		printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
+		if (threads == NULL) {
+			fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+			return 0;
+		}
 
-	resort_rb__delete(threads);
+		resort_rb__for_each_entry(nd, threads)
+			printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
+		resort_rb__delete(threads);
+	}
 	return printed;
 }
 

tools/perf/perf.h

@@ -65,6 +65,7 @@ struct record_opts {
 	unsigned int user_freq;
 	u64          branch_stack;
 	u64	     sample_intr_regs;
+	u64	     sample_user_regs;
 	u64	     default_interval;
 	u64	     user_interval;
 	size_t	     auxtrace_snapshot_size;

tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "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 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+	"MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / 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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( 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/broadwellde/bdwde-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "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 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+	"MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / 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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( 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/broadwellx/bdx-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "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 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+	"MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / 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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (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/haswell/hsw-metrics.json

@@ -0,0 +1,158 @@
+[
+    {
+        "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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "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.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else (UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION ) ) / 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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( 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": "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/haswellx/hsx-metrics.json

@@ -0,0 +1,158 @@
+[
+    {
+        "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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "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.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION ) ) / 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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( 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": "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/ivybridge/ivb-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "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 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( 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_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.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/ivytown/ivt-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "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 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_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_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "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 / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 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_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( 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_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.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/jaketown/jkt-metrics.json

@@ -0,0 +1,140 @@
+[
+    {
+        "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 * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "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_DISPATCHED.THREAD / ( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "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": "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_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.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/sandybridge/snb-metrics.json

@@ -0,0 +1,140 @@
+[
+    {
+        "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 * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "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_DISPATCHED.THREAD / ( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "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": "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_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.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/skylake/skl-metrics.json

@@ -0,0 +1,164 @@
+[
+    {
+        "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 + MEM_LOAD_RETIRED.FB_HIT )",
+        "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/skylakex/skx-metrics.json

@@ -0,0 +1,182 @@
+[
+    {
+        "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 (per-core)",
+        "MetricExpr": "4*cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
+        "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 / cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
+        "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": "( RS_EVENTS.EMPTY_CYCLES - (ICACHE_16B.IFDATA_STALL +2* ICACHE_16B.IFDATA_STALL:c1:e1) - 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 if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if 1 else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
+        "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 * cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "L1 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "BriefDescription": "L2 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "BriefDescription": "L3 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
+        "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 + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16* FP_ARITH_INST_RETIRED.512B_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/jevents.c

@@ -292,7 +292,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
 				    char *desc, char *long_desc,
 				    char *pmu, char *unit, char *perpkg,
 				    char *metric_expr,
-				    char *metric_name)
+				    char *metric_name, char *metric_group)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -304,8 +304,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
 	 */
 	fprintf(outfp, "{\n");
 
-	fprintf(outfp, "\t.name = \"%s\",\n", name);
-	fprintf(outfp, "\t.event = \"%s\",\n", event);
+	if (name)
+		fprintf(outfp, "\t.name = \"%s\",\n", name);
+	if (event)
+		fprintf(outfp, "\t.event = \"%s\",\n", event);
 	fprintf(outfp, "\t.desc = \"%s\",\n", desc);
 	fprintf(outfp, "\t.topic = \"%s\",\n", topic);
 	if (long_desc && long_desc[0])
@@ -320,6 +322,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
 	if (metric_name)
 		fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
+	if (metric_group)
+		fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -357,6 +361,9 @@ static char *real_event(const char *name, char *event)
 {
 	int i;
 
+	if (!name)
+		return NULL;
+
 	for (i = 0; fixed[i].name; i++)
 		if (!strcasecmp(name, fixed[i].name))
 			return (char *)fixed[i].event;
@@ -369,7 +376,7 @@ int json_events(const char *fn,
 		      char *long_desc,
 		      char *pmu, char *unit, char *perpkg,
 		      char *metric_expr,
-		      char *metric_name),
+		      char *metric_name, char *metric_group),
 	  void *data)
 {
 	int err = -EIO;
@@ -397,6 +404,7 @@ int json_events(const char *fn,
 		char *unit = NULL;
 		char *metric_expr = NULL;
 		char *metric_name = NULL;
+		char *metric_group = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;
@@ -476,6 +484,8 @@ int json_events(const char *fn,
 				addfield(map, &perpkg, "", "", val);
 			} else if (json_streq(map, field, "MetricName")) {
 				addfield(map, &metric_name, "", "", val);
+			} else if (json_streq(map, field, "MetricGroup")) {
+				addfield(map, &metric_group, "", "", val);
 			} else if (json_streq(map, field, "MetricExpr")) {
 				addfield(map, &metric_expr, "", "", val);
 				for (s = metric_expr; *s; s++)
@@ -501,10 +511,11 @@ int json_events(const char *fn,
 			addfield(map, &event, ",", filter, NULL);
 		if (msr != NULL)
 			addfield(map, &event, ",", msr->pname, msrval);
-		fixname(name);
+		if (name)
+			fixname(name);
 
 		err = func(data, name, real_event(name, event), desc, long_desc,
-				pmu, unit, perpkg, metric_expr, metric_name);
+			   pmu, unit, perpkg, metric_expr, metric_name, metric_group);
 		free(event);
 		free(desc);
 		free(name);
@@ -516,6 +527,7 @@ int json_events(const char *fn,
 		free(unit);
 		free(metric_expr);
 		free(metric_name);
+		free(metric_group);
 		if (err)
 			break;
 		tok += j;

tools/perf/pmu-events/jevents.h

@@ -6,7 +6,7 @@ int json_events(const char *fn,
 				char *long_desc,
 				char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
-				char *metric_name),
+				char *metric_name, char *metric_group),
 		void *data);
 char *get_cpu_str(void);
 

tools/perf/pmu-events/pmu-events.h

@@ -15,6 +15,7 @@ struct pmu_event {
 	const char *perpkg;
 	const char *metric_expr;
 	const char *metric_name;
+	const char *metric_group;
 };
 
 /*

tools/perf/tests/builtin-test.c

@@ -3,6 +3,7 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <fcntl.h>
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>

tools/perf/trace/beauty/madvise_behavior.sh

@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *madvise_advices[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/mman-common.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"

tools/perf/trace/beauty/mmap.c

@@ -94,35 +94,21 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 #define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
 
+static size_t madvise__scnprintf_behavior(int behavior, char *bf, size_t size)
+{
+#include "trace/beauty/generated/madvise_behavior_array.c"
+       static DEFINE_STRARRAY(madvise_advices);
+
+       if (behavior < strarray__madvise_advices.nr_entries && strarray__madvise_advices.entries[behavior] != NULL)
+               return scnprintf(bf, size, "MADV_%s", strarray__madvise_advices.entries[behavior]);
+
+       return scnprintf(bf, size, "%#", behavior);
+}
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
-	int behavior = arg->val;
-
-	switch (behavior) {
-#define	P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
-	P_MADV_BHV(NORMAL);
-	P_MADV_BHV(RANDOM);
-	P_MADV_BHV(SEQUENTIAL);
-	P_MADV_BHV(WILLNEED);
-	P_MADV_BHV(DONTNEED);
-	P_MADV_BHV(FREE);
-	P_MADV_BHV(REMOVE);
-	P_MADV_BHV(DONTFORK);
-	P_MADV_BHV(DOFORK);
-	P_MADV_BHV(HWPOISON);
-	P_MADV_BHV(SOFT_OFFLINE);
-	P_MADV_BHV(MERGEABLE);
-	P_MADV_BHV(UNMERGEABLE);
-	P_MADV_BHV(HUGEPAGE);
-	P_MADV_BHV(NOHUGEPAGE);
-	P_MADV_BHV(DONTDUMP);
-	P_MADV_BHV(DODUMP);
-#undef P_MADV_BHV
-	default: break;
-	}
-
-	return scnprintf(bf, size, "%#x", behavior);
+	return madvise__scnprintf_behavior(arg->val, bf, size);
 }
 
 #define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior

tools/perf/ui/progress.c

@@ -27,13 +27,17 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
 	}
 }
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+void __ui_progress__init(struct ui_progress *p, u64 total,
+			 const char *title, bool size)
 {
 	p->curr = 0;
 	p->next = p->step = total / 16 ?: 1;
 	p->total = total;
 	p->title = title;
+	p->size  = size;
 
+	if (ui_progress__ops->init)
+		ui_progress__ops->init(p);
 }
 
 void ui_progress__finish(void)

tools/perf/ui/progress.h

@@ -8,12 +8,22 @@ void ui_progress__finish(void);
 struct ui_progress {
 	const char *title;
 	u64 curr, next, step, total;
+	bool size;
 };
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void __ui_progress__init(struct ui_progress *p, u64 total,
+			 const char *title, bool size);
+
+#define ui_progress__init(p, total, title) \
+	__ui_progress__init(p, total, title, false)
+
+#define ui_progress__init_size(p, total, title) \
+	__ui_progress__init(p, total, title, true)
+
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
 struct ui_progress_ops {
+	void (*init)(struct ui_progress *p);
 	void (*update)(struct ui_progress *p);
 	void (*finish)(void);
 };

tools/perf/ui/tui/progress.c

@@ -1,12 +1,33 @@
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
 #include "tui.h"
+#include "units.h"
 #include "../browser.h"
 
+static void __tui_progress__init(struct ui_progress *p)
+{
+	p->next = p->step = p->total / (SLtt_Screen_Cols - 2) ?: 1;
+}
+
+static int get_title(struct ui_progress *p, char *buf, size_t size)
+{
+	char buf_cur[20];
+	char buf_tot[20];
+	int ret;
+
+	ret  = unit_number__scnprintf(buf_cur, sizeof(buf_cur), p->curr);
+	ret += unit_number__scnprintf(buf_tot, sizeof(buf_tot), p->total);
+
+	return ret + scnprintf(buf, size, "%s [%s/%s]",
+			       p->title, buf_cur, buf_tot);
+}
+
 static void tui_progress__update(struct ui_progress *p)
 {
+	char buf[100], *title = (char *) p->title;
 	int bar, y;
 	/*
 	 * FIXME: We should have a per UI backend way of showing progress,
@@ -18,13 +39,18 @@ static void tui_progress__update(struct ui_progress *p)
 	if (p->total == 0)
 		return;
 
+	if (p->size) {
+		get_title(p, buf, sizeof(buf));
+		title = buf;
+	}
+
 	ui__refresh_dimensions(false);
 	pthread_mutex_lock(&ui__lock);
 	y = SLtt_Screen_Rows / 2 - 2;
 	SLsmg_set_color(0);
 	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
 	SLsmg_gotorc(y++, 1);
-	SLsmg_write_string((char *)p->title);
+	SLsmg_write_string(title);
 	SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
 	SLsmg_set_color(HE_COLORSET_SELECTED);
 	bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
@@ -49,8 +75,8 @@ static void tui_progress__finish(void)
 	pthread_mutex_unlock(&ui__lock);
 }
 
-static struct ui_progress_ops tui_progress__ops =
-{
+static struct ui_progress_ops tui_progress__ops = {
+	.init   = __tui_progress__init,
 	.update = tui_progress__update,
 	.finish = tui_progress__finish,
 };

tools/perf/util/Build

@@ -34,6 +34,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -78,6 +79,7 @@ libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
 libperf-y += call-path.o
+libperf-y += rwsem.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/

tools/perf/util/config.c

@@ -700,10 +700,7 @@ struct perf_config_set *perf_config_set__new(void)
 
 	if (set) {
 		INIT_LIST_HEAD(&set->sections);
-		if (perf_config_set__init(set) < 0) {
-			perf_config_set__delete(set);
-			set = NULL;
-		}
+		perf_config_set__init(set);
 	}
 
 	return set;

tools/perf/util/data.c

@@ -3,6 +3,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
 

tools/perf/util/dso.c

@@ -6,6 +6,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <errno.h>
+#include <fcntl.h>
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
@@ -1365,9 +1366,9 @@ void __dsos__add(struct dsos *dsos, struct dso *dso)
 
 void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 	__dsos__add(dsos, dso);
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 }
 
 struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
@@ -1386,9 +1387,9 @@ struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
 	struct dso *dso;
-	pthread_rwlock_rdlock(&dsos->lock);
+	down_read(&dsos->lock);
 	dso = __dsos__find(dsos, name, cmp_short);
-	pthread_rwlock_unlock(&dsos->lock);
+	up_read(&dsos->lock);
 	return dso;
 }
 
@@ -1415,9 +1416,9 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 struct dso *dsos__findnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso;
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 	dso = dso__get(__dsos__findnew(dsos, name));
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 	return dso;
 }
 

tools/perf/util/dso.h

@@ -6,7 +6,7 @@
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include <pthread.h>
+#include "rwsem.h"
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -129,7 +129,7 @@ struct dso_cache {
 struct dsos {
 	struct list_head head;
 	struct rb_root	 root;	/* rbtree root sorted by long name */
-	pthread_rwlock_t lock;
+	struct rw_semaphore lock;
 };
 
 struct auxtrace_cache;

tools/perf/util/event.c

@@ -1,5 +1,6 @@
 #include <dirent.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -683,12 +684,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   bool mmap_data,
 				   unsigned int proc_map_timeout)
 {
-	DIR *proc;
-	char proc_path[PATH_MAX];
-	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	union perf_event *namespaces_event;
+	char proc_path[PATH_MAX];
+	struct dirent **dirent;
 	int err = -1;
+	char *end;
+	pid_t pid;
+	int n, i;
 
 	if (machine__is_default_guest(machine))
 		return 0;
@@ -712,29 +715,32 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		goto out_free_fork;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	proc = opendir(proc_path);
+	n = scandir(proc_path, &dirent, 0, alphasort);
 
-	if (proc == NULL)
+	if (n < 0)
 		goto out_free_namespaces;
 
-	while ((dirent = readdir(proc)) != NULL) {
-		char *end;
-		pid_t pid = strtol(dirent->d_name, &end, 10);
-
-		if (*end) /* only interested in proper numerical dirents */
+	for (i = 0; i < n; i++) {
+		if (!isdigit(dirent[i]->d_name[0]))
 			continue;
-		/*
- 		 * We may race with exiting thread, so don't stop just because
- 		 * one thread couldn't be synthesized.
- 		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event,
-					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data,
-					   proc_map_timeout);
-	}
 
+		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+		/* only interested in proper numerical dirents */
+		if (!*end) {
+			/*
+			 * We may race with exiting thread, so don't stop just because
+			 * one thread couldn't be synthesized.
+			 */
+			__event__synthesize_thread(comm_event, mmap_event, fork_event,
+						   namespaces_event, pid, 1, process,
+						   tool, machine, mmap_data,
+						   proc_map_timeout);
+		}
+		free(dirent[i]);
+	}
+	free(dirent);
 	err = 0;
-	closedir(proc);
+
 out_free_namespaces:
 	free(namespaces_event);
 out_free_fork:

tools/perf/util/evlist.h

@@ -6,6 +6,7 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"

tools/perf/util/evsel.c

@@ -678,7 +678,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_regs_user |= PERF_REGS_MASK;
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {
@@ -931,6 +931,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
+	if (opts->sample_user_regs) {
+		attr->sample_regs_user |= opts->sample_user_regs;
+		perf_evsel__set_sample_bit(evsel, REGS_USER);
+	}
+
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 

tools/perf/util/evsel.h

@@ -137,6 +137,7 @@ struct perf_evsel {
 	const char *		metric_name;
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
+	bool			weak_group;
 };
 
 union u64_swap {

tools/perf/util/machine.c

@@ -30,7 +30,21 @@ static void dsos__init(struct dsos *dsos)
 {
 	INIT_LIST_HEAD(&dsos->head);
 	dsos->root = RB_ROOT;
-	pthread_rwlock_init(&dsos->lock, NULL);
+	init_rwsem(&dsos->lock);
+}
+
+static void machine__threads_init(struct machine *machine)
+{
+	int i;
+
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		threads->entries = RB_ROOT;
+		init_rwsem(&threads->lock);
+		threads->nr = 0;
+		INIT_LIST_HEAD(&threads->dead);
+		threads->last_match = NULL;
+	}
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -40,11 +54,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
-	machine->threads = RB_ROOT;
-	pthread_rwlock_init(&machine->threads_lock, NULL);
-	machine->nr_threads = 0;
-	INIT_LIST_HEAD(&machine->dead_threads);
-	machine->last_match = NULL;
+	machine__threads_init(machine);
 
 	machine->vdso_info = NULL;
 	machine->env = NULL;
@@ -120,7 +130,7 @@ static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
@@ -129,39 +139,49 @@ static void dsos__purge(struct dsos *dsos)
 		dso__put(pos);
 	}
 
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 }
 
 static void dsos__exit(struct dsos *dsos)
 {
 	dsos__purge(dsos);
-	pthread_rwlock_destroy(&dsos->lock);
+	exit_rwsem(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
 	struct rb_node *nd;
+	int i;
 
-	pthread_rwlock_wrlock(&machine->threads_lock);
-	nd = rb_first(&machine->threads);
-	while (nd) {
-		struct thread *t = rb_entry(nd, struct thread, rb_node);
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		down_write(&threads->lock);
+		nd = rb_first(&threads->entries);
+		while (nd) {
+			struct thread *t = rb_entry(nd, struct thread, rb_node);
 
-		nd = rb_next(nd);
-		__machine__remove_thread(machine, t, false);
+			nd = rb_next(nd);
+			__machine__remove_thread(machine, t, false);
+		}
+		up_write(&threads->lock);
 	}
-	pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
+	int i;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
 	zfree(&machine->current_tid);
-	pthread_rwlock_destroy(&machine->threads_lock);
+
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		exit_rwsem(&threads->lock);
+	}
 }
 
 void machine__delete(struct machine *machine)
@@ -379,10 +399,11 @@ out_err:
  * lookup/new thread inserted.
  */
 static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
 						  pid_t pid, pid_t tid,
 						  bool create)
 {
-	struct rb_node **p = &machine->threads.rb_node;
+	struct rb_node **p = &threads->entries.rb_node;
 	struct rb_node *parent = NULL;
 	struct thread *th;
 
@@ -391,14 +412,14 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	th = machine->last_match;
+	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
 
-		machine->last_match = NULL;
+		threads->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -406,7 +427,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = th;
+			threads->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -423,7 +444,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &machine->threads);
+		rb_insert_color(&th->rb_node, &threads->entries);
 
 		/*
 		 * We have to initialize map_groups separately
@@ -434,7 +455,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase_init(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &threads->entries);
 			RB_CLEAR_NODE(&th->rb_node);
 			thread__put(th);
 			return NULL;
@@ -443,8 +464,8 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = th;
-		++machine->nr_threads;
+		threads->last_match = th;
+		++threads->nr;
 	}
 
 	return th;
@@ -452,27 +473,30 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-	return ____machine__findnew_thread(machine, pid, tid, true);
+	return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 				       pid_t tid)
 {
+	struct threads *threads = machine__threads(machine, tid);
 	struct thread *th;
 
-	pthread_rwlock_wrlock(&machine->threads_lock);
+	down_write(&threads->lock);
 	th = __machine__findnew_thread(machine, pid, tid);
-	pthread_rwlock_unlock(&machine->threads_lock);
+	up_write(&threads->lock);
 	return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
+	struct threads *threads = machine__threads(machine, tid);
 	struct thread *th;
-	pthread_rwlock_rdlock(&machine->threads_lock);
-	th =  ____machine__findnew_thread(machine, pid, tid, false);
-	pthread_rwlock_unlock(&machine->threads_lock);
+
+	down_read(&threads->lock);
+	th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
+	up_read(&threads->lock);
 	return th;
 }
 
@@ -564,7 +588,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 {
 	struct dso *dso;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
+	down_write(&machine->dsos.lock);
 
 	dso = __dsos__find(&machine->dsos, m->name, true);
 	if (!dso) {
@@ -578,7 +602,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
 	dso__get(dso);
 out_unlock:
-	pthread_rwlock_unlock(&machine->dsos.lock);
+	up_write(&machine->dsos.lock);
 	return dso;
 }
 
@@ -719,21 +743,25 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
 size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
-	size_t ret;
 	struct rb_node *nd;
+	size_t ret;
+	int i;
 
-	pthread_rwlock_rdlock(&machine->threads_lock);
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
 
-	ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+		down_read(&threads->lock);
 
-	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+		ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-		ret += thread__fprintf(pos, fp);
-	}
+		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+			struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
-	pthread_rwlock_unlock(&machine->threads_lock);
+			ret += thread__fprintf(pos, fp);
+		}
 
+		up_read(&threads->lock);
+	}
 	return ret;
 }
 
@@ -1292,7 +1320,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		struct dso *kernel = NULL;
 		struct dso *dso;
 
-		pthread_rwlock_rdlock(&machine->dsos.lock);
+		down_read(&machine->dsos.lock);
 
 		list_for_each_entry(dso, &machine->dsos.head, node) {
 
@@ -1322,7 +1350,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			break;
 		}
 
-		pthread_rwlock_unlock(&machine->dsos.lock);
+		up_read(&machine->dsos.lock);
 
 		if (kernel == NULL)
 			kernel = machine__findnew_dso(machine, kmmap_prefix);
@@ -1479,23 +1507,25 @@ out_problem:
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
-	if (machine->last_match == th)
-		machine->last_match = NULL;
+	struct threads *threads = machine__threads(machine, th->tid);
+
+	if (threads->last_match == th)
+		threads->last_match = NULL;
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
-		pthread_rwlock_wrlock(&machine->threads_lock);
-	rb_erase_init(&th->rb_node, &machine->threads);
+		down_write(&threads->lock);
+	rb_erase_init(&th->rb_node, &threads->entries);
 	RB_CLEAR_NODE(&th->rb_node);
-	--machine->nr_threads;
+	--threads->nr;
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
 	 * will be called and we will remove it from the dead_threads list.
 	 */
-	list_add_tail(&th->node, &machine->dead_threads);
+	list_add_tail(&th->node, &threads->dead);
 	if (lock)
-		pthread_rwlock_unlock(&machine->threads_lock);
+		up_write(&threads->lock);
 	thread__put(th);
 }
 
@@ -2140,21 +2170,26 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv)
 {
+	struct threads *threads;
 	struct rb_node *nd;
 	struct thread *thread;
 	int rc = 0;
+	int i;
 
-	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-		thread = rb_entry(nd, struct thread, rb_node);
-		rc = fn(thread, priv);
-		if (rc != 0)
-			return rc;
-	}
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		threads = &machine->threads[i];
+		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+			thread = rb_entry(nd, struct thread, rb_node);
+			rc = fn(thread, priv);
+			if (rc != 0)
+				return rc;
+		}
 
-	list_for_each_entry(thread, &machine->dead_threads, node) {
-		rc = fn(thread, priv);
-		if (rc != 0)
-			return rc;
+		list_for_each_entry(thread, &threads->dead, node) {
+			rc = fn(thread, priv);
+			if (rc != 0)
+				return rc;
+		}
 	}
 	return rc;
 }

tools/perf/util/machine.h

@@ -6,6 +6,7 @@
 #include "map.h"
 #include "dso.h"
 #include "event.h"
+#include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
@@ -23,6 +24,17 @@ extern const char *ref_reloc_sym_names[];
 
 struct vdso_info;
 
+#define THREADS__TABLE_BITS	8
+#define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
+
+struct threads {
+	struct rb_root	  entries;
+	struct rw_semaphore lock;
+	unsigned int	  nr;
+	struct list_head  dead;
+	struct thread	  *last_match;
+};
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -30,11 +42,7 @@ struct machine {
 	bool		  comm_exec;
 	bool		  kptr_restrict_warned;
 	char		  *root_dir;
-	struct rb_root	  threads;
-	pthread_rwlock_t  threads_lock;
-	unsigned int	  nr_threads;
-	struct list_head  dead_threads;
-	struct thread	  *last_match;
+	struct threads    threads[THREADS__TABLE_SIZE];
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
 	struct dsos	  dsos;
@@ -48,6 +56,12 @@ struct machine {
 	};
 };
 
+static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
+{
+	/* Cast it to handle tid == -1 */
+	return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
 static inline
 struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
 {

tools/perf/util/map.c

@@ -488,7 +488,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 static void maps__init(struct maps *maps)
 {
 	maps->entries = RB_ROOT;
-	pthread_rwlock_init(&maps->lock, NULL);
+	init_rwsem(&maps->lock);
 }
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
@@ -517,9 +517,9 @@ static void __maps__purge(struct maps *maps)
 
 static void maps__exit(struct maps *maps)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__purge(maps);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
@@ -586,7 +586,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 	struct symbol *sym;
 	struct rb_node *nd;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -602,7 +602,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
 	sym = NULL;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return sym;
 }
 
@@ -638,7 +638,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 	size_t printed = 0;
 	struct rb_node *nd;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -650,7 +650,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 		}
 	}
 
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 
 	return printed;
 }
@@ -682,7 +682,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 	struct rb_node *next;
 	int err = 0;
 
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 
 	root = &maps->entries;
 	next = rb_first(root);
@@ -750,7 +750,7 @@ put_map:
 
 	err = 0;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 	return err;
 }
 
@@ -771,7 +771,7 @@ int map_groups__clone(struct thread *thread,
 	struct map *map;
 	struct maps *maps = &parent->maps[type];
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
@@ -788,7 +788,7 @@ int map_groups__clone(struct thread *thread,
 
 	err = 0;
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return err;
 }
 
@@ -815,9 +815,9 @@ static void __maps__insert(struct maps *maps, struct map *map)
 
 void maps__insert(struct maps *maps, struct map *map)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__insert(maps, map);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 static void __maps__remove(struct maps *maps, struct map *map)
@@ -828,9 +828,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 
 void maps__remove(struct maps *maps, struct map *map)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__remove(maps, map);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 struct map *maps__find(struct maps *maps, u64 ip)
@@ -838,7 +838,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 	struct rb_node **p, *parent = NULL;
 	struct map *m;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	p = &maps->entries.rb_node;
 	while (*p != NULL) {
@@ -854,7 +854,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 
 	m = NULL;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return m;
 }
 

tools/perf/util/map.h

@@ -9,6 +9,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include "rwsem.h"
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -61,7 +62,7 @@ struct kmap {
 
 struct maps {
 	struct rb_root	 entries;
-	pthread_rwlock_t lock;
+	struct rw_semaphore lock;
 };
 
 struct map_groups {

tools/perf/util/metricgroup.c

@@ -0,0 +1,490 @@
+/*
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+/* Manage metrics and groups of metrics from JSON files */
+
+#include "metricgroup.h"
+#include "evlist.h"
+#include "strbuf.h"
+#include "pmu.h"
+#include "expr.h"
+#include "rblist.h"
+#include "pmu.h"
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include "pmu-events/pmu-events.h"
+#include "strbuf.h"
+#include "strlist.h"
+#include <assert.h>
+#include <ctype.h>
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create)
+{
+	struct rb_node *nd;
+	struct metric_event me = {
+		.evsel = evsel
+	};
+	nd = rblist__find(metric_events, &me);
+	if (nd)
+		return container_of(nd, struct metric_event, nd);
+	if (create) {
+		rblist__add_node(metric_events, &me);
+		nd = rblist__find(metric_events, &me);
+		if (nd)
+			return container_of(nd, struct metric_event, nd);
+	}
+	return NULL;
+}
+
+static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct metric_event *a = container_of(rb_node,
+					      struct metric_event,
+					      nd);
+	const struct metric_event *b = entry;
+
+	if (a->evsel == b->evsel)
+		return 0;
+	if ((char *)a->evsel < (char *)b->evsel)
+		return -1;
+	return +1;
+}
+
+static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
+					const void *entry)
+{
+	struct metric_event *me = malloc(sizeof(struct metric_event));
+
+	if (!me)
+		return NULL;
+	memcpy(me, entry, sizeof(struct metric_event));
+	me->evsel = ((struct metric_event *)entry)->evsel;
+	INIT_LIST_HEAD(&me->head);
+	return &me->nd;
+}
+
+static void metricgroup__rblist_init(struct rblist *metric_events)
+{
+	rblist__init(metric_events);
+	metric_events->node_cmp = metric_event_cmp;
+	metric_events->node_new = metric_event_new;
+}
+
+struct egroup {
+	struct list_head nd;
+	int idnum;
+	const char **ids;
+	const char *metric_name;
+	const char *metric_expr;
+};
+
+static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
+				     const char **ids,
+				     int idnum,
+				     struct perf_evsel **metric_events)
+{
+	struct perf_evsel *ev, *start = NULL;
+	int ind = 0;
+
+	evlist__for_each_entry (perf_evlist, ev) {
+		if (!strcmp(ev->name, ids[ind])) {
+			metric_events[ind] = ev;
+			if (ind == 0)
+				start = ev;
+			if (++ind == idnum) {
+				metric_events[ind] = NULL;
+				return start;
+			}
+		} else {
+			ind = 0;
+			start = NULL;
+		}
+	}
+	/*
+	 * This can happen when an alias expands to multiple
+	 * events, like for uncore events.
+	 * We don't support this case for now.
+	 */
+	return NULL;
+}
+
+static int metricgroup__setup_events(struct list_head *groups,
+				     struct perf_evlist *perf_evlist,
+				     struct rblist *metric_events_list)
+{
+	struct metric_event *me;
+	struct metric_expr *expr;
+	int i = 0;
+	int ret = 0;
+	struct egroup *eg;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry (eg, groups, nd) {
+		struct perf_evsel **metric_events;
+
+		metric_events = calloc(sizeof(void *), eg->idnum + 1);
+		if (!metric_events) {
+			ret = -ENOMEM;
+			break;
+		}
+		evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
+				   metric_events);
+		if (!evsel) {
+			pr_debug("Cannot resolve %s: %s\n",
+					eg->metric_name, eg->metric_expr);
+			continue;
+		}
+		for (i = 0; i < eg->idnum; i++)
+			metric_events[i]->collect_stat = true;
+		me = metricgroup__lookup(metric_events_list, evsel, true);
+		if (!me) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr = malloc(sizeof(struct metric_expr));
+		if (!expr) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr->metric_expr = eg->metric_expr;
+		expr->metric_name = eg->metric_name;
+		expr->metric_events = metric_events;
+		list_add(&expr->nd, &me->head);
+	}
+	return ret;
+}
+
+static bool match_metric(const char *n, const char *list)
+{
+	int len;
+	char *m;
+
+	if (!list)
+		return false;
+	if (!strcmp(list, "all"))
+		return true;
+	if (!n)
+		return !strcasecmp(list, "No_group");
+	len = strlen(list);
+	m = strcasestr(n, list);
+	if (!m)
+		return false;
+	if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
+	    (m[len] == 0 || m[len] == ';'))
+		return true;
+	return false;
+}
+
+struct mep {
+	struct rb_node nd;
+	const char *name;
+	struct strlist *metrics;
+};
+
+static int mep_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct mep *a = container_of(rb_node, struct mep, nd);
+	struct mep *b = (struct mep *)entry;
+
+	return strcmp(a->name, b->name);
+}
+
+static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
+					const void *entry)
+{
+	struct mep *me = malloc(sizeof(struct mep));
+
+	if (!me)
+		return NULL;
+	memcpy(me, entry, sizeof(struct mep));
+	me->name = strdup(me->name);
+	if (!me->name)
+		goto out_me;
+	me->metrics = strlist__new(NULL, NULL);
+	if (!me->metrics)
+		goto out_name;
+	return &me->nd;
+out_name:
+	free((char *)me->name);
+out_me:
+	free(me);
+	return NULL;
+}
+
+static struct mep *mep_lookup(struct rblist *groups, const char *name)
+{
+	struct rb_node *nd;
+	struct mep me = {
+		.name = name
+	};
+	nd = rblist__find(groups, &me);
+	if (nd)
+		return container_of(nd, struct mep, nd);
+	rblist__add_node(groups, &me);
+	nd = rblist__find(groups, &me);
+	if (nd)
+		return container_of(nd, struct mep, nd);
+	return NULL;
+}
+
+static void mep_delete(struct rblist *rl __maybe_unused,
+		       struct rb_node *nd)
+{
+	struct mep *me = container_of(nd, struct mep, nd);
+
+	strlist__delete(me->metrics);
+	free((void *)me->name);
+	free(me);
+}
+
+static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
+{
+	struct str_node *sn;
+	int n = 0;
+
+	strlist__for_each_entry (sn, metrics) {
+		if (raw)
+			printf("%s%s", n > 0 ? " " : "", sn->s);
+		else
+			printf("  %s\n", sn->s);
+		n++;
+	}
+	if (raw)
+		putchar('\n');
+}
+
+void metricgroup__print(bool metrics, bool metricgroups, char *filter,
+			bool raw)
+{
+	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_event *pe;
+	int i;
+	struct rblist groups;
+	struct rb_node *node, *next;
+	struct strlist *metriclist = NULL;
+
+	if (!map)
+		return;
+
+	if (!metricgroups) {
+		metriclist = strlist__new(NULL, NULL);
+		if (!metriclist)
+			return;
+	}
+
+	rblist__init(&groups);
+	groups.node_new = mep_new;
+	groups.node_cmp = mep_cmp;
+	groups.node_delete = mep_delete;
+	for (i = 0; ; i++) {
+		const char *g;
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		g = pe->metric_group;
+		if (!g && pe->metric_name) {
+			if (pe->name)
+				continue;
+			g = "No_group";
+		}
+		if (g) {
+			char *omg;
+			char *mg = strdup(g);
+
+			if (!mg)
+				return;
+			omg = mg;
+			while ((g = strsep(&mg, ";")) != NULL) {
+				struct mep *me;
+				char *s;
+
+				if (*g == 0)
+					g = "No_group";
+				while (isspace(*g))
+					g++;
+				if (filter && !strstr(g, filter))
+					continue;
+				if (raw)
+					s = (char *)pe->metric_name;
+				else {
+					if (asprintf(&s, "%s\n\t[%s]",
+						     pe->metric_name, pe->desc) < 0)
+						return;
+				}
+
+				if (!s)
+					continue;
+
+				if (!metricgroups) {
+					strlist__add(metriclist, s);
+				} else {
+					me = mep_lookup(&groups, g);
+					if (!me)
+						continue;
+					strlist__add(me->metrics, s);
+				}
+			}
+			free(omg);
+		}
+	}
+
+	if (metricgroups && !raw)
+		printf("\nMetric Groups:\n\n");
+	else if (metrics && !raw)
+		printf("\nMetrics:\n\n");
+
+	for (node = rb_first(&groups.entries); node; node = next) {
+		struct mep *me = container_of(node, struct mep, nd);
+
+		if (metricgroups)
+			printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+		if (metrics)
+			metricgroup__print_strlist(me->metrics, raw);
+		next = rb_next(node);
+		rblist__remove_node(&groups, node);
+	}
+	if (!metricgroups)
+		metricgroup__print_strlist(metriclist, raw);
+	strlist__delete(metriclist);
+}
+
+static int metricgroup__add_metric(const char *metric, struct strbuf *events,
+				   struct list_head *group_list)
+{
+	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_event *pe;
+	int ret = -EINVAL;
+	int i, j;
+
+	if (!map)
+		return 0;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_group, metric) ||
+		    match_metric(pe->metric_name, metric)) {
+			const char **ids;
+			int idnum;
+			struct egroup *eg;
+
+			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
+
+			if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)
+				continue;
+			if (events->len > 0)
+				strbuf_addf(events, ",");
+			for (j = 0; j < idnum; j++) {
+				pr_debug("found event %s\n", ids[j]);
+				strbuf_addf(events, "%s%s",
+					j == 0 ? "{" : ",",
+					ids[j]);
+			}
+			strbuf_addf(events, "}:W");
+
+			eg = malloc(sizeof(struct egroup));
+			if (!eg) {
+				ret = -ENOMEM;
+				break;
+			}
+			eg->ids = ids;
+			eg->idnum = idnum;
+			eg->metric_name = pe->metric_name;
+			eg->metric_expr = pe->metric_expr;
+			list_add_tail(&eg->nd, group_list);
+			ret = 0;
+		}
+	}
+	return ret;
+}
+
+static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
+				        struct list_head *group_list)
+{
+	char *llist, *nlist, *p;
+	int ret = -EINVAL;
+
+	nlist = strdup(list);
+	if (!nlist)
+		return -ENOMEM;
+	llist = nlist;
+
+	strbuf_init(events, 100);
+	strbuf_addf(events, "%s", "");
+
+	while ((p = strsep(&llist, ",")) != NULL) {
+		ret = metricgroup__add_metric(p, events, group_list);
+		if (ret == -EINVAL) {
+			fprintf(stderr, "Cannot find metric or group `%s'\n",
+					p);
+			break;
+		}
+	}
+	free(nlist);
+	return ret;
+}
+
+static void metricgroup__free_egroups(struct list_head *group_list)
+{
+	struct egroup *eg, *egtmp;
+	int i;
+
+	list_for_each_entry_safe (eg, egtmp, group_list, nd) {
+		for (i = 0; i < eg->idnum; i++)
+			free((char *)eg->ids[i]);
+		free(eg->ids);
+		free(eg);
+	}
+}
+
+int metricgroup__parse_groups(const struct option *opt,
+			   const char *str,
+			   struct rblist *metric_events)
+{
+	struct parse_events_error parse_error;
+	struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+	struct strbuf extra_events;
+	LIST_HEAD(group_list);
+	int ret;
+
+	if (metric_events->nr_entries == 0)
+		metricgroup__rblist_init(metric_events);
+	ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
+	if (ret)
+		return ret;
+	pr_debug("adding %s\n", extra_events.buf);
+	memset(&parse_error, 0, sizeof(struct parse_events_error));
+	ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
+	if (ret) {
+		parse_events_print_error(&parse_error, extra_events.buf);
+		goto out;
+	}
+	strbuf_release(&extra_events);
+	ret = metricgroup__setup_events(&group_list, perf_evlist,
+					metric_events);
+out:
+	metricgroup__free_egroups(&group_list);
+	return ret;
+}

tools/perf/util/metricgroup.h

@@ -0,0 +1,31 @@
+#ifndef METRICGROUP_H
+#define METRICGROUP_H 1
+
+#include "linux/list.h"
+#include "rblist.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "strbuf.h"
+
+struct metric_event {
+	struct rb_node nd;
+	struct perf_evsel *evsel;
+	struct list_head head; /* list of metric_expr */
+};
+
+struct metric_expr {
+	struct list_head nd;
+	const char *metric_expr;
+	const char *metric_name;
+	struct perf_evsel **metric_events;
+};
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create);
+int metricgroup__parse_groups(const struct option *opt,
+			const char *str,
+			struct rblist *metric_events);
+
+void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+#endif

tools/perf/util/namespaces.c

@@ -11,6 +11,7 @@
 #include "event.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <limits.h>
 #include <sched.h>
 #include <stdlib.h>

tools/perf/util/parse-events.c

@@ -28,6 +28,7 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 
@@ -1218,11 +1219,17 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
+	struct parse_events_error *err = parse_state->error;
 	LIST_HEAD(config_terms);
 
 	pmu = perf_pmu__find(name);
-	if (!pmu)
+	if (!pmu) {
+		if (asprintf(&err->str,
+				"Cannot find PMU `%s'. Missing kernel support?",
+				name) < 0)
+			err->str = NULL;
 		return -EINVAL;
+	}
 
 	if (pmu->default_config) {
 		memcpy(&attr, pmu->default_config,
@@ -1366,6 +1373,7 @@ struct event_modifier {
 	int exclude_GH;
 	int sample_read;
 	int pinned;
+	int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1384,6 +1392,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 
 	int exclude = eu | ek | eh;
 	int exclude_GH = evsel ? evsel->exclude_GH : 0;
+	int weak = 0;
 
 	memset(mod, 0, sizeof(*mod));
 
@@ -1421,6 +1430,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			sample_read = 1;
 		} else if (*str == 'D') {
 			pinned = 1;
+		} else if (*str == 'W') {
+			weak = 1;
 		} else
 			break;
 
@@ -1451,6 +1462,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	mod->exclude_GH = exclude_GH;
 	mod->sample_read = sample_read;
 	mod->pinned = pinned;
+	mod->weak = weak;
 
 	return 0;
 }
@@ -1464,7 +1476,7 @@ static int check_modifier(char *str)
 	char *p = str;
 
 	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
+	if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
 		return -1;
 
 	while (*p) {
@@ -1504,6 +1516,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 		evsel->exclude_GH          = mod.exclude_GH;
 		evsel->sample_read         = mod.sample_read;
 		evsel->precise_max         = mod.precise_max;
+		evsel->weak_group	   = mod.weak;
 
 		if (perf_evsel__is_group_leader(evsel))
 			evsel->attr.pinned = mod.pinned;
@@ -1726,8 +1739,8 @@ static int get_term_width(void)
 	return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
 }
 
-static void parse_events_print_error(struct parse_events_error *err,
-				     const char *event)
+void parse_events_print_error(struct parse_events_error *err,
+			      const char *event)
 {
 	const char *str = "invalid or unsupported event: ";
 	char _buf[MAX_WIDTH];
@@ -1782,8 +1795,6 @@ static void parse_events_print_error(struct parse_events_error *err,
 		zfree(&err->str);
 		zfree(&err->help);
 	}
-
-	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 }
 
 #undef MAX_WIDTH
@@ -1795,8 +1806,10 @@ int parse_events_option(const struct option *opt, const char *str,
 	struct parse_events_error err = { .idx = 0, };
 	int ret = parse_events(evlist, str, &err);
 
-	if (ret)
+	if (ret) {
 		parse_events_print_error(&err, str);
+		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+	}
 
 	return ret;
 }
@@ -2374,6 +2387,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 	print_tracepoint_events(NULL, NULL, name_only);
 
 	print_sdt_events(NULL, NULL, name_only);
+
+	metricgroup__print(true, true, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)

tools/perf/util/parse-events.h

@@ -202,6 +202,9 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+void parse_events_print_error(struct parse_events_error *err,
+			      const char *event);
+
 #ifdef HAVE_LIBELF_SUPPORT
 /*
  * If the probe point starts with '%',

tools/perf/util/parse-events.l

@@ -161,7 +161,7 @@ name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
-modifier_event	[ukhpPGHSDI]+
+modifier_event	[ukhpPGHSDIW]+
 modifier_bp	[rwx]{1,3}
 
 %%
@@ -288,6 +288,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*

tools/perf/util/pmu.c

@@ -2,6 +2,7 @@
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -516,16 +517,8 @@ char * __weak get_cpuid_str(void)
 	return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static char *perf_pmu__getcpuid(void)
 {
-	int i;
-	struct pmu_events_map *map;
-	struct pmu_event *pe;
 	char *cpuid;
 	static bool printed;
 
@@ -535,22 +528,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	if (!cpuid)
 		cpuid = get_cpuid_str();
 	if (!cpuid)
-		return;
+		return NULL;
 
 	if (!printed) {
 		pr_debug("Using CPUID %s\n", cpuid);
 		printed = true;
 	}
+	return cpuid;
+}
+
+struct pmu_events_map *perf_pmu__find_map(void)
+{
+	struct pmu_events_map *map;
+	char *cpuid = perf_pmu__getcpuid();
+	int i;
 
 	i = 0;
-	while (1) {
+	for (;;) {
 		map = &pmu_events_map[i++];
-		if (!map->table)
-			goto out;
+		if (!map->table) {
+			map = NULL;
+			break;
+		}
 
 		if (!strcmp(map->cpuid, cpuid))
 			break;
 	}
+	free(cpuid);
+	return map;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+{
+	int i;
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+
+	map = perf_pmu__find_map();
+	if (!map)
+		return;
 
 	/*
 	 * Found a matching PMU events table. Create aliases
@@ -560,8 +581,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		const char *pname;
 
 		pe = &map->table[i++];
-		if (!pe->name)
+		if (!pe->name) {
+			if (pe->metric_group || pe->metric_name)
+				continue;
 			break;
+		}
 
 		pname = pe->pmu ? pe->pmu : "cpu";
 		if (strncmp(pname, name, strlen(pname)))
@@ -575,9 +599,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 				(char *)pe->metric_expr,
 				(char *)pe->metric_name);
 	}
-
-out:
-	free(cpuid);
 }
 
 struct perf_event_attr * __weak

tools/perf/util/pmu.h

@@ -90,4 +90,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+struct pmu_events_map *perf_pmu__find_map(void);
+
 #endif /* __PMU_H */

tools/perf/util/probe-file.c

@@ -15,6 +15,7 @@
  *
  */
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/uio.h>

tools/perf/util/rb_resort.h

@@ -143,7 +143,8 @@ struct __name##_sorted *__name = __name##_sorted__new
 				  __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine)			\
-	DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)	\
+	DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,	\
+				  __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */

tools/perf/util/rwsem.c

@@ -0,0 +1,32 @@
+#include "util.h"
+#include "rwsem.h"
+
+int init_rwsem(struct rw_semaphore *sem)
+{
+	return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+int exit_rwsem(struct rw_semaphore *sem)
+{
+	return pthread_rwlock_destroy(&sem->lock);
+}
+
+int down_read(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock);
+}
+
+int up_read(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
+
+int down_write(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock);
+}
+
+int up_write(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}

tools/perf/util/rwsem.h

@@ -0,0 +1,19 @@
+#ifndef _PERF_RWSEM_H
+#define _PERF_RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+	pthread_rwlock_t lock;
+};
+
+int init_rwsem(struct rw_semaphore *sem);
+int exit_rwsem(struct rw_semaphore *sem);
+
+int down_read(struct rw_semaphore *sem);
+int up_read(struct rw_semaphore *sem);
+
+int down_write(struct rw_semaphore *sem);
+int up_write(struct rw_semaphore *sem);
+
+#endif /* _PERF_RWSEM_H */

tools/perf/util/session.c

@@ -1847,7 +1847,7 @@ static int __perf_session__process_events(struct perf_session *session,
 	if (data_offset + data_size < file_size)
 		file_size = data_offset + data_size;
 
-	ui_progress__init(&prog, file_size, "Processing events...");
+	ui_progress__init_size(&prog, file_size, "Processing events...");
 
 	mmap_size = MMAP_SIZE;
 	if (mmap_size > file_size) {

tools/perf/util/stat-shadow.c

@@ -6,6 +6,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -55,7 +56,6 @@ struct saved_value {
 	struct rb_node rb_node;
 	struct perf_evsel *evsel;
 	int cpu;
-	int ctx;
 	struct stats stats;
 };
 
@@ -66,8 +66,6 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 					     rb_node);
 	const struct saved_value *b = entry;
 
-	if (a->ctx != b->ctx)
-		return a->ctx - b->ctx;
 	if (a->cpu != b->cpu)
 		return a->cpu - b->cpu;
 	if (a->evsel == b->evsel)
@@ -89,13 +87,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 }
 
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
-					      int cpu, int ctx,
+					      int cpu,
 					      bool create)
 {
 	struct rb_node *nd;
 	struct saved_value dm = {
 		.cpu = cpu,
-		.ctx = ctx,
 		.evsel = evsel,
 	};
 	nd = rblist__find(&runtime_saved_values, &dm);
@@ -231,8 +228,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
 
 	if (counter->collect_stat) {
-		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
-							   true);
+		struct saved_value *v = saved_value_lookup(counter, cpu, true);
 		update_stats(&v->stats, count[0]);
 	}
 }
@@ -627,15 +623,68 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
+static void generic_metric(const char *metric_expr,
+			   struct perf_evsel **metric_events,
+			   char *name,
+			   const char *metric_name,
+			   double avg,
+			   int cpu,
+			   struct perf_stat_output_ctx *out)
+{
+	print_metric_t print_metric = out->print_metric;
+	struct parse_ctx pctx;
+	double ratio;
+	int i;
+	void *ctxp = out->ctx;
+
+	expr__ctx_init(&pctx);
+	expr__add_id(&pctx, name, avg);
+	for (i = 0; metric_events[i]; i++) {
+		struct saved_value *v;
+		struct stats *stats;
+		double scale;
+
+		if (!strcmp(metric_events[i]->name, "duration_time")) {
+			stats = &walltime_nsecs_stats;
+			scale = 1e-9;
+		} else {
+			v = saved_value_lookup(metric_events[i], cpu, false);
+			if (!v)
+				break;
+			stats = &v->stats;
+			scale = 1.0;
+		}
+		expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+	}
+	if (!metric_events[i]) {
+		const char *p = metric_expr;
+
+		if (expr__parse(&ratio, &pctx, &p) == 0)
+			print_metric(ctxp, NULL, "%8.1f",
+				metric_name ?
+				metric_name :
+				out->force_header ?  name : "",
+				ratio);
+		else
+			print_metric(ctxp, NULL, NULL,
+				     out->force_header ?
+				     (metric_name ? metric_name : name) : "", 0);
+	} else
+		print_metric(ctxp, NULL, NULL, "", 0);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out)
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events)
 {
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
 	int ctx = evsel_context(evsel);
+	struct metric_event *me;
+	int num = 1;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
@@ -819,33 +868,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		struct parse_ctx pctx;
-		int i;
-
-		expr__ctx_init(&pctx);
-		expr__add_id(&pctx, evsel->name, avg);
-		for (i = 0; evsel->metric_events[i]; i++) {
-			struct saved_value *v;
-
-			v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
-			if (!v)
-				break;
-			expr__add_id(&pctx, evsel->metric_events[i]->name,
-					     avg_stats(&v->stats));
-		}
-		if (!evsel->metric_events[i]) {
-			const char *p = evsel->metric_expr;
-
-			if (expr__parse(&ratio, &pctx, &p) == 0)
-				print_metric(ctxp, NULL, "%8.1f",
-					evsel->metric_name ?
-					evsel->metric_name :
-					out->force_header ?  evsel->name : "",
-					ratio);
-			else
-				print_metric(ctxp, NULL, NULL, "", 0);
-		} else
-			print_metric(ctxp, NULL, NULL, "", 0);
+		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+				evsel->metric_name, avg, cpu, out);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
@@ -863,6 +887,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
 		print_smi_cost(cpu, evsel, out);
 	} else {
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		num = 0;
 	}
+
+	if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+		struct metric_expr *mexp;
+
+		list_for_each_entry (mexp, &me->head, nd) {
+			if (num++ > 0)
+				out->new_line(ctxp);
+			generic_metric(mexp->metric_expr, mexp->metric_events,
+					evsel->name, mexp->metric_name,
+					avg, cpu, out);
+		}
+	}
+	if (num == 0)
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 }

tools/perf/util/stat.h

@@ -91,9 +91,11 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
+struct rblist;
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out);
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);

tools/perf/util/symbol.c

@@ -226,7 +226,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	struct maps *maps = &mg->maps[type];
 	struct map *next, *curr;
 
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 
 	curr = maps__first(maps);
 	if (curr == NULL)
@@ -246,7 +246,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 		curr->end = ~0ULL;
 
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -1671,7 +1671,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 	struct maps *maps = &mg->maps[type];
 	struct map *map;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1681,7 +1681,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 	map = NULL;
 
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return map;
 }
 

tools/perf/util/thread.c

@@ -264,7 +264,7 @@ static int __thread__prepare_access(struct thread *thread)
 		struct maps *maps = &thread->mg->maps[i];
 		struct map *map;
 
-		pthread_rwlock_rdlock(&maps->lock);
+		down_read(&maps->lock);
 
 		for (map = maps__first(maps); map; map = map__next(map)) {
 			err = unwind__prepare_access(thread, map, &initialized);
@@ -272,7 +272,7 @@ static int __thread__prepare_access(struct thread *thread)
 				break;
 		}
 
-		pthread_rwlock_unlock(&maps->lock);
+		up_read(&maps->lock);
 	}
 
 	return err;

tools/perf/util/trace-event-info.c

@@ -28,7 +28,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>

tools/perf/util/trace-event-read.c

@@ -27,7 +27,6 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/mman.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>

tools/perf/util/util.c

@@ -6,6 +6,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <dirent.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <signal.h>
 #include <stdio.h>
@@ -22,6 +23,19 @@
 /*
  * XXX We need to find a better place for these things...
  */
+
+bool perf_singlethreaded = true;
+
+void perf_set_singlethreaded(void)
+{
+	perf_singlethreaded = true;
+}
+
+void perf_set_multithreaded(void)
+{
+	perf_singlethreaded = false;
+}
+
 unsigned int page_size;
 int cacheline_size;
 
@@ -174,7 +188,7 @@ out:
 	return err;
 }
 
-int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;

tools/perf/util/util.h

@@ -5,7 +5,6 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
-#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -35,7 +34,6 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
-int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
@@ -64,4 +62,9 @@ int sched_getcpu(void);
 int setns(int fd, int nstype);
 #endif
 
+extern bool perf_singlethreaded;
+
+void perf_set_singlethreaded(void);
+void perf_set_multithreaded(void);
+
 #endif /* GIT_COMPAT_UTIL_H */

tools/perf/util/vdso.c

@@ -319,7 +319,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
+	down_write(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
@@ -347,7 +347,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 
 out_unlock:
 	dso__get(dso);
-	pthread_rwlock_unlock(&machine->dsos.lock);
+	up_write(&machine->dsos.lock);
 	return dso;
 }
 

tools/perf/util/zlib.c

@@ -1,3 +1,4 @@
+#include <fcntl.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/stat.h>