Merge tag 'perf-tools-for-v6.1-1-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Add support for AMD on 'perf mem' and 'perf c2c', the kernel
   enablement patches went via tip.

   Example:

      $ sudo perf mem record -- -c 10000
      ^C[ perf record: Woken up 227 times to write data ]
      [ perf record: Captured and wrote 58.760 MB perf.data (836978 samples) ]

      $ sudo perf mem report -F mem,sample,snoop
      Samples: 836K of event 'ibs_op//', Event count (approx.): 8418762
      Memory access                  Samples  Snoop
      N/A                             700620  N/A
      L1 hit                          126675  N/A
      L2 hit                             424  N/A
      L3 hit                             664  HitM
      L3 hit                              10  N/A
      Local RAM hit                        2  N/A
      Remote RAM (1 hop) hit            8558  N/A
      Remote Cache (1 hop) hit             3  N/A
      Remote Cache (1 hop) hit             2  HitM
      Remote Cache (2 hops) hit           10  HitM
      Remote Cache (2 hops) hit            6  N/A
      Uncached hit                         4  N/A
      $

 - "perf lock" improvements:

     - Add -E/--entries option to limit the number of entries to
       display, say to ask for just the top 5 contended locks.

     - Add -q/--quiet option to suppress header and debug messages.

     - Add a 'perf test' kernel lock contention entry to test 'perf
       lock'.

 - "perf lock contention" improvements:

     - Ask BPF's bpf_get_stackid() to skip some callchain entries.

       The ones closer to the tooling are bpf related and not that
       interesting, the ones calling the locking function are the ones
       we're interested in, example of a full, unskipped callstack:

     - Allow changing the callstack depth and number of entries to skip.

           1     10.74 us     10.74 us     10.74 us     spinlock   __bpf_trace_contention_begin+0xb
                          0xffffffffc03b5c47  bpf_prog_bf07ae9e2cbd02c5_contention_begin+0x117
                          0xffffffffc03b5c47  bpf_prog_bf07ae9e2cbd02c5_contention_begin+0x117
                          0xffffffffbb8b8e75  bpf_trace_run2+0x35
                          0xffffffffbb7eab9b  __bpf_trace_contention_begin+0xb
                          0xffffffffbb7ebe75  queued_spin_lock_slowpath+0x1f5
                          0xffffffffbc1c26ff  _raw_spin_lock+0x1f
                          0xffffffffbb841015  tick_do_update_jiffies64+0x25
                          0xffffffffbb8409ee  tick_irq_enter+0x9e

     - Show full callstack in verbose mode (-v option), sometimes this
       is desirable instead of showing just one callstack entry.

 - Allow multiple time ranges in 'perf record --delay' to help in
   reducing the amount of data collected from hardware tracing (Intel
   PT, etc) when there is a rough idea of periods of time where events
   of interest take time.

 - Add Intel PT to record only decoder debug messages when error
   happens.

 - Improve layout of Intel PT man page.

 - Add new branch types: alignment, data and inst faults and arch
   specific ones, such as fiq, debug_halt, debug_exit, debug_inst and
   debug_data on arm64.

   Kernel enablement went thru the tip tree.

 - Fix 'perf probe' error log check in 'perf test' when no debuginfo is
   available.

 - Fix 'perf stat' aggregation mode logic, it should be looking at the
   CPU not at the core number.

 - Fix flags parsing in 'perf trace' filters.

 - Introduce compact encoding of CPU range encoding on perf.data, to
   avoid having a bitmap with all the CPUs.

 - Improvements to the 'perf stat' metrics, including adding
   "core_wide", and computing "smt" from the CPU topology.

 - Add support to the new PERF_FORMAT_LOST perf_event_attr.read_format,
   that allows tooling to ask for the precise number of lost samples for
   a given event.

 - Add 'addr' sort key to see just the address of sampled instructions:

      $ perf record -o- true | perf report -i- -s addr
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 0.000 MB - ]
      # Samples: 12  of event 'cycles:u'
      # Event count (approx.): 252512
      #
      # Overhead  Address
      # ........  ..................
          42.96%  0x7f96f08443d7
          29.55%  0x7f96f0859b50
          14.76%  0x7f96f0852e02
           8.30%  0x7f96f0855028
           4.43%  0xffffffff8de01087

      perf annotate: Toggle full address <-> offset display

 - Add 'f' hotkey to the 'perf annotate' TUI interface when in
   'disassembler output' mode ('o' hotkey) to toggle showing full
   virtual address or just the offset.

 - Cache DSO build-ids when synthesizing PERF_RECORD_MMAP records for
   pre-existing threads, at the start of a 'perf record' session,
   speeding up that record startup phase.

 - Add a command line option to specify build ids in 'perf inject'.

 - Update JSON event files for the Intel alderlake, broadwell,
   broadwellde, broadwellx, cascadelakex, haswell, haswellx, icelake,
   icelakex, ivybridge, ivytown, jaketown, sandybridge, sapphirerapids,
   skylake, skylakex, and tigerlake processors.

 - Update vendor JSON event files for the ARM Neoverse V1 and E1
   platforms.

 - Add a 'perf test' entry for 'perf mem' where a struct has false
   sharing and this gets detected in the 'perf mem' output, tested with
   Intel, AMD and ARM64 systems.

 - Add a 'perf test' entry to test the resolution of java symbols, where
   an output like this is expected:

       8.18%  jshell    jitted-50116-29.so    [.] Interpreter
       0.75%  Thread-1  jitted-83602-1670.so  [.] jdk.internal.jimage.BasicImageReader.getString(int)

 - Add tests for the ARM64 CoreSight hardware tracing feature, with
   specially crafted pureloop, memcpy, thread loop and unroll tread that
   then gets traced and the output compared with expected output.

   Documentation explaining it is also included.

 - Add per thread Intel PT 'perf test' entry to check that
   PERF_RECORD_TEXT_POKE events are recorded per CPU, resulting in a
   mixture of per thread and per CPU events and mmaps, verify that this
   gets all recorded correctly.

 - Introduce pthread mutex wrappers to allow for building with clang's
   -Wthread-safety, i.e. using the "guarded_by" "pt_guarded_by"
   "lockable", "exclusive_lock_function", "exclusive_trylock_function",
   "exclusive_locks_required", and "no_thread_safety_analysis" compiler
   function attributes.

 - Fix empty version number when building outside of a git repo.

 - Improve feature detection display when multiple versions of a feature
   are present, such as for binutils libbfd, that has a mix of possible
   ways to detect according to the Linux distribution.

   Previously in some cases we had:

      Auto-detecting system features
      <SNIP>
      ...                                  libbfd: [ on  ]
      ...                          libbfd-liberty: [ on  ]
      ...                        libbfd-liberty-z: [ on  ]
      <SNIP>

   Now for this case we show just the main feature:

      Auto-detecting system features
      <SNIP>
      ...                                  libbfd: [ on  ]
      <SNIP>

 - Remove some unused structs, variables, macros, function prototypes
   and includes from various places.

* tag 'perf-tools-for-v6.1-1-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (169 commits)
  perf script: Add missing fields in usage hint
  perf mem: Print "LFB/MAB" for PERF_MEM_LVLNUM_LFB
  perf mem/c2c: Avoid printing empty lines for unsupported events
  perf mem/c2c: Add load store event mappings for AMD
  perf mem/c2c: Set PERF_SAMPLE_WEIGHT for LOAD_STORE events
  perf mem: Add support for printing PERF_MEM_LVLNUM_{CXL|IO}
  perf amd ibs: Sync arch/x86/include/asm/amd-ibs.h header with the kernel
  tools headers UAPI: Sync include/uapi/linux/perf_event.h header with the kernel
  perf stat: Fix cpu check to use id.cpu.cpu in aggr_printout()
  perf test coresight: Add relevant documentation about ARM64 CoreSight testing
  perf test: Add git ignore for tmp and output files of ARM CoreSight tests
  perf test coresight: Add unroll thread test shell script
  perf test coresight: Add unroll thread test tool
  perf test coresight: Add thread loop test shell scripts
  perf test coresight: Add thread loop test tool
  perf test coresight: Add memcpy thread test shell script
  perf test coresight: Add memcpy thread test tool
  perf test: Add git ignore for perf data generated by the ARM CoreSight tests
  perf test: Add arm64 asm pureloop test shell script
  perf test: Add asm pureloop test tool
  ...

8 files changed, 153 insertions, 171 deletions

diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 4256dc5d6236..521d1ff97b06 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -23,6 +23,7 @@
 #include <sys/eventfd.h>
 #include <perf/cpumap.h>
 
+#include "../util/mutex.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
@@ -58,10 +59,10 @@ static unsigned int nested = 0;
 /* amount of fds to monitor, per thread */
 static unsigned int nfds = 64;
 
-static pthread_mutex_t thread_lock;
+static struct mutex thread_lock;
 static unsigned int threads_starting;
 static struct stats all_stats[EPOLL_NR_OPS];
-static pthread_cond_t thread_parent, thread_worker;
+static struct cond thread_parent, thread_worker;
 
 struct worker {
 	int tid;
@@ -174,12 +175,12 @@ static void *workerfn(void *arg)
 	struct timespec ts = { .tv_sec = 0,
 			       .tv_nsec = 250 };
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	/* Let 'em loose */
 	do {
@@ -367,9 +368,9 @@ int bench_epoll_ctl(int argc, const char **argv)
 	for (i = 0; i < EPOLL_NR_OPS; i++)
 		init_stats(&all_stats[i]);
 
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	threads_starting = nthreads;
 
@@ -377,11 +378,11 @@ int bench_epoll_ctl(int argc, const char **argv)
 
 	do_threads(worker, cpu);
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	while (threads_starting)
-		pthread_cond_wait(&thread_parent, &thread_lock);
-	pthread_cond_broadcast(&thread_worker);
-	pthread_mutex_unlock(&thread_lock);
+		cond_wait(&thread_parent, &thread_lock);
+	cond_broadcast(&thread_worker);
+	mutex_unlock(&thread_lock);
 
 	sleep(nsecs);
 	toggle_done(0, NULL, NULL);
@@ -394,9 +395,9 @@ int bench_epoll_ctl(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
 		unsigned long t[EPOLL_NR_OPS];
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 2728b0140853..c1cdf03c075d 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -79,6 +79,7 @@
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
+#include "../util/mutex.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
 
@@ -109,10 +110,10 @@ static bool multiq; /* use an epoll instance per thread */
 /* amount of fds to monitor, per thread */
 static unsigned int nfds = 64;
 
-static pthread_mutex_t thread_lock;
+static struct mutex thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
-static pthread_cond_t thread_parent, thread_worker;
+static struct cond thread_parent, thread_worker;
 
 struct worker {
 	int tid;
@@ -189,12 +190,12 @@ static void *workerfn(void *arg)
 	int to = nonblocking? 0 : -1;
 	int efd = multiq ? w->epollfd : epollfd;
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	do {
 		/*
@@ -485,9 +486,9 @@ int bench_epoll_wait(int argc, const char **argv)
 	       getpid(), nthreads, oneshot ? " (EPOLLONESHOT semantics)": "", nfds, nsecs);
 
 	init_stats(&throughput_stats);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	threads_starting = nthreads;
 
@@ -495,11 +496,11 @@ int bench_epoll_wait(int argc, const char **argv)
 
 	do_threads(worker, cpu);
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	while (threads_starting)
-		pthread_cond_wait(&thread_parent, &thread_lock);
-	pthread_cond_broadcast(&thread_worker);
-	pthread_mutex_unlock(&thread_lock);
+		cond_wait(&thread_parent, &thread_lock);
+	cond_broadcast(&thread_worker);
+	mutex_unlock(&thread_lock);
 
 	/*
 	 * At this point the workers should be blocked waiting for read events
@@ -522,9 +523,9 @@ int bench_epoll_wait(int argc, const char **argv)
 		err(EXIT_FAILURE, "pthread_join");
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 
 	/* sort the array back before reporting */
 	if (randomize)
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index f05db4cf983d..2005a3fa3026 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -23,6 +23,7 @@
 #include <sys/mman.h>
 #include <perf/cpumap.h>
 
+#include "../util/mutex.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
@@ -34,10 +35,10 @@ static bool done = false;
 static int futex_flag = 0;
 
 struct timeval bench__start, bench__end, bench__runtime;
-static pthread_mutex_t thread_lock;
+static struct mutex thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
-static pthread_cond_t thread_parent, thread_worker;
+static struct cond thread_parent, thread_worker;
 
 struct worker {
 	int tid;
@@ -73,12 +74,12 @@ static void *workerfn(void *arg)
 	unsigned int i;
 	unsigned long ops = w->ops; /* avoid cacheline bouncing */
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	do {
 		for (i = 0; i < params.nfutexes; i++, ops++) {
@@ -165,9 +166,9 @@ int bench_futex_hash(int argc, const char **argv)
 	       getpid(), params.nthreads, params.nfutexes, params.fshared ? "shared":"private", params.runtime);
 
 	init_stats(&throughput_stats);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
@@ -203,11 +204,11 @@ int bench_futex_hash(int argc, const char **argv)
 	CPU_FREE(cpuset);
 	pthread_attr_destroy(&thread_attr);
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	while (threads_starting)
-		pthread_cond_wait(&thread_parent, &thread_lock);
-	pthread_cond_broadcast(&thread_worker);
-	pthread_mutex_unlock(&thread_lock);
+		cond_wait(&thread_parent, &thread_lock);
+	cond_broadcast(&thread_worker);
+	mutex_unlock(&thread_lock);
 
 	sleep(params.runtime);
 	toggle_done(0, NULL, NULL);
@@ -219,9 +220,9 @@ int bench_futex_hash(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 
 	for (i = 0; i < params.nthreads; i++) {
 		unsigned long t = bench__runtime.tv_sec > 0 ?
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 0abb3f7ee24f..2d0417949727 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -8,6 +8,7 @@
 #include <pthread.h>
 
 #include <signal.h>
+#include "../util/mutex.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
@@ -34,10 +35,10 @@ static u_int32_t global_futex = 0;
 static struct worker *worker;
 static bool done = false;
 static int futex_flag = 0;
-static pthread_mutex_t thread_lock;
+static struct mutex thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
-static pthread_cond_t thread_parent, thread_worker;
+static struct cond thread_parent, thread_worker;
 
 static struct bench_futex_parameters params = {
 	.runtime  = 10,
@@ -83,12 +84,12 @@ static void *workerfn(void *arg)
 	struct worker *w = (struct worker *) arg;
 	unsigned long ops = w->ops;
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	do {
 		int ret;
@@ -197,9 +198,9 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	       getpid(), params.nthreads, params.runtime);
 
 	init_stats(&throughput_stats);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
@@ -208,11 +209,11 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	create_threads(worker, thread_attr, cpu);
 	pthread_attr_destroy(&thread_attr);
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	while (threads_starting)
-		pthread_cond_wait(&thread_parent, &thread_lock);
-	pthread_cond_broadcast(&thread_worker);
-	pthread_mutex_unlock(&thread_lock);
+		cond_wait(&thread_parent, &thread_lock);
+	cond_broadcast(&thread_worker);
+	mutex_unlock(&thread_lock);
 
 	sleep(params.runtime);
 	toggle_done(0, NULL, NULL);
@@ -224,9 +225,9 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 
 	for (i = 0; i < params.nthreads; i++) {
 		unsigned long t = bench__runtime.tv_sec > 0 ?
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index b6faabfafb8e..69ad896f556c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -15,6 +15,7 @@
 #include <pthread.h>
 
 #include <signal.h>
+#include "../util/mutex.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
@@ -34,8 +35,8 @@ static u_int32_t futex1 = 0, futex2 = 0;
 
 static pthread_t *worker;
 static bool done = false;
-static pthread_mutex_t thread_lock;
-static pthread_cond_t thread_parent, thread_worker;
+static struct mutex thread_lock;
+static struct cond thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
 static unsigned int threads_starting;
 static int futex_flag = 0;
@@ -82,12 +83,12 @@ static void *workerfn(void *arg __maybe_unused)
 {
 	int ret;
 
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	while (1) {
 		if (!params.pi) {
@@ -209,9 +210,9 @@ int bench_futex_requeue(int argc, const char **argv)
 	init_stats(&requeued_stats);
 	init_stats(&requeuetime_stats);
 	pthread_attr_init(&thread_attr);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nrequeued = 0, wakeups = 0;
@@ -221,11 +222,11 @@ int bench_futex_requeue(int argc, const char **argv)
 		block_threads(worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
-		pthread_mutex_lock(&thread_lock);
+		mutex_lock(&thread_lock);
 		while (threads_starting)
-			pthread_cond_wait(&thread_parent, &thread_lock);
-		pthread_cond_broadcast(&thread_worker);
-		pthread_mutex_unlock(&thread_lock);
+			cond_wait(&thread_parent, &thread_lock);
+		cond_broadcast(&thread_worker);
+		mutex_unlock(&thread_lock);
 
 		usleep(100000);
 
@@ -297,9 +298,9 @@ int bench_futex_requeue(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 	pthread_attr_destroy(&thread_attr);
 
 	print_summary();
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index e47f46a3a47e..6682e49d0ee0 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -10,6 +10,7 @@
 #include "bench.h"
 #include <linux/compiler.h>
 #include "../util/debug.h"
+#include "../util/mutex.h"
 
 #ifndef HAVE_PTHREAD_BARRIER
 int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused)
@@ -49,8 +50,8 @@ static u_int32_t futex = 0;
 
 static pthread_t *blocked_worker;
 static bool done = false;
-static pthread_mutex_t thread_lock;
-static pthread_cond_t thread_parent, thread_worker;
+static struct mutex thread_lock;
+static struct cond thread_parent, thread_worker;
 static pthread_barrier_t barrier;
 static struct stats waketime_stats, wakeup_stats;
 static unsigned int threads_starting;
@@ -125,12 +126,12 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 static void *blocked_workerfn(void *arg __maybe_unused)
 {
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	while (1) { /* handle spurious wakeups */
 		if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR)
@@ -294,9 +295,9 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	init_stats(&waketime_stats);
 
 	pthread_attr_init(&thread_attr);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
 		waking_worker = calloc(params.nwakes, sizeof(*waking_worker));
@@ -307,11 +308,11 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		block_threads(blocked_worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
-		pthread_mutex_lock(&thread_lock);
+		mutex_lock(&thread_lock);
 		while (threads_starting)
-			pthread_cond_wait(&thread_parent, &thread_lock);
-		pthread_cond_broadcast(&thread_worker);
-		pthread_mutex_unlock(&thread_lock);
+			cond_wait(&thread_parent, &thread_lock);
+		cond_broadcast(&thread_worker);
+		mutex_unlock(&thread_lock);
 
 		usleep(100000);
 
@@ -332,9 +333,9 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 	pthread_attr_destroy(&thread_attr);
 
 	print_summary();
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 201a3555f09a..9ecab6620a87 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -14,6 +14,7 @@
 #include <pthread.h>
 
 #include <signal.h>
+#include "../util/mutex.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
@@ -34,8 +35,8 @@ static u_int32_t futex1 = 0;
 
 static pthread_t *worker;
 static bool done = false;
-static pthread_mutex_t thread_lock;
-static pthread_cond_t thread_parent, thread_worker;
+static struct mutex thread_lock;
+static struct cond thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
 static unsigned int threads_starting;
 static int futex_flag = 0;
@@ -65,12 +66,12 @@ static const char * const bench_futex_wake_usage[] = {
 
 static void *workerfn(void *arg __maybe_unused)
 {
-	pthread_mutex_lock(&thread_lock);
+	mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
-		pthread_cond_signal(&thread_parent);
-	pthread_cond_wait(&thread_worker, &thread_lock);
-	pthread_mutex_unlock(&thread_lock);
+		cond_signal(&thread_parent);
+	cond_wait(&thread_worker, &thread_lock);
+	mutex_unlock(&thread_lock);
 
 	while (1) {
 		if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
@@ -178,9 +179,9 @@ int bench_futex_wake(int argc, const char **argv)
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
 	pthread_attr_init(&thread_attr);
-	pthread_mutex_init(&thread_lock, NULL);
-	pthread_cond_init(&thread_parent, NULL);
-	pthread_cond_init(&thread_worker, NULL);
+	mutex_init(&thread_lock);
+	cond_init(&thread_parent);
+	cond_init(&thread_worker);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nwoken = 0;
@@ -190,11 +191,11 @@ int bench_futex_wake(int argc, const char **argv)
 		block_threads(worker, thread_attr, cpu);
 
 		/* make sure all threads are already blocked */
-		pthread_mutex_lock(&thread_lock);
+		mutex_lock(&thread_lock);
 		while (threads_starting)
-			pthread_cond_wait(&thread_parent, &thread_lock);
-		pthread_cond_broadcast(&thread_worker);
-		pthread_mutex_unlock(&thread_lock);
+			cond_wait(&thread_parent, &thread_lock);
+		cond_broadcast(&thread_worker);
+		mutex_unlock(&thread_lock);
 
 		usleep(100000);
 
@@ -224,9 +225,9 @@ int bench_futex_wake(int argc, const char **argv)
 	}
 
 	/* cleanup & report results */
-	pthread_cond_destroy(&thread_parent);
-	pthread_cond_destroy(&thread_worker);
-	pthread_mutex_destroy(&thread_lock);
+	cond_destroy(&thread_parent);
+	cond_destroy(&thread_worker);
+	mutex_destroy(&thread_lock);
 	pthread_attr_destroy(&thread_attr);
 
 	print_summary();
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 20eed1e53f80..e78dedf9e682 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -6,8 +6,6 @@
  */
 
 #include <inttypes.h>
-/* For the CLR_() macros */
-#include <pthread.h>
 
 #include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
@@ -35,6 +33,7 @@
 #include <linux/zalloc.h>
 
 #include "../util/header.h"
+#include "../util/mutex.h"
 #include <numa.h>
 #include <numaif.h>
 
@@ -67,7 +66,7 @@ struct thread_data {
 	u64			system_time_ns;
 	u64			user_time_ns;
 	double			speed_gbs;
-	pthread_mutex_t		*process_lock;
+	struct mutex		*process_lock;
 };
 
 /* Parameters set by options: */
@@ -137,16 +136,16 @@ struct params {
 struct global_info {
 	u8			*data;
 
-	pthread_mutex_t		startup_mutex;
-	pthread_cond_t		startup_cond;
+	struct mutex		startup_mutex;
+	struct cond		startup_cond;
 	int			nr_tasks_started;
 
-	pthread_mutex_t		start_work_mutex;
-	pthread_cond_t		start_work_cond;
+	struct mutex		start_work_mutex;
+	struct cond		start_work_cond;
 	int			nr_tasks_working;
 	bool			start_work;
 
-	pthread_mutex_t		stop_work_mutex;
+	struct mutex		stop_work_mutex;
 	u64			bytes_done;
 
 	struct thread_data	*threads;
@@ -524,30 +523,6 @@ static void * setup_private_data(ssize_t bytes)
 	return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
 }
 
-/*
- * Return a process-shared (global) mutex:
- */
-static void init_global_mutex(pthread_mutex_t *mutex)
-{
-	pthread_mutexattr_t attr;
-
-	pthread_mutexattr_init(&attr);
-	pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
-	pthread_mutex_init(mutex, &attr);
-}
-
-/*
- * Return a process-shared (global) condition variable:
- */
-static void init_global_cond(pthread_cond_t *cond)
-{
-	pthread_condattr_t attr;
-
-	pthread_condattr_init(&attr);
-	pthread_condattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
-	pthread_cond_init(cond, &attr);
-}
-
 static int parse_cpu_list(const char *arg)
 {
 	p0.cpu_list_str = strdup(arg);
@@ -1220,22 +1195,22 @@ static void *worker_thread(void *__tdata)
 	}
 
 	if (g->p.serialize_startup) {
-		pthread_mutex_lock(&g->startup_mutex);
+		mutex_lock(&g->startup_mutex);
 		g->nr_tasks_started++;
 		/* The last thread wakes the main process. */
 		if (g->nr_tasks_started == g->p.nr_tasks)
-			pthread_cond_signal(&g->startup_cond);
+			cond_signal(&g->startup_cond);
 
-		pthread_mutex_unlock(&g->startup_mutex);
+		mutex_unlock(&g->startup_mutex);
 
 		/* Here we will wait for the main process to start us all at once: */
-		pthread_mutex_lock(&g->start_work_mutex);
+		mutex_lock(&g->start_work_mutex);
 		g->start_work = false;
 		g->nr_tasks_working++;
 		while (!g->start_work)
-			pthread_cond_wait(&g->start_work_cond, &g->start_work_mutex);
+			cond_wait(&g->start_work_cond, &g->start_work_mutex);
 
-		pthread_mutex_unlock(&g->start_work_mutex);
+		mutex_unlock(&g->start_work_mutex);
 	}
 
 	gettimeofday(&start0, NULL);
@@ -1254,17 +1229,17 @@ static void *worker_thread(void *__tdata)
 		val += do_work(thread_data,  g->p.bytes_thread,  0,          1,		l, val);
 
 		if (g->p.sleep_usecs) {
-			pthread_mutex_lock(td->process_lock);
+			mutex_lock(td->process_lock);
 			usleep(g->p.sleep_usecs);
-			pthread_mutex_unlock(td->process_lock);
+			mutex_unlock(td->process_lock);
 		}
 		/*
 		 * Amount of work to be done under a process-global lock:
 		 */
 		if (g->p.bytes_process_locked) {
-			pthread_mutex_lock(td->process_lock);
+			mutex_lock(td->process_lock);
 			val += do_work(process_data, g->p.bytes_process_locked, thread_nr,  g->p.nr_threads,	l, val);
-			pthread_mutex_unlock(td->process_lock);
+			mutex_unlock(td->process_lock);
 		}
 
 		work_done = g->p.bytes_global + g->p.bytes_process +
@@ -1361,9 +1336,9 @@ static void *worker_thread(void *__tdata)
 
 	free_data(thread_data, g->p.bytes_thread);
 
-	pthread_mutex_lock(&g->stop_work_mutex);
+	mutex_lock(&g->stop_work_mutex);
 	g->bytes_done += bytes_done;
-	pthread_mutex_unlock(&g->stop_work_mutex);
+	mutex_unlock(&g->stop_work_mutex);
 
 	return NULL;
 }
@@ -1373,7 +1348,7 @@ static void *worker_thread(void *__tdata)
  */
 static void worker_process(int process_nr)
 {
-	pthread_mutex_t process_lock;
+	struct mutex process_lock;
 	struct thread_data *td;
 	pthread_t *pthreads;
 	u8 *process_data;
@@ -1381,7 +1356,7 @@ static void worker_process(int process_nr)
 	int ret;
 	int t;
 
-	pthread_mutex_init(&process_lock, NULL);
+	mutex_init(&process_lock);
 	set_taskname("process %d", process_nr);
 
 	/*
@@ -1540,11 +1515,11 @@ static int init(void)
 	g->data = setup_shared_data(g->p.bytes_global);
 
 	/* Startup serialization: */
-	init_global_mutex(&g->start_work_mutex);
-	init_global_cond(&g->start_work_cond);
-	init_global_mutex(&g->startup_mutex);
-	init_global_cond(&g->startup_cond);
-	init_global_mutex(&g->stop_work_mutex);
+	mutex_init_pshared(&g->start_work_mutex);
+	cond_init_pshared(&g->start_work_cond);
+	mutex_init_pshared(&g->startup_mutex);
+	cond_init_pshared(&g->startup_cond);
+	mutex_init_pshared(&g->stop_work_mutex);
 
 	init_thread_data();
 
@@ -1633,17 +1608,17 @@ static int __bench_numa(const char *name)
 		 * Wait for all the threads to start up. The last thread will
 		 * signal this process.
 		 */
-		pthread_mutex_lock(&g->startup_mutex);
+		mutex_lock(&g->startup_mutex);
 		while (g->nr_tasks_started != g->p.nr_tasks)
-			pthread_cond_wait(&g->startup_cond, &g->startup_mutex);
+			cond_wait(&g->startup_cond, &g->startup_mutex);
 
-		pthread_mutex_unlock(&g->startup_mutex);
+		mutex_unlock(&g->startup_mutex);
 
 		/* Wait for all threads to be at the start_work_cond. */
 		while (!threads_ready) {
-			pthread_mutex_lock(&g->start_work_mutex);
+			mutex_lock(&g->start_work_mutex);
 			threads_ready = (g->nr_tasks_working == g->p.nr_tasks);
-			pthread_mutex_unlock(&g->start_work_mutex);
+			mutex_unlock(&g->start_work_mutex);
 			if (!threads_ready)
 				usleep(1);
 		}
@@ -1661,10 +1636,10 @@ static int __bench_numa(const char *name)
 
 		start = stop;
 		/* Start all threads running. */
-		pthread_mutex_lock(&g->start_work_mutex);
+		mutex_lock(&g->start_work_mutex);
 		g->start_work = true;
-		pthread_mutex_unlock(&g->start_work_mutex);
-		pthread_cond_broadcast(&g->start_work_cond);
+		mutex_unlock(&g->start_work_mutex);
+		cond_broadcast(&g->start_work_cond);
 	} else {
 		gettimeofday(&start, NULL);
 	}