Merge tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Improvements for the flamegraph python script, including:
       - Display perf.data header
       - Display PIDs of user stacks
       - Added option to change color scheme
       - Default to blue/green color scheme to improve accessibility
       - Correctly identify kernel stacks when debuginfo is available

   - Improvements for 'perf bench futex':
       - Add --mlockall parameter
       - Add --broadcast and --pi to the 'requeue' sub benchmark

   - Add support for PMU aliases.

   - Introduce an ARM Coresight ETE decoder.

   - Add a 'perf bench' entry for evlist open/close operations, to help
     quantify improvements with multithreading 'perf record'.

   - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf
     script's python scripting.

   - Add a 'perf test' entry for PMU aliases.

   - Add a 'perf test' entry for 'perf record/perf report/perf script'
     pipe mode.

  Fixes:

   - perf script dlfilter (API for filtering via dynamically loaded
     shared object introduced in v5.14) fixes and a 'perf test' entry
     for it.

   - Fix get_current_dir_name() compilation on Android.

   - Fix issues with asciidoc and double dashes uses.

   - Fix memory leaks in the BTF handling code.

   - Fix leftover problems in the Documentation from the infrastructure
     originally lifted from the git codebase.

   - Fix *probe_vfs_getname.sh 'perf test' failures.

   - Handle fd gaps in 'perf test's test__dso_data_reopen().

   - Make sure to show disasembly warnings for 'perf annotate --stdio'.

   - Fix output from pipe to file and vice-versa in 'perf
     record/report/script'.

   - Correct 'perf data -h' output.

   - Fix wrong comm in system-wide mode with 'perf record --delay'.

   - Do not allow --for-each-cgroup without cpu in 'perf stat'

   - Make 'perf test --skip' work on shell tests.

   - Fix libperf's verbose printing.

  Misc improvements:

   - Preparatory patches for multithreading various 'perf record' phases
     (synthesizing, opening, recording, etc).

   - Add sparse context/locking annotations in compiler-types.h, also to
     help with the multithreading effort.

   - Optimize the generation of the arch specific erno tables used in
     'perf trace'.

   - Optimize libperf's perf_cpu_map__max().

   - Improve ARM's CoreSight warnings.

   - Report collisions in AUX records.

   - Improve warnings for the LLVM 'perf test' entry.

   - Improve the PMU events 'perf test' codebase.

   - perf test: Do not compare overheads in the zstd comp test

   - Better support annotation on ARM.

   - Update 'perf trace's cmd string table to decode sys_bpf() first
     arg.

  Vendor events:

   - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and
     Elhart Lake.

   - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake
     servers.

  Hardware tracing:

   - Improvements for the ARM hardware tracing auxtrace support"

* tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits)
  perf tests: Add test for PMU aliases
  perf pmu: Add PMU alias support
  perf session: Report collisions in AUX records
  perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event
  perf build: Report failure for testing feature libopencsd
  perf cs-etm: Show a warning for an unknown magic number
  perf cs-etm: Print the decoder name
  perf cs-etm: Create ETE decoder
  perf cs-etm: Update OpenCSD decoder for ETE
  perf cs-etm: Fix typo
  perf cs-etm: Save TRCDEVARCH register
  perf cs-etm: Refactor out ETMv4 header saving
  perf cs-etm: Initialise architecture based on TRCIDR1
  perf cs-etm: Refactor initialisation of decoder params.
  tools build: Fix feature detect clean for out of source builds
  perf evlist: Add evlist__for_each_entry_from() macro
  perf evsel: Handle precise_ip fallback in evsel__open_cpu()
  perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()
  perf evsel: Move test_attr__open() to success path in evsel__open_cpu()
  perf evsel: Move ignore_missing_thread() to fallback code
  ...

1 files changed, 38 insertions, 28 deletions

diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 6e6f5247e1fe..e970e6b9ad53 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -34,6 +34,7 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.h>
 
 struct thread_data {
 	pthread_t worker;
@@ -47,8 +48,7 @@ static unsigned int nwakes = 1;
 static u_int32_t futex = 0;
 
 static pthread_t *blocked_worker;
-static bool done = false, silent = false, fshared = false;
-static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static bool done = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static pthread_barrier_t barrier;
@@ -56,11 +56,15 @@ static struct stats waketime_stats, wakeup_stats;
 static unsigned int threads_starting;
 static int futex_flag = 0;
 
+static struct bench_futex_parameters params;
+
 static const struct option options[] = {
-	OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
-	OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
-	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
-	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakers", &params.nwakes, "Specify amount of waking threads"),
+	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
+
 	OPT_END()
 };
 
@@ -96,10 +100,10 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 	pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
 
-	pthread_barrier_init(&barrier, NULL, nwaking_threads + 1);
+	pthread_barrier_init(&barrier, NULL, params.nwakes + 1);
 
 	/* create and block all threads */
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		/*
 		 * Thread creation order will impact per-thread latency
 		 * as it will affect the order to acquire the hb spinlock.
@@ -112,7 +116,7 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 	pthread_barrier_wait(&barrier);
 
-	for (i = 0; i < nwaking_threads; i++)
+	for (i = 0; i < params.nwakes; i++)
 		if (pthread_join(td[i].worker, NULL))
 			err(EXIT_FAILURE, "pthread_join");
 
@@ -143,10 +147,10 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
 	cpu_set_t cpuset;
 	unsigned int i;
 
-	threads_starting = nblocked_threads;
+	threads_starting = params.nthreads;
 
 	/* create and block all threads */
-	for (i = 0; i < nblocked_threads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
 		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
@@ -167,7 +171,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
 	init_stats(&__wakeup_stats);
 	init_stats(&__waketime_stats);
 
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
 		update_stats(&__wakeup_stats, waking_worker[i].nwoken);
 	}
@@ -178,7 +182,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
 
 	printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
 	       "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
-	       nblocked_threads, waketime_avg / USEC_PER_MSEC,
+	       params.nthreads, waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
 
@@ -193,7 +197,7 @@ static void print_summary(void)
 
 	printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
 	       wakeup_avg,
-	       nblocked_threads,
+	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
@@ -203,7 +207,7 @@ static void do_run_stats(struct thread_data *waking_worker)
 {
 	unsigned int i;
 
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
 		update_stats(&wakeup_stats, waking_worker[i].nwoken);
 	}
@@ -238,36 +242,42 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
 	cpu = perf_cpu_map__new(NULL);
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!nblocked_threads)
-		nblocked_threads = cpu->nr;
+	if (!params.nthreads)
+		params.nthreads = cpu->nr;
 
 	/* some sanity checks */
-	if (nwaking_threads > nblocked_threads || !nwaking_threads)
-		nwaking_threads = nblocked_threads;
+	if (params.nwakes > params.nthreads ||
+	    !params.nwakes)
+		params.nwakes = params.nthreads;
 
-	if (nblocked_threads % nwaking_threads)
+	if (params.nthreads % params.nwakes)
 		errx(EXIT_FAILURE, "Must be perfectly divisible");
 	/*
 	 * Each thread will wakeup nwakes tasks in
 	 * a single futex_wait call.
 	 */
-	nwakes = nblocked_threads/nwaking_threads;
+	nwakes = params.nthreads/params.nwakes;
 
-	blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+	blocked_worker = calloc(params.nthreads, sizeof(*blocked_worker));
 	if (!blocked_worker)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
 	printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
 	       "futex %p), %d threads waking up %d at a time.\n\n",
-	       getpid(), nblocked_threads, fshared ? "shared":"private",
-	       &futex, nwaking_threads, nwakes);
+	       getpid(), params.nthreads, params.fshared ? "shared":"private",
+	       &futex, params.nwakes, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -278,7 +288,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	pthread_cond_init(&thread_worker, NULL);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
-		waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+		waking_worker = calloc(params.nwakes, sizeof(*waking_worker));
 		if (!waking_worker)
 			err(EXIT_FAILURE, "calloc");
 
@@ -297,14 +307,14 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		/* Ok, all threads are patiently blocked, start waking folks up */
 		wakeup_threads(waking_worker, thread_attr);
 
-		for (i = 0; i < nblocked_threads; i++) {
+		for (i = 0; i < params.nthreads; i++) {
 			ret = pthread_join(blocked_worker[i], NULL);
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
 
 		do_run_stats(waking_worker);
-		if (!silent)
+		if (!params.silent)
 			print_run(waking_worker, j);
 
 		free(waking_worker);