perf tools fixes for v5.18: 1st batch

- Fix the clang command line option probing and remove some options to filter
   out, fixing the build with the latest clang versions.
 
 - Fix 'perf bench' futex and epoll benchmarks to deal with machines with more
   than 1K CPUs.
 
 - Fix 'perf test tsc' error message when not supported.
 
 - Remap perf ring buffer if there is no space for event, fixing perf usage
   in 32-bit ChromeOS.
 
 - Drop objdump stderr to avoid getting stuck waiting for stdout output in
   'perf annotate'.
 
 - Fix up garbled output by now showing unwind error messages when augmenting
   frame in best effort mode.
 
 - Fix perf's libperf_print callback, use the va_args eprintf() variant.
 
 - Sync vhost and arm64 cputype headers with the kernel sources.
 
 - Fix 'perf report --mem-mode' with ARM SPE.
 
 - Add missing external commands ('perf iiostat', etc) to 'perf --list-cmds'.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCYlIM+gAKCRCyPKLppCJ+
 J5l6AQCCY4co/6FBh8JMmMX4RVHAUriX0YfKTJfpeLU3nsiXPAD/TVqf1LOyYaPv
 /ZqJ8DwqvKr9nkUsf5kAOfPrDB/j/QQ=
 =0UV/
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-fixes-for-v5.18-2022-04-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix the clang command line option probing and remove some options to
   filter out, fixing the build with the latest clang versions

 - Fix 'perf bench' futex and epoll benchmarks to deal with machines
   with more than 1K CPUs

 - Fix 'perf test tsc' error message when not supported

 - Remap perf ring buffer if there is no space for event, fixing perf
   usage in 32-bit ChromeOS

 - Drop objdump stderr to avoid getting stuck waiting for stdout output
   in 'perf annotate'

 - Fix up garbled output by now showing unwind error messages when
   augmenting frame in best effort mode

 - Fix perf's libperf_print callback, use the va_args eprintf() variant

 - Sync vhost and arm64 cputype headers with the kernel sources

 - Fix 'perf report --mem-mode' with ARM SPE

 - Add missing external commands ('iiostat', etc) to 'perf --list-cmds'

* tag 'perf-tools-fixes-for-v5.18-2022-04-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf annotate: Drop objdump stderr to avoid getting stuck waiting for stdout output
  perf tools: Add external commands to list-cmds
  perf docs: Add perf-iostat link to manpages
  perf session: Remap buf if there is no space for event
  perf bench: Fix epoll bench to correct usage of affinity for machines with #CPUs > 1K
  perf bench: Fix futex bench to correct usage of affinity for machines with #CPUs > 1K
  perf tools: Fix perf's libperf_print callback
  perf: arm-spe: Fix perf report --mem-mode
  perf unwind: Don't show unwind error messages when augmenting frame pointer stack
  tools headers arm64: Sync arm64's cputype.h with the kernel sources
  perf test tsc: Fix error message when not supported
  perf build: Don't use -ffat-lto-objects in the python feature test when building with clang-13
  perf python: Fix probing for some clang command line options
  tools build: Filter out options and warnings not supported by clang
  tools build: Use $(shell ) instead of `` to get embedded libperl's ccopts
  tools include UAPI: Sync linux/vhost.h with the kernel sources

tools/arch/arm64/include/asm/cputype.h

@@ -75,6 +75,7 @@
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
@@ -130,6 +131,7 @@
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)

tools/build/feature/Makefile

@@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1))
 PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
 PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
 PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
 FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
+ifeq ($(CC_NO_CLANG), 0)
+  PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro
+endif
+
 $(OUTPUT)test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 

tools/include/uapi/linux/vhost.h

@@ -150,4 +150,11 @@
 /* Get the valid iova range */
 #define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
 					     struct vhost_vdpa_iova_range)
+
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
 #endif

tools/perf/Documentation/perf.txt

@@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1],
 linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1],
 linkperf:perf-evlist[1], linkperf:perf-ftrace[1],
 linkperf:perf-help[1], linkperf:perf-inject[1],
-linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1],
+linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1],
 linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1],
 linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1],
 linkperf:perf-script[1], linkperf:perf-test[1],

tools/perf/Makefile.config

@@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+  ifeq ($(CC_NO_CLANG), 0)
+    PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS))
+  endif
 endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
@@ -790,6 +793,9 @@ else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
     CFLAGS += -DHAVE_LIBPERL_SUPPORT
+    ifeq ($(CC_NO_CLANG), 0)
+      CFLAGS += -Wno-compound-token-split-by-macro
+    endif
     $(call detected,CONFIG_LIBPERL)
   endif
 endif

tools/perf/arch/arm64/util/arm-spe.c

@@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		arm_spe_set_timestamp(itr, arm_spe_evsel);
 	}
 
+	/*
+	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
+	 * on the opening of the event or the SPE data produced.
+	 */
+	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
+
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
 	if (err)

tools/perf/bench/epoll-ctl.c

@@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct)
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 {
 	pthread_attr_t thread_attr, *attrp = NULL;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i, j;
 	int ret = 0;
+	int nrcpus;
+	size_t size;
 
 	if (!noaffinity)
 		pthread_attr_init(&thread_attr);
 
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < nthreads; i++) {
 		struct worker *w = &worker[i];
 
@@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 			init_fdmaps(w, 50);
 
 		if (!noaffinity) {
-			CPU_ZERO(&cpuset);
-			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+			CPU_ZERO_S(size, cpuset);
+			CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+					size, cpuset);
 
-			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-			if (ret)
+			ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+			if (ret) {
+				CPU_FREE(cpuset);
 				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+			}
 
 			attrp = &thread_attr;
 		}
 
 		ret = pthread_create(&w->thread, attrp, workerfn,
 				     (void *)(struct worker *) w);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
 
+	CPU_FREE(cpuset);
 	if (!noaffinity)
 		pthread_attr_destroy(&thread_attr);
 

tools/perf/bench/epoll-wait.c

@@ -291,9 +291,11 @@ static void print_summary(void)
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 {
 	pthread_attr_t thread_attr, *attrp = NULL;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i, j;
 	int ret = 0, events = EPOLLIN;
+	int nrcpus;
+	size_t size;
 
 	if (oneshot)
 		events |= EPOLLONESHOT;
@@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 	if (!noaffinity)
 		pthread_attr_init(&thread_attr);
 
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < nthreads; i++) {
 		struct worker *w = &worker[i];
 
@@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 		}
 
 		if (!noaffinity) {
-			CPU_ZERO(&cpuset);
-			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+			CPU_ZERO_S(size, cpuset);
+			CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+					size, cpuset);
 
-			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-			if (ret)
+			ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+			if (ret) {
+				CPU_FREE(cpuset);
 				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+			}
 
 			attrp = &thread_attr;
 		}
 
 		ret = pthread_create(&w->thread, attrp, workerfn,
 				     (void *)(struct worker *) w);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
 
+	CPU_FREE(cpuset);
 	if (!noaffinity)
 		pthread_attr_destroy(&thread_attr);
 

tools/perf/bench/futex-hash.c

@@ -122,12 +122,14 @@ static void print_summary(void)
 int bench_futex_hash(int argc, const char **argv)
 {
 	int ret = 0;
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	struct sigaction act;
 	unsigned int i;
 	pthread_attr_t thread_attr;
 	struct worker *worker = NULL;
 	struct perf_cpu_map *cpu;
+	int nrcpus;
+	size_t size;
 
 	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
 	if (argc) {
@@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv)
 	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&bench__start, NULL);
+
+	nrcpus = perf_cpu_map__nr(cpu);
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
 		worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex));
 		if (!worker[i].futex)
 			goto errmem;
 
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
 
-		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
-		if (ret)
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
+		ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
-
+		}
 		ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
 				     (void *)(struct worker *) &worker[i]);
-		if (ret)
+		if (ret) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 
 	}
+	CPU_FREE(cpuset);
 	pthread_attr_destroy(&thread_attr);
 
 	pthread_mutex_lock(&thread_lock);

tools/perf/bench/futex-lock-pi.c

@@ -120,11 +120,17 @@ static void *workerfn(void *arg)
 static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 			   struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus =  perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
 
@@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 		} else
 			worker[i].futex = &global_futex;
 
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
+		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 int bench_futex_lock_pi(int argc, const char **argv)

tools/perf/bench/futex-requeue.c

@@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused)
 static void block_threads(pthread_t *w,
 			  pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus = perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void toggle_done(int sig __maybe_unused,

tools/perf/bench/futex-wake-parallel.c

@@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused)
 static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
 			  struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
+	int nrcpus = perf_cpu_map__nr(cpu);
+	size_t size;
 
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void print_run(struct thread_data *waking_worker, unsigned int run_num)

tools/perf/bench/futex-wake.c

@@ -97,22 +97,32 @@ static void print_summary(void)
 static void block_threads(pthread_t *w,
 			  pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
 {
-	cpu_set_t cpuset;
+	cpu_set_t *cpuset;
 	unsigned int i;
-
+	size_t size;
+	int nrcpus = perf_cpu_map__nr(cpu);
 	threads_starting = params.nthreads;
 
+	cpuset = CPU_ALLOC(nrcpus);
+	BUG_ON(!cpuset);
+	size = CPU_ALLOC_SIZE(nrcpus);
+
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
-		CPU_ZERO(&cpuset);
-		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+		CPU_ZERO_S(size, cpuset);
+		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
 
-		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
 
-		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+			CPU_FREE(cpuset);
 			err(EXIT_FAILURE, "pthread_create");
+		}
 	}
+	CPU_FREE(cpuset);
 }
 
 static void toggle_done(int sig __maybe_unused,

tools/perf/perf.c

@@ -55,6 +55,7 @@ struct cmd_struct {
 };
 
 static struct cmd_struct commands[] = {
+	{ "archive",	NULL,	0 },
 	{ "buildid-cache", cmd_buildid_cache, 0 },
 	{ "buildid-list", cmd_buildid_list, 0 },
 	{ "config",	cmd_config,	0 },
@@ -62,6 +63,7 @@ static struct cmd_struct commands[] = {
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
+	{ "iostat",	NULL,	0 },
 	{ "kallsyms",	cmd_kallsyms,	0 },
 	{ "list",	cmd_list,	0 },
 	{ "record",	cmd_record,	0 },
@@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv)
 
 	for (i = 0; i < ARRAY_SIZE(commands); i++) {
 		struct cmd_struct *p = commands+i;
+		if (p->fn == NULL)
+			continue;
 		if (strcmp(p->cmd, cmd))
 			continue;
 		exit(run_builtin(p, argc, argv));
@@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void)
 static int libperf_print(enum libperf_print_level level,
 			 const char *fmt, va_list ap)
 {
-	return eprintf(level, verbose, fmt, ap);
+	return veprintf(level, verbose, fmt, ap);
 }
 
 int main(int argc, const char **argv)

tools/perf/tests/dwarf-unwind.c

@@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr
 	}
 
 	err = unwind__get_entries(unwind_entry, &cnt, thread,
-				  &sample, MAX_STACK);
+				  &sample, MAX_STACK, false);
 	if (err)
 		pr_debug("unwind failed\n");
 	else if (cnt != MAX_STACK) {

tools/perf/tests/perf-time-to-tsc.c

@@ -47,6 +47,17 @@
 	}					\
 }
 
+static int test__tsc_is_supported(struct test_suite *test __maybe_unused,
+				  int subtest __maybe_unused)
+{
+	if (!TSC_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture\n");
+		return TEST_SKIP;
+	}
+
+	return TEST_OK;
+}
+
 /**
  * test__perf_time_to_tsc - test converting perf time to TSC.
  *
@@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	struct perf_cpu_map *cpus = NULL;
 	struct evlist *evlist = NULL;
 	struct evsel *evsel = NULL;
-	int err = -1, ret, i;
+	int err = TEST_FAIL, ret, i;
 	const char *comm1, *comm2;
 	struct perf_tsc_conversion tc;
 	struct perf_event_mmap_page *pc;
@@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct mmap *md;
 
-	if (!TSC_IS_SUPPORTED) {
-		pr_debug("Test not supported on this architecture");
-		return TEST_SKIP;
-	}
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	ret = perf_read_tsc_conversion(pc, &tc);
 	if (ret) {
 		if (ret == -EOPNOTSUPP) {
-			fprintf(stderr, " (not supported)");
-			return 0;
+			pr_debug("perf_read_tsc_conversion is not supported in current kernel\n");
+			err = TEST_SKIP;
 		}
 		goto out_err;
 	}
@@ -191,7 +198,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	    test_tsc >= comm2_tsc)
 		goto out_err;
 
-	err = 0;
+	err = TEST_OK;
 
 out_err:
 	evlist__delete(evlist);
@@ -200,4 +207,15 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	return err;
 }
 
-DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc);
+static struct test_case time_to_tsc_tests[] = {
+	TEST_CASE_REASON("TSC support", tsc_is_supported,
+			 "This architecture does not support"),
+	TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc,
+			 "perf_read_tsc_conversion is not supported"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__perf_time_to_tsc = {
+	.desc = "Convert perf time to TSC",
+	.test_cases = time_to_tsc_tests,
+};

tools/perf/util/annotate.c

@@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	objdump_process.argv = objdump_argv;
 	objdump_process.out = -1;
 	objdump_process.err = -1;
+	objdump_process.no_stderr = 1;
 	if (start_command(&objdump_process)) {
 		pr_err("Failure starting to run %s\n", command);
 		err = -1;

tools/perf/util/arm64-frame-pointer-unwind-support.c

@@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
 		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
 	}
 
-	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
 	sample->user_regs = old_regs;
 
 	if (ret || entries.length != 2)

tools/perf/util/machine.c

@@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 		return 0;
 
 	return unwind__get_entries(unwind_entry, cursor,
-				   thread, sample, max_stack);
+				   thread, sample, max_stack, false);
 }
 
 int thread__resolve_callchain(struct thread *thread,

tools/perf/util/session.c

@@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	       bool needs_swap, union perf_event *error)
 {
 	union perf_event *event;
+	u16 event_size;
 
 	/*
 	 * Ensure we have enough space remaining to read
@@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (head + event->header.size <= mmap_size)
+	event_size = event->header.size;
+	if (head + event_size <= mmap_size)
 		return event;
 
 	/* We're not fetching the event so swap back again */
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:"
-		 " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size);
+	/* Check if the event fits into the next mmapped buf. */
+	if (event_size <= mmap_size - head % page_size) {
+		/* Remap buf and fetch again. */
+		return NULL;
+	}
+
+	/* Invalid input. Event size should never exceed mmap_size. */
+	pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:"
+		 " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size);
 
 	return error;
 }

tools/perf/util/setup.py

@@ -1,12 +1,14 @@
-from os import getenv
+from os import getenv, path
 from subprocess import Popen, PIPE
 from re import sub
 
 cc = getenv("CC")
 cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline()
+src_feature_tests  = getenv('srctree') + '/tools/build/feature'
 
 def clang_has_option(option):
-    return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+    cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines()
+    return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ]
 
 if cc_is_clang:
     from distutils.sysconfig import get_config_vars
@@ -23,6 +25,8 @@ if cc_is_clang:
             vars[var] = sub("-fstack-protector-strong", "", vars[var])
         if not clang_has_option("-fno-semantic-interposition"):
             vars[var] = sub("-fno-semantic-interposition", "", vars[var])
+        if not clang_has_option("-ffat-lto-objects"):
+            vars[var] = sub("-ffat-lto-objects", "", vars[var])
 
 from distutils.core import setup, Extension
 

tools/perf/util/unwind-libdw.c

@@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 	bool isactivation;
 
 	if (!dwfl_frame_pc(state, &pc, NULL)) {
-		pr_err("%s", dwfl_errmsg(-1));
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
@@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 	report_module(pc, ui);
 
 	if (!dwfl_frame_pc(state, &pc, &isactivation)) {
-		pr_err("%s", dwfl_errmsg(-1));
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
@@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data,
-			int max_stack)
+			int max_stack,
+			bool best_effort)
 {
 	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
@@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,
+		.best_effort    = best_effort
 	};
 	Dwarf_Word ip;
 	int err = -EINVAL, i;

tools/perf/util/unwind-libdw.h

@@ -20,6 +20,7 @@ struct unwind_info {
 	void			*arg;
 	int			max_stack;
 	int			idx;
+	bool			best_effort;
 	struct unwind_entry	entries[];
 };
 

tools/perf/util/unwind-libunwind-local.c

@@ -96,6 +96,7 @@ struct unwind_info {
 	struct perf_sample	*sample;
 	struct machine		*machine;
 	struct thread		*thread;
+	bool			 best_effort;
 };
 
 #define dw_read(ptr, type, end) ({	\
@@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
 
 	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
 	if (ret) {
-		pr_err("unwind: can't read reg %d\n", regnum);
+		if (!ui->best_effort)
+			pr_err("unwind: can't read reg %d\n", regnum);
 		return ret;
 	}
 
@@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 			return -1;
 
 		ret = unw_init_remote(&c, addr_space, ui);
-		if (ret)
+		if (ret && !ui->best_effort)
 			display_error(ret);
 
 		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
@@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
-			struct perf_sample *data, int max_stack)
+			struct perf_sample *data, int max_stack,
+			bool best_effort)
 {
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
 		.machine      = thread->maps->machine,
+		.best_effort  = best_effort
 	};
 
 	if (!data->user_regs.regs)

tools/perf/util/unwind-libunwind.c

@@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps)
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			 struct thread *thread,
-			 struct perf_sample *data, int max_stack)
+			 struct perf_sample *data, int max_stack,
+			 bool best_effort)
 {
 	if (thread->maps->unwind_libunwind_ops)
-		return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+		return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data,
+								       max_stack, best_effort);
 	return 0;
 }

tools/perf/util/unwind.h

@@ -23,13 +23,19 @@ struct unwind_libunwind_ops {
 	void (*finish_access)(struct maps *maps);
 	int (*get_entries)(unwind_entry_cb_t cb, void *arg,
 			   struct thread *thread,
-			   struct perf_sample *data, int max_stack);
+			   struct perf_sample *data, int max_stack, bool best_effort);
 };
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
+/*
+ * When best_effort is set, don't report errors and fail silently. This could
+ * be expanded in the future to be more permissive about things other than
+ * error messages.
+ */
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
-			struct perf_sample *data, int max_stack);
+			struct perf_sample *data, int max_stack,
+			bool best_effort);
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 #ifndef LIBUNWIND__ARCH_REG_ID
@@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
-		    int max_stack __maybe_unused)
+		    int max_stack __maybe_unused,
+		    bool best_effort __maybe_unused)
 {
 	return 0;
 }