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

Author: torvalds

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)