Merge tag 'perf-tools-for-v5.17-2022-01-22' of git://git.kernel.org/p…

…ub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:

 - Fix printing 'phys_addr' in 'perf script'.

 - Fix failure to add events with 'perf probe' in ppc64 due to not
   removing leading dot (ppc64 ABIv1).

 - Fix cpu_map__item() python binding building.

 - Support event alias in form foo-bar-baz, add pmu-events and
   parse-event tests for it.

 - No need to setup affinities when starting a workload or attaching to
   a pid.

 - Use path__join() to compose a path instead of ad-hoc snprintf()
   equivalent.

 - Override attr->sample_period for non-libpfm4 events.

 - Use libperf cpumap APIs instead of accessing the internal state
   directly.

 - Sync x86 arch prctl headers and files changed by the new
   set_mempolicy_home_node syscall with the kernel sources.

 - Remove duplicate include in cpumap.h.

 - Remove redundant err variable.

* tag 'perf-tools-for-v5.17-2022-01-22' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf tools: Remove redundant err variable
  perf test: Add parse-events test for aliases with hyphens
  perf test: Add pmu-events test for aliases with hyphens
  perf parse-events: Support event alias in form foo-bar-baz
  perf evsel: Override attr->sample_period for non-libpfm4 events
  perf cpumap: Remove duplicate include in cpumap.h
  perf cpumap: Migrate to libperf cpumap api
  perf python: Fix cpu_map__item() building
  perf script: Fix printing 'phys_addr' failure issue
  tools headers UAPI: Sync files changed by new set_mempolicy_home_node syscall
  tools headers UAPI: Sync x86 arch prctl headers with the kernel sources
  perf machine: Use path__join() to compose a path instead of snprintf(dir, '/', filename)
  perf evlist: No need to setup affinities when disabling events for pid targets
  perf evlist: No need to setup affinities when enabling events for pid targets
  perf stat: No need to setup affinities when starting a workload
  perf affinity: Allow passing a NULL arg to affinity__cleanup()
  perf probe: Fix ppc64 'perf probe add events failed' case

tools/arch/x86/include/uapi/asm/prctl.h

@@ -2,20 +2,22 @@
 #ifndef _ASM_X86_PRCTL_H
 #define _ASM_X86_PRCTL_H
 
-#define ARCH_SET_GS		0x1001
-#define ARCH_SET_FS		0x1002
-#define ARCH_GET_FS		0x1003
-#define ARCH_GET_GS		0x1004
+#define ARCH_SET_GS			0x1001
+#define ARCH_SET_FS			0x1002
+#define ARCH_GET_FS			0x1003
+#define ARCH_GET_GS			0x1004
 
-#define ARCH_GET_CPUID		0x1011
-#define ARCH_SET_CPUID		0x1012
+#define ARCH_GET_CPUID			0x1011
+#define ARCH_SET_CPUID			0x1012
 
-#define ARCH_GET_XCOMP_SUPP	0x1021
-#define ARCH_GET_XCOMP_PERM	0x1022
-#define ARCH_REQ_XCOMP_PERM	0x1023
+#define ARCH_GET_XCOMP_SUPP		0x1021
+#define ARCH_GET_XCOMP_PERM		0x1022
+#define ARCH_REQ_XCOMP_PERM		0x1023
+#define ARCH_GET_XCOMP_GUEST_PERM	0x1024
+#define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
 
-#define ARCH_MAP_VDSO_X32	0x2001
-#define ARCH_MAP_VDSO_32	0x2002
-#define ARCH_MAP_VDSO_64	0x2003
+#define ARCH_MAP_VDSO_X32		0x2001
+#define ARCH_MAP_VDSO_32		0x2002
+#define ARCH_MAP_VDSO_64		0x2003
 
 #endif /* _ASM_X86_PRCTL_H */

tools/include/uapi/asm-generic/unistd.h

@@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 #define __NR_futex_waitv 449
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
 #undef __NR_syscalls
-#define __NR_syscalls 450
+#define __NR_syscalls 451
 
 /*
  * 32 bit systems traditionally used different

tools/lib/perf/evsel.c

@@ -141,7 +141,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	}
 
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
 		return -ENOMEM;
 
 	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
@@ -384,7 +384,7 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
 	int err = 0, i;
 
-	for (i = 0; i < evsel->cpus->nr && !err; i++)
+	for (i = 0; i < perf_cpu_map__nr(evsel->cpus) && !err; i++)
 		err = perf_evsel__run_ioctl(evsel,
 				     PERF_EVENT_IOC_SET_FILTER,
 				     (void *)filter, i);

tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl

@@ -364,3 +364,4 @@
 # 447 reserved for memfd_secret
 448	n64	process_mrelease		sys_process_mrelease
 449	n64	futex_waitv			sys_futex_waitv
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

tools/perf/arch/powerpc/entry/syscalls/syscall.tbl

@@ -529,3 +529,4 @@
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
+450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node

tools/perf/arch/s390/entry/syscalls/syscall.tbl

@@ -452,3 +452,4 @@
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
+450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -371,6 +371,7 @@
 447	common	memfd_secret		sys_memfd_secret
 448	common	process_mrelease	sys_process_mrelease
 449	common	futex_waitv		sys_futex_waitv
+450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

tools/perf/bench/epoll-ctl.c

@@ -333,7 +333,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 
 	/* default to the number of CPUs */
 	if (!nthreads)
-		nthreads = cpu->nr;
+		nthreads = perf_cpu_map__nr(cpu);
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)

tools/perf/bench/epoll-wait.c

@@ -452,7 +452,7 @@ int bench_epoll_wait(int argc, const char **argv)
 
 	/* default to the number of CPUs and leave one for the writer pthread */
 	if (!nthreads)
-		nthreads = cpu->nr - 1;
+		nthreads = perf_cpu_map__nr(cpu) - 1;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker) {

tools/perf/bench/evlist-open-close.c

@@ -71,7 +71,7 @@ static int evlist__count_evsel_fds(struct evlist *evlist)
 	int cnt = 0;
 
 	evlist__for_each_entry(evlist, evsel)
-		cnt += evsel->core.threads->nr * evsel->core.cpus->nr;
+		cnt += evsel->core.threads->nr * perf_cpu_map__nr(evsel->core.cpus);
 
 	return cnt;
 }
@@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr)
 
 	init_stats(&time_stats);
 
-	printf("  Number of cpus:\t%d\n", evlist->core.cpus->nr);
+	printf("  Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus));
 	printf("  Number of threads:\t%d\n", evlist->core.threads->nr);
 	printf("  Number of events:\t%d (%d fds)\n",
 		evlist->core.nr_entries, evlist__count_evsel_fds(evlist));

tools/perf/bench/futex-hash.c

@@ -150,7 +150,7 @@ int bench_futex_hash(int argc, const char **argv)
 	}
 
 	if (!params.nthreads) /* default to the number of CPUs */
-		params.nthreads = cpu->nr;
+		params.nthreads = perf_cpu_map__nr(cpu);
 
 	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)

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

@@ -173,7 +173,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	}
 
 	if (!params.nthreads)
-		params.nthreads = cpu->nr;
+		params.nthreads = perf_cpu_map__nr(cpu);
 
 	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)

tools/perf/bench/futex-requeue.c

@@ -175,7 +175,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	}
 
 	if (!params.nthreads)
-		params.nthreads = cpu->nr;
+		params.nthreads = perf_cpu_map__nr(cpu);
 
 	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)

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

@@ -252,7 +252,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		err(EXIT_FAILURE, "calloc");
 
 	if (!params.nthreads)
-		params.nthreads = cpu->nr;
+		params.nthreads = perf_cpu_map__nr(cpu);
 
 	/* some sanity checks */
 	if (params.nwakes > params.nthreads ||

tools/perf/bench/futex-wake.c

@@ -151,7 +151,7 @@ int bench_futex_wake(int argc, const char **argv)
 	}
 
 	if (!params.nthreads)
-		params.nthreads = cpu->nr;
+		params.nthreads = perf_cpu_map__nr(cpu);
 
 	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)

tools/perf/builtin-ftrace.c

@@ -281,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
 	int ret;
 	int last_cpu;
 
-	last_cpu = perf_cpu_map__cpu(cpumap, cpumap->nr - 1).cpu;
+	last_cpu = perf_cpu_map__cpu(cpumap, perf_cpu_map__nr(cpumap) - 1).cpu;
 	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 

tools/perf/builtin-inject.c

@@ -535,12 +535,9 @@ static int perf_event__repipe_exit(struct perf_tool *tool,
 static int perf_event__repipe_tracing_data(struct perf_session *session,
 					   union perf_event *event)
 {
-	int err;
-
 	perf_event__repipe_synth(session->tool, event);
-	err = perf_event__process_tracing_data(session, event);
 
-	return err;
+	return perf_event__process_tracing_data(session, event);
 }
 
 static int dso__read_build_id(struct dso *dso)

tools/perf/builtin-script.c

@@ -515,7 +515,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 		return -EINVAL;
 
 	if (PRINT_FIELD(PHYS_ADDR) &&
-	    evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
+	    evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(DATA_PAGE_SIZE) &&

tools/perf/builtin-stat.c

@@ -230,11 +230,12 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b)
 	if (!a->core.cpus || !b->core.cpus)
 		return false;
 
-	if (a->core.cpus->nr != b->core.cpus->nr)
+	if (perf_cpu_map__nr(a->core.cpus) != perf_cpu_map__nr(b->core.cpus))
 		return false;
 
-	for (int i = 0; i < a->core.cpus->nr; i++) {
-		if (a->core.cpus->map[i].cpu != b->core.cpus->map[i].cpu)
+	for (int i = 0; i < perf_cpu_map__nr(a->core.cpus); i++) {
+		if (perf_cpu_map__cpu(a->core.cpus, i).cpu !=
+		    perf_cpu_map__cpu(b->core.cpus, i).cpu)
 			return false;
 	}
 
@@ -788,7 +789,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity affinity;
+	struct affinity saved_affinity, *affinity = NULL;
 	int err;
 	bool second_pass = false;
 
@@ -803,8 +804,11 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (group)
 		evlist__set_leader(evsel_list);
 
-	if (affinity__setup(&affinity) < 0)
-		return -1;
+	if (!cpu_map__is_dummy(evsel_list->core.cpus)) {
+		if (affinity__setup(&saved_affinity) < 0)
+			return -1;
+		affinity = &saved_affinity;
+	}
 
 	evlist__for_each_entry(evsel_list, counter) {
 		if (bpf_counter__load(counter, &target))
@@ -813,7 +817,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			all_counters_use_bpf = false;
 	}
 
-	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
 		counter = evlist_cpu_itr.evsel;
 
 		/*
@@ -869,7 +873,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		 */
 
 		/* First close errored or weak retry */
-		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
 			counter = evlist_cpu_itr.evsel;
 
 			if (!counter->reset_group && !counter->errored)
@@ -878,7 +882,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx);
 		}
 		/* Now reopen weak */
-		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
 			counter = evlist_cpu_itr.evsel;
 
 			if (!counter->reset_group && !counter->errored)
@@ -904,7 +908,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			counter->supported = true;
 		}
 	}
-	affinity__cleanup(&affinity);
+	affinity__cleanup(affinity);
 
 	evlist__for_each_entry(evsel_list, counter) {
 		if (!counter->supported) {

tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json

@@ -18,6 +18,22 @@
 	    "Invert": "0",
 	    "EdgeDetect": "0"
   },
+  {
+	    "Unit": "CBO",
+	    "EventCode": "0xE0",
+	    "UMask": "0x00",
+	    "EventName": "event-hyphen",
+	    "BriefDescription": "UNC_CBO_HYPHEN",
+	    "PublicDescription": "UNC_CBO_HYPHEN"
+  },
+  {
+	    "Unit": "CBO",
+	    "EventCode": "0xC0",
+	    "UMask": "0x00",
+	    "EventName": "event-two-hyph",
+	    "BriefDescription": "UNC_CBO_TWO_HYPH",
+	    "PublicDescription": "UNC_CBO_TWO_HYPH"
+  },
   {
 	    "EventCode": "0x7",
 	    "EventName": "uncore_hisi_l3c.rd_hit_cpipe",

tools/perf/tests/bitmap.c

@@ -17,8 +17,8 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 	bm = bitmap_zalloc(nbits);
 
 	if (map && bm) {
-		for (i = 0; i < map->nr; i++)
-			set_bit(map->map[i].cpu, bm);
+		for (i = 0; i < perf_cpu_map__nr(map); i++)
+			set_bit(perf_cpu_map__cpu(map, i).cpu, bm);
 	}
 
 	if (map)

tools/perf/tests/event_update.c

@@ -75,10 +75,10 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong id", ev->id == 123);
 	TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
-	TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
-	TEST_ASSERT_VAL("wrong cpus", map->map[0].cpu == 1);
-	TEST_ASSERT_VAL("wrong cpus", map->map[1].cpu == 2);
-	TEST_ASSERT_VAL("wrong cpus", map->map[2].cpu == 3);
+	TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__nr(map) == 3);
+	TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 0).cpu == 1);
+	TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 1).cpu == 2);
+	TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 2).cpu == 3);
 	perf_cpu_map__put(map);
 	return 0;
 }

tools/perf/tests/mem2node.c

@@ -25,14 +25,15 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 {
 	struct perf_cpu_map *map = perf_cpu_map__new(str);
 	unsigned long *bm = NULL;
-	int i;
 
 	bm = bitmap_zalloc(nbits);
 
 	if (map && bm) {
-		for (i = 0; i < map->nr; i++) {
-			set_bit(map->map[i].cpu, bm);
-		}
+		struct perf_cpu cpu;
+		int i;
+
+		perf_cpu_map__for_each_cpu(cpu, i, map)
+			set_bit(cpu.cpu, bm);
 	}
 
 	if (map)

tools/perf/tests/mmap-basic.c

@@ -59,11 +59,12 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 	}
 
 	CPU_ZERO(&cpu_set);
-	CPU_SET(cpus->map[0].cpu, &cpu_set);
+	CPU_SET(perf_cpu_map__cpu(cpus, 0).cpu, &cpu_set);
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0].cpu, str_error_r(errno, sbuf, sizeof(sbuf)));
+			 perf_cpu_map__cpu(cpus, 0).cpu,
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}