Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

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

   - Add 'trace' subcommand for 'perf ftrace', setting the stage for
     more 'perf ftrace' subcommands. Not using a subcommand yields the
     previous behaviour of 'perf ftrace'.

   - Add 'latency' subcommand to 'perf ftrace', that can use the
     function graph tracer or a BPF optimized one, via the -b/--use-bpf
     option.

     E.g.:

	$ sudo perf ftrace latency -a -T mutex_lock sleep 1
	#   DURATION     |      COUNT | GRAPH                          |
	     0 - 1    us |       4596 | ########################       |
	     1 - 2    us |       1680 | #########                      |
	     2 - 4    us |       1106 | #####                          |
	     4 - 8    us |        546 | ##                             |
	     8 - 16   us |        562 | ###                            |
	    16 - 32   us |          1 |                                |
	    32 - 64   us |          0 |                                |
	    64 - 128  us |          0 |                                |
	   128 - 256  us |          0 |                                |
	   256 - 512  us |          0 |                                |
	   512 - 1024 us |          0 |                                |
	     1 - 2    ms |          0 |                                |
	     2 - 4    ms |          0 |                                |
	     4 - 8    ms |          0 |                                |
	     8 - 16   ms |          0 |                                |
	    16 - 32   ms |          0 |                                |
	    32 - 64   ms |          0 |                                |
	    64 - 128  ms |          0 |                                |
	   128 - 256  ms |          0 |                                |
	   256 - 512  ms |          0 |                                |
	   512 - 1024 ms |          0 |                                |
	     1 - ...   s |          0 |                                |

     The original implementation of this command was in the bcc tool.

   - Support --cputype option for hybrid events in 'perf stat'.

  Improvements:

   - Call chain improvements for ARM64.

   - No need to do any affinity setup when profiling pids.

   - Reduce multiplexing with duration_time in 'perf stat' metrics.

   - Improve error message for uncore events, stating that some event
     groups are can only be used in system wide (-a) mode.

   - perf stat metric group leader fixes/improvements, including arch
     specific changes to better support Intel topdown events.

   - Probe non-deprecated sysfs path first, i.e. try the path
     /sys/devices/system/cpu/cpuN/topology/thread_siblings first, then
     the old /sys/devices/system/cpu/cpuN/topology/core_cpus.

   - Disable debuginfod by default in 'perf record', to avoid stalls on
     distros such as Fedora 35.

   - Use unbuffered output in 'perf bench' when pipe/tee'ing to a file.

   - Enable ignore_missing_thread in 'perf trace'

  Fixes:

   - Avoid TUI crash when navigating in the annotation of recursive
     functions.

   - Fix hex dump character output in 'perf script'.

   - Fix JSON indentation to 4 spaces standard in the ARM vendor event
     files.

   - Fix use after free in metric__new().

   - Fix IS_ERR_OR_NULL() usage in the perf BPF loader.

   - Fix up cross-arch register support, i.e. when printing register
     names take into account the architecture where the perf.data file
     was collected.

   - Fix SMT fallback with large core counts.

   - Don't lower case MetricExpr when parsing JSON files so as not to
     lose info such as the ":G" event modifier in metrics.

  perf test:

   - Add basic stress test for sigtrap handling to 'perf test'.

   - Fix 'perf test' failures on s/390

   - Enable system wide for metricgroups test in 'perf test´.

   - Use 3 digits for test numbering now we can have more tests.

  Arch specific:

   - Add events for Arm Neoverse N2 in the ARM JSON vendor event files

   - Support PERF_MEM_LVLNUM encodings in powerpc, that came from a
     single patch series, where I incorrectly merged the kernel bits,
     that were then reverted after coordination with Michael Ellerman
     and Stephen Rothwell.

   - Add ARM SPE total latency as PERF_SAMPLE_WEIGHT.

   - Update AMD documentation, with info on raw event encoding.

   - Add support for global and local variants of the "p_stage_cyc" sort
     key, applicable to perf.data files collected on powerpc.

   - Remove duplicate and incorrect aux size checks in the ARM CoreSight
     ETM code.

  Refactorings:

   - Add a perf_cpu abstraction to disambiguate CPUs and CPU map
     indexes, fixing problems along the way.

   - Document CPU map methods.

  UAPI sync:

   - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench
     mem memcpy'

   - Sync UAPI files with the kernel sources: drm, msr-index,
     cpufeatures.

  Build system

   - Enable warnings through HOSTCFLAGS.

   - Drop requirement for libstdc++.so for libopencsd check

  libperf:

   - Make libperf adopt perf_counts_values__scale() from tools/perf/util/.

   - Add a stat multiplexing test to libperf"

* tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits)
  perf record: Disable debuginfod by default
  perf evlist: No need to do any affinity setup when profiling pids
  perf cpumap: Add is_dummy() method
  perf metric: Fix metric_leader
  perf cputopo: Fix CPU topology reading on s/390
  perf metricgroup: Fix use after free in metric__new()
  libperf tests: Update a use of the new cpumap API
  perf arm: Fix off-by-one directory path
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Update tools's copy of drm.h header
  tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy'
  perf pmu-events: Don't lower case MetricExpr
  perf expr: Add debug logging for literals
  perf tools: Probe non-deprecated sysfs path 1st
  perf tools: Fix SMT fallback with large core counts
  perf cpumap: Give CPUs their own type
  perf stat: Correct first_shadow_cpu to return index
  perf script: Fix flipped index and cpu
  perf c2c: Use more intention revealing iterator
  ...

1 files changed, 76 insertions, 90 deletions

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f29d37004f55..2f6b18af49e5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1372,9 +1372,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 }
 
 /* Caller has to clear disabled after going through all CPUs. */
-int evsel__enable_cpu(struct evsel *evsel, int cpu)
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__enable_cpu(&evsel->core, cpu);
+	return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx);
 }
 
 int evsel__enable(struct evsel *evsel)
@@ -1387,9 +1387,9 @@ int evsel__enable(struct evsel *evsel)
 }
 
 /* Caller has to set disabled after going through all CPUs. */
-int evsel__disable_cpu(struct evsel *evsel, int cpu)
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__disable_cpu(&evsel->core, cpu);
+	return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx);
 }
 
 int evsel__disable(struct evsel *evsel)
@@ -1455,7 +1455,7 @@ void evsel__delete(struct evsel *evsel)
 	free(evsel);
 }
 
-void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
 			   struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -1463,12 +1463,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 	if (!evsel->prev_raw_counts)
 		return;
 
-	if (cpu == -1) {
+	if (cpu_map_idx == -1) {
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
-		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -1476,46 +1476,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 	count->run = count->run - tmp.run;
 }
 
-void perf_counts_values__scale(struct perf_counts_values *count,
-			       bool scale, s8 *pscaled)
+static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 {
-	s8 scaled = 0;
+	struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread);
 
-	if (scale) {
-		if (count->run == 0) {
-			scaled = -1;
-			count->val = 0;
-		} else if (count->run < count->ena) {
-			scaled = 1;
-			count->val = (u64)((double) count->val * count->ena / count->run);
-		}
-	}
-
-	if (pscaled)
-		*pscaled = scaled;
-}
-
-static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
-{
-	struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
-
-	return perf_evsel__read(&evsel->core, cpu, thread, count);
+	return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count);
 }
 
-static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
+			     u64 val, u64 ena, u64 run)
 {
 	struct perf_counts_values *count;
 
-	count = perf_counts(counter->counts, cpu, thread);
+	count = perf_counts(counter->counts, cpu_map_idx, thread);
 
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
 
-	perf_counts__set_loaded(counter->counts, cpu, thread, true);
+	perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 }
 
-static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data)
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
@@ -1534,7 +1516,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
 
 	v = (struct sample_read_value *) data;
 
-	evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
+	evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
 
 	for (i = 1; i < nr; i++) {
 		struct evsel *counter;
@@ -1543,13 +1525,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
 		if (!counter)
 			return -EINVAL;
 
-		evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
+		evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
 	}
 
 	return 0;
 }
 
-static int evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread)
 {
 	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->core.attr.read_format;
@@ -1570,67 +1552,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
 		ps->group_data = data;
 	}
 
-	if (FD(leader, cpu, thread) < 0)
+	if (FD(leader, cpu_map_idx, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(leader, cpu, thread), data, size) <= 0)
+	if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0)
 		return -errno;
 
-	return evsel__process_group_data(leader, cpu, thread, data);
+	return evsel__process_group_data(leader, cpu_map_idx, thread, data);
 }
 
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	u64 read_format = evsel->core.attr.read_format;
 
 	if (read_format & PERF_FORMAT_GROUP)
-		return evsel__read_group(evsel, cpu, thread);
+		return evsel__read_group(evsel, cpu_map_idx, thread);
 
-	return evsel__read_one(evsel, cpu, thread);
+	return evsel__read_one(evsel, cpu_map_idx, thread);
 }
 
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale)
 {
 	struct perf_counts_values count;
 	size_t nv = scale ? 3 : 1;
 
-	if (FD(evsel, cpu, thread) < 0)
+	if (FD(evsel, cpu_map_idx, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
+	if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0)
 		return -ENOMEM;
 
-	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
+	if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0)
 		return -errno;
 
-	evsel__compute_deltas(evsel, cpu, thread, &count);
+	evsel__compute_deltas(evsel, cpu_map_idx, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	*perf_counts(evsel->counts, cpu, thread) = count;
+	*perf_counts(evsel->counts, cpu_map_idx, thread) = count;
 	return 0;
 }
 
 static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other,
-				  int cpu)
+				  int cpu_map_idx)
 {
-	int cpuid;
+	struct perf_cpu cpu;
 
-	cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu);
-	return perf_cpu_map__idx(other->core.cpus, cpuid);
+	cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
+	return perf_cpu_map__idx(other->core.cpus, cpu);
 }
 
-static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu)
+static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx)
 {
 	struct evsel *leader = evsel__leader(evsel);
 
 	if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) ||
 	    (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) {
-		return evsel__match_other_cpu(evsel, leader, cpu);
+		return evsel__match_other_cpu(evsel, leader, cpu_map_idx);
 	}
 
-	return cpu;
+	return cpu_map_idx;
 }
 
-static int get_group_fd(struct evsel *evsel, int cpu, int thread)
+static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	struct evsel *leader = evsel__leader(evsel);
 	int fd;
@@ -1644,11 +1626,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
 	 */
 	BUG_ON(!leader->core.fd);
 
-	cpu = evsel__hybrid_group_cpu(evsel, cpu);
-	if (cpu == -1)
+	cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx);
+	if (cpu_map_idx == -1)
 		return -1;
 
-	fd = FD(leader, cpu, thread);
+	fd = FD(leader, cpu_map_idx, thread);
 	BUG_ON(fd == -1);
 
 	return fd;
@@ -1662,16 +1644,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int
 }
 
 static int update_fds(struct evsel *evsel,
-		      int nr_cpus, int cpu_idx,
+		      int nr_cpus, int cpu_map_idx,
 		      int nr_threads, int thread_idx)
 {
 	struct evsel *pos;
 
-	if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+	if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads)
 		return -EINVAL;
 
 	evlist__for_each_entry(evsel->evlist, pos) {
-		nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+		nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx;
 
 		evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
 
@@ -1685,10 +1667,10 @@ static int update_fds(struct evsel *evsel,
 	return 0;
 }
 
-bool evsel__ignore_missing_thread(struct evsel *evsel,
-				  int nr_cpus, int cpu,
-				  struct perf_thread_map *threads,
-				  int thread, int err)
+static bool evsel__ignore_missing_thread(struct evsel *evsel,
+					 int nr_cpus, int cpu_map_idx,
+					 struct perf_thread_map *threads,
+					 int thread, int err)
 {
 	pid_t ignore_pid = perf_thread_map__pid(threads, thread);
 
@@ -1711,7 +1693,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel,
 	 * We should remove fd for missing_thread first
 	 * because thread_map__remove() will decrease threads->nr.
 	 */
-	if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+	if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread))
 		return false;
 
 	if (thread_map__remove(threads, thread))
@@ -1993,9 +1975,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit)
 
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
-		int start_cpu, int end_cpu)
+		int start_cpu_map_idx, int end_cpu_map_idx)
 {
-	int cpu, thread, nthreads;
+	int idx, thread, nthreads;
 	int pid = -1, err, old_errno;
 	enum rlimit_action set_rlimit = NO_CHANGE;
 
@@ -2022,7 +2004,7 @@ fallback_missing_features:
 
 	display_attr(&evsel->core.attr);
 
-	for (cpu = start_cpu; cpu < end_cpu; cpu++) {
+	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd, group_fd;
@@ -2033,17 +2015,17 @@ retry_open:
 			if (!evsel->cgrp && !evsel->core.system_wide)
 				pid = perf_thread_map__pid(threads, thread);
 
-			group_fd = get_group_fd(evsel, cpu, thread);
+			group_fd = get_group_fd(evsel, idx, thread);
 
 			test_attr__ready();
 
 			pr_debug2_peo("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				pid, cpus->map[cpu], group_fd, evsel->open_flags);
+				pid, cpus->map[idx].cpu, group_fd, evsel->open_flags);
 
-			fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu],
+			fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[idx].cpu,
 						group_fd, evsel->open_flags);
 
-			FD(evsel, cpu, thread) = fd;
+			FD(evsel, idx, thread) = fd;
 
 			if (fd < 0) {
 				err = -errno;
@@ -2053,10 +2035,10 @@ retry_open:
 				goto try_fallback;
 			}
 
-			bpf_counter__install_pe(evsel, cpu, fd);
+			bpf_counter__install_pe(evsel, idx, fd);
 
 			if (unlikely(test_attr__enabled)) {
-				test_attr__open(&evsel->core.attr, pid, cpus->map[cpu],
+				test_attr__open(&evsel->core.attr, pid, cpus->map[idx],
 						fd, group_fd, evsel->open_flags);
 			}
 
@@ -2097,7 +2079,7 @@ try_fallback:
 	if (evsel__precise_ip_fallback(evsel))
 		goto retry_open;
 
-	if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
+	if (evsel__ignore_missing_thread(evsel, cpus->nr, idx, threads, thread, err)) {
 		/* We just removed 1 thread, so lower the upper nthreads limit. */
 		nthreads--;
 
@@ -2112,7 +2094,7 @@ try_fallback:
 	if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
 		goto retry_open;
 
-	if (err != -EINVAL || cpu > 0 || thread > 0)
+	if (err != -EINVAL || idx > 0 || thread > 0)
 		goto out_close;
 
 	if (evsel__detect_missing_features(evsel))
@@ -2124,12 +2106,12 @@ out_close:
 	old_errno = errno;
 	do {
 		while (--thread >= 0) {
-			if (FD(evsel, cpu, thread) >= 0)
-				close(FD(evsel, cpu, thread));
-			FD(evsel, cpu, thread) = -1;
+			if (FD(evsel, idx, thread) >= 0)
+				close(FD(evsel, idx, thread));
+			FD(evsel, idx, thread) = -1;
 		}
 		thread = nthreads;
-	} while (--cpu >= 0);
+	} while (--idx >= 0);
 	errno = old_errno;
 	return err;
 }
@@ -2146,13 +2128,13 @@ void evsel__close(struct evsel *evsel)
 	perf_evsel__free_id(&evsel->core);
 }
 
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx)
 {
-	if (cpu == -1)
+	if (cpu_map_idx == -1)
 		return evsel__open_cpu(evsel, cpus, NULL, 0,
 					cpus ? cpus->nr : 1);
 
-	return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
+	return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1);
 }
 
 int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
@@ -2952,6 +2934,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
 		if (perf_missing_features.aux_output)
 			return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
+		if (!target__has_cpu(target))
+			return scnprintf(msg, size,
+	"Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
+					evsel__name(evsel));
 		break;
 	case ENODATA:
 		return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. "
@@ -2975,15 +2961,15 @@ struct perf_env *evsel__env(struct evsel *evsel)
 
 static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
 {
-	int cpu, thread;
+	int cpu_map_idx, thread;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
+	for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
 		     thread++) {
-			int fd = FD(evsel, cpu, thread);
+			int fd = FD(evsel, cpu_map_idx, thread);
 
 			if (perf_evlist__id_add_fd(&evlist->core, &evsel->core,
-						   cpu, thread, fd) < 0)
+						   cpu_map_idx, thread, fd) < 0)
 				return -1;
 		}
 	}