Merge tag 'perf-tools-fixes-for-v5.17-2022-02-17' of...

Merge tag 'perf-tools-fixes-for-v5.17-2022-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix corrupt inject files when only last branch option is enabled with
   ARM CoreSight ETM

 - Fix use-after-free for realloc(..., 0) in libsubcmd, found by gcc 12

 - Defer freeing string after possible strlen() on it in the BPF loader,
   found by gcc 12

 - Avoid early exit in 'perf trace' due SIGCHLD from non-workload
   processes

 - Fix arm64 perf_event_attr 'perf test's wrt --call-graph
   initialization

 - Fix libperf 32-bit build for 'perf test' wrt uint64_t printf

 - Fix perf_cpu_map__for_each_cpu macro in libperf, providing access to
   the CPU iterator

 - Sync linux/perf_event.h UAPI with the kernel sources

 - Update Jiri Olsa's email address in MAINTAINERS

* tag 'perf-tools-fixes-for-v5.17-2022-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf bpf: Defer freeing string after possible strlen() on it
  perf test: Fix arm64 perf_event_attr tests wrt --call-graph initialization
  libsubcmd: Fix use-after-free for realloc(..., 0)
  libperf: Fix perf_cpu_map__for_each_cpu macro
  perf cs-etm: Fix corrupt inject files when only last branch option is enabled
  perf cs-etm: No-op refactor of synth opt usage
  libperf: Fix 32-bit build for tests uint64_t printf
  tools headers UAPI: Sync linux/perf_event.h with the kernel sources
  perf trace: Avoid early exit due SIGCHLD from non-workload processes
  MAINTAINERS: Update Jiri's email address

MAINTAINERS

@@ -15147,7 +15147,7 @@ M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 R:	Mark Rutland <mark.rutland@arm.com>
 R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
-R:	Jiri Olsa <jolsa@redhat.com>
+R:	Jiri Olsa <jolsa@kernel.org>
 R:	Namhyung Kim <namhyung@kernel.org>
 L:	linux-perf-users@vger.kernel.org
 L:	linux-kernel@vger.kernel.org

tools/include/uapi/linux/perf_event.h

@@ -465,6 +465,8 @@ struct perf_event_attr {
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
 	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+	 * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+	 * truncated accordingly on 32 bit architectures.
 	 */
 	__u64	sig_data;
 };

tools/lib/perf/include/internal/cpumap.h

@@ -3,11 +3,7 @@
 #define __LIBPERF_INTERNAL_CPUMAP_H
 
 #include <linux/refcount.h>
-
-/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
-struct perf_cpu {
-	int cpu;
-};
+#include <perf/cpumap.h>
 
 /**
  * A sized, reference counted, sorted array of integers representing CPU

tools/lib/perf/include/perf/cpumap.h

@@ -7,6 +7,11 @@
 #include <stdio.h>
 #include <stdbool.h>
 
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+	int cpu;
+};
+
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);

tools/lib/perf/libperf.map

@@ -2,6 +2,7 @@ LIBPERF_0.0.1 {
 	global:
 		libperf_init;
 		perf_cpu_map__dummy_new;
+		perf_cpu_map__default_new;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
 		perf_cpu_map__new;

tools/lib/perf/tests/test-cpumap.c

@@ -14,6 +14,8 @@ static int libperf_print(enum libperf_print_level level,
 int test_cpumap(int argc, char **argv)
 {
 	struct perf_cpu_map *cpus;
+	struct perf_cpu cpu;
+	int idx;
 
 	__T_START;
 
@@ -27,6 +29,15 @@ int test_cpumap(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 	perf_cpu_map__put(cpus);
 
+	cpus = perf_cpu_map__default_new();
+	if (!cpus)
+		return -1;
+
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus)
+		__T("wrong cpu number", cpu.cpu != -1);
+
+	perf_cpu_map__put(cpus);
+
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;
 }

tools/lib/perf/tests/test-evlist.c

 // SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET)
+#include <inttypes.h>
 #include <sched.h>
 #include <stdio.h>
 #include <stdarg.h>
@@ -526,12 +527,12 @@ static int test_stat_multiplexing(void)
 
 	min = counts[0].val;
 	for (i = 0; i < EVENT_NUM; i++) {
-		__T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n",
+		__T_VERBOSE("Event %2d -- Raw count = %" PRIu64 ", run = %" PRIu64 ", enable = %" PRIu64 "\n",
 			    i, counts[i].val, counts[i].run, counts[i].ena);
 
 		perf_counts_values__scale(&counts[i], true, &scaled);
 		if (scaled == 1) {
-			__T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n",
+			__T_VERBOSE("\t Scaled count = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n",
 				    counts[i].val,
 				    (double)counts[i].run / (double)counts[i].ena * 100.0,
 				    counts[i].run, counts[i].ena);

tools/lib/subcmd/subcmd-util.h

@@ -50,15 +50,8 @@ static NORETURN inline void die(const char *err, ...)
 static inline void *xrealloc(void *ptr, size_t size)
 {
 	void *ret = realloc(ptr, size);
-	if (!ret && !size)
-		ret = realloc(ptr, 1);
-	if (!ret) {
-		ret = realloc(ptr, size);
-		if (!ret && !size)
-			ret = realloc(ptr, 1);
-		if (!ret)
-			die("Out of memory, realloc failed");
-	}
+	if (!ret)
+		die("Out of memory, realloc failed");
 	return ret;
 }
 

tools/perf/builtin-trace.c

@@ -1536,13 +1536,20 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 	return fprintf(fp, "         ? ");
 }
 
+static pid_t workload_pid = -1;
 static bool done = false;
 static bool interrupted = false;
 
-static void sig_handler(int sig)
+static void sighandler_interrupt(int sig __maybe_unused)
 {
-	done = true;
-	interrupted = sig == SIGINT;
+	done = interrupted = true;
+}
+
+static void sighandler_chld(int sig __maybe_unused, siginfo_t *info,
+			    void *context __maybe_unused)
+{
+	if (info->si_pid == workload_pid)
+		done = true;
 }
 
 static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
@@ -3938,7 +3945,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	bool draining = false;
 
 	trace->live = true;
-	signal(SIGCHLD, sig_handler);
 
 	if (!trace->raw_augmented_syscalls) {
 		if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
@@ -4018,6 +4024,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 			fprintf(trace->output, "Couldn't run the workload!\n");
 			goto out_delete_evlist;
 		}
+		workload_pid = evlist->workload.pid;
 	}
 
 	err = evlist__open(evlist);
@@ -4887,10 +4894,16 @@ int cmd_trace(int argc, const char **argv)
 	const char * const trace_subcommands[] = { "record", NULL };
 	int err = -1;
 	char bf[BUFSIZ];
+	struct sigaction sigchld_act;
 
 	signal(SIGSEGV, sighandler_dump_stack);
 	signal(SIGFPE, sighandler_dump_stack);
-	signal(SIGINT, sig_handler);
+	signal(SIGINT, sighandler_interrupt);
+
+	memset(&sigchld_act, 0, sizeof(sigchld_act));
+	sigchld_act.sa_flags = SA_SIGINFO;
+	sigchld_act.sa_sigaction = sighandler_chld;
+	sigaction(SIGCHLD, &sigchld_act, NULL);
 
 	trace.evlist = evlist__new();
 	trace.sctbl = syscalltbl__new();

tools/perf/tests/attr/README

@@ -45,8 +45,10 @@ Following tests are defined (with perf commands):
   perf record -d kill                           (test-record-data)
   perf record -F 100 kill                       (test-record-freq)
   perf record -g kill                           (test-record-graph-default)
+  perf record -g kill                           (test-record-graph-default-aarch64)
   perf record --call-graph dwarf kill		(test-record-graph-dwarf)
   perf record --call-graph fp kill              (test-record-graph-fp)
+  perf record --call-graph fp kill              (test-record-graph-fp-aarch64)
   perf record --group -e cycles,instructions kill (test-record-group)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
   perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)

tools/perf/tests/attr/test-record-graph-default

@@ -2,6 +2,8 @@
 command = record
 args    = --no-bpf-event -g kill >/dev/null 2>&1
 ret     = 1
+# arm64 enables registers in the default mode (fp)
+arch    = !aarch64
 
 [event:base-record]
 sample_type=295

tools/perf/tests/attr/test-record-graph-default-aarch64

+[config]
+command = record
+args    = --no-bpf-event -g kill >/dev/null 2>&1
+ret     = 1
+arch    = aarch64
+
+[event:base-record]
+sample_type=4391
+sample_regs_user=1073741824

tools/perf/tests/attr/test-record-graph-fp

@@ -2,6 +2,8 @@
 command = record
 args    = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
 ret     = 1
+# arm64 enables registers in fp mode
+arch    = !aarch64
 
 [event:base-record]
 sample_type=295

tools/perf/tests/attr/test-record-graph-fp-aarch64

+[config]
+command = record
+args    = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
+ret     = 1
+arch    = aarch64
+
+[event:base-record]
+sample_type=4391
+sample_regs_user=1073741824

tools/perf/util/bpf-loader.c

@@ -1220,9 +1220,10 @@ bpf__obj_config_map(struct bpf_object *obj,
 	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
 	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
 out:
-	free(map_name);
 	if (!err)
 		*key_scan_pos += strlen(map_opt);
+
+	free(map_name);
 	return err;
 }
 

tools/perf/util/cs-etm.c

@@ -50,8 +50,6 @@ struct cs_etm_auxtrace {
 	u8 timeless_decoding;
 	u8 snapshot_mode;
 	u8 data_queued;
-	u8 sample_branches;
-	u8 sample_instructions;
 
 	int num_cpu;
 	u64 latest_kernel_timestamp;
@@ -410,8 +408,8 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
 {
 	struct cs_etm_packet *tmp;
 
-	if (etm->sample_branches || etm->synth_opts.last_branch ||
-	    etm->sample_instructions) {
+	if (etm->synth_opts.branches || etm->synth_opts.last_branch ||
+	    etm->synth_opts.instructions) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1365,7 +1363,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		err = cs_etm__synth_event(session, &attr, id);
 		if (err)
 			return err;
-		etm->sample_branches = true;
 		etm->branches_sample_type = attr.sample_type;
 		etm->branches_id = id;
 		id += 1;
@@ -1389,7 +1386,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		err = cs_etm__synth_event(session, &attr, id);
 		if (err)
 			return err;
-		etm->sample_instructions = true;
 		etm->instructions_sample_type = attr.sample_type;
 		etm->instructions_id = id;
 		id += 1;
@@ -1420,7 +1416,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 	    tidq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq, tidq);
 
-	if (etm->sample_instructions &&
+	if (etm->synth_opts.instructions &&
 	    tidq->period_instructions >= etm->instructions_sample_period) {
 		/*
 		 * Emit instruction sample periodically
@@ -1503,7 +1499,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches) {
+	if (etm->synth_opts.branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
@@ -1557,6 +1553,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		goto swap_packet;
 
 	if (etmq->etm->synth_opts.last_branch &&
+	    etmq->etm->synth_opts.instructions &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
 		u64 addr;
 
@@ -1582,7 +1579,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	}
 
-	if (etm->sample_branches &&
+	if (etm->synth_opts.branches &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
 		err = cs_etm__synth_branch_sample(etmq, tidq);
 		if (err)
@@ -1614,6 +1611,7 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 * the trace.
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
+	    etmq->etm->synth_opts.instructions &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
 		u64 addr;