perf top: populate PMU capabilities data in perf_env

Calling perf top with branch filters enabled on Intel CPU's
with branch counters logging (A.K.A LBR event logging [1]) support
results in a segfault.

$ perf top  -e '{cpu_core/cpu-cycles/,cpu_core/event=0xc6,umask=0x3,frontend=0x11,name=frontend_retired_dsb_miss/}' -j any,counter
...
Thread 27 "perf" received signal SIGSEGV, Segmentation fault.
[Switching to Thread 0x7fffafff76c0 (LWP 949003)]
perf_env__find_br_cntr_info (env=0xf66dc0 <perf_env>, nr=0x0, width=0x7fffafff62c0) at util/env.c:653
653			*width = env->cpu_pmu_caps ? env->br_cntr_width :
(gdb) bt
 #0  perf_env__find_br_cntr_info (env=0xf66dc0 <perf_env>, nr=0x0, width=0x7fffafff62c0) at util/env.c:653
 #1  0x00000000005b1599 in symbol__account_br_cntr (branch=0x7fffcc3db580, evsel=0xfea2d0, offset=12, br_cntr=8) at util/annotate.c:345
 #2  0x00000000005b17fb in symbol__account_cycles (addr=5658172, start=5658160, sym=0x7fffcc0ee420, cycles=539, evsel=0xfea2d0, br_cntr=8) at util/annotate.c:389
 #3  0x00000000005b1976 in addr_map_symbol__account_cycles (ams=0x7fffcd7b01d0, start=0x7fffcd7b02b0, cycles=539, evsel=0xfea2d0, br_cntr=8) at util/annotate.c:422
 #4  0x000000000068d57f in hist__account_cycles (bs=0x110d288, al=0x7fffafff6540, sample=0x7fffafff6760, nonany_branch_mode=false, total_cycles=0x0, evsel=0xfea2d0) at util/hist.c:2850
 #5  0x0000000000446216 in hist_iter__top_callback (iter=0x7fffafff6590, al=0x7fffafff6540, single=true, arg=0x7fffffff9e00) at builtin-top.c:737
 #6  0x0000000000689787 in hist_entry_iter__add (iter=0x7fffafff6590, al=0x7fffafff6540, max_stack_depth=127, arg=0x7fffffff9e00) at util/hist.c:1359
 #7  0x0000000000446710 in perf_event__process_sample (tool=0x7fffffff9e00, event=0x110d250, evsel=0xfea2d0, sample=0x7fffafff6760, machine=0x108c968) at builtin-top.c:845
 #8  0x0000000000447735 in deliver_event (qe=0x7fffffffa120, qevent=0x10fc200) at builtin-top.c:1211
 #9  0x000000000064ccae in do_flush (oe=0x7fffffffa120, show_progress=false) at util/ordered-events.c:245
 #10 0x000000000064d005 in __ordered_events__flush (oe=0x7fffffffa120, how=OE_FLUSH__TOP, timestamp=0) at util/ordered-events.c:324
 #11 0x000000000064d0ef in ordered_events__flush (oe=0x7fffffffa120, how=OE_FLUSH__TOP) at util/ordered-events.c:342
 #12 0x00000000004472a9 in process_thread (arg=0x7fffffff9e00) at builtin-top.c:1120
 #13 0x00007ffff6e7dba8 in start_thread (arg=<optimized out>) at pthread_create.c:448
 #14 0x00007ffff6f01b8c in __GI___clone3 () at ../sysdeps/unix/sysv/linux/x86_64/clone3.S:78

The cause is that perf_env__find_br_cntr_info tries to access a
null pointer pmu_caps in the perf_env struct. A similar issue exists
for homogeneous core systems which use the cpu_pmu_caps structure.

Fix this by populating cpu_pmu_caps and pmu_caps structures with
values from sysfs when calling perf top with branch stack sampling
enabled.

[1], LBR event logging introduced here:
https://lore.kernel.org/all/[email protected]/

Reviewed-by: Ian Rogers <[email protected]>
Signed-off-by: Thomas Falcon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

Author: tlfalcon

tools/perf/builtin-top.c

@@ -1734,6 +1734,14 @@ int cmd_top(int argc, const char **argv)
 	if (opts->branch_stack && callchain_param.enabled)
 		symbol_conf.show_branchflag_count = true;
 
+	if (opts->branch_stack) {
+		status = perf_env__read_core_pmu_caps(&perf_env);
+		if (status) {
+			pr_err("PMU capability data is not available\n");
+			goto out_delete_evlist;
+		}
+	}
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	perf_hpp_list.need_collapse = 1;

tools/perf/util/env.c

@@ -433,6 +433,116 @@ static int perf_env__read_nr_cpus_avail(struct perf_env *env)
 	return env->nr_cpus_avail ? 0 : -ENOENT;
 }
 
+static int __perf_env__read_core_pmu_caps(const struct perf_pmu *pmu,
+					  int *nr_caps, char ***caps,
+					  unsigned int *max_branches,
+					  unsigned int *br_cntr_nr,
+					  unsigned int *br_cntr_width)
+{
+	struct perf_pmu_caps *pcaps = NULL;
+	char *ptr, **tmp;
+	int ret = 0;
+
+	*nr_caps = 0;
+	*caps = NULL;
+
+	if (!pmu->nr_caps)
+		return 0;
+
+	*caps = calloc(pmu->nr_caps, sizeof(char *));
+	if (!*caps)
+		return -ENOMEM;
+
+	tmp = *caps;
+	list_for_each_entry(pcaps, &pmu->caps, list) {
+		if (asprintf(&ptr, "%s=%s", pcaps->name, pcaps->value) < 0) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		*tmp++ = ptr;
+
+		if (!strcmp(pcaps->name, "branches"))
+			*max_branches = atoi(pcaps->value);
+		else if (!strcmp(pcaps->name, "branch_counter_nr"))
+			*br_cntr_nr = atoi(pcaps->value);
+		else if (!strcmp(pcaps->name, "branch_counter_width"))
+			*br_cntr_width = atoi(pcaps->value);
+	}
+	*nr_caps = pmu->nr_caps;
+	return 0;
+error:
+	while (tmp-- != *caps)
+		zfree(tmp);
+	zfree(caps);
+	*nr_caps = 0;
+	return ret;
+}
+
+int perf_env__read_core_pmu_caps(struct perf_env *env)
+{
+	struct pmu_caps *pmu_caps;
+	struct perf_pmu *pmu = NULL;
+	int nr_pmu, i = 0, j;
+	int ret;
+
+	nr_pmu = perf_pmus__num_core_pmus();
+
+	if (!nr_pmu)
+		return -ENODEV;
+
+	if (nr_pmu == 1) {
+		pmu = perf_pmus__find_core_pmu();
+		if (!pmu)
+			return -ENODEV;
+		ret = perf_pmu__caps_parse(pmu);
+		if (ret < 0)
+			return ret;
+		return __perf_env__read_core_pmu_caps(pmu, &env->nr_cpu_pmu_caps,
+						      &env->cpu_pmu_caps,
+						      &env->max_branches,
+						      &env->br_cntr_nr,
+						      &env->br_cntr_width);
+	}
+
+	pmu_caps = calloc(nr_pmu, sizeof(*pmu_caps));
+	if (!pmu_caps)
+		return -ENOMEM;
+
+	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+		if (perf_pmu__caps_parse(pmu) <= 0)
+			continue;
+		ret = __perf_env__read_core_pmu_caps(pmu, &pmu_caps[i].nr_caps,
+						     &pmu_caps[i].caps,
+						     &pmu_caps[i].max_branches,
+						     &pmu_caps[i].br_cntr_nr,
+						     &pmu_caps[i].br_cntr_width);
+		if (ret)
+			goto error;
+
+		pmu_caps[i].pmu_name = strdup(pmu->name);
+		if (!pmu_caps[i].pmu_name) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		i++;
+	}
+
+	env->nr_pmus_with_caps = nr_pmu;
+	env->pmu_caps = pmu_caps;
+
+	return 0;
+error:
+	for (i = 0; i < nr_pmu; i++) {
+		for (j = 0; j < pmu_caps[i].nr_caps; j++)
+			zfree(&pmu_caps[i].caps[j]);
+		zfree(&pmu_caps[i].caps);
+		zfree(&pmu_caps[i].pmu_name);
+	}
+	zfree(&pmu_caps);
+	return ret;
+}
+
 const char *perf_env__raw_arch(struct perf_env *env)
 {
 	return env && !perf_env__read_arch(env) ? env->arch : "unknown";

tools/perf/util/env.h

@@ -152,6 +152,7 @@ struct btf_node;
 
 extern struct perf_env perf_env;
 
+int perf_env__read_core_pmu_caps(struct perf_env *env);
 void perf_env__exit(struct perf_env *env);
 
 int perf_env__kernel_is_64_bit(struct perf_env *env);