diff options
Diffstat (limited to 'tools/perf/tests')
| -rw-r--r-- | tools/perf/tests/bp_account.c | 16 | ||||
| -rw-r--r-- | tools/perf/tests/bpf-script-example.c | 35 | ||||
| -rw-r--r-- | tools/perf/tests/expr.c | 15 | ||||
| -rw-r--r-- | tools/perf/tests/mmap-basic.c | 127 | ||||
| -rw-r--r-- | tools/perf/tests/perf-time-to-tsc.c | 27 | ||||
| -rw-r--r-- | tools/perf/tests/pmu-events.c | 10 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/perf_csv_output_lint.py | 48 | ||||
| -rwxr-xr-x | tools/perf/tests/shell/stat+csv_output.sh | 70 | ||||
| -rwxr-xr-x | tools/perf/tests/shell/stat_all_metrics.sh | 47 | ||||
| -rwxr-xr-x | tools/perf/tests/shell/test_arm_callgraph_fp.sh | 2 | ||||
| -rwxr-xr-x | tools/perf/tests/shell/test_arm_spe.sh | 30 | ||||
| -rwxr-xr-x | tools/perf/tests/shell/test_brstack.sh | 114 | ||||
| -rw-r--r-- | tools/perf/tests/topology.c | 2 |
13 files changed, 418 insertions, 125 deletions
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index d1ebb5561e5b..6f921db33cf9 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -151,11 +151,21 @@ static int detect_ioctl(void) static int detect_share(int wp_cnt, int bp_cnt) { struct perf_event_attr attr; - int i, fd[wp_cnt + bp_cnt], ret; + int i, *fd = NULL, ret = -1; + + if (wp_cnt + bp_cnt == 0) + return 0; + + fd = malloc(sizeof(int) * (wp_cnt + bp_cnt)); + if (!fd) + return -1; for (i = 0; i < wp_cnt; i++) { fd[i] = wp_event((void *)&the_var, &attr); - TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1); + if (fd[i] == -1) { + pr_err("failed to create wp\n"); + goto out; + } } for (; i < (bp_cnt + wp_cnt); i++) { @@ -166,9 +176,11 @@ static int detect_share(int wp_cnt, int bp_cnt) ret = i != (bp_cnt + wp_cnt); +out: while (i--) close(fd[i]); + free(fd); return ret; } diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c index ab4b98b3165d..7981c69ed1b4 100644 --- a/tools/perf/tests/bpf-script-example.c +++ b/tools/perf/tests/bpf-script-example.c @@ -17,20 +17,31 @@ static void *(*bpf_map_lookup_elem)(void *map, void *key) = static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = (void *) BPF_FUNC_map_update_elem; -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; -}; +/* + * Following macros are taken from tools/lib/bpf/bpf_helpers.h, + * and are used to create BTF defined maps. It is easier to take + * 2 simple macros, than being able to include above header in + * runtime. + * + * __uint - defines integer attribute of BTF map definition, + * Such attributes are represented using a pointer to an array, + * in which dimensionality of array encodes specified integer + * value. + * + * __type - defines pointer variable with typeof(val) type for + * attributes like key or value, which will be defined by the + * size of the type. + */ +#define __uint(name, val) int (*name)[val] +#define __type(name, val) typeof(val) *name #define SEC(NAME) __attribute__((section(NAME), used)) -struct bpf_map_def SEC("maps") flip_table = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} flip_table SEC(".maps"); SEC("func=do_epoll_wait") int bpf_func__SyS_epoll_pwait(void *ctx) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index d54c5371c6a6..2efe9e3a63b8 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/debug.h" #include "util/expr.h" +#include "util/header.h" #include "util/smt.h" #include "tests.h" +#include <math.h> #include <stdlib.h> #include <string.h> #include <linux/zalloc.h> @@ -69,6 +71,11 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u double val, num_cpus, num_cores, num_dies, num_packages; int ret; struct expr_parse_ctx *ctx; + bool is_intel = false; + char buf[128]; + + if (!get_cpuid(buf, sizeof(buf))) + is_intel = strstr(buf, "Intel") != NULL; TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); @@ -97,6 +104,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u ret |= test(ctx, "2.2 > 2.2", 0); ret |= test(ctx, "2.2 < 1.1", 0); ret |= test(ctx, "1.1 > 2.2", 0); + ret |= test(ctx, "1.1e10 < 1.1e100", 1); + ret |= test(ctx, "1.1e2 > 1.1e-2", 1); if (ret) { expr__ctx_free(ctx); @@ -173,6 +182,12 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u if (num_dies) // Some platforms do not have CPU die support, for example s390 TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0); + if (is_intel) + TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0); + else + TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO); + /* * Source count returns the number of events aggregating in a leader * event including the leader. Check parsing yields an id. diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 30bbe144648a..dfb6173b2a82 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -170,14 +170,139 @@ out_free_threads: return err; } +static int test_stat_user_read(int event) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_mmap_page *pc; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = event, +#ifdef __aarch64__ + .config1 = 0x2, /* Request user access */ +#endif + }; + int err, i, ret = TEST_FAIL; + bool opened = false, mapped = false; + + threads = perf_thread_map__new_dummy(); + TEST_ASSERT_VAL("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + TEST_ASSERT_VAL("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + if (err) { + pr_err("failed to open evsel: %s\n", strerror(-err)); + ret = TEST_SKIP; + goto out; + } + opened = true; + + err = perf_evsel__mmap(evsel, 0); + if (err) { + pr_err("failed to mmap evsel: %s\n", strerror(-err)); + goto out; + } + mapped = true; + + pc = perf_evsel__mmap_base(evsel, 0, 0); + if (!pc) { + pr_err("failed to get mmapped address\n"); + goto out; + } + + if (!pc->cap_user_rdpmc || !pc->index) { + pr_err("userspace counter access not %s\n", + !pc->cap_user_rdpmc ? "supported" : "enabled"); + ret = TEST_SKIP; + goto out; + } + if (pc->pmc_width < 32) { + pr_err("userspace counter width not set (%d)\n", pc->pmc_width); + goto out; + } + + perf_evsel__read(evsel, 0, 0, &counts); + if (counts.val == 0) { + pr_err("failed to read value for evsel\n"); + goto out; + } + + for (i = 0; i < 5; i++) { + volatile int count = 0x10000 << i; + __u64 start, end, last = 0; + + pr_debug("\tloop = %u, ", count); + + perf_evsel__read(evsel, 0, 0, &counts); + start = counts.val; + + while (count--) ; + + perf_evsel__read(evsel, 0, 0, &counts); + end = counts.val; + + if ((end - start) < last) { + pr_err("invalid counter data: end=%llu start=%llu last= %llu\n", + end, start, last); + goto out; + } + last = end - start; + pr_debug("count = %llu\n", end - start); + } + ret = TEST_OK; + +out: + if (mapped) + perf_evsel__munmap(evsel); + if (opened) + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return ret; +} + +static int test__mmap_user_read_instr(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + return test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS); +} + +static int test__mmap_user_read_cycles(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + return test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES); +} + static struct test_case tests__basic_mmap[] = { TEST_CASE_REASON("Read samples using the mmap interface", basic_mmap, "permissions"), + TEST_CASE_REASON("User space counter reading of instructions", + mmap_user_read_instr, +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) + "permissions" +#else + "unsupported" +#endif + ), + TEST_CASE_REASON("User space counter reading of cycles", + mmap_user_read_cycles, +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) + "permissions" +#else + "unsupported" +#endif + ), { .name = NULL, } }; struct test_suite suite__basic_mmap = { - .desc = "Read samples using the mmap interface", + .desc = "mmap interface tests", .test_cases = tests__basic_mmap, }; diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 4ad0dfbc8b21..7c7d20fc503a 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -20,8 +20,6 @@ #include "tsc.h" #include "mmap.h" #include "tests.h" -#include "pmu.h" -#include "pmu-hybrid.h" /* * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just @@ -106,28 +104,21 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evlist__config(evlist, &opts, NULL); - evsel = evlist__first(evlist); - - evsel->core.attr.comm = 1; - evsel->core.attr.disabled = 1; - evsel->core.attr.enable_on_exec = 0; - - /* - * For hybrid "cycles:u", it creates two events. - * Init the second evsel here. - */ - if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) { - evsel = evsel__next(evsel); + /* For hybrid "cycles:u", it creates two events */ + evlist__for_each_entry(evlist, evsel) { evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; evsel->core.attr.enable_on_exec = 0; } - if (evlist__open(evlist) == -ENOENT) { - err = TEST_SKIP; + ret = evlist__open(evlist); + if (ret < 0) { + if (ret == -ENOENT) + err = TEST_SKIP; + else + pr_debug("evlist__open() failed\n"); goto out_err; } - CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); @@ -167,10 +158,12 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm1_time = sample.time; } if (strcmp(event->comm.comm, comm2) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm2_time = sample.time; } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index f13368569d8b..263cbb67c861 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -812,6 +812,15 @@ static int check_parse_id(const char *id, struct parse_events_error *error, for (cur = strchr(dup, '@') ; cur; cur = strchr(++cur, '@')) *cur = '/'; + if (fake_pmu) { + /* + * Every call to __parse_events will try to initialize the PMU + * state from sysfs and then clean it up at the end. Reset the + * PMU events to the test state so that we don't pick up + * erroneous prefixes and suffixes. + */ + perf_pmu__test_parse_init(); + } ret = __parse_events(evlist, dup, error, fake_pmu); free(dup); @@ -1115,6 +1124,7 @@ static int test__parsing_fake(struct test_suite *test __maybe_unused, break; if (!pe->metric_expr) continue; + pr_debug("Found metric '%s' for '%s'\n", pe->metric_name, map->cpuid); err = metric_parse_fake(pe->metric_expr); if (err) return err; diff --git a/tools/perf/tests/shell/lib/perf_csv_output_lint.py b/tools/perf/tests/shell/lib/perf_csv_output_lint.py deleted file mode 100644 index 714f283cfb1b..000000000000 --- a/tools/perf/tests/shell/lib/perf_csv_output_lint.py +++ /dev/null @@ -1,48 +0,0 @@ -#!/usr/bin/python -# SPDX-License-Identifier: GPL-2.0 - -import argparse -import sys - -# Basic sanity check of perf CSV output as specified in the man page. -# Currently just checks the number of fields per line in output. - -ap = argparse.ArgumentParser() -ap.add_argument('--no-args', action='store_true') -ap.add_argument('--interval', action='store_true') -ap.add_argument('--system-wide-no-aggr', action='store_true') -ap.add_argument('--system-wide', action='store_true') -ap.add_argument('--event', action='store_true') -ap.add_argument('--per-core', action='store_true') -ap.add_argument('--per-thread', action='store_true') -ap.add_argument('--per-die', action='store_true') -ap.add_argument('--per-node', action='store_true') -ap.add_argument('--per-socket', action='store_true') -ap.add_argument('--separator', default=',', nargs='?') -args = ap.parse_args() - -Lines = sys.stdin.readlines() - -def check_csv_output(exp): - for line in Lines: - if 'failed' not in line: - count = line.count(args.separator) - if count != exp: - sys.stdout.write(''.join(Lines)) - raise RuntimeError(f'wrong number of fields. expected {exp} in {line}') - -try: - if args.no_args or args.system_wide or args.event: - expected_items = 6 - elif args.interval or args.per_thread or args.system_wide_no_aggr: - expected_items = 7 - elif args.per_core or args.per_socket or args.per_node or args.per_die: - expected_items = 8 - else: - ap.print_help() - raise RuntimeError('No checking option specified') - check_csv_output(expected_items) - -except: - sys.stdout.write('Test failed for input: ' + ''.join(Lines)) - raise diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index 983220ef3cb4..eb5196f58190 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -6,20 +6,42 @@ set -e -pythonchecker=$(dirname $0)/lib/perf_csv_output_lint.py -if [ "x$PYTHON" == "x" ] -then - if which python3 > /dev/null - then - PYTHON=python3 - elif which python > /dev/null - then - PYTHON=python - else - echo Skipping test, python not detected please set environment variable PYTHON. - exit 2 - fi -fi +function commachecker() +{ + local -i cnt=0 + local exp=0 + + case "$1" + in "--no-args") exp=6 + ;; "--system-wide") exp=6 + ;; "--event") exp=6 + ;; "--interval") exp=7 + ;; "--per-thread") exp=7 + ;; "--system-wide-no-aggr") exp=7 + [ $(uname -m) = "s390x" ] && exp='^[6-7]$' + ;; "--per-core") exp=8 + ;; "--per-socket") exp=8 + ;; "--per-node") exp=8 + ;; "--per-die") exp=8 + esac + + while read line + do + # Check for lines beginning with Failed + x=${line:0:6} + [ "$x" = "Failed" ] && continue + + # Count the number of commas + x=$(echo $line | tr -d -c ',') + cnt="${#x}" + # echo $line $cnt + [[ ! "$cnt" =~ $exp ]] && { + echo "wrong number of fields. expected $exp in $line" 1>&2 + exit 1; + } + done + return 0 +} # Return true if perf_event_paranoid is > $1 and not running as root. function ParanoidAndNotRoot() @@ -30,7 +52,7 @@ function ParanoidAndNotRoot() check_no_args() { echo -n "Checking CSV output: no args " - perf stat -x, true 2>&1 | $PYTHON $pythonchecker --no-args + perf stat -x, true 2>&1 | commachecker --no-args echo "[Success]" } @@ -42,7 +64,7 @@ check_system_wide() echo "[Skip] paranoid and not root" return fi - perf stat -x, -a true 2>&1 | $PYTHON $pythonchecker --system-wide + perf stat -x, -a true 2>&1 | commachecker --system-wide echo "[Success]" } @@ -55,14 +77,14 @@ check_system_wide_no_aggr() return fi echo -n "Checking CSV output: system wide no aggregation " - perf stat -x, -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr + perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr echo "[Success]" } check_interval() { echo -n "Checking CSV output: interval " - perf stat -x, -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval + perf stat -x, -I 1000 true 2>&1 | commachecker --interval echo "[Success]" } @@ -70,7 +92,7 @@ check_interval() check_event() { echo -n "Checking CSV output: event " - perf stat -x, -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event + perf stat -x, -e cpu-clock true 2>&1 | commachecker --event echo "[Success]" } @@ -82,7 +104,7 @@ check_per_core() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core + perf stat -x, --per-core -a true 2>&1 | commachecker --per-core echo "[Success]" } @@ -94,7 +116,7 @@ check_per_thread() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread + perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread echo "[Success]" } @@ -106,7 +128,7 @@ check_per_die() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die + perf stat -x, --per-die -a true 2>&1 | commachecker --per-die echo "[Success]" } @@ -118,7 +140,7 @@ check_per_node() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node + perf stat -x, --per-node -a true 2>&1 | commachecker --per-node echo "[Success]" } @@ -130,7 +152,7 @@ check_per_socket() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket + perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket echo "[Success]" } diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh index e7c59e5a7a98..6e79349e42be 100755 --- a/tools/perf/tests/shell/stat_all_metrics.sh +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -1,26 +1,41 @@ -#!/bin/sh +#!/bin/bash # perf all metrics test # SPDX-License-Identifier: GPL-2.0 -set -e - err=0 for m in $(perf list --raw-dump metrics); do echo "Testing $m" result=$(perf stat -M "$m" true 2>&1) - if [[ ! "$result" =~ "$m" ]] && [[ ! "$result" =~ "<not supported>" ]]; then - # We failed to see the metric and the events are support. Possibly the - # workload was too small so retry with something longer. - result=$(perf stat -M "$m" perf bench internals synthesize 2>&1) - if [[ ! "$result" =~ "$m" ]]; then - echo "Metric '$m' not printed in:" - echo "$result" - if [[ "$result" =~ "FP_ARITH" && "$err" != "1" ]]; then - echo "Skip, not fail, for FP issues" - err=2 - else - err=1 - fi + if [[ "$result" =~ "${m:0:50}" ]] || [[ "$result" =~ "<not supported>" ]] + then + continue + fi + # Failed so try system wide. + result=$(perf stat -M "$m" -a true 2>&1) + if [[ "$result" =~ "${m:0:50}" ]] + then + continue + fi + # Failed again, possibly the workload was too small so retry with something + # longer. + result=$(perf stat -M "$m" perf bench internals synthesize 2>&1) + if [[ "$result" =~ "${m:0:50}" ]] + then + continue + fi + echo "Metric '$m' not printed in:" + echo "$result" + if [[ "$err" != "1" ]] + then + err=2 + if [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]] + then + echo "Skip, not fail, for FP issues" + elif [[ "$result" =~ "PMM" ]] + then + echo "Skip, not fail, for Optane memory issues" + else + err=1 fi fi done diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh index 6ffbb27afaba..ec108d45d3c6 100755 --- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh +++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh @@ -43,7 +43,7 @@ CFLAGS="-g -O0 -fno-inline -fno-omit-frame-pointer" cc $CFLAGS $TEST_PROGRAM_SOURCE -o $TEST_PROGRAM || exit 1 # Add a 1 second delay to skip samples that are not in the leaf() function -perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 -- $TEST_PROGRAM 2> /dev/null & +perf record -o $PERF_DATA --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null & PID=$! echo " + Recording (PID=$PID)..." diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh index e59044edc406..0d47479adba8 100755 --- a/tools/perf/tests/shell/test_arm_spe.sh +++ b/tools/perf/tests/shell/test_arm_spe.sh @@ -23,17 +23,20 @@ glb_err=0 cleanup_files() { rm -f ${perfdata} + rm -f ${perfdata}.old exit $glb_err } trap cleanup_files exit term int arm_spe_report() { - if [ $2 != 0 ]; then + if [ $2 = 0 ]; then + echo "$1: PASS" + elif [ $2 = 2 ]; then + echo "$1: SKIPPED" + else echo "$1: FAIL" glb_err=$2 - else - echo "$1: PASS" fi } @@ -85,5 +88,26 @@ arm_spe_snapshot_test() { arm_spe_report "SPE snapshot testing" $err } +arm_spe_system_wide_test() { + echo "Recording trace with system-wide mode $perfdata" + + perf record -o - -e dummy -a -B true > /dev/null 2>&1 + if [ $? != 0 ]; then + arm_spe_report "SPE system-wide testing" 2 + return + fi + + perf record -o ${perfdata} -e arm_spe// -a --no-bpf-event \ + -- dd if=/dev/zero of=/dev/null count=100000 > /dev/null 2>&1 + + perf_script_samples dd && + perf_report_samples dd + + err=$? + arm_spe_report "SPE system-wide testing" $err +} + arm_spe_snapshot_test +arm_spe_system_wide_test + exit $glb_err diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh new file mode 100755 index 000000000000..c644f94a6500 --- /dev/null +++ b/tools/perf/tests/shell/test_brstack.sh @@ -0,0 +1,114 @@ +#!/bin/sh +# Check branch stack sampling + +# SPDX-License-Identifier: GPL-2.0 +# German Gomez <german.gomez@arm.com>, 2022 + +# we need a C compiler to build the test programs +# so bail if none is found +if ! [ -x "$(command -v cc)" ]; then + echo "failed: no compiler, install gcc" + exit 2 +fi + +# skip the test if the hardware doesn't support branch stack sampling +perf record -b -o- -B true > /dev/null 2>&1 || exit 2 + +TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) + +cleanup() { + rm -rf $TMPDIR +} + +trap cleanup exit term int + +gen_test_program() { + # generate test program + cat << EOF > $1 +#define BENCH_RUNS 999999 +int cnt; +void bar(void) { +} /* return */ +void foo(void) { + bar(); /* call */ +} /* return */ +void bench(void) { + void (*foo_ind)(void) = foo; + if ((cnt++) % 3) /* branch (cond) */ + foo(); /* call */ + bar(); /* call */ + foo_ind(); /* call (ind) */ +} +int main(void) +{ + int cnt = 0; + while (1) { + if ((cnt++) > BENCH_RUNS) + break; + bench(); /* call */ + } /* branch (uncond) */ + return 0; +} +EOF +} + +test_user_branches() { + echo "Testing user branch stack sampling" + + gen_test_program "$TEMPDIR/program.c" + cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out + + perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1 + perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script + + # example of branch entries: + # foo+0x14/bar+0x40/P/-/-/0/CALL + + set -x + egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/IND_CALL$" $TMPDIR/perf.script + egrep -m1 "^foo\+[^ ]*/bar\+[^ ]*/CALL$" $TMPDIR/perf.script + egrep -m1 "^bench\+[^ ]*/foo\+[^ ]*/CALL$" $TMPDIR/perf.script + egrep -m1 "^bench\+[^ ]*/bar\+[^ ]*/CALL$" $TMPDIR/perf.script + egrep -m1 "^bar\+[^ ]*/foo\+[^ ]*/RET$" $TMPDIR/perf.script + egrep -m1 "^foo\+[^ ]*/bench\+[^ ]*/RET$" $TMPDIR/perf.script + egrep -m1 "^bench\+[^ ]*/bench\+[^ ]*/COND$" $TMPDIR/perf.script + egrep -m1 "^main\+[^ ]*/main\+[^ ]*/UNCOND$" $TMPDIR/perf.script + set +x + + # some branch types are still not being tested: + # IND COND_CALL COND_RET SYSCALL SYSRET IRQ SERROR NO_TX +} + +# first argument <arg0> is the argument passed to "--branch-stack <arg0>,save_type,u" +# second argument are the expected branch types for the given filter +test_filter() { + local filter=$1 + local expect=$2 + + echo "Testing branch stack filtering permutation ($filter,$expect)" + + gen_test_program "$TEMPDIR/program.c" + cc -fno-inline -g "$TEMPDIR/program.c" -o $TMPDIR/a.out + + perf record -o $TMPDIR/perf.data --branch-filter $filter,save_type,u -- $TMPDIR/a.out > /dev/null 2>&1 + perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script + + # fail if we find any branch type that doesn't match any of the expected ones + # also consider UNKNOWN branch types (-) + if egrep -vm1 "^[^ ]*/($expect|-|( *))$" $TMPDIR/perf.script; then + return 1 + fi +} + +set -e + +test_user_branches + +test_filter "any_call" "CALL|IND_CALL|COND_CALL|SYSCALL|IRQ" +test_filter "call" "CALL|SYSCALL" +test_filter "cond" "COND" +test_filter "any_ret" "RET|COND_RET|SYSRET|ERET" + +test_filter "call,cond" "CALL|SYSCALL|COND" +test_filter "any_call,cond" "CALL|IND_CALL|COND_CALL|IRQ|SYSCALL|COND" +test_filter "cond,any_call,any_ret" "COND|CALL|IND_CALL|COND_CALL|SYSCALL|IRQ|RET|COND_RET|SYSRET|ERET" diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index d23a9e322ff5..0b4f61b6cc6b 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -115,7 +115,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) * physical_package_id will be set to -1. Hence skip this * test if physical_package_id returns -1 for cpu from perf_cpu_map. */ - if (strncmp(session->header.env.arch, "powerpc", 7)) { + if (!strncmp(session->header.env.arch, "ppc64le", 7)) { if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1) return TEST_SKIP; } |