diff options
Diffstat (limited to 'tools/perf/tests')
28 files changed, 739 insertions, 214 deletions
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 934f32090553..2181f5a92148 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -56,6 +56,7 @@ perf-test-y += genelf.o perf-test-y += api-io.o perf-test-y += demangle-java-test.o perf-test-y += demangle-ocaml-test.o +perf-test-y += demangle-rust-v0-test.o perf-test-y += pfm.o perf-test-y += parse-metric.o perf-test-y += pe-file-parsing.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 14d30a5053be..45d3d8b3317a 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -126,6 +126,7 @@ static struct test_suite *generic_tests[] = { &suite__maps__merge_in, &suite__demangle_java, &suite__demangle_ocaml, + &suite__demangle_rust, &suite__parse_metric, &suite__pe_file_parsing, &suite__expand_cgroup_events, diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c index 93c94408bdc8..0fb3e5a4a0ed 100644 --- a/tools/perf/tests/demangle-java-test.c +++ b/tools/perf/tests/demangle-java-test.c @@ -3,10 +3,9 @@ #include <stdlib.h> #include <stdio.h> #include <linux/kernel.h> -#include "tests.h" -#include "session.h" #include "debug.h" -#include "demangle-java.h" +#include "symbol.h" +#include "tests.h" static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { @@ -18,19 +17,24 @@ static int test__demangle_java(struct test_suite *test __maybe_unused, int subte const char *mangled, *demangled; } test_cases[] = { { "Ljava/lang/StringLatin1;equals([B[B)Z", - "boolean java.lang.StringLatin1.equals(byte[], byte[])" }, + "java.lang.StringLatin1.equals(byte[], byte[])" }, { "Ljava/util/zip/ZipUtils;CENSIZ([BI)J", - "long java.util.zip.ZipUtils.CENSIZ(byte[], int)" }, + "java.util.zip.ZipUtils.CENSIZ(byte[], int)" }, { "Ljava/util/regex/Pattern$BmpCharProperty;match(Ljava/util/regex/Matcher;ILjava/lang/CharSequence;)Z", - "boolean java.util.regex.Pattern$BmpCharProperty.match(java.util.regex.Matcher, int, java.lang.CharSequence)" }, + "java.util.regex.Pattern$BmpCharProperty.match(java.util.regex.Matcher, int, java.lang.CharSequence)" }, { "Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V", - "void java.lang.AbstractStringBuilder.appendChars(java.lang.String, int, int)" }, + "java.lang.AbstractStringBuilder.appendChars(java.lang.String, int, int)" }, { "Ljava/lang/Object;<init>()V", - "void java.lang.Object<init>()" }, + "java.lang.Object<init>()" }, }; for (i = 0; i < ARRAY_SIZE(test_cases); i++) { - buf = java_demangle_sym(test_cases[i].mangled, 0); + buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled); + if (!buf) { + pr_debug("FAILED to demangle: \"%s\"\n \"%s\"\n", test_cases[i].mangled, + test_cases[i].demangled); + continue; + } if (strcmp(buf, test_cases[i].demangled)) { pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled, buf, test_cases[i].demangled); diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c index 90a4285e2ad5..612c788b7e0d 100644 --- a/tools/perf/tests/demangle-ocaml-test.c +++ b/tools/perf/tests/demangle-ocaml-test.c @@ -2,10 +2,9 @@ #include <string.h> #include <stdlib.h> #include <stdio.h> -#include "tests.h" -#include "session.h" #include "debug.h" -#include "demangle-ocaml.h" +#include "symbol.h" +#include "tests.h" static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { @@ -27,7 +26,7 @@ static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subt }; for (i = 0; i < ARRAY_SIZE(test_cases); i++) { - buf = ocaml_demangle_sym(test_cases[i].mangled); + buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled); if ((buf == NULL && test_cases[i].demangled != NULL) || (buf != NULL && test_cases[i].demangled == NULL) || (buf != NULL && strcmp(buf, test_cases[i].demangled))) { diff --git a/tools/perf/tests/demangle-rust-v0-test.c b/tools/perf/tests/demangle-rust-v0-test.c new file mode 100644 index 000000000000..904f966c65d7 --- /dev/null +++ b/tools/perf/tests/demangle-rust-v0-test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT +#include "tests.h" +#include "debug.h" +#include "symbol.h" +#include <linux/kernel.h> +#include <stdlib.h> +#include <string.h> + +static int test__demangle_rust(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + int ret = TEST_OK; + char *buf = NULL; + size_t i; + + struct { + const char *mangled, *demangled; + } test_cases[] = { + { "_RNvMsr_NtCs3ssYzQotkvD_3std4pathNtB5_7PathBuf3newCs15kBYyAo9fc_7mycrate", + "<std::path::PathBuf>::new" }, + { "_RNvCs15kBYyAo9fc_7mycrate7example", + "mycrate::example" }, + { "_RNvMs_Cs4Cv8Wi1oAIB_7mycrateNtB4_7Example3foo", + "<mycrate::Example>::foo" }, + { "_RNvXCs15kBYyAo9fc_7mycrateNtB2_7ExampleNtB2_5Trait3foo", + "<mycrate::Example as mycrate::Trait>::foo" }, + { "_RNvMCs7qp2U7fqm6G_7mycrateNtB2_7Example3foo", + "<mycrate::Example>::foo" }, + { "_RNvMs_Cs7qp2U7fqm6G_7mycrateNtB4_7Example3bar", + "<mycrate::Example>::bar" }, + { "_RNvYNtCs15kBYyAo9fc_7mycrate7ExampleNtB4_5Trait7exampleB4_", + "<mycrate::Example as mycrate::Trait>::example" }, + { "_RNCNvCsgStHSCytQ6I_7mycrate4main0B3_", + "mycrate::main::{closure#0}" }, + { "_RNCNvCsgStHSCytQ6I_7mycrate4mains_0B3_", + "mycrate::main::{closure#1}" }, + { "_RINvCsgStHSCytQ6I_7mycrate7examplelKj1_EB2_", + "mycrate::example::<i32, 1>" }, + { "_RINvCs7qp2U7fqm6G_7mycrate7exampleFG0_RL1_hRL0_tEuEB2_", + "mycrate::example::<for<'a, 'b> fn(&'a u8, &'b u16)>", + }, + { "_RINvCs7qp2U7fqm6G_7mycrate7exampleKy12345678_EB2_", + "mycrate::example::<305419896>" }, + { "_RNvNvMCsd9PVOYlP1UU_7mycrateINtB4_7ExamplepKpE3foo14EXAMPLE_STATIC", + "<mycrate::Example<_, _>>::foo::EXAMPLE_STATIC", + }, + { "_RINvCs7qp2U7fqm6G_7mycrate7exampleAtj8_EB2_", + "mycrate::example::<[u16; 8]>" }, + { "_RINvCs7qp2U7fqm6G_7mycrate7exampleNtB2_7ExampleBw_EB2_", + "mycrate::example::<mycrate::Example, mycrate::Example>" }, + { "_RINvMsY_NtCseXNvpPnDBDp_3std4pathNtB6_4Path3neweECs7qp2U7fqm6G_7mycrate", + "<std::path::Path>::new::<str>" }, + { "_RNvNvNvCs7qp2U7fqm6G_7mycrate7EXAMPLE7___getit5___KEY", + "mycrate::EXAMPLE::__getit::__KEY" }, + }; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled); + if (!buf) { + pr_debug("FAILED to demangle: \"%s\"\n \"%s\"\n", test_cases[i].mangled, + test_cases[i].demangled); + continue; + } + if (strcmp(buf, test_cases[i].demangled)) { + pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled, + buf, test_cases[i].demangled); + ret = TEST_FAIL; + } + free(buf); + } + + return ret; +} + +DEFINE_SUITE("Demangle Rust", demangle_rust); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 4803ab2d97ba..525c46b7971a 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -15,7 +15,6 @@ #include "symbol.h" #include "thread.h" #include "callchain.h" -#include "util/synthetic-events.h" /* For bsearch. We try to unwind functions in shared object. */ #include <stdlib.h> @@ -37,24 +36,6 @@ #define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory"); #endif -static int mmap_handler(const struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine) -{ - return machine__process_mmap2_event(machine, event, sample); -} - -static int init_live_machine(struct machine *machine) -{ - union perf_event event; - pid_t pid = getpid(); - - memset(&event, 0, sizeof(event)); - return perf_event__synthesize_mmap_events(NULL, &event, pid, pid, - mmap_handler, machine, true); -} - /* * We need to keep these functions global, despite the * fact that they are used only locally in this object, @@ -202,8 +183,12 @@ noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused, struct machine *machine; struct thread *thread; int err = -1; + pid_t pid = getpid(); - machine = machine__new_host(); + callchain_param.record_mode = CALLCHAIN_DWARF; + dwarf_callchain_users = true; + + machine = machine__new_live(/*kernel_maps=*/true, pid); if (!machine) { pr_err("Could not get machine\n"); return -1; @@ -214,18 +199,10 @@ noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused, return -1; } - callchain_param.record_mode = CALLCHAIN_DWARF; - dwarf_callchain_users = true; - - if (init_live_machine(machine)) { - pr_err("Could not init machine\n"); - goto out; - } - if (verbose > 1) machine__fprintf(machine, stderr); - thread = machine__find_thread(machine, getpid(), getpid()); + thread = machine__find_thread(machine, pid, pid); if (!thread) { pr_err("Could not get thread\n"); goto out; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index db004d26fcb0..815b40097428 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -38,7 +38,9 @@ struct perf_pmu_test_event { }; struct perf_pmu_test_pmu { - struct perf_pmu pmu; + const char *pmu_name; + bool pmu_is_uncore; + const char *pmu_id; struct perf_pmu_test_event const *aliases[10]; }; @@ -553,11 +555,10 @@ static int __test_core_pmu_event_aliases(const char *pmu_name, int *count) if (!pmu) return -1; - INIT_LIST_HEAD(&pmu->format); - INIT_LIST_HEAD(&pmu->aliases); - INIT_LIST_HEAD(&pmu->caps); - INIT_LIST_HEAD(&pmu->list); - pmu->name = strdup(pmu_name); + if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, pmu_name) != 0) { + perf_pmu__delete(pmu); + return -1; + } pmu->is_core = true; pmu->events_table = table; @@ -594,14 +595,30 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) { int alias_count = 0, to_match_count = 0, matched_count = 0; struct perf_pmu_test_event const **table; - struct perf_pmu *pmu = &test_pmu->pmu; - const char *pmu_name = pmu->name; + struct perf_pmu *pmu; const struct pmu_events_table *events_table; int res = 0; events_table = find_core_events_table("testarch", "testcpu"); if (!events_table) return -1; + + pmu = zalloc(sizeof(*pmu)); + if (!pmu) + return -1; + + if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, test_pmu->pmu_name) != 0) { + perf_pmu__delete(pmu); + return -1; + } + pmu->is_uncore = test_pmu->pmu_is_uncore; + if (test_pmu->pmu_id) { + pmu->id = strdup(test_pmu->pmu_id); + if (!pmu->id) { + perf_pmu__delete(pmu); + return -1; + } + } pmu->events_table = events_table; pmu_add_cpu_aliases_table(pmu, events_table); pmu->cpu_aliases_added = true; @@ -617,7 +634,8 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) if (alias_count != to_match_count) { pr_debug("testing aliases uncore PMU %s: mismatch expected aliases (%d) vs found (%d)\n", - pmu_name, to_match_count, alias_count); + pmu->name, to_match_count, alias_count); + perf_pmu__delete(pmu); return -1; } @@ -630,9 +648,10 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) .count = &matched_count, }; - if (strcmp(pmu_name, test_event.matching_pmu)) { + if (strcmp(pmu->name, test_event.matching_pmu)) { pr_debug("testing aliases uncore PMU %s: mismatched matching_pmu, %s vs %s\n", - pmu_name, test_event.matching_pmu, pmu_name); + pmu->name, test_event.matching_pmu, pmu->name); + perf_pmu__delete(pmu); return -1; } @@ -641,34 +660,32 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) if (err) { res = err; pr_debug("testing aliases uncore PMU %s: could not match alias %s\n", - pmu_name, event->name); + pmu->name, event->name); + perf_pmu__delete(pmu); return -1; } } if (alias_count != matched_count) { pr_debug("testing aliases uncore PMU %s: mismatch found aliases (%d) vs matched (%d)\n", - pmu_name, matched_count, alias_count); + pmu->name, matched_count, alias_count); res = -1; } + perf_pmu__delete(pmu); return res; } static struct perf_pmu_test_pmu test_pmus[] = { { - .pmu = { - .name = "hisi_sccl1_ddrc2", - .is_uncore = 1, - }, + .pmu_name = "hisi_sccl1_ddrc2", + .pmu_is_uncore = 1, .aliases = { &uncore_hisi_ddrc_flux_wcmd, }, }, { - .pmu = { - .name = "uncore_cbox_0", - .is_uncore = 1, - }, + .pmu_name = "uncore_cbox_0", + .pmu_is_uncore = 1, .aliases = { &unc_cbo_xsnp_response_miss_eviction, &uncore_hyphen, @@ -676,88 +693,70 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, }, { - .pmu = { - .name = "hisi_sccl3_l3c7", - .is_uncore = 1, - }, + .pmu_name = "hisi_sccl3_l3c7", + .pmu_is_uncore = 1, .aliases = { &uncore_hisi_l3c_rd_hit_cpipe, }, }, { - .pmu = { - .name = "uncore_imc_free_running_0", - .is_uncore = 1, - }, + .pmu_name = "uncore_imc_free_running_0", + .pmu_is_uncore = 1, .aliases = { &uncore_imc_free_running_cache_miss, }, }, { - .pmu = { - .name = "uncore_imc_0", - .is_uncore = 1, - }, + .pmu_name = "uncore_imc_0", + .pmu_is_uncore = 1, .aliases = { &uncore_imc_cache_hits, }, }, { - .pmu = { - .name = "uncore_sys_ddr_pmu0", - .is_uncore = 1, - .id = "v8", - }, + .pmu_name = "uncore_sys_ddr_pmu0", + .pmu_is_uncore = 1, + .pmu_id = "v8", .aliases = { &sys_ddr_pmu_write_cycles, }, }, { - .pmu = { - .name = "uncore_sys_ccn_pmu4", - .is_uncore = 1, - .id = "0x01", - }, + .pmu_name = "uncore_sys_ccn_pmu4", + .pmu_is_uncore = 1, + .pmu_id = "0x01", .aliases = { &sys_ccn_pmu_read_cycles, }, }, { - .pmu = { - .name = (char *)"uncore_sys_cmn_pmu0", - .is_uncore = 1, - .id = (char *)"43401", - }, + .pmu_name = "uncore_sys_cmn_pmu0", + .pmu_is_uncore = 1, + .pmu_id = "43401", .aliases = { &sys_cmn_pmu_hnf_cache_miss, }, }, { - .pmu = { - .name = (char *)"uncore_sys_cmn_pmu0", - .is_uncore = 1, - .id = (char *)"43602", - }, + .pmu_name = "uncore_sys_cmn_pmu0", + .pmu_is_uncore = 1, + .pmu_id = "43602", .aliases = { &sys_cmn_pmu_hnf_cache_miss, }, }, { - .pmu = { - .name = (char *)"uncore_sys_cmn_pmu0", - .is_uncore = 1, - .id = (char *)"43c03", - }, + .pmu_name = "uncore_sys_cmn_pmu0", + .pmu_is_uncore = 1, + .pmu_id = "43c03", .aliases = { &sys_cmn_pmu_hnf_cache_miss, }, }, { - .pmu = { - .name = (char *)"uncore_sys_cmn_pmu0", - .is_uncore = 1, - .id = (char *)"43a01", - }, + .pmu_name = "uncore_sys_cmn_pmu0", + .pmu_is_uncore = 1, + .pmu_id = "43a01", .aliases = { &sys_cmn_pmu_hnf_cache_miss, }, @@ -796,10 +795,6 @@ static int test__aliases(struct test_suite *test __maybe_unused, for (i = 0; i < ARRAY_SIZE(test_pmus); i++) { int res; - INIT_LIST_HEAD(&test_pmus[i].pmu.format); - INIT_LIST_HEAD(&test_pmus[i].pmu.aliases); - INIT_LIST_HEAD(&test_pmus[i].pmu.caps); - res = __test_uncore_pmu_event_aliases(&test_pmus[i]); if (res) return res; diff --git a/tools/perf/tests/shell/amd-ibs-swfilt.sh b/tools/perf/tests/shell/amd-ibs-swfilt.sh new file mode 100755 index 000000000000..83937aa687cc --- /dev/null +++ b/tools/perf/tests/shell/amd-ibs-swfilt.sh @@ -0,0 +1,67 @@ +#!/bin/sh +# AMD IBS software filtering + +echo "check availability of IBS swfilt" + +# check if IBS PMU is available +if [ ! -d /sys/bus/event_source/devices/ibs_op ]; then + echo "[SKIP] IBS PMU does not exist" + exit 2 +fi + +# check if IBS PMU has swfilt format +if [ ! -f /sys/bus/event_source/devices/ibs_op/format/swfilt ]; then + echo "[SKIP] IBS PMU does not have swfilt" + exit 2 +fi + +echo "run perf record with modifier and swfilt" + +# setting any modifiers should fail +perf record -B -e ibs_op//u -o /dev/null true 2> /dev/null +if [ $? -eq 0 ]; then + echo "[FAIL] IBS PMU should not accept exclude_kernel" + exit 1 +fi + +# setting it with swfilt should be fine +perf record -B -e ibs_op/swfilt/u -o /dev/null true +if [ $? -ne 0 ]; then + echo "[FAIL] IBS op PMU cannot handle swfilt for exclude_kernel" + exit 1 +fi + +# setting it with swfilt=1 should be fine +perf record -B -e ibs_op/swfilt=1/k -o /dev/null true +if [ $? -ne 0 ]; then + echo "[FAIL] IBS op PMU cannot handle swfilt for exclude_user" + exit 1 +fi + +# check ibs_fetch PMU as well +perf record -B -e ibs_fetch/swfilt/u -o /dev/null true +if [ $? -ne 0 ]; then + echo "[FAIL] IBS fetch PMU cannot handle swfilt for exclude_kernel" + exit 1 +fi + +# check system wide recording +perf record -aB --synth=no -e ibs_op/swfilt/k -o /dev/null true +if [ $? -ne 0 ]; then + echo "[FAIL] IBS op PMU cannot handle swfilt in system-wide mode" + exit 1 +fi + +echo "check number of samples with swfilt" + +kernel_sample=$(perf record -e ibs_op/swfilt/u -o- true | perf script -i- -F misc | grep -c ^K) +if [ ${kernel_sample} -ne 0 ]; then + echo "[FAIL] unexpected kernel samples: " ${kernel_sample} + exit 1 +fi + +user_sample=$(perf record -e ibs_fetch/swfilt/k -o- true | perf script -i- -F misc | grep -c ^U) +if [ ${user_sample} -ne 0 ]; then + echo "[FAIL] unexpected user samples: " ${user_sample} + exit 1 +fi diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py index 0b94216c9c46..dea8ef1977bf 100644 --- a/tools/perf/tests/shell/lib/perf_metric_validation.py +++ b/tools/perf/tests/shell/lib/perf_metric_validation.py @@ -35,7 +35,8 @@ class TestError: class Validator: - def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', workload='true', metrics=''): + def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', + workload='true', metrics='', cputype='cpu'): self.rulefname = rulefname self.reportfname = reportfname self.rules = None @@ -43,6 +44,7 @@ class Validator: self.metrics = self.__set_metrics(metrics) self.skiplist = set() self.tolerance = t + self.cputype = cputype self.workloads = [x for x in workload.split(",") if x] self.wlidx = 0 # idx of current workloads @@ -377,7 +379,7 @@ class Validator: def _run_perf(self, metric, workload: str): tool = 'perf' - command = [tool, 'stat', '-j', '-M', f"{metric}", "-a"] + command = [tool, 'stat', '--cputype', self.cputype, '-j', '-M', f"{metric}", "-a"] wl = workload.split() command.extend(wl) print(" ".join(command)) @@ -443,6 +445,8 @@ class Validator: if 'MetricName' not in m: print("Warning: no metric name") continue + if 'Unit' in m and m['Unit'] != self.cputype: + continue name = m['MetricName'].lower() self.metrics.add(name) if 'ScaleUnit' in m and (m['ScaleUnit'] == '1%' or m['ScaleUnit'] == '100%'): @@ -578,6 +582,8 @@ def main() -> None: parser.add_argument( "-wl", help="Workload to run while data collection", default="true") parser.add_argument("-m", help="Metric list to validate", default="") + parser.add_argument("-cputype", help="Only test metrics for the given CPU/PMU type", + default="cpu") args = parser.parse_args() outpath = Path(args.output_dir) reportf = Path.joinpath(outpath, 'perf_report.json') @@ -586,7 +592,7 @@ def main() -> None: validator = Validator(args.rule, reportf, debug=args.debug, datafname=datafile, fullrulefname=fullrule, workload=args.wl, - metrics=args.m) + metrics=args.m, cputype=args.cputype) ret = validator.test() return ret diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 5c33ec7a5a63..58debce9ab42 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -13,14 +13,28 @@ cleanup_probe_vfs_getname() { add_probe_vfs_getname() { add_probe_verbose=$1 if [ $had_vfs_getname -eq 1 ] ; then - result_filename_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*" - line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_filename_re" | sed -r "s/$result_filename_re/\1/") + result_initname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+initname.*" + line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_initname_re" | sed -r "s/$result_initname_re/\1/") + + # Search the old regular expressions so that this will + # pass on older kernels as well. + if [ -z "$line" ] ; then + result_filename_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*" + line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_filename_re" | sed -r "s/$result_filename_re/\1/") + fi + if [ -z "$line" ] ; then result_aname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->aname = NULL;" line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_aname_re" | sed -r "s/$result_aname_re/\1/") fi + + if [ -z "$line" ] ; then + echo "Could not find probeable line" + return 2 + fi + perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" + perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" || return 1 fi } diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh index 4d4aac547f01..c2ec7881ec1d 100644 --- a/tools/perf/tests/shell/lib/stat_output.sh +++ b/tools/perf/tests/shell/lib/stat_output.sh @@ -151,6 +151,11 @@ check_per_socket() check_metric_only() { echo -n "Checking $1 output: metric only " + if [ "$(uname -m)" = "s390x" ] && ! grep '^facilities' /proc/cpuinfo | grep -qw 67 + then + echo "[Skip] CPU-measurement counter facility not installed" + return + fi perf stat --metric-only $2 -e instructions,cycles true commachecker --metric-only echo "[Success]" diff --git a/tools/perf/tests/shell/perf-report-hierarchy.sh b/tools/perf/tests/shell/perf-report-hierarchy.sh new file mode 100755 index 000000000000..02e3b6aee4ed --- /dev/null +++ b/tools/perf/tests/shell/perf-report-hierarchy.sh @@ -0,0 +1,43 @@ +#!/bin/sh +# perf report --hierarchy +# SPDX-License-Identifier: GPL-2.0 +# Arnaldo Carvalho de Melo <acme@redhat.com> + +set -e + +temp_dir=$(mktemp -d /tmp/perf-test-report.XXXXXXXXXX) + +cleanup() +{ + trap - EXIT TERM INT + sane=$(echo "${temp_dir}" | cut -b 1-21) + if [ "${sane}" = "/tmp/perf-test-report" ] ; then + echo "--- Cleaning up ---" + rm -rf "${temp_dir:?}/"* + rmdir "${temp_dir}" + fi +} + +trap_cleanup() +{ + cleanup + exit 1 +} + +trap trap_cleanup EXIT TERM INT + +test_report_hierarchy() +{ + echo "perf report --hierarchy" + + perf_data="${temp_dir}/perf-report-hierarchy-perf.data" + perf record -o "${perf_data}" uname + perf report --hierarchy -i "${perf_data}" > /dev/null + echo "perf report --hierarchy test [Success]" +} + +test_report_hierarchy + +cleanup + +exit 0 diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh index c51a32931af6..0f52654c914a 100755 --- a/tools/perf/tests/shell/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -13,7 +13,13 @@ skip_if_no_perf_probe || exit 2 # shellcheck source=lib/probe_vfs_getname.sh . "$(dirname $0)"/lib/probe_vfs_getname.sh -add_probe_vfs_getname || skip_if_no_debuginfo +add_probe_vfs_getname err=$? + +if [ $err -eq 1 ] ; then + skip_if_no_debuginfo + err=$? +fi + cleanup_probe_vfs_getname exit $err diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh index fd5b10d46915..1ad252f0d36e 100755 --- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -35,8 +35,14 @@ perf_script_filenames() { grep -E " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname[_0-9]*: +\([[:xdigit:]]+\) +pathname=\"${file}\"" } -add_probe_vfs_getname || skip_if_no_debuginfo +add_probe_vfs_getname err=$? + +if [ $err -eq 1 ] ; then + skip_if_no_debuginfo + err=$? +fi + if [ $err -ne 0 ] ; then exit $err fi diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index ba8d873d3ca7..587f62e34414 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -34,13 +34,15 @@ default_fd_limit=$(ulimit -Sn) min_fd_limit=$(($(getconf _NPROCESSORS_ONLN) * 16)) cleanup() { - rm -rf "${perfdata}" - rm -rf "${perfdata}".old + rm -f "${perfdata}" + rm -f "${perfdata}".old + rm -f "${script_output}" trap - EXIT TERM INT } trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" cleanup exit 1 } @@ -238,22 +240,43 @@ test_leader_sampling() { err=1 return fi + perf script -i "${perfdata}" | grep brstack > $script_output + # Check if the two instruction counts are equal in each record. + # However, the throttling code doesn't consider event grouping. During throttling, only the + # leader is stopped, causing the slave's counts significantly higher. To temporarily solve this, + # let's set the tolerance rate to 80%. + # TODO: Revert the code for tolerance once the throttling mechanism is fixed. index=0 - perf script -i "${perfdata}" > $script_output + valid_counts=0 + invalid_counts=0 + tolerance_rate=0.8 while IFS= read -r line do - # Check if the two instruction counts are equal in each record cycles=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="cycles:") print $(i-1)}') if [ $(($index%2)) -ne 0 ] && [ ${cycles}x != ${prev_cycles}x ] then - echo "Leader sampling [Failed inconsistent cycles count]" - err=1 - return + invalid_counts=$(($invalid_counts+1)) + else + valid_counts=$(($valid_counts+1)) fi index=$(($index+1)) prev_cycles=$cycles - done < $script_output - echo "Basic leader sampling test [Success]" + done < "${script_output}" + total_counts=$(bc <<< "$invalid_counts+$valid_counts") + if (( $(bc <<< "$total_counts <= 0") )) + then + echo "Leader sampling [No sample generated]" + err=1 + return + fi + isok=$(bc <<< "scale=2; if (($invalid_counts/$total_counts) < (1-$tolerance_rate)) { 0 } else { 1 };") + if [ $isok -eq 1 ] + then + echo "Leader sampling [Failed inconsistent cycles count]" + err=1 + else + echo "Basic leader sampling test [Success]" + fi } test_topdown_leader_sampling() { diff --git a/tools/perf/tests/shell/record_lbr.sh b/tools/perf/tests/shell/record_lbr.sh index 8d750ee631f8..6fcb5e52b9b4 100755 --- a/tools/perf/tests/shell/record_lbr.sh +++ b/tools/perf/tests/shell/record_lbr.sh @@ -4,7 +4,8 @@ set -e -if [ ! -f /sys/devices/cpu/caps/branches ] && [ ! -f /sys/devices/cpu_core/caps/branches ] +if [ ! -f /sys/bus/event_source/devices/cpu/caps/branches ] && + [ ! -f /sys/bus/event_source/devices/cpu_core/caps/branches ] then echo "Skip: only x86 CPUs support LBR" exit 2 @@ -93,7 +94,7 @@ lbr_test() { return fi - zero_nr=$(echo "$out" | grep -c 'branch stack: nr:0' || true) + zero_nr=$(echo "$out" | grep -A3 'branch stack: nr:0' | grep thread | grep -cv swapper || true) r=$(($zero_nr * 100 / $bs_nr)) if [ $r -gt $threshold ]; then echo "$test [Failed empty br stack ratio exceed $threshold%: $r%]" diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index 678947fe69ee..21a22efe08f5 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -7,6 +7,9 @@ set -e err=0 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +ts=$(printf "%u" $((~0 << 32))) # OFF_CPU_TIMESTAMP +dummy_timestamp=${ts%???} # remove the last 3 digits to match perf script + cleanup() { rm -f ${perfdata} rm -f ${perfdata}.old @@ -19,6 +22,9 @@ trap_cleanup() { } trap trap_cleanup EXIT TERM INT +test_above_thresh="Threshold test (above threshold)" +test_below_thresh="Threshold test (below threshold)" + test_offcpu_priv() { echo "Checking off-cpu privilege" @@ -88,6 +94,63 @@ test_offcpu_child() { echo "Child task off-cpu test [Success]" } +# task blocks longer than the --off-cpu-thresh, perf should collect a direct sample +test_offcpu_above_thresh() { + echo "${test_above_thresh}" + + # collect direct off-cpu samples for tasks blocked for more than 999ms + if ! perf record -e dummy --off-cpu --off-cpu-thresh 999 -o ${perfdata} -- sleep 1 2> /dev/null + then + echo "${test_above_thresh} [Failed record]" + err=1 + return + fi + # direct sample's timestamp should be lower than the dummy_timestamp of the at-the-end sample + # check if a direct sample exists + if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q "offcpu-time" + then + echo "${test_above_thresh} [Failed missing direct samples]" + err=1 + return + fi + # there should only be one direct sample, and its period should be higher than off-cpu-thresh + if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F period | \ + awk '{ if (int($1) > 999000000) exit 0; else exit 1; }' + then + echo "${test_above_thresh} [Failed off-cpu time too short]" + err=1 + return + fi + echo "${test_above_thresh} [Success]" +} + +# task blocks shorter than the --off-cpu-thresh, perf should collect an at-the-end sample +test_offcpu_below_thresh() { + echo "${test_below_thresh}" + + # collect direct off-cpu samples for tasks blocked for more than 1.2s + if ! perf record -e dummy --off-cpu --off-cpu-thresh 1200 -o ${perfdata} -- sleep 1 2> /dev/null + then + echo "${test_below_thresh} [Failed record]" + err=1 + return + fi + # see if there's an at-the-end sample + if ! perf script --time "${dummy_timestamp}," -i ${perfdata} -F event | grep -q 'offcpu-time' + then + echo "${test_below_thresh} [Failed at-the-end samples cannot be found]" + err=1 + return + fi + # plus there shouldn't be any direct samples + if perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q 'offcpu-time' + then + echo "${test_below_thresh} [Failed direct samples are found when they shouldn't be]" + err=1 + return + fi + echo "${test_below_thresh} [Success]" +} test_offcpu_priv @@ -99,5 +162,13 @@ if [ $err = 0 ]; then test_offcpu_child fi +if [ $err = 0 ]; then + test_offcpu_above_thresh +fi + +if [ $err = 0 ]; then + test_offcpu_below_thresh +fi + cleanup exit $err diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh new file mode 100755 index 000000000000..5ec35c52b7d9 --- /dev/null +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh @@ -0,0 +1,69 @@ +#!/bin/bash +# perf stat events uniquifying +# SPDX-License-Identifier: GPL-2.0 + +set -e + +stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX) +perf_tool=perf +err=0 + +test_event_uniquifying() { + # We use `clockticks` to verify the uniquify behavior. + event="clockticks" + + # If the `-A` option is added, the event should be uniquified. + # + # $perf list -v clockticks + # + # List of pre-defined events (to be used in -e or -M): + # + # uncore_imc_0/clockticks/ [Kernel PMU event] + # uncore_imc_1/clockticks/ [Kernel PMU event] + # uncore_imc_2/clockticks/ [Kernel PMU event] + # uncore_imc_3/clockticks/ [Kernel PMU event] + # uncore_imc_4/clockticks/ [Kernel PMU event] + # uncore_imc_5/clockticks/ [Kernel PMU event] + # + # ... + # + # $perf stat -e clockticks -A -- true + # + # Performance counter stats for 'system wide': + # + # CPU0 3,773,018 uncore_imc_0/clockticks/ + # CPU0 3,609,025 uncore_imc_1/clockticks/ + # CPU0 0 uncore_imc_2/clockticks/ + # CPU0 3,230,009 uncore_imc_3/clockticks/ + # CPU0 3,049,897 uncore_imc_4/clockticks/ + # CPU0 0 uncore_imc_5/clockticks/ + # + # 0.002029828 seconds time elapsed + + echo "stat event uniquifying test" + uniquified_event_array=() + + # Check how many uniquified events. + while IFS= read -r line; do + uniquified_event=$(echo "$line" | awk '{print $1}') + uniquified_event_array+=("${uniquified_event}") + done < <(${perf_tool} list -v ${event} | grep "\[Kernel PMU event\]") + + perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true" + $perf_command + + # Check the output contains all uniquified events. + for uniquified_event in "${uniquified_event_array[@]}"; do + if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then + echo "Event is not uniquified [Failed]" + echo "${perf_command}" + cat "${stat_output}" + err=1 + break + fi + done +} + +test_event_uniquifying +rm -f "${stat_output}" +exit $err diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index a4f257ea839e..98fb65274ac4 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -176,6 +176,11 @@ check_per_socket() check_metric_only() { echo -n "Checking json output: metric only " + if [ "$(uname -m)" = "s390x" ] && ! grep '^facilities' /proc/cpuinfo | grep -qw 67 + then + echo "[Skip] CPU-measurement counter facility not installed" + return + fi perf stat -j --metric-only -e instructions,cycles -o "${stat_output}" true $PYTHON $pythonchecker --metric-only --file "${stat_output}" echo "[Success]" diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh index ee817c66da06..6fa585a1e34c 100755 --- a/tools/perf/tests/shell/stat_all_metrics.sh +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -7,86 +7,96 @@ ParanoidAndNotRoot() [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ] } +test_prog="sleep 0.01" system_wide_flag="-a" if ParanoidAndNotRoot 0 then system_wide_flag="" + test_prog="perf test -w noploop" fi err=0 for m in $(perf list --raw-dump metrics); do echo "Testing $m" - result=$(perf stat -M "$m" $system_wide_flag -- sleep 0.01 2>&1) + result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1) result_err=$? - if [[ $result_err -gt 0 ]] + if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]] then - if [[ "$result" =~ "Cannot resolve IDs for" ]] - then - echo "Metric contains missing events" - echo $result - err=1 # Fail - continue - elif [[ "$result" =~ \ - "Access to performance monitoring and observability operations is limited" ]] + # No error result and metric shown. + continue + fi + if [[ "$result" =~ "Cannot resolve IDs for" ]] + then + echo "Metric contains missing events" + echo $result + err=1 # Fail + continue + elif [[ "$result" =~ \ + "Access to performance monitoring and observability operations is limited" ]] + then + echo "Permission failure" + echo $result + if [[ $err -eq 0 ]] then - echo "Permission failure" - echo $result - if [[ $err -eq 0 ]] - then - err=2 # Skip - fi - continue - elif [[ "$result" =~ "in per-thread mode, enable system wide" ]] + err=2 # Skip + fi + continue + elif [[ "$result" =~ "in per-thread mode, enable system wide" ]] + then + echo "Permissions - need system wide mode" + echo $result + if [[ $err -eq 0 ]] then - echo "Permissions - need system wide mode" - echo $result - if [[ $err -eq 0 ]] - then - err=2 # Skip - fi - continue - elif [[ "$result" =~ "<not supported>" ]] + err=2 # Skip + fi + continue + elif [[ "$result" =~ "<not supported>" ]] + then + echo "Not supported events" + echo $result + if [[ $err -eq 0 ]] then - echo "Not supported events" - echo $result - if [[ $err -eq 0 ]] - then - err=2 # Skip - fi - continue - elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]] + err=2 # Skip + fi + continue + elif [[ "$result" =~ "<not counted>" ]] + then + echo "Not counted events" + echo $result + if [[ $err -eq 0 ]] then - echo "FP issues" - echo $result - if [[ $err -eq 0 ]] - then - err=2 # Skip - fi - continue - elif [[ "$result" =~ "PMM" ]] + err=2 # Skip + fi + continue + elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]] + then + echo "FP issues" + echo $result + if [[ $err -eq 0 ]] then - echo "Optane memory issues" - echo $result - if [[ $err -eq 0 ]] - then - err=2 # Skip - fi - continue + err=2 # Skip fi - fi - - if [[ "$result" =~ ${m:0:50} ]] + continue + elif [[ "$result" =~ "PMM" ]] then + echo "Optane memory issues" + echo $result + if [[ $err -eq 0 ]] + then + err=2 # Skip + fi continue fi # Failed, possibly the workload was too small so retry with something longer. result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1) - if [[ "$result" =~ ${m:0:50} ]] + result_err=$? + if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]] then + # No error result and metric shown. continue fi - echo "Metric '$m' not printed in:" + echo "Metric '$m' has non-zero error '$result_err' or not printed in:" echo "$result" err=1 done diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh index 279f19c5919a..30566f0b5427 100755 --- a/tools/perf/tests/shell/stat_metrics_values.sh +++ b/tools/perf/tests/shell/stat_metrics_values.sh @@ -16,11 +16,16 @@ workload="perf bench futex hash -r 2 -s" # Add -debug, save data file and full rule file echo "Launch python validation script $pythonvalidator" echo "Output will be stored in: $tmpdir" -$PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}" -ret=$? -rm -rf $tmpdir -if [ $ret -ne 0 ]; then - echo "Metric validation return with erros. Please check metrics reported with errors." -fi +for cputype in /sys/bus/event_source/devices/cpu_*; do + cputype=$(basename "$cputype") + echo "Testing metrics for: $cputype" + $PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}" \ + -cputype "${cputype}" + ret=$? + rm -rf $tmpdir + if [ $ret -ne 0 ]; then + echo "Metric validation return with errors. Please check metrics reported with errors." + fi +done exit $ret diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index e01df7581393..9138fa83bf36 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # Check branch stack sampling # SPDX-License-Identifier: GPL-2.0 @@ -17,35 +17,50 @@ fi skip_test_missing_symbol brstack_bench +err=0 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) TESTPROG="perf test -w brstack" cleanup() { rm -rf $TMPDIR + trap - EXIT TERM INT } -trap cleanup EXIT TERM INT +trap_cleanup() { + set +e + echo "Unexpected signal in ${FUNCNAME[1]}" + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT test_user_branches() { echo "Testing user branch stack sampling" - perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script + perf record -o "$TMPDIR/perf.data" --branch-filter any,save_type,u -- ${TESTPROG} > "$TMPDIR/record.txt" 2>&1 + perf script -i "$TMPDIR/perf.data" --fields brstacksym > "$TMPDIR/perf.script" # example of branch entries: # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL - set -x - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$" $TMPDIR/perf.script - grep -E -m1 "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$" $TMPDIR/perf.script - set +x - + expected=( + "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$" + "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" + "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$" + "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" + "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$" + "^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$" + "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$" + "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$" + ) + for x in "${expected[@]}" + do + if ! tr -s ' ' '\n' < "$TMPDIR/perf.script" | grep -E -m1 -q "$x" + then + echo "Branches missing $x" + err=1 + fi + done # some branch types are still not being tested: # IND COND_CALL COND_RET SYSCALL SYSRET IRQ SERROR NO_TX } @@ -57,14 +72,28 @@ test_filter() { test_filter_expect=$2 echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)" - - perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script + perf record -o "$TMPDIR/perf.data" --branch-filter "$test_filter_filter,save_type,u" -- ${TESTPROG} > "$TMPDIR/record.txt" 2>&1 + perf script -i "$TMPDIR/perf.data" --fields brstack > "$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 grep -E -vm1 "^[^ ]*/($test_filter_expect|-|( *))/.*$" $TMPDIR/perf.script; then - return 1 + if [ ! -s "$TMPDIR/perf.script" ] + then + echo "Empty script output" + err=1 + return + fi + # Look for lines not matching test_filter_expect ignoring issues caused + # by empty output + tr -s ' ' '\n' < "$TMPDIR/perf.script" | grep '.' | \ + grep -E -vm1 "^[^ ]*/($test_filter_expect|-|( *))/.*$" \ + > "$TMPDIR/perf.script-filtered" || true + if [ -s "$TMPDIR/perf.script-filtered" ] + then + echo "Unexpected branch filter in script output" + cat "$TMPDIR/perf.script" + err=1 + return fi } @@ -80,3 +109,6 @@ 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" + +cleanup +exit $err diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh index bbe8277496ae..d61b5659a46d 100755 --- a/tools/perf/tests/shell/test_data_symbol.sh +++ b/tools/perf/tests/shell/test_data_symbol.sh @@ -54,11 +54,34 @@ trap cleanup_files exit term int echo "Recording workload..." -# perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't support -# user/kernel filtering and per-process monitoring, spin program on -# specific CPU and test in per-CPU mode. is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo) if (($is_amd >= 1)); then + mem_events="$(perf mem record -v -e list 2>&1)" + if ! [[ "$mem_events" =~ ^mem\-ldst.*ibs_op/(.*)/.*available ]]; then + echo "ERROR: mem-ldst event is not matching" + exit 1 + fi + + # --ldlat on AMD: + # o Zen4 and earlier uarch does not support ldlat + # o Even on supported platforms, it's disabled (--ldlat=0) by default. + ldlat=${BASH_REMATCH[1]} + if [[ -n $ldlat ]]; then + if ! [[ "$ldlat" =~ ldlat=0 ]]; then + echo "ERROR: ldlat not initialized to 0?" + exit 1 + fi + + mem_events="$(perf mem record -v --ldlat=150 -e list 2>&1)" + if ! [[ "$mem_events" =~ ^mem-ldst.*ibs_op/ldlat=150/.*available ]]; then + echo "ERROR: --ldlat not honored?" + exit 1 + fi + fi + + # perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't + # support user/kernel filtering and per-process monitoring on older + # kernels, spin program on specific CPU and test in per-CPU mode. perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" else perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index f3a9a040bacc..32a9b8dcb200 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -288,6 +288,11 @@ test_jitdump() jitdump_incl_dir="${script_dir}/../../util" jitdump_h="${jitdump_incl_dir}/jitdump.h" + if ! perf check feature -q libelf ; then + echo "SKIP: libelf is needed for jitdump" + return 2 + fi + if [ ! -e "${jitdump_h}" ] ; then echo "SKIP: Include file jitdump.h not found" return 2 diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 60fccb62c540..5d5019988d61 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -25,9 +25,14 @@ trace_open_vfs_getname() { grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +\"?${file}\"?, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } - -add_probe_vfs_getname || skip_if_no_debuginfo +add_probe_vfs_getname err=$? + +if [ $err -eq 1 ] ; then + skip_if_no_debuginfo + err=$? +fi + if [ $err -ne 0 ] ; then exit $err fi diff --git a/tools/perf/tests/shell/trace_summary.sh b/tools/perf/tests/shell/trace_summary.sh new file mode 100755 index 000000000000..f9bb7f9388be --- /dev/null +++ b/tools/perf/tests/shell/trace_summary.sh @@ -0,0 +1,77 @@ +#!/bin/sh +# perf trace summary (exclusive) +# SPDX-License-Identifier: GPL-2.0 + +# Check that perf trace works with various summary mode + +# shellcheck source=lib/probe.sh +. "$(dirname $0)"/lib/probe.sh + +skip_if_no_perf_trace || exit 2 +[ "$(id -u)" = 0 ] || exit 2 + +OUTPUT=$(mktemp /tmp/perf_trace_test.XXXXX) + +test_perf_trace() { + args=$1 + workload="true" + search="^\s*(open|read|close).*[0-9]+%$" + + echo "testing: perf trace ${args} -- ${workload}" + perf trace ${args} -- ${workload} >${OUTPUT} 2>&1 + if [ $? -ne 0 ]; then + echo "Error: perf trace ${args} failed unexpectedly" + cat ${OUTPUT} + rm -f ${OUTPUT} + exit 1 + fi + + count=$(grep -E -c -m 3 "${search}" ${OUTPUT}) + if [ "${count}" != "3" ]; then + echo "Error: cannot find enough pattern ${search} in the output" + cat ${OUTPUT} + rm -f ${OUTPUT} + exit 1 + fi +} + +# summary only for a process +test_perf_trace "-s" + +# normal output with summary at the end +test_perf_trace "-S" + +# summary only with an explicit summary mode +test_perf_trace "-s --summary-mode=thread" + +# summary with normal output - total summary mode +test_perf_trace "-S --summary-mode=total" + +# summary only for system wide - per-thread summary +test_perf_trace "-as --summary-mode=thread --no-bpf-summary" + +# summary only for system wide - total summary mode +test_perf_trace "-as --summary-mode=total --no-bpf-summary" + +if ! perf check feature -q bpf; then + echo "Skip --bpf-summary tests as perf built without libbpf" + rm -f ${OUTPUT} + exit 2 +fi + +# summary only for system wide - per-thread summary with BPF +test_perf_trace "-as --summary-mode=thread --bpf-summary" + +# summary only for system wide - total summary mode with BPF +test_perf_trace "-as --summary-mode=total --bpf-summary" + +# summary with normal output for system wide - total summary mode with BPF +test_perf_trace "-aS --summary-mode=total --bpf-summary" + +# summary only for system wide - cgroup summary mode with BPF +test_perf_trace "-as --summary-mode=cgroup --bpf-summary" + +# summary with normal output for system wide - cgroup summary mode with BPF +test_perf_trace "-aS --summary-mode=cgroup --bpf-summary" + +rm -f ${OUTPUT} diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 8df3f9d9ffd2..6b3aac283c37 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -264,7 +264,7 @@ static int compar(const void *a, const void *b) const struct event_node *nodeb = b; s64 cmp = nodea->event_time - nodeb->event_time; - return cmp; + return cmp < 0 ? -1 : (cmp > 0 ? 1 : 0); } static int process_events(struct evlist *evlist, diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 8aea344536b8..bb7951c61971 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -157,6 +157,7 @@ DECLARE_SUITE(jit_write_elf); DECLARE_SUITE(api_io); DECLARE_SUITE(demangle_java); DECLARE_SUITE(demangle_ocaml); +DECLARE_SUITE(demangle_rust); DECLARE_SUITE(pfm); DECLARE_SUITE(parse_metric); DECLARE_SUITE(pe_file_parsing); |