diff options
Diffstat (limited to 'tools/perf')
-rw-r--r-- | tools/perf/Makefile.perf | 2 | ||||
-rw-r--r-- | tools/perf/builtin-trace.c | 4 | ||||
-rw-r--r-- | tools/perf/perf.h | 2 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json | 10 | ||||
-rw-r--r-- | tools/perf/tests/perf-record.c | 4 | ||||
-rwxr-xr-x | tools/perf/tests/shell/amd-ibs-swfilt.sh | 51 | ||||
-rwxr-xr-x | tools/perf/tests/shell/record_lbr.sh | 26 | ||||
-rwxr-xr-x | tools/perf/tests/shell/stat+event_uniquifying.sh | 109 | ||||
-rwxr-xr-x | tools/perf/tests/shell/trace_btf_enum.sh | 11 | ||||
-rw-r--r-- | tools/perf/util/arm-spe.c | 6 | ||||
-rw-r--r-- | tools/perf/util/bpf-filter.c | 8 | ||||
-rw-r--r-- | tools/perf/util/bpf_counter.c | 26 | ||||
-rw-r--r-- | tools/perf/util/bpf_counter_cgroup.c | 3 | ||||
-rw-r--r-- | tools/perf/util/bpf_skel/kwork_top.bpf.c | 2 | ||||
-rw-r--r-- | tools/perf/util/build-id.c | 7 | ||||
-rw-r--r-- | tools/perf/util/disasm.c | 7 | ||||
-rw-r--r-- | tools/perf/util/drm_pmu.c | 4 | ||||
-rw-r--r-- | tools/perf/util/evsel.c | 42 | ||||
-rw-r--r-- | tools/perf/util/lzma.c | 2 | ||||
-rw-r--r-- | tools/perf/util/parse-events.c | 116 | ||||
-rw-r--r-- | tools/perf/util/session.c | 2 | ||||
-rw-r--r-- | tools/perf/util/setup.py | 5 | ||||
-rw-r--r-- | tools/perf/util/zlib.c | 2 |
23 files changed, 262 insertions, 189 deletions
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e2150acc2c13..f561025d4085 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -941,7 +941,7 @@ $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o ifndef NO_JVMTI LIBJVMTI_IN := $(OUTPUT)jvmti/jvmti-in.o -$(LIBJVMTI_IN): FORCE +$(LIBJVMTI_IN): prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti $(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index fe737b3ac6e6..25c41b89f8ab 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4440,7 +4440,7 @@ create_maps: if (trace->summary_mode == SUMMARY__BY_TOTAL && !trace->summary_bpf) { trace->syscall_stats = alloc_syscall_stats(); - if (trace->syscall_stats == NULL) + if (IS_ERR(trace->syscall_stats)) goto out_delete_evlist; } @@ -4748,7 +4748,7 @@ static int trace__replay(struct trace *trace) if (trace->summary_mode == SUMMARY__BY_TOTAL) { trace->syscall_stats = alloc_syscall_stats(); - if (trace->syscall_stats == NULL) + if (IS_ERR(trace->syscall_stats)) goto out; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 3cb40965549f..e004178472d9 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -2,9 +2,7 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H -#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 4096 -#endif enum perf_affinity { PERF_AFFINITY_SYS = 0, diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json index 5228f94a793f..6817cac149e0 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -113,7 +113,7 @@ { "MetricName": "load_store_spec_rate", "MetricExpr": "LDST_SPEC / INST_SPEC", - "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "100percent of operations" }, @@ -132,7 +132,7 @@ { "MetricName": "pc_write_spec_rate", "MetricExpr": "PC_WRITE_SPEC / INST_SPEC", - "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "100percent of operations" }, @@ -195,14 +195,14 @@ { "MetricName": "stall_frontend_cache_rate", "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and cache miss", "MetricGroup": "Stall", "ScaleUnit": "100percent of cycles" }, { "MetricName": "stall_frontend_tlb_rate", "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and TLB miss", "MetricGroup": "Stall", "ScaleUnit": "100percent of cycles" }, @@ -391,7 +391,7 @@ "ScaleUnit": "100percent of cache acceses" }, { - "MetricName": "l1d_cache_access_prefetces", + "MetricName": "l1d_cache_access_prefetches", "MetricExpr": "L1D_CACHE_PRFM / L1D_CACHE", "BriefDescription": "L1D cache access - prefetch", "MetricGroup": "Cache", diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0b3c37e66871..8c79b5166a05 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -115,6 +115,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest if (err < 0) { pr_debug("sched__get_first_possible_cpu: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + evlist__cancel_workload(evlist); goto out_delete_evlist; } @@ -126,6 +127,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) { pr_debug("sched_setaffinity: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + evlist__cancel_workload(evlist); goto out_delete_evlist; } @@ -137,6 +139,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + evlist__cancel_workload(evlist); goto out_delete_evlist; } @@ -149,6 +152,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest if (err < 0) { pr_debug("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + evlist__cancel_workload(evlist); goto out_delete_evlist; } diff --git a/tools/perf/tests/shell/amd-ibs-swfilt.sh b/tools/perf/tests/shell/amd-ibs-swfilt.sh index 7045ec72ba4c..e7f66df05c4b 100755 --- a/tools/perf/tests/shell/amd-ibs-swfilt.sh +++ b/tools/perf/tests/shell/amd-ibs-swfilt.sh @@ -1,6 +1,10 @@ #!/bin/bash # AMD IBS software filtering +ParanoidAndNotRoot() { + [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ] +} + echo "check availability of IBS swfilt" # check if IBS PMU is available @@ -16,6 +20,7 @@ if [ ! -f /sys/bus/event_source/devices/ibs_op/format/swfilt ]; then fi echo "run perf record with modifier and swfilt" +err=0 # setting any modifiers should fail perf record -B -e ibs_op//u -o /dev/null true 2> /dev/null @@ -31,11 +36,17 @@ if [ $? -ne 0 ]; then 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 +if ! ParanoidAndNotRoot 1 +then + # 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 +else + echo "[SKIP] not root and perf_event_paranoid too high for exclude_user" + err=2 fi # check ibs_fetch PMU as well @@ -46,10 +57,16 @@ if [ $? -ne 0 ]; then 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 +if ! ParanoidAndNotRoot 0 +then + 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 +else + echo "[SKIP] not root and perf_event_paranoid too high for system-wide/exclude_user" + err=2 fi echo "check number of samples with swfilt" @@ -60,8 +77,16 @@ if [ ${kernel_sample} -ne 0 ]; then exit 1 fi -user_sample=$(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: " ${user_sample} - exit 1 +if ! ParanoidAndNotRoot 1 +then + user_sample=$(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 +else + echo "[SKIP] not root and perf_event_paranoid too high for exclude_user" + err=2 fi + +exit $err diff --git a/tools/perf/tests/shell/record_lbr.sh b/tools/perf/tests/shell/record_lbr.sh index 6fcb5e52b9b4..78a02e90ece1 100755 --- a/tools/perf/tests/shell/record_lbr.sh +++ b/tools/perf/tests/shell/record_lbr.sh @@ -4,6 +4,10 @@ set -e +ParanoidAndNotRoot() { + [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ] +} + if [ ! -f /sys/bus/event_source/devices/cpu/caps/branches ] && [ ! -f /sys/bus/event_source/devices/cpu_core/caps/branches ] then @@ -23,6 +27,7 @@ cleanup() { } trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" cleanup exit 1 } @@ -123,8 +128,11 @@ lbr_test "-j ind_call" "any indirect call" 2 lbr_test "-j ind_jmp" "any indirect jump" 100 lbr_test "-j call" "direct calls" 2 lbr_test "-j ind_call,u" "any indirect user call" 100 -lbr_test "-a -b" "system wide any branch" 2 -lbr_test "-a -j any_call" "system wide any call" 2 +if ! ParanoidAndNotRoot 1 +then + lbr_test "-a -b" "system wide any branch" 2 + lbr_test "-a -j any_call" "system wide any call" 2 +fi # Parallel parallel_lbr_test "-b" "parallel any branch" 100 & @@ -141,10 +149,16 @@ parallel_lbr_test "-j call" "parallel direct calls" 100 & pid6=$! parallel_lbr_test "-j ind_call,u" "parallel any indirect user call" 100 & pid7=$! -parallel_lbr_test "-a -b" "parallel system wide any branch" 100 & -pid8=$! -parallel_lbr_test "-a -j any_call" "parallel system wide any call" 100 & -pid9=$! +if ParanoidAndNotRoot 1 +then + pid8= + pid9= +else + parallel_lbr_test "-a -b" "parallel system wide any branch" 100 & + pid8=$! + parallel_lbr_test "-a -j any_call" "parallel system wide any call" 100 & + pid9=$! +fi for pid in $pid1 $pid2 $pid3 $pid4 $pid5 $pid6 $pid7 $pid8 $pid9 do diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh index bf54bd6c3e2e..b5dec6b6da36 100755 --- a/tools/perf/tests/shell/stat+event_uniquifying.sh +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh @@ -4,74 +4,63 @@ set -e -stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX) -perf_tool=perf err=0 +stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX) -test_event_uniquifying() { - # We use `clockticks` in `uncore_imc` to verify the uniquify behavior. - pmu="uncore_imc" - 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] - # - # ... - # - # $perf stat -e clockticks -A -- true - # - # Performance counter stats for 'system wide': - # - # CPU0 3,773,018 uncore_imc_0/clockticks/ - # CPU0 3,609,025 uncore_imc_1/clockticks/ - # CPU0 0 uncore_imc_2/clockticks/ - # CPU0 3,230,009 uncore_imc_3/clockticks/ - # CPU0 3,049,897 uncore_imc_4/clockticks/ - # CPU0 0 uncore_imc_5/clockticks/ - # - # 0.002029828 seconds time elapsed - - echo "stat event uniquifying test" - uniquified_event_array=() +cleanup() { + rm -f "${stat_output}" - # Skip if the machine does not have `uncore_imc` device. - if ! ${perf_tool} list pmu | grep -q ${pmu}; then - echo "Target does not support PMU ${pmu} [Skipped]" - err=2 - return - fi + trap - EXIT TERM INT +} - # Check how many uniquified events. - while IFS= read -r line; do - uniquified_event=$(echo "$line" | awk '{print $1}') - uniquified_event_array+=("${uniquified_event}") - done < <(${perf_tool} list -v ${event} | grep ${pmu}) +trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT - perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true" - $perf_command +test_event_uniquifying() { + echo "Uniquification of PMU sysfs events test" - # Check the output contains all uniquified events. - for uniquified_event in "${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 + # Read events from perf list with and without -v. With -v the duplicate PMUs + # aren't deduplicated. Note, json events are listed by perf list without a + # PMU. + read -ra pmu_events <<< "$(perf list --raw pmu)" + read -ra pmu_v_events <<< "$(perf list -v --raw pmu)" + # For all non-deduplicated events. + for pmu_v_event in "${pmu_v_events[@]}"; do + # If the event matches an event in the deduplicated events then it musn't + # be an event with duplicate PMUs, continue the outer loop. + for pmu_event in "${pmu_events[@]}"; do + if [[ "$pmu_v_event" == "$pmu_event" ]]; then + continue 2 + fi + done + # Strip the suffix from the non-deduplicated event's PMU. + event=$(echo "$pmu_v_event" | sed -E 's/_[0-9]+//') + for pmu_event in "${pmu_events[@]}"; do + if [[ "$event" == "$pmu_event" ]]; then + echo "Testing event ${event} is uniquified to ${pmu_v_event}" + if ! perf stat -e "$event" -A -o ${stat_output} -- true; then + echo "Error running perf stat for event '$event' [Skip]" + if [ $err = 0 ]; then + err=2 + fi + continue + fi + # Ensure the non-deduplicated event appears in the output. + if ! grep -q "${pmu_v_event}" "${stat_output}"; then + echo "Uniquification of PMU sysfs events test [Failed]" + cat "${stat_output}" + err=1 + fi + break + fi + done done } test_event_uniquifying -rm -f "${stat_output}" +cleanup exit $err diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 572001d75d78..03e9f680a4a6 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -23,6 +23,14 @@ check_vmlinux() { fi } +check_permissions() { + if perf trace -e $syscall $TESTPROG 2>&1 | grep -q "Operation not permitted" + then + echo "trace+enum test [Skipped permissions]" + err=2 + fi +} + trace_landlock() { echo "Tracing syscall ${syscall}" @@ -56,6 +64,9 @@ trace_non_syscall() { } check_vmlinux +if [ $err = 0 ]; then + check_permissions +fi if [ $err = 0 ]; then trace_landlock diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 8942fa598a84..3086dad92965 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -670,8 +670,8 @@ static void arm_spe__synth_data_source_common(const struct arm_spe_record *recor * socket */ case ARM_SPE_COMMON_DS_REMOTE: - data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1; - data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE; + data_src->mem_lvl = PERF_MEM_LVL_NA; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA; data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; break; @@ -839,7 +839,7 @@ static void arm_spe__synth_memory_level(const struct arm_spe_record *record, } if (record->type & ARM_SPE_REMOTE_ACCESS) - data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1; + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; } static bool arm_spe__synth_ds(struct arm_spe_queue *speq, diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index a0b11f35395f..92308c38fbb5 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -443,6 +443,10 @@ err: return -1; } +#define LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target) { int i, x, y, fd, ret; @@ -451,8 +455,12 @@ int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target) struct bpf_link *link; struct perf_bpf_filter_entry *entry; bool needs_idx_hash = !target__has_cpu(target); +#if LIBBPF_CURRENT_VERSION_GEQ(1, 7) DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts, .dont_enable = true); +#else + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); +#endif entry = calloc(MAX_FILTERS, sizeof(*entry)); if (entry == NULL) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 73fcafbffc6a..ed88ba570c80 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -278,6 +278,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx { struct bpf_prog_profiler_bpf *skel; struct bpf_counter *counter; + int cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx).cpu; int ret; list_for_each_entry(counter, &evsel->bpf_counter_list, list) { @@ -285,7 +286,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx assert(skel != NULL); ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu_map_idx, &fd, BPF_ANY); + &cpu, &fd, BPF_ANY); if (ret) return ret; } @@ -393,7 +394,6 @@ static int bperf_check_target(struct evsel *evsel, return 0; } -static struct perf_cpu_map *all_cpu_map; static __u32 filter_entry_cnt; static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, @@ -437,7 +437,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, * following evsel__open_per_cpu call */ evsel->leader_skel = skel; - evsel__open_per_cpu(evsel, all_cpu_map, -1); + evsel__open(evsel, evsel->core.cpus, evsel->core.threads); out: bperf_leader_bpf__destroy(skel); @@ -475,12 +475,6 @@ static int bperf__load(struct evsel *evsel, struct target *target) if (bperf_check_target(evsel, target, &filter_type, &filter_entry_cnt)) return -1; - if (!all_cpu_map) { - all_cpu_map = perf_cpu_map__new_online_cpus(); - if (!all_cpu_map) - return -1; - } - evsel->bperf_leader_prog_fd = -1; evsel->bperf_leader_link_fd = -1; @@ -598,9 +592,10 @@ out: static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bperf_leader_bpf *skel = evsel->leader_skel; + int cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx).cpu; return bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu_map_idx, &fd, BPF_ANY); + &cpu, &fd, BPF_ANY); } /* @@ -609,13 +604,12 @@ static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) */ static int bperf_sync_counters(struct evsel *evsel) { - int num_cpu, i, cpu; + struct perf_cpu cpu; + int idx; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) + bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu.cpu); - num_cpu = perf_cpu_map__nr(all_cpu_map); - for (i = 0; i < num_cpu; i++) { - cpu = perf_cpu_map__cpu(all_cpu_map, i).cpu; - bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); - } return 0; } diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 6ff42619de12..883ce8a670bc 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -185,7 +185,8 @@ static int bperf_cgrp__load(struct evsel *evsel, } static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused, - int cpu __maybe_unused, int fd __maybe_unused) + int cpu_map_idx __maybe_unused, + int fd __maybe_unused) { /* nothing to do */ return 0; diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c index 73e32e063030..6673386302e2 100644 --- a/tools/perf/util/bpf_skel/kwork_top.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c @@ -18,9 +18,7 @@ enum kwork_class_type { }; #define MAX_ENTRIES 102400 -#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 4096 -#endif #define PF_KTHREAD 0x00200000 #define MAX_COMMAND_LEN 16 diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index bf7f3268b9a2..35505a1ffd11 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -86,6 +86,13 @@ int build_id__snprintf(const struct build_id *build_id, char *bf, size_t bf_size { size_t offs = 0; + if (build_id->size == 0) { + /* Ensure bf is always \0 terminated. */ + if (bf_size > 0) + bf[0] = '\0'; + return 0; + } + for (size_t i = 0; i < build_id->size && offs < bf_size; ++i) offs += snprintf(bf + offs, bf_size - offs, "%02x", build_id->data[i]); diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index b1e4919d016f..e257bd918c89 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -390,13 +390,16 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * skip over possible up to 2 operands to get to address, e.g.: * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> */ - if (c++ != NULL) { + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); c = validate_comma(c, ops); - if (c++ != NULL) + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); + } } } else { ops->target.addr = strtoull(ops->raw, NULL, 16); diff --git a/tools/perf/util/drm_pmu.c b/tools/perf/util/drm_pmu.c index 988890f37ba7..98d4d2b556d4 100644 --- a/tools/perf/util/drm_pmu.c +++ b/tools/perf/util/drm_pmu.c @@ -458,8 +458,10 @@ static int for_each_drm_fdinfo_in_dir(int (*cb)(void *args, int fdinfo_dir_fd, c } ret = cb(args, fdinfo_dir_fd, fd_entry->d_name); if (ret) - return ret; + goto close_fdinfo; } + +close_fdinfo: if (fdinfo_dir_fd != -1) close(fdinfo_dir_fd); closedir(fd_dir); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d264c143b592..5df59812b80c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -3562,7 +3562,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, /* If event has exclude user then don't exclude kernel. */ if (evsel->core.attr.exclude_user) - return false; + goto no_fallback; /* Is there already the separator in the name. */ if (strchr(name, '/') || @@ -3570,7 +3570,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%su", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; @@ -3593,17 +3593,19 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%sH", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; /* Apple M1 requires exclude_guest */ - scnprintf(msg, msgsize, "trying to fall back to excluding guest samples"); + scnprintf(msg, msgsize, "Trying to fall back to excluding guest samples"); evsel->core.attr.exclude_guest = 1; return true; } - +no_fallback: + scnprintf(msg, msgsize, "No fallback found for '%s' for error %d", + evsel__name(evsel), err); return false; } @@ -3935,6 +3937,8 @@ bool evsel__is_hybrid(const struct evsel *evsel) struct evsel *evsel__leader(const struct evsel *evsel) { + if (evsel->core.leader == NULL) + return NULL; return container_of(evsel->core.leader, struct evsel, core); } @@ -4048,9 +4052,9 @@ bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_con void evsel__uniquify_counter(struct evsel *counter) { - const char *name, *pmu_name; - char *new_name, *config; - int ret; + const char *name, *pmu_name, *config; + char *new_name; + int len, ret; /* No uniquification necessary. */ if (!counter->needs_uniquify) @@ -4064,15 +4068,23 @@ void evsel__uniquify_counter(struct evsel *counter) counter->uniquified_name = true; name = evsel__name(counter); + config = strchr(name, '/'); pmu_name = counter->pmu->name; - /* Already prefixed by the PMU name. */ - if (!strncmp(name, pmu_name, strlen(pmu_name))) - return; - config = strchr(name, '/'); - if (config) { - int len = config - name; + /* Already prefixed by the PMU name? */ + len = pmu_name_len_no_suffix(pmu_name); + + if (!strncmp(name, pmu_name, len)) { + /* + * If the PMU name is there, then there is no sense in not + * having a slash. Do this for robustness. + */ + if (config == NULL) + config = name - 1; + ret = asprintf(&new_name, "%s/%s", pmu_name, config + 1); + } else if (config) { + len = config - name; if (config[1] == '/') { /* case: event// */ ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2); @@ -4084,7 +4096,7 @@ void evsel__uniquify_counter(struct evsel *counter) config = strchr(name, ':'); if (config) { /* case: event:.. */ - int len = config - name; + len = config - name; ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1); } else { diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index bbcd2ffcf4bd..c355757ed391 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -120,7 +120,7 @@ bool lzma_is_compressed(const char *input) ssize_t rc; if (fd < 0) - return -1; + return false; rc = read(fd, buf, sizeof(buf)); close(fd); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 8282ddf68b98..0026cff4d69e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -126,7 +126,8 @@ static char *get_config_name(const struct parse_events_terms *head_terms) return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME); } -static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head_terms) +static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head_terms, + bool fake_pmu) { struct parse_events_term *term; struct perf_cpu_map *cpus = NULL; @@ -135,24 +136,33 @@ static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head return NULL; list_for_each_entry(term, &head_terms->terms, list) { - if (term->type_term == PARSE_EVENTS__TERM_TYPE_CPU) { - struct perf_cpu_map *term_cpus; + struct perf_cpu_map *term_cpus; - if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { - term_cpus = perf_cpu_map__new_int(term->val.num); + if (term->type_term != PARSE_EVENTS__TERM_TYPE_CPU) + continue; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + term_cpus = perf_cpu_map__new_int(term->val.num); + } else { + struct perf_pmu *pmu = perf_pmus__find(term->val.str); + + if (pmu) { + term_cpus = pmu->is_core && perf_cpu_map__is_empty(pmu->cpus) + ? cpu_map__online() + : perf_cpu_map__get(pmu->cpus); } else { - struct perf_pmu *pmu = perf_pmus__find(term->val.str); - - if (pmu && perf_cpu_map__is_empty(pmu->cpus)) - term_cpus = pmu->is_core ? cpu_map__online() : NULL; - else if (pmu) - term_cpus = perf_cpu_map__get(pmu->cpus); - else - term_cpus = perf_cpu_map__new(term->val.str); + term_cpus = perf_cpu_map__new(term->val.str); + if (!term_cpus && fake_pmu) { + /* + * Assume the PMU string makes sense on a different + * machine and fake a value with all online CPUs. + */ + term_cpus = cpu_map__online(); + } } - perf_cpu_map__merge(&cpus, term_cpus); - perf_cpu_map__put(term_cpus); } + perf_cpu_map__merge(&cpus, term_cpus); + perf_cpu_map__put(term_cpus); } return cpus; @@ -369,13 +379,13 @@ static int parse_aliases(const char *str, const char *const names[][EVSEL__MAX_A typedef int config_term_func_t(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err); + struct parse_events_state *parse_state); static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err); + struct parse_events_state *parse_state); static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, - struct parse_events_error *err, + struct parse_events_state *parse_state, config_term_func_t config_term); /** @@ -471,7 +481,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, bool found_supported = false; const char *config_name = get_config_name(parsed_terms); const char *metric_id = get_config_metric_id(parsed_terms); - struct perf_cpu_map *cpus = get_config_cpu(parsed_terms); + struct perf_cpu_map *cpus = get_config_cpu(parsed_terms, parse_state->fake_pmu); int ret = 0; struct evsel *first_wildcard_match = NULL; @@ -514,8 +524,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, found_supported = true; if (parsed_terms) { - if (config_attr(&attr, parsed_terms, parse_state->error, - config_term_common)) { + if (config_attr(&attr, parsed_terms, parse_state, config_term_common)) { ret = -EINVAL; goto out_err; } @@ -767,8 +776,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state, attr.sample_period = 1; if (head_config) { - if (config_attr(&attr, head_config, parse_state->error, - config_term_common)) + if (config_attr(&attr, head_config, parse_state, config_term_common)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) @@ -903,12 +911,12 @@ void parse_events__shrink_config_terms(void) static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err) + struct parse_events_state *parse_state) { -#define CHECK_TYPE_VAL(type) \ -do { \ - if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \ - return -EINVAL; \ +#define CHECK_TYPE_VAL(type) \ +do { \ + if (check_type_val(term, parse_state->error, PARSE_EVENTS__TERM_TYPE_ ## type)) \ + return -EINVAL; \ } while (0) switch (term->type_term) { @@ -939,7 +947,7 @@ do { \ if (strcmp(term->val.str, "no") && parse_branch_str(term->val.str, &attr->branch_sample_type)) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("invalid branch sample type"), NULL); return -EINVAL; @@ -948,7 +956,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); if (term->val.num > 1) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -990,7 +998,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_PERCORE: CHECK_TYPE_VAL(NUM); if ((unsigned int)term->val.num > 1) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -1005,7 +1013,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("too big"), NULL); return -EINVAL; @@ -1016,7 +1024,7 @@ do { \ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { if (term->val.num >= (u64)cpu__max_present_cpu().cpu) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("too big"), /*help=*/NULL); return -EINVAL; @@ -1028,8 +1036,8 @@ do { \ break; map = perf_cpu_map__new(term->val.str); - if (!map) { - parse_events_error__handle(err, term->err_val, + if (!map && !parse_state->fake_pmu) { + parse_events_error__handle(parse_state->error, term->err_val, strdup("not a valid PMU or CPU number"), /*help=*/NULL); return -EINVAL; @@ -1042,7 +1050,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, strdup(parse_events__term_type_str(term->type_term)), parse_events_formats_error_string(NULL)); return -EINVAL; @@ -1057,7 +1065,7 @@ do { \ * if an invalid config term is provided for legacy events * (for example, instructions/badterm/...), which is confusing. */ - if (!config_term_avail(term->type_term, err)) + if (!config_term_avail(term->type_term, parse_state->error)) return -EINVAL; return 0; #undef CHECK_TYPE_VAL @@ -1065,7 +1073,7 @@ do { \ static int config_term_pmu(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err) + struct parse_events_state *parse_state) { if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) { struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); @@ -1074,7 +1082,7 @@ static int config_term_pmu(struct perf_event_attr *attr, char *err_str; if (asprintf(&err_str, "Failed to find PMU for type %d", attr->type) >= 0) - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, err_str, /*help=*/NULL); return -EINVAL; } @@ -1100,7 +1108,7 @@ static int config_term_pmu(struct perf_event_attr *attr, char *err_str; if (asprintf(&err_str, "Failed to find PMU for type %d", attr->type) >= 0) - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, err_str, /*help=*/NULL); return -EINVAL; } @@ -1128,12 +1136,12 @@ static int config_term_pmu(struct perf_event_attr *attr, */ return 0; } - return config_term_common(attr, term, err); + return config_term_common(attr, term, parse_state); } static int config_term_tracepoint(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err) + struct parse_events_state *parse_state) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: @@ -1147,7 +1155,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - return config_term_common(attr, term, err); + return config_term_common(attr, term, parse_state); case PARSE_EVENTS__TERM_TYPE_USER: case PARSE_EVENTS__TERM_TYPE_CONFIG: case PARSE_EVENTS__TERM_TYPE_CONFIG1: @@ -1166,12 +1174,10 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_HARDWARE: case PARSE_EVENTS__TERM_TYPE_CPU: default: - if (err) { - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, strdup(parse_events__term_type_str(term->type_term)), strdup("valid terms: call-graph,stack-size\n") ); - } return -EINVAL; } @@ -1180,13 +1186,13 @@ static int config_term_tracepoint(struct perf_event_attr *attr, static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, - struct parse_events_error *err, + struct parse_events_state *parse_state, config_term_func_t config_term) { struct parse_events_term *term; list_for_each_entry(term, &head->terms, list) - if (config_term(attr, term, err)) + if (config_term(attr, term, parse_state)) return -EINVAL; return 0; @@ -1378,8 +1384,7 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, if (head_config) { struct perf_event_attr attr; - if (config_attr(&attr, head_config, err, - config_term_tracepoint)) + if (config_attr(&attr, head_config, parse_state, config_term_tracepoint)) return -EINVAL; } @@ -1408,8 +1413,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state, } if (head_config) { - if (config_attr(&attr, head_config, parse_state->error, - config_term_common)) + if (config_attr(&attr, head_config, parse_state, config_term_common)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) @@ -1418,7 +1422,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state, name = get_config_name(head_config); metric_id = get_config_metric_id(head_config); - cpus = get_config_cpu(head_config); + cpus = get_config_cpu(head_config, parse_state->fake_pmu); ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name, metric_id, pmu, &config_terms, first_wildcard_match, cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) ? 0 : -ENOMEM; @@ -1531,7 +1535,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, fix_raw(&parsed_terms, pmu); /* Configure attr/terms with a known PMU, this will set hardcoded terms. */ - if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + if (config_attr(&attr, &parsed_terms, parse_state, config_term_pmu)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } @@ -1555,7 +1559,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, /* Configure attr/terms again if an alias was expanded. */ if (alias_rewrote_terms && - config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + config_attr(&attr, &parsed_terms, parse_state, config_term_pmu)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } @@ -1583,7 +1587,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; } - term_cpu = get_config_cpu(&parsed_terms); + term_cpu = get_config_cpu(&parsed_terms, parse_state->fake_pmu); evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, get_config_name(&parsed_terms), get_config_metric_id(&parsed_terms), pmu, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 26ae078278cd..09af486c83e4 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1402,7 +1402,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, const struct perf_tool *tool = session->tool; struct perf_sample sample; int fd = perf_data__fd(session->data); - int err; + s64 err; perf_sample__init(&sample, /*all=*/true); if ((event->header.type != PERF_RECORD_COMPRESSED && diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index dd289d15acfd..9cae2c472f4a 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,6 +1,7 @@ from os import getenv, path from subprocess import Popen, PIPE from re import sub +import shlex cc = getenv("CC") assert cc, "Environment variable CC not set" @@ -22,7 +23,9 @@ assert srctree, "Environment variable srctree, for the Linux sources, not set" src_feature_tests = f'{srctree}/tools/build/feature' def clang_has_option(option): - cc_output = Popen([cc, cc_options + option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + cmd = shlex.split(f"{cc} {cc_options} {option}") + cmd.append(path.join(src_feature_tests, "test-hello.c")) + cc_output = Popen(cmd, stderr=PIPE).stderr.readlines() return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o) or (b"unknown warning option" in o))] == [ ] if cc_is_clang: diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 78d2297c1b67..1f7c06523059 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -88,7 +88,7 @@ bool gzip_is_compressed(const char *input) ssize_t rc; if (fd < 0) - return -1; + return false; rc = read(fd, buf, sizeof(buf)); close(fd); |