From de9f498d2b381de1abf654ca3459c4f01227b5cd Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 8 Feb 2022 22:07:25 +0800 Subject: perf trace: Avoid early exit due SIGCHLD from non-workload processes The function trace__symbols_init() runs "perf-read-vdso32" and that ends up with a SIGCHLD delivered to 'perf'. And this SIGCHLD make perf exit early. 'perf trace' should exit only if the SIGCHLD is from our workload process. So let's use sigaction() instead of signal() to match such condition. Committer notes: Use memset to zero the 'struct sigaction' variable as the '= { 0 }' method isn't accepted in many compiler versions, e.g.: 4 34.02 alpine:3.6 : FAIL clang version 4.0.0 (tags/RELEASE_400/final) builtin-trace.c:4897:35: error: suggest braces around initialization of subobject [-Werror,-Wmissing-braces] struct sigaction sigchld_act = { 0 }; ^ {} builtin-trace.c:4897:37: error: missing field 'sa_mask' initializer [-Werror,-Wmissing-field-initializers] struct sigaction sigchld_act = { 0 }; ^ 2 errors generated. 6 32.60 alpine:3.8 : FAIL gcc version 6.4.0 (Alpine 6.4.0) builtin-trace.c:4897:35: error: suggest braces around initialization of subobject [-Werror,-Wmissing-braces] struct sigaction sigchld_act = { 0 }; ^ {} builtin-trace.c:4897:37: error: missing field 'sa_mask' initializer [-Werror,-Wmissing-field-initializers] struct sigaction sigchld_act = { 0 }; ^ 2 errors generated. 7 34.82 alpine:3.9 : FAIL gcc version 8.3.0 (Alpine 8.3.0) builtin-trace.c:4897:35: error: suggest braces around initialization of subobject [-Werror,-Wmissing-braces] struct sigaction sigchld_act = { 0 }; ^ {} builtin-trace.c:4897:37: error: missing field 'sa_mask' initializer [-Werror,-Wmissing-field-initializers] struct sigaction sigchld_act = { 0 }; ^ 2 errors generated. Signed-off-by: Changbin Du Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220208140725.3947-1-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 32844d8a0ea5..52b137a184a6 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1536,13 +1536,20 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) return fprintf(fp, " ? "); } +static pid_t workload_pid = -1; static bool done = false; static bool interrupted = false; -static void sig_handler(int sig) +static void sighandler_interrupt(int sig __maybe_unused) { - done = true; - interrupted = sig == SIGINT; + done = interrupted = true; +} + +static void sighandler_chld(int sig __maybe_unused, siginfo_t *info, + void *context __maybe_unused) +{ + if (info->si_pid == workload_pid) + done = true; } static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp) @@ -3938,7 +3945,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) bool draining = false; trace->live = true; - signal(SIGCHLD, sig_handler); if (!trace->raw_augmented_syscalls) { if (trace->trace_syscalls && trace__add_syscall_newtp(trace)) @@ -4018,6 +4024,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) fprintf(trace->output, "Couldn't run the workload!\n"); goto out_delete_evlist; } + workload_pid = evlist->workload.pid; } err = evlist__open(evlist); @@ -4887,10 +4894,16 @@ int cmd_trace(int argc, const char **argv) const char * const trace_subcommands[] = { "record", NULL }; int err = -1; char bf[BUFSIZ]; + struct sigaction sigchld_act; signal(SIGSEGV, sighandler_dump_stack); signal(SIGFPE, sighandler_dump_stack); - signal(SIGINT, sig_handler); + signal(SIGINT, sighandler_interrupt); + + memset(&sigchld_act, 0, sizeof(sigchld_act)); + sigchld_act.sa_flags = SA_SIGINFO; + sigchld_act.sa_sigaction = sighandler_chld; + sigaction(SIGCHLD, &sigchld_act, NULL); trace.evlist = evlist__new(); trace.sctbl = syscalltbl__new(); -- cgit v1.3.1 From 0b31ea6613ad1e6b9b84d877c1be18e39934e90a Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 10 Feb 2022 20:06:19 +0000 Subject: perf cs-etm: No-op refactor of synth opt usage sample_branches and sample_instructions are already saved in the synth_opts struct. Other usages like synth_opts.last_branch don't save a value, so make this more consistent by always going through synth_opts and not saving duplicate values. Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20220210200620.1227232-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 4f672f7d008c..796a065a500e 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -50,8 +50,6 @@ struct cs_etm_auxtrace { u8 timeless_decoding; u8 snapshot_mode; u8 data_queued; - u8 sample_branches; - u8 sample_instructions; int num_cpu; u64 latest_kernel_timestamp; @@ -410,8 +408,8 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm, { struct cs_etm_packet *tmp; - if (etm->sample_branches || etm->synth_opts.last_branch || - etm->sample_instructions) { + if (etm->synth_opts.branches || etm->synth_opts.last_branch || + etm->synth_opts.instructions) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1365,7 +1363,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, err = cs_etm__synth_event(session, &attr, id); if (err) return err; - etm->sample_branches = true; etm->branches_sample_type = attr.sample_type; etm->branches_id = id; id += 1; @@ -1389,7 +1386,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, err = cs_etm__synth_event(session, &attr, id); if (err) return err; - etm->sample_instructions = true; etm->instructions_sample_type = attr.sample_type; etm->instructions_id = id; id += 1; @@ -1420,7 +1416,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, tidq->prev_packet->last_instr_taken_branch) cs_etm__update_last_branch_rb(etmq, tidq); - if (etm->sample_instructions && + if (etm->synth_opts.instructions && tidq->period_instructions >= etm->instructions_sample_period) { /* * Emit instruction sample periodically @@ -1503,7 +1499,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, } } - if (etm->sample_branches) { + if (etm->synth_opts.branches) { bool generate_sample = false; /* Generate sample for tracing on packet */ @@ -1582,7 +1578,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, } - if (etm->sample_branches && + if (etm->synth_opts.branches && tidq->prev_packet->sample_type == CS_ETM_RANGE) { err = cs_etm__synth_branch_sample(etmq, tidq); if (err) -- cgit v1.3.1 From 9de0736973dd7f0f710d0f5e0a3dfd9fa9ffeb3f Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 10 Feb 2022 20:06:20 +0000 Subject: perf cs-etm: Fix corrupt inject files when only last branch option is enabled 'perf inject' with Coresight data generates files that cannot be opened when only the last branch option is specified: perf inject -i perf.data --itrace=l -o inject.data perf script -i inject.data 0x33faa8 [0x8]: failed to process type: 9 [Bad address] This is because cs_etm__synth_instruction_sample() is called even when the sample type for instructions hasn't been setup. Last branch records are attached to instruction samples so it doesn't make sense to generate them when --itrace=i isn't specified anyway. This change disables all calls of cs_etm__synth_instruction_sample() unless --itrace=i is specified, resulting in a file with no samples if only --itrace=l is provided, rather than a bad file. Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20220210200620.1227232-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 796a065a500e..8b95fb3c4d7b 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1553,6 +1553,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, goto swap_packet; if (etmq->etm->synth_opts.last_branch && + etmq->etm->synth_opts.instructions && tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr; @@ -1610,6 +1611,7 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq, * the trace. */ if (etmq->etm->synth_opts.last_branch && + etmq->etm->synth_opts.instructions && tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr; -- cgit v1.3.1 From 047e6032c4f054372311eb20c759cfe0b3ca7ffe Mon Sep 17 00:00:00 2001 From: German Gomez Date: Tue, 25 Jan 2022 10:44:34 +0000 Subject: perf test: Fix arm64 perf_event_attr tests wrt --call-graph initialization The struct perf_event_attr is initialised differently in Arm64 when recording in call-graph fp mode, so update the relevant tests, and add two extra arm64-only tests. Before: $ perf test 17 -v 17: Setup struct perf_event_attr [...] running './tests/attr/test-record-graph-default' expected sample_type=295, got 4391 expected sample_regs_user=0, got 1073741824 FAILED './tests/attr/test-record-graph-default' - match failure test child finished with -1 ---- end ---- After: [...] running './tests/attr/test-record-graph-default-aarch64' test limitation 'aarch64' running './tests/attr/test-record-graph-fp-aarch64' test limitation 'aarch64' running './tests/attr/test-record-graph-default' test limitation '!aarch64' excluded architecture list ['aarch64'] skipped [aarch64] './tests/attr/test-record-graph-default' running './tests/attr/test-record-graph-fp' test limitation '!aarch64' excluded architecture list ['aarch64'] skipped [aarch64] './tests/attr/test-record-graph-fp' [...] Fixes: 7248e308a5758761 ("perf tools: Record ARM64 LR register automatically") Signed-off-by: German Gomez Cc: Alexander Shishkin Cc: Alexandre Truong Cc: Ian Rogers Cc: James Clark Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Song Liu Cc: Yonghong Song Link: http://lore.kernel.org/lkml/20220125104435.2737-1-german.gomez@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/README | 2 ++ tools/perf/tests/attr/test-record-graph-default | 2 ++ tools/perf/tests/attr/test-record-graph-default-aarch64 | 9 +++++++++ tools/perf/tests/attr/test-record-graph-fp | 2 ++ tools/perf/tests/attr/test-record-graph-fp-aarch64 | 9 +++++++++ 5 files changed, 24 insertions(+) create mode 100644 tools/perf/tests/attr/test-record-graph-default-aarch64 create mode 100644 tools/perf/tests/attr/test-record-graph-fp-aarch64 (limited to 'tools/perf') diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index a36f49fb4dbe..1116fc6bf2ac 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -45,8 +45,10 @@ Following tests are defined (with perf commands): perf record -d kill (test-record-data) perf record -F 100 kill (test-record-freq) perf record -g kill (test-record-graph-default) + perf record -g kill (test-record-graph-default-aarch64) perf record --call-graph dwarf kill (test-record-graph-dwarf) perf record --call-graph fp kill (test-record-graph-fp) + perf record --call-graph fp kill (test-record-graph-fp-aarch64) perf record --group -e cycles,instructions kill (test-record-group) perf record -e '{cycles,instructions}' kill (test-record-group1) perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2) diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default index 5d8234d50845..f0a18b4ea4f5 100644 --- a/tools/perf/tests/attr/test-record-graph-default +++ b/tools/perf/tests/attr/test-record-graph-default @@ -2,6 +2,8 @@ command = record args = --no-bpf-event -g kill >/dev/null 2>&1 ret = 1 +# arm64 enables registers in the default mode (fp) +arch = !aarch64 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-default-aarch64 b/tools/perf/tests/attr/test-record-graph-default-aarch64 new file mode 100644 index 000000000000..e98d62efb6f7 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-default-aarch64 @@ -0,0 +1,9 @@ +[config] +command = record +args = --no-bpf-event -g kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event:base-record] +sample_type=4391 +sample_regs_user=1073741824 diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp index 5630521c0b0f..a6e60e839205 100644 --- a/tools/perf/tests/attr/test-record-graph-fp +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -2,6 +2,8 @@ command = record args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1 ret = 1 +# arm64 enables registers in fp mode +arch = !aarch64 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-fp-aarch64 b/tools/perf/tests/attr/test-record-graph-fp-aarch64 new file mode 100644 index 000000000000..cbeea9971285 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-fp-aarch64 @@ -0,0 +1,9 @@ +[config] +command = record +args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event:base-record] +sample_type=4391 +sample_regs_user=1073741824 -- cgit v1.3.1 From 31ded1535e3182778a1d0e5c32711f55da3bc512 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 16 Feb 2022 16:01:00 -0300 Subject: perf bpf: Defer freeing string after possible strlen() on it This was detected by the gcc in Fedora Rawhide's gcc: 50 11.01 fedora:rawhide : FAIL gcc version 12.0.1 20220205 (Red Hat 12.0.1-0) (GCC) inlined from 'bpf__config_obj' at util/bpf-loader.c:1242:9: util/bpf-loader.c:1225:34: error: pointer 'map_opt' may be used after 'free' [-Werror=use-after-free] 1225 | *key_scan_pos += strlen(map_opt); | ^~~~~~~~~~~~~~~ util/bpf-loader.c:1223:9: note: call to 'free' here 1223 | free(map_name); | ^~~~~~~~~~~~~~ cc1: all warnings being treated as errors So do the calculations on the pointer before freeing it. Fixes: 04f9bf2bac72480c ("perf bpf-loader: Add missing '*' for key_scan_pos") Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang ShaoBo Link: https://lore.kernel.org/lkml/Yg1VtQxKrPpS3uNA@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-loader.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 7ecfaac7536a..16ec605a9fe4 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1220,9 +1220,10 @@ bpf__obj_config_map(struct bpf_object *obj, pr_debug("ERROR: Invalid map config option '%s'\n", map_opt); err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT; out: - free(map_name); if (!err) *key_scan_pos += strlen(map_opt); + + free(map_name); return err; } -- cgit v1.3.1 From f268088f65af69aa6ae1fb65e696cbb6478bcc9a Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 18 Feb 2022 17:33:33 +0800 Subject: perf test: Skip failing sigtrap test for arm+aarch64 Skip the Sigtrap test for arm + arm64, same as was done for s390 in commit a840974e96fd ("perf test: Test 73 Sig_trap fails on s390"). For this, reuse BP_SIGNAL_IS_SUPPORTED - meaning that the arch can use BP to generate signals - instead of BP_ACCOUNT_IS_SUPPORTED, which is appropriate. As described by Will at [0], in the test we get stuck in a loop of handling the HW breakpoint exception and never making progress. GDB handles this by stepping over the faulting instruction, but with perf the kernel is expected to handle the step (which it doesn't for arm). Dmitry made an attempt to get this work, also mentioned in the same thread as [0], which was appreciated. But the best thing to do is skip the test for now. [0] https://lore.kernel.org/linux-perf-users/20220118124343.GC98966@leoy-ThinkPad-X240s/T/#m13b06c39d2a5100d340f009435df6f4d8ee57b5a Fixes: 5504f67944484495 ("perf test sigtrap: Add basic stress test for sigtrap handling") Signed-off-by: John Garry Tested-by: Leo Yan Acked-by: Marco Elver Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Marco Elver Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux@armlinux.org.uk Link: https://lore.kernel.org/r/1645176813-202756-1-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/sigtrap.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index 1f147fe6595f..e32ece90e164 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -22,19 +22,6 @@ #include "tests.h" #include "../perf-sys.h" -/* - * PowerPC and S390 do not support creation of instruction breakpoints using the - * perf_event interface. - * - * Just disable the test for these architectures until these issues are - * resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) -#define BP_ACCOUNT_IS_SUPPORTED 0 -#else -#define BP_ACCOUNT_IS_SUPPORTED 1 -#endif - #define NUM_THREADS 5 static struct { @@ -135,7 +122,7 @@ static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __m char sbuf[STRERR_BUFSIZE]; int i, fd, ret = TEST_FAIL; - if (!BP_ACCOUNT_IS_SUPPORTED) { + if (!BP_SIGNAL_IS_SUPPORTED) { pr_debug("Test not supported on this architecture"); return TEST_SKIP; } -- cgit v1.3.1 From 8a3d2ee0de3828e0d01f9682d35ee53704659bd0 Mon Sep 17 00:00:00 2001 From: Zhengjun Xing Date: Fri, 18 Feb 2022 17:31:27 +0800 Subject: perf evlist: Fix failed to use cpu list for uncore events The 'perf record' and 'perf stat' commands have supported the option '-C/--cpus' to count or collect only on the list of CPUs provided. Commit 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for hybrid") add it to be supported for hybrid. For hybrid support, it checks the cpu list are available on hybrid PMU. But when we test only uncore events(or events not in cpu_core and cpu_atom), there is a bug: Before: # perf stat -C0 -e uncore_clock/clockticks/ sleep 1 failed to use cpu list 0 In this case, for uncore event, its pmu_name is not cpu_core or cpu_atom, so in evlist__fix_hybrid_cpus, perf_pmu__find_hybrid_pmu should return NULL,both events_nr and unmatched_count should be 0 ,then the cpu list check function evlist__fix_hybrid_cpus return -1 and the error "failed to use cpu list 0" will happen. Bypass "events_nr=0" case then the issue is fixed. After: # perf stat -C0 -e uncore_clock/clockticks/ sleep 1 Performance counter stats for 'CPU(s) 0': 195,476,873 uncore_clock/clockticks/ 1.004518677 seconds time elapsed When testing with at least one core event and uncore events, it has no issue. # perf stat -C0 -e cpu_core/cpu-cycles/,uncore_clock/clockticks/ sleep 1 Performance counter stats for 'CPU(s) 0': 5,993,774 cpu_core/cpu-cycles/ 301,025,912 uncore_clock/clockticks/ 1.003964934 seconds time elapsed Fixes: 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for hybrid") Reviewed-by: Kan Liang Signed-off-by: Zhengjun Xing Cc: Adrian Hunter Cc: alexander.shishkin@intel.com Cc: Andi Kleen Cc: Ian Rogers Cc: Jin Yao Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20220218093127.1844241-1-zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist-hybrid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c index 7f234215147d..57f02beef023 100644 --- a/tools/perf/util/evlist-hybrid.c +++ b/tools/perf/util/evlist-hybrid.c @@ -154,8 +154,8 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list) perf_cpu_map__put(matched_cpus); perf_cpu_map__put(unmatched_cpus); } - - ret = (unmatched_count == events_nr) ? -1 : 0; + if (events_nr) + ret = (unmatched_count == events_nr) ? -1 : 0; out: perf_cpu_map__put(cpus); return ret; -- cgit v1.3.1 From 69560e366fc4d5fca7bebb0e44edbfafc8bcaf05 Mon Sep 17 00:00:00 2001 From: Alexey Bayduraev Date: Fri, 18 Feb 2022 18:23:41 +0300 Subject: perf data: Fix double free in perf_session__delete() When perf_data__create_dir() fails, it calls close_dir(), but perf_session__delete() also calls close_dir() and since dir.version and dir.nr were initialized by perf_data__create_dir(), a double free occurs. This patch moves the initialization of dir.version and dir.nr after successful initialization of dir.files, that prevents double freeing. This behavior is already implemented in perf_data__open_dir(). Fixes: 145520631130bd64 ("perf data: Add perf_data__(create_dir|close_dir) functions") Signed-off-by: Alexey Bayduraev Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Antonov Cc: Alexander Shishkin Cc: Alexei Budankov Cc: Andi Kleen Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220218152341.5197-2-alexey.v.bayduraev@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index f5d260b1df4d..15a4547d608e 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -44,10 +44,6 @@ int perf_data__create_dir(struct perf_data *data, int nr) if (!files) return -ENOMEM; - data->dir.version = PERF_DIR_VERSION; - data->dir.files = files; - data->dir.nr = nr; - for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -62,6 +58,9 @@ int perf_data__create_dir(struct perf_data *data, int nr) file->fd = ret; } + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; return 0; out_err: -- cgit v1.3.1 From 13e741b834538a225512912608f0182079fc64e2 Mon Sep 17 00:00:00 2001 From: German Gomez Date: Mon, 21 Feb 2022 17:17:06 +0000 Subject: perf script: Fix error when printing 'weight' field In SPE traces the 'weight' field can't be printed in 'perf script' because the 'dummy:u' event doesn't have the WEIGHT attribute set. Use evsel__do_check_stype(..) to check this field, as it's done with other fields such as "phys_addr". Before: $ perf record -e arm_spe_0// -- sleep 1 $ perf script -F event,ip,weight Samples for 'dummy:u' event do not have WEIGHT attribute set. Cannot print 'weight' field. After: $ perf script -F event,ip,weight l1d-access: 12 ffffaf629d4cb320 tlb-access: 12 ffffaf629d4cb320 memory: 12 ffffaf629d4cb320 Fixes: b0fde9c6e291e528 ("perf arm-spe: Add SPE total latency as PERF_SAMPLE_WEIGHT") Signed-off-by: German Gomez Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/r/20220221171707.62960-1-german.gomez@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index abae8184e171..fa478ddcd18a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -463,7 +463,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set)) return -EINVAL; if (PRINT_FIELD(SYM) && -- cgit v1.3.1 From a7a72631f62445e3671b7cab5ad01f856c1aa90d Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:06:57 +0800 Subject: perf parse-events: Fix NULL check against wrong variable We did a null check after "tmp->symbol = strdup(...)", but we checked "list->symbol" other than "tmp->symbol". Reviewed-by: John Garry Signed-off-by: Weiguo Li Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_DF39269807EC9425E24787E6DB632441A405@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9739b05b999e..dfb50a5f83d0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2193,7 +2193,7 @@ int perf_pmu__test_parse_init(void) for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { tmp->type = symbols[i].type; tmp->symbol = strdup(symbols[i].symbol); - if (!list->symbol) + if (!tmp->symbol) goto err_free; } -- cgit v1.3.1 From 073a15c3512f6b8d36c0c05992cf31e845f4dfe0 Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:07:16 +0800 Subject: perf bench: Fix NULL check against wrong variable We did a NULL check after "epollfdp = calloc(...)", but we checked "epollfd" instead of "epollfdp". Signed-off-by: Weiguo Li Acked-by: Davidlohr Bueso Cc: Alexander Shishkin Cc: Davidlohr Bueso Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_B5D64530EB9C7DBB8D2C88A0C790F1489D0A@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/epoll-ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 740ae764537e..134612bde0cb 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -106,7 +106,7 @@ static void nest_epollfd(void) printinfo("Nesting level(s): %d\n", nested); epollfdp = calloc(nested, sizeof(int)); - if (!epollfd) + if (!epollfdp) err(EXIT_FAILURE, "calloc"); for (i = 0; i < nested; i++) { -- cgit v1.3.1 From 91c9923a473a694eb1c5c01ab778a77114969707 Mon Sep 17 00:00:00 2001 From: Zhengjun Xing Date: Mon, 7 Mar 2022 23:16:27 +0800 Subject: perf parse: Fix event parser error for hybrid systems This bug happened on hybrid systems when both cpu_core and cpu_atom have the same event name such as "UOPS_RETIRED.MS" while their event terms are different, then during perf stat, the event for cpu_atom will parse fail and then no output for cpu_atom. UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ It is because event terms in the "head" of parse_events_multi_pmu_add will be changed to event terms for cpu_core after parsing UOPS_RETIRED.MS for cpu_core, then when parsing the same event for cpu_atom, it still uses the event terms for cpu_core, but event terms for cpu_atom are different with cpu_core, the event parses for cpu_atom will fail. This patch fixes it, the event terms should be parsed from the original event. This patch can work for the hybrid systems that have the same event in more than 2 PMUs. It also can work in non-hybrid systems. Before: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ Control descriptor is not initialized UOPS_RETIRED.MS: 2737845 16068518485 16068518485 Performance counter stats for 'system wide': 2,737,845 cpu_core/UOPS_RETIRED.MS/ 1.002553850 seconds time elapsed After: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ Control descriptor is not initialized UOPS_RETIRED.MS: 1977555 16076950711 16076950711 UOPS_RETIRED.MS: 568684 8038694234 8038694234 Performance counter stats for 'system wide': 1,977,555 cpu_core/UOPS_RETIRED.MS/ 568,684 cpu_atom/UOPS_RETIRED.MS/ 1.004758259 seconds time elapsed Fixes: fb0811535e92c6c1 ("perf parse-events: Allow config on kernel PMU events") Reviewed-by: Kan Liang Signed-off-by: Zhengjun Xing Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220307151627.30049-1-zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index dfb50a5f83d0..24997925ae00 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, { struct parse_events_term *term; struct list_head *list = NULL; + struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; int ok = 0; char *config; @@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } list_add_tail(&term->list, head); - /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) @@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, + pmu->name, orig_head, true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } + parse_events_terms__delete(orig_head); } } } -- cgit v1.3.1