diff options
Diffstat (limited to 'tools/perf')
58 files changed, 419 insertions, 197 deletions
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt index c0a66400a960..9af8b8dfb7b6 100644 --- a/tools/perf/Documentation/perf-evlist.txt +++ b/tools/perf/Documentation/perf-evlist.txt @@ -29,7 +29,7 @@ OPTIONS Show just the sample frequency used for each event. -v:: ---verbose=:: +--verbose:: Show all fields. -g:: diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 1e91121bac0f..6e82b7cc0bf0 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -28,8 +28,8 @@ OPTIONS specified: function_graph or function. -v:: ---verbose=:: - Verbosity level. +--verbose:: + Increase the verbosity level. -F:: --funcs:: diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index f3c620951f6e..c97527df8ecd 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -20,5 +20,5 @@ modules). OPTIONS ------- -v:: ---verbose=:: +--verbose:: Increase verbosity level, showing details about symbol table loading, etc. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index abc9b5d83312..f0da8cf63e9a 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -97,8 +97,8 @@ filter out the startup phase of the program, which is often very different. Filter out events for these pids and for 'trace' itself (comma separated list). -v:: ---verbose=:: - Verbosity level. +--verbose:: + Increase the verbosity level. --no-inherit:: Child tasks do not inherit counters. diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5345ac70cd83..f6e609673de2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -607,7 +607,7 @@ arch_errno_hdr_dir := $(srctree)/tools arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh $(arch_errno_name_array): $(arch_errno_tbl) - $(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@ + $(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@ sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh @@ -1001,14 +1001,6 @@ $(INSTALL_DOC_TARGETS): ### Cleaning rules -# -# This is here, not in Makefile.config, because Makefile.config does -# not get included for the clean target: -# -config-clean: - $(call QUIET_CLEAN, config) - $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null - python-clean: $(python-clean) @@ -1048,7 +1040,7 @@ endif # BUILD_BPF_SKEL bpf-skel-clean: $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean bpf-skel-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index bd446aba64f7..c25c878fd06c 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -156,6 +156,10 @@ out: return err; } +#define ETM_SET_OPT_CTXTID (1 << 0) +#define ETM_SET_OPT_TS (1 << 1) +#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS) + static int cs_etm_set_option(struct auxtrace_record *itr, struct evsel *evsel, u32 option) { @@ -169,17 +173,17 @@ static int cs_etm_set_option(struct auxtrace_record *itr, !cpu_map__has(online_cpus, i)) continue; - if (option & ETM_OPT_CTXTID) { + if (option & ETM_SET_OPT_CTXTID) { err = cs_etm_set_context_id(itr, evsel, i); if (err) goto out; } - if (option & ETM_OPT_TS) { + if (option & ETM_SET_OPT_TS) { err = cs_etm_set_timestamp(itr, evsel, i); if (err) goto out; } - if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS)) + if (option & ~(ETM_SET_OPT_MASK)) /* Nothing else is currently supported */ goto out; } @@ -406,7 +410,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, evsel__set_sample_bit(cs_etm_evsel, CPU); err = cs_etm_set_option(itr, cs_etm_evsel, - ETM_OPT_CTXTID | ETM_OPT_TS); + ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS); if (err) goto out; } diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index f744eb5cba88..0b2480cf3e47 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -9,9 +9,7 @@ # 0 nospu restart_syscall sys_restart_syscall 1 nospu exit sys_exit -2 32 fork ppc_fork sys_fork -2 64 fork sys_fork -2 spu fork sys_ni_syscall +2 nospu fork sys_fork 3 common read sys_read 4 common write sys_write 5 common open sys_open compat_sys_open @@ -160,9 +158,7 @@ 119 32 sigreturn sys_sigreturn compat_sys_sigreturn 119 64 sigreturn sys_ni_syscall 119 spu sigreturn sys_ni_syscall -120 32 clone ppc_clone sys_clone -120 64 clone sys_clone -120 spu clone sys_ni_syscall +120 nospu clone sys_clone 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall @@ -244,9 +240,7 @@ 186 spu sendfile sys_sendfile64 187 common getpmsg sys_ni_syscall 188 common putpmsg sys_ni_syscall -189 32 vfork ppc_vfork sys_vfork -189 64 vfork sys_vfork -189 spu vfork sys_ni_syscall +189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 common readahead sys_readahead compat_sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 @@ -322,9 +316,7 @@ 248 32 clock_nanosleep sys_clock_nanosleep_time32 248 64 clock_nanosleep sys_clock_nanosleep 248 spu clock_nanosleep sys_clock_nanosleep -249 32 swapcontext ppc_swapcontext compat_sys_swapcontext -249 64 swapcontext sys_swapcontext -249 spu swapcontext sys_ni_syscall +249 nospu swapcontext sys_swapcontext compat_sys_swapcontext 250 common tgkill sys_tgkill 251 32 utimes sys_utimes_time32 251 64 utimes sys_utimes @@ -522,12 +514,11 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -435 32 clone3 ppc_clone3 sys_clone3 -435 64 clone3 sys_clone3 -435 spu clone3 sys_ni_syscall +435 nospu clone3 sys_clone3 436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index d443423495e5..3abef2144dac 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr sys_mount_setattr diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 8cc6642fce7a..5a9f9a7bf07d 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -10,10 +10,11 @@ PERF_HAVE_JITDUMP := 1 # Syscall table generation # -out := $(OUTPUT)arch/x86/include/generated/asm -header := $(out)/syscalls_64.c -sys := $(srctree)/tools/perf/arch/x86/entry/syscalls -systbl := $(sys)/syscalltbl.sh +generated := $(OUTPUT)arch/x86/include/generated +out := $(generated)/asm +header := $(out)/syscalls_64.c +sys := $(srctree)/tools/perf/arch/x86/entry/syscalls +systbl := $(sys)/syscalltbl.sh # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') @@ -22,6 +23,6 @@ $(header): $(sys)/syscall_64.tbl $(systbl) $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ clean:: - $(call QUIET_CLEAN, x86) $(RM) $(header) + $(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated) archheaders: $(header) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 78672124d28b..7bf01cbe582f 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 6a54b94f1c25..0e20f3dc69f3 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -10,6 +10,7 @@ int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); int test__intel_pt_pkt_decoder(struct test *test, int subtest); int test__bp_modify(struct test *test, int subtest); +int test__x86_sample_parsing(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 36d4f248b51d..28d793390198 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -3,5 +3,6 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += rdpmc.o +perf-y += sample-parsing.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index bc25d727b4e9..71aa67367ad6 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -31,6 +31,10 @@ struct test arch_tests[] = { }, #endif { + .desc = "x86 Sample parsing", + .func = test__x86_sample_parsing, + }, + { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index f782ef8c5982..4f75ae990140 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> -#include "../../../../arch/x86/include/asm/insn.h" #include <string.h> #include "debug.h" #include "tests/tests.h" #include "arch-tests.h" +#include "../../../../arch/x86/include/asm/insn.h" #include "intel-pt-decoder/intel-pt-insn-decoder.h" diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c new file mode 100644 index 000000000000..c92db87e4479 --- /dev/null +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdbool.h> +#include <inttypes.h> +#include <stdlib.h> +#include <string.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/types.h> + +#include "event.h" +#include "evsel.h" +#include "debug.h" +#include "util/synthetic-events.h" + +#include "tests/tests.h" +#include "arch-tests.h" + +#define COMP(m) do { \ + if (s1->m != s2->m) { \ + pr_debug("Samples differ at '"#m"'\n"); \ + return false; \ + } \ +} while (0) + +static bool samples_same(const struct perf_sample *s1, + const struct perf_sample *s2, + u64 type) +{ + if (type & PERF_SAMPLE_WEIGHT_STRUCT) + COMP(ins_lat); + + return true; +} + +static int do_test(u64 sample_type) +{ + struct evsel evsel = { + .needs_swap = false, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = 0, + }, + }, + }; + union perf_event *event; + struct perf_sample sample = { + .weight = 101, + .ins_lat = 102, + }; + struct perf_sample sample_out; + size_t i, sz, bufsz; + int err, ret = -1; + + sz = perf_event__sample_event_size(&sample, sample_type, 0); + bufsz = sz + 4096; /* Add a bit for overrun checking */ + event = malloc(bufsz); + if (!event) { + pr_debug("malloc failed\n"); + return -1; + } + + memset(event, 0xff, bufsz); + event->header.type = PERF_RECORD_SAMPLE; + event->header.misc = 0; + event->header.size = sz; + + err = perf_event__synthesize_sample(event, sample_type, 0, &sample); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "perf_event__synthesize_sample", sample_type, err); + goto out_free; + } + + /* The data does not contain 0xff so we use that to check the size */ + for (i = bufsz; i > 0; i--) { + if (*(i - 1 + (u8 *)event) != 0xff) + break; + } + if (i != sz) { + pr_debug("Event size mismatch: actual %zu vs expected %zu\n", + i, sz); + goto out_free; + } + + evsel.sample_size = __evsel__sample_size(sample_type); + + err = evsel__parse_sample(&evsel, event, &sample_out); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "evsel__parse_sample", sample_type, err); + goto out_free; + } + + if (!samples_same(&sample, &sample_out, sample_type)) { + pr_debug("parsing failed for sample_type %#"PRIx64"\n", + sample_type); + goto out_free; + } + + ret = 0; +out_free: + free(event); + + return ret; +} + +/** + * test__x86_sample_parsing - test X86 specific sample parsing + * + * This function implements a test that synthesizes a sample event, parses it + * and then checks that the parsed sample matches the original sample. If the + * test passes %0 is returned, otherwise %-1 is returned. + * + * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. + * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. + */ +int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + return do_test(PERF_SAMPLE_WEIGHT_STRUCT); +} diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c index 3e6791531ca5..34d600c51044 100644 --- a/tools/perf/arch/x86/util/archinsn.c +++ b/tools/perf/arch/x86/util/archinsn.c @@ -1,10 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../../../arch/x86/include/asm/insn.h" #include "archinsn.h" #include "event.h" #include "machine.h" #include "thread.h" #include "symbol.h" +#include "../../../../arch/x86/include/asm/insn.h" void arch_fetch_insn(struct perf_sample *sample, struct thread *thread, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 11726ec6285f..20b87e29c96f 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -344,18 +344,22 @@ static void mempol_restore(void) static void bind_to_memnode(int node) { - unsigned long nodemask; + struct bitmask *node_mask; int ret; if (node == NUMA_NO_NODE) return; - BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8); - nodemask = 1L << node; + node_mask = numa_allocate_nodemask(); + BUG_ON(!node_mask); - ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8); - dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret); + numa_bitmask_clearall(node_mask); + numa_bitmask_setbit(node_mask, node); + ret = set_mempolicy(MPOL_BIND, node_mask->maskp, node_mask->size + 1); + dprintf("binding to node %d, mask: %016lx => %d\n", node, *node_mask->maskp, ret); + + numa_bitmask_free(node_mask); BUG_ON(ret); } @@ -876,8 +880,6 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked) prctl(0, bytes_worked); } -#define MAX_NR_NODES 64 - /* * Count the number of nodes a process's threads * are spread out on. @@ -888,10 +890,15 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked) */ static int count_process_nodes(int process_nr) { - char node_present[MAX_NR_NODES] = { 0, }; + char *node_present; int nodes; int n, t; + node_present = (char *)malloc(g->p.nr_nodes * sizeof(char)); + BUG_ON(!node_present); + for (nodes = 0; nodes < g->p.nr_nodes; nodes++) + node_present[nodes] = 0; + for (t = 0; t < g->p.nr_threads; t++) { struct thread_data *td; int task_nr; @@ -901,17 +908,20 @@ static int count_process_nodes(int process_nr) td = g->threads + task_nr; node = numa_node_of_cpu(td->curr_cpu); - if (node < 0) /* curr_cpu was likely still -1 */ + if (node < 0) /* curr_cpu was likely still -1 */ { + free(node_present); return 0; + } node_present[node] = 1; } nodes = 0; - for (n = 0; n < MAX_NR_NODES; n++) + for (n = 0; n < g->p.nr_nodes; n++) nodes += node_present[n]; + free(node_present); return nodes; } @@ -980,7 +990,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence) { unsigned int loops_done_min, loops_done_max; int process_groups; - int nodes[MAX_NR_NODES]; + int *nodes; int distance; int nr_min; int nr_max; @@ -994,6 +1004,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence) if (!g->p.show_convergence && !g->p.measure_convergence) return; + nodes = (int *)malloc(g->p.nr_nodes * sizeof(int)); + BUG_ON(!nodes); for (node = 0; node < g->p.nr_nodes; node++) nodes[node] = 0; @@ -1035,8 +1047,10 @@ static void calc_convergence(double runtime_ns_max, double *convergence) BUG_ON(sum > g->p.nr_tasks); - if (0 && (sum < g->p.nr_tasks)) + if (0 && (sum < g->p.nr_tasks)) { + free(nodes); return; + } /* * Count the number of distinct process groups present @@ -1088,6 +1102,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence) } tprintf("\n"); } + + free(nodes); } static void show_summary(double runtime_ns_max, int l, double *convergence) @@ -1413,7 +1429,7 @@ static int init(void) g->p.nr_nodes = numa_max_node() + 1; /* char array in count_process_nodes(): */ - BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0); + BUG_ON(g->p.nr_nodes < 0); if (g->p.show_quiet && !g->p.show_details) g->p.show_details = -1; diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index cecce93ccc63..488f6e6ba1a5 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -309,11 +309,11 @@ int bench_sched_messaging(int argc, const char **argv) num_groups, num_groups * 2 * num_fds, thread_mode ? "threads" : "processes"); printf(" %14s: %lu.%03lu [sec]\n", "Total time", - diff.tv_sec, + (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); break; case BENCH_FORMAT_SIMPLE: - printf("%lu.%03lu\n", diff.tv_sec, + printf("%lu.%03lu\n", (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); break; default: diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 3c88d1f201f1..a960e7a93aec 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -156,7 +156,7 @@ int bench_sched_pipe(int argc, const char **argv) result_usec += diff.tv_usec; printf(" %14s: %lu.%03lu [sec]\n\n", "Total time", - diff.tv_sec, + (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); printf(" %14lf usecs/op\n", @@ -168,7 +168,7 @@ int bench_sched_pipe(int argc, const char **argv) case BENCH_FORMAT_SIMPLE: printf("%lu.%03lu\n", - diff.tv_sec, + (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); break; diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index 5fe621cff8e9..9b751016f4b6 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -54,7 +54,7 @@ int bench_syscall_basic(int argc, const char **argv) result_usec += diff.tv_usec; printf(" %14s: %lu.%03lu [sec]\n\n", "Total time", - diff.tv_sec, + (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec/1000)); printf(" %14lf usecs/op\n", @@ -66,7 +66,7 @@ int bench_syscall_basic(int argc, const char **argv) case BENCH_FORMAT_SIMPLE: printf("%lu.%03lu\n", - diff.tv_sec, + (unsigned long) diff.tv_sec, (unsigned long) (diff.tv_usec / 1000)); break; diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 617feaf020f6..7c4a9d424a64 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -161,7 +161,7 @@ static int session_config(struct daemon *daemon, const char *var, const char *va struct daemon_session *session; char name[100]; - if (get_session_name(var, name, sizeof(name))) + if (get_session_name(var, name, sizeof(name) - 1)) return -EINVAL; var = strchr(var, '.'); @@ -373,12 +373,12 @@ static int daemon_session__run(struct daemon_session *session, dup2(fd, 2); close(fd); - if (mkfifo(SESSION_CONTROL, O_RDWR) && errno != EEXIST) { + if (mkfifo(SESSION_CONTROL, 0600) && errno != EEXIST) { perror("failed: create control fifo"); return -1; } - if (mkfifo(SESSION_ACK, O_RDWR) && errno != EEXIST) { + if (mkfifo(SESSION_ACK, 0600) && errno != EEXIST) { perror("failed: create ack fifo"); return -1; } @@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon) int status; pid_t pid; + /* + * Take signal fd data as pure signal notification and check all + * the sessions state. The reason is that multiple signals can get + * coalesced in kernel and we can receive only single signal even + * if multiple SIGCHLD were generated. + */ err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo)); - if (err != sizeof(struct signalfd_siginfo)) + if (err != sizeof(struct signalfd_siginfo)) { + pr_err("failed to read signal fd\n"); return -1; + } list_for_each_entry(session, &daemon->sessions, list) { + if (session->pid == -1) + continue; - if (session->pid != (int) si.ssi_pid) + pid = waitpid(session->pid, &status, WNOHANG); + if (pid <= 0) continue; - pid = waitpid(session->pid, &status, 0); - if (pid == session->pid) { - if (WIFEXITED(status)) { - pr_info("session '%s' exited, status=%d\n", - session->name, WEXITSTATUS(status)); - } else if (WIFSIGNALED(status)) { - pr_info("session '%s' killed (signal %d)\n", - session->name, WTERMSIG(status)); - } else if (WIFSTOPPED(status)) { - pr_info("session '%s' stopped (signal %d)\n", - session->name, WSTOPSIG(status)); - } else { - pr_info("session '%s' Unexpected status (0x%x)\n", - session->name, status); - } + if (WIFEXITED(status)) { + pr_info("session '%s' exited, status=%d\n", + session->name, WEXITSTATUS(status)); + } else if (WIFSIGNALED(status)) { + pr_info("session '%s' killed (signal %d)\n", + session->name, WTERMSIG(status)); + } else if (WIFSTOPPED(status)) { + pr_info("session '%s' stopped (signal %d)\n", + session->name, WSTOPSIG(status)); + } else { + pr_info("session '%s' Unexpected status (0x%x)\n", + session->name, status); } session->state = KILL; session->pid = -1; - return pid; } return 0; @@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d .fd = daemon->signal_fd, .events = POLLIN, }; - pid_t wpid = 0, pid = session->pid; time_t start; start = time(NULL); @@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d int err = poll(&pollfd, 1, 1000); if (err > 0) { - wpid = handle_signalfd(daemon); + handle_signalfd(daemon); } else if (err < 0) { perror("failed: poll\n"); return -1; @@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d if (start + secs < time(NULL)) return -1; - } while (wpid != pid); + } while (session->pid != -1); return 0; } @@ -902,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session, daemon_session__signal(session, SIGKILL); break; default: - break; + pr_err("failed to wait for session %s\n", + session->name); + return; } how++; @@ -955,7 +963,8 @@ static void daemon__kill(struct daemon *daemon) daemon__signal(daemon, SIGKILL); break; default: - break; + pr_err("failed to wait for sessions\n"); + return; } how++; @@ -1344,7 +1353,7 @@ out: close(sock_fd); if (conf_fd != -1) close(conf_fd); - if (conf_fd != -1) + if (signal_fd != -1) close(signal_fd); pr_info("daemon exited\n"); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 8f6c784ce629..878e04b1fab7 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1236,7 +1236,8 @@ static int __cmd_diff(void) out_delete: data__for_each_file(i, d) { - perf_session__delete(d->session); + if (!IS_ERR(d->session)) + perf_session__delete(d->session); data__free(d); } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6fe44d97fde5..ddccc0eb7390 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -906,7 +906,7 @@ int cmd_inject(int argc, const char **argv) } data.path = inject.input_name; - inject.session = perf_session__new(&data, true, &inject.tool); + inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool); if (IS_ERR(inject.session)) return PTR_ERR(inject.session); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 85b6a46e85b6..7ec18ff57fc4 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3964,9 +3964,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) evlist__config(evlist, &trace->opts, &callchain_param); - signal(SIGCHLD, sig_handler); - signal(SIGINT, sig_handler); - if (forks) { err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL); if (err < 0) { @@ -4827,6 +4824,8 @@ int cmd_trace(int argc, const char **argv) signal(SIGSEGV, sighandler_dump_stack); signal(SIGFPE, sighandler_dump_stack); + signal(SIGCHLD, sig_handler); + signal(SIGINT, sig_handler); trace.evlist = evlist__new(); trace.sctbl = syscalltbl__new(); diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh index 0cfb3e2cefef..133f0eddbcc4 100644 --- a/tools/perf/perf-archive.sh +++ b/tools/perf/perf-archive.sh @@ -20,9 +20,8 @@ else fi BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX) -NOBUILDID=0000000000000000000000000000000000000000 -perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS +perf buildid-list -i $PERF_DATA --with-hits | grep -v "^ " > $BUILDIDS if [ ! -s $BUILDIDS ] ; then echo "perf archive: no build-ids found" rm $BUILDIDS || true diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index ec972e0892ab..dd39ce9b0277 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -182,14 +182,20 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) struct stat st; char path_perf[PATH_MAX]; char path_dir[PATH_MAX]; + char *exec_path; /* First try development tree tests. */ if (!lstat("./tests", &st)) return run_dir("./tests", "./perf"); + exec_path = get_argv_exec_path(); + if (exec_path == NULL) + return -1; + /* Then installed path. */ - snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path()); + snprintf(path_dir, PATH_MAX, "%s/tests", exec_path); snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR); + free(exec_path); if (!lstat(path_dir, &st) && !lstat(path_perf, &st)) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index f57e075b0ed2..c72adbd67386 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -86,7 +86,7 @@ static struct { .msg_load_fail = "check your vmlinux setting?", .target_func = &epoll_pwait_loop, .expect_result = (NR_ITERS + 1) / 2, - .pin = true, + .pin = true, }, #ifdef HAVE_BPF_PROLOGUE { @@ -99,13 +99,6 @@ static struct { .expect_result = (NR_ITERS + 1) / 4, }, #endif - { - .prog_id = LLVM_TESTCASE_BPF_RELOCATION, - .desc = "BPF relocation checker", - .name = "[bpf_relocation_test]", - .msg_compile_fail = "fix 'perf test LLVM' first", - .msg_load_fail = "libbpf error when dealing with relocation", - }, }; static int do_test(struct bpf_object *obj, int (*func)(void), diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 280f0348a09c..2fdc7b2f996e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -706,13 +706,9 @@ static int do_test_code_reading(bool try_kcore) out_put: thread__put(thread); out_err: - - if (evlist) { - evlist__delete(evlist); - } else { - perf_cpu_map__put(cpus); - perf_thread_map__put(threads); - } + evlist__delete(evlist); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); machine__delete_threads(machine); machine__delete(machine); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 29c793ac7d10..0472b110fe65 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -106,6 +106,8 @@ static int cpu_map_print(const char *str) return -1; cpu_map__snprint(map, buf, sizeof(buf)); + perf_cpu_map__put(map); + return !strcmp(buf, str); } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index e6f1b2a38e03..a0438b0f0805 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -154,10 +154,9 @@ out_err: if (evlist) { evlist__disable(evlist); evlist__delete(evlist); - } else { - perf_cpu_map__put(cpus); - perf_thread_map__put(threads); } + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); return err; } diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 57093aeacc6f..73ae8f7aa066 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -158,8 +158,6 @@ out_init: out_delete_evlist: evlist__delete(evlist); - cpus = NULL; - threads = NULL; out_free_cpus: perf_cpu_map__put(cpus); out_free_threads: diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 7cff02664d0e..680c3cffb128 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -167,6 +167,8 @@ next_event: out_err: evlist__delete(evlist); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); return err; } diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 0dbe3aa99853..8fd8a4ef97da 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -129,9 +129,6 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_WEIGHT) COMP(weight); - if (type & PERF_SAMPLE_WEIGHT_STRUCT) - COMP(ins_lat); - if (type & PERF_SAMPLE_DATA_SRC) COMP(data_src); @@ -245,7 +242,6 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .cgroup = 114, .data_page_size = 115, .code_page_size = 116, - .ins_lat = 117, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data, diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh index e5b824dd08d9..58984380b211 100755 --- a/tools/perf/tests/shell/daemon.sh +++ b/tools/perf/tests/shell/daemon.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # daemon operations # SPDX-License-Identifier: GPL-2.0 @@ -140,10 +140,10 @@ test_list() base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 [session-time] -run = -e task-clock +run = -e task-clock -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} @@ -159,14 +159,14 @@ EOF # check 1st session # pid:size:-e cpu-clock:base/size:base/size/output:base/size/control:base/size/ack:0 local line=`perf daemon --config ${config} -x: | head -2 | tail -1` - check_line_other "${line}" size "-e cpu-clock" ${base}/session-size \ + check_line_other "${line}" size "-e cpu-clock -m 1 sleep 10" ${base}/session-size \ ${base}/session-size/output ${base}/session-size/control \ ${base}/session-size/ack "0" # check 2nd session # pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0 local line=`perf daemon --config ${config} -x: | head -3 | tail -1` - check_line_other "${line}" time "-e task-clock" ${base}/session-time \ + check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \ ${base}/session-time/output ${base}/session-time/control \ ${base}/session-time/ack "0" @@ -190,10 +190,10 @@ test_reconfig() base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 [session-time] -run = -e task-clock +run = -e task-clock -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} @@ -204,7 +204,7 @@ EOF # check 2nd session # pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0 local line=`perf daemon --config ${config} -x: | head -3 | tail -1` - check_line_other "${line}" time "-e task-clock" ${base}/session-time \ + check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \ ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0" local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'` @@ -215,10 +215,10 @@ EOF base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 [session-time] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 EOF # TEST 1 - change config @@ -238,7 +238,7 @@ EOF # check reconfigured 2nd session # pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0 local line=`perf daemon --config ${config} -x: | head -3 | tail -1` - check_line_other "${line}" time "-e cpu-clock" ${base}/session-time \ + check_line_other "${line}" time "-e cpu-clock -m 1 sleep 10" ${base}/session-time \ ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0" # TEST 2 - empty config @@ -309,10 +309,10 @@ test_stop() base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 [session-time] -run = -e task-clock +run = -e task-clock -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} @@ -361,7 +361,7 @@ test_signal() base=BASE [session-test] -run = -e cpu-clock --switch-output +run = -e cpu-clock --switch-output -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} @@ -400,10 +400,10 @@ test_ping() base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 [session-time] -run = -e task-clock +run = -e task-clock -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} @@ -439,7 +439,7 @@ test_lock() base=BASE [session-size] -run = -e cpu-clock +run = -e cpu-clock -m 1 sleep 10 EOF sed -i -e "s|BASE|${base}|" ${config} diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index a49c9e23053b..74988846be1d 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -42,8 +42,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) .disabled = 1, .freq = 1, }; - struct perf_cpu_map *cpus; - struct perf_thread_map *threads; + struct perf_cpu_map *cpus = NULL; + struct perf_thread_map *threads = NULL; struct mmap *md; attr.sample_freq = 500; @@ -66,14 +66,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_free_maps; + goto out_delete_evlist; } perf_evlist__set_maps(&evlist->core, cpus, threads); - cpus = NULL; - threads = NULL; - if (evlist__open(evlist)) { const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate"; @@ -129,10 +126,9 @@ out_init: err = -1; } -out_free_maps: +out_delete_evlist: perf_cpu_map__put(cpus); perf_thread_map__put(threads); -out_delete_evlist: evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 15a2ab765d89..3ebaa758df77 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -574,10 +574,9 @@ out: if (evlist) { evlist__disable(evlist); evlist__delete(evlist); - } else { - perf_cpu_map__put(cpus); - perf_thread_map__put(threads); } + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); return err; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index bbf94e4aa145..4c2969db59b0 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -75,14 +75,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_free_maps; + goto out_delete_evlist; } perf_evlist__set_maps(&evlist->core, cpus, threads); - cpus = NULL; - threads = NULL; - err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal); if (err < 0) { pr_debug("Couldn't run the workload!\n"); @@ -137,7 +134,7 @@ out_init: if (retry_count++ > 1000) { pr_debug("Failed after retrying 1000 times\n"); err = -1; - goto out_free_maps; + goto out_delete_evlist; } goto retry; @@ -148,10 +145,9 @@ out_init: err = -1; } -out_free_maps: +out_delete_evlist: perf_cpu_map__put(cpus); perf_thread_map__put(threads); -out_delete_evlist: evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index 28f51c4bd373..d1e208b4a571 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -102,6 +102,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __ TEST_ASSERT_VAL("failed to synthesize map", !perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL)); + perf_thread_map__put(threads); return 0; } @@ -109,12 +110,12 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb { struct perf_thread_map *threads; char *str; - int i; TEST_ASSERT_VAL("failed to allocate map string", asprintf(&str, "%d,%d", getpid(), getppid()) >= 0); threads = thread_map__new_str(str, NULL, 0, false); + free(str); TEST_ASSERT_VAL("failed to allocate thread_map", threads); @@ -141,9 +142,6 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb TEST_ASSERT_VAL("failed to not remove thread", thread_map__remove(threads, 0)); - for (i = 0; i < threads->nr; i++) - zfree(&threads->map[i].comm); - - free(threads); + perf_thread_map__put(threads); return 0; } diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index f3ac9d40cebf..2e5eff4f8f03 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -210,8 +210,10 @@ static int arm_spe_do_get_packet(const unsigned char *buf, size_t len, if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) { /* 16-bit extended format header */ - ext_hdr = 1; + if (len == 1) + return ARM_SPE_BAD_PACKET; + ext_hdr = 1; hdr = buf[1]; if (hdr == SPE_HEADER1_ALIGNMENT) return arm_spe_get_alignment(buf, len, packet); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 953f4afacd3b..5b6ccb90b397 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, queue->set = true; queue->tid = buffer->tid; queue->cpu = buffer->cpu; - } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) { - pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n", - queue->cpu, queue->tid, buffer->cpu, buffer->tid); - return -EINVAL; } buffer->buffer_nr = queues->next_buffer_nr++; diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index 423ec69bda6c..5ecd4f401f32 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -201,7 +201,7 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt, double ratio = 0.0; if (block_fmt->total_cycles) - ratio = (double)bi->cycles / (double)block_fmt->total_cycles; + ratio = (double)bi->cycles_aggr / (double)block_fmt->total_cycles; return color_pct(hpp, block_fmt->width, 100.0 * ratio); } @@ -216,9 +216,9 @@ static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt, double l, r; if (block_fmt->total_cycles) { - l = ((double)bi_l->cycles / + l = ((double)bi_l->cycles_aggr / (double)block_fmt->total_cycles) * 100000.0; - r = ((double)bi_r->cycles / + r = ((double)bi_r->cycles_aggr / (double)block_fmt->total_cycles) * 100000.0; return (int64_t)l - (int64_t)r; } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 57d58c81a5f8..cdecda1ddd36 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, } if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) { + free(info_linear); pr_debug("%s: the kernel is too old, aborting\n", __func__); return -2; } info = &info_linear->info; + if (!info->jited_ksyms) { + free(info_linear); + return -1; + } /* number of ksyms, func_lengths, and tags should match */ sub_prog_cnt = info->nr_jited_ksyms; if (sub_prog_cnt != info->nr_prog_tags || - sub_prog_cnt != info->nr_jited_func_lens) + sub_prog_cnt != info->nr_jited_func_lens) { + free(info_linear); return -1; + } /* check BTF func info support */ if (info->btf_id && info->nr_func_info && info->func_info_rec_size) { /* btf func info number should be same as sub_prog_cnt */ if (sub_prog_cnt != info->nr_func_info) { pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__); - err = -1; - goto out; + free(info_linear); + return -1; } if (btf__get_from_id(info->btf_id, &btf)) { pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 5121b4db66fe..882cd1f721d9 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1306,6 +1306,7 @@ void evlist__close(struct evlist *evlist) perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); } + perf_evlist__reset_id_hash(&evlist->core); } static int evlist__create_syswide_maps(struct evlist *evlist) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1bf76864c4f2..7ecbc8e2fbfa 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -46,6 +46,7 @@ #include "string2.h" #include "memswap.h" #include "util.h" +#include "hashmap.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include <internal/xyarray.h> @@ -1390,7 +1391,9 @@ void evsel__exit(struct evsel *evsel) zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->pmu_name); - zfree(&evsel->per_pkg_mask); + evsel__zero_per_pkg(evsel); + hashmap__free(evsel->per_pkg_mask); + evsel->per_pkg_mask = NULL; zfree(&evsel->metric_events); perf_evsel__object.fini(evsel); } @@ -2781,3 +2784,16 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist) return store_evsel_ids(evsel, evlist); } + +void evsel__zero_per_pkg(struct evsel *evsel) +{ + struct hashmap_entry *cur; + size_t bkt; + + if (evsel->per_pkg_mask) { + hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt) + free((char *)cur->key); + + hashmap__clear(evsel->per_pkg_mask); + } +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4e8e49fb7e9d..6026487353dd 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -19,6 +19,7 @@ struct perf_stat_evsel; union perf_event; struct bpf_counter_ops; struct target; +struct hashmap; typedef int (evsel__sb_cb_t)(union perf_event *event, void *data); @@ -112,7 +113,7 @@ struct evsel { bool merged_stat; bool reset_group; bool errored; - unsigned long *per_pkg_mask; + struct hashmap *per_pkg_mask; struct evsel *leader; struct list_head config_terms; int err; @@ -433,4 +434,5 @@ struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); +void evsel__zero_per_pkg(struct evsel *evsel); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 4fe9e2a54346..20effdff76ce 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1618,8 +1618,8 @@ static void print_clock_data(struct feat_fd *ff, FILE *fp) fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid); fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n", - tstr, tod_ns.tv_sec, (int) tod_ns.tv_usec, - clockid_ns.tv_sec, clockid_ns.tv_nsec, + tstr, (long) tod_ns.tv_sec, (int) tod_ns.tv_usec, + (long) clockid_ns.tv_sec, clockid_ns.tv_nsec, clockid_name(clockid)); } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 692e56dc832e..fbc40a2c17d4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -77,8 +77,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) if (strstarts(filename, "/system/lib/")) { char *ndk, *app; const char *arch; - size_t ndk_length; - size_t app_length; + int ndk_length, app_length; ndk = getenv("NDK_ROOT"); app = getenv("APP_PLATFORM"); @@ -106,8 +105,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) if (new_length > PATH_MAX) return false; snprintf(newfilename, new_length, - "%s/platforms/%s/arch-%s/usr/lib/%s", - ndk, app, arch, libname); + "%.*s/platforms/%.*s/arch-%s/usr/lib/%s", + ndk_length, ndk, app_length, app, arch, libname); return true; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 42c84adeb2fb..c0c0fab22cb8 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu && attr->type == PERF_TYPE_RAW) + perf_pmu__warn_invalid_config(pmu, attr->config, name); + if (init_attr) event_attr_init(attr); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d5b6aff82f21..d57ac86ce7ca 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -89,6 +89,7 @@ static void inc_group_count(struct list_head *list, %type <str> PE_EVENT_NAME %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type <str> PE_DRV_CFG_TERM +%type <str> event_pmu_name %destructor { free ($$); } <str> %type <term> event_term %destructor { parse_events_term__delete ($$); } <term> @@ -272,8 +273,11 @@ event_def: event_pmu | event_legacy_raw sep_dc | event_bpf_file +event_pmu_name: +PE_NAME | PE_PMU_EVENT_PRE + event_pmu: -PE_NAME opt_pmu_config +event_pmu_name opt_pmu_config { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 44ef28302fc7..46fd0f998484 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) return nr_caps; } + +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name) +{ + struct perf_pmu_format *format; + __u64 masks = 0, bits; + char buf[100]; + unsigned int i; + + list_for_each_entry(format, &pmu->format, list) { + if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + + for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS) + masks |= 1ULL << i; + } + + /* + * Kernel doesn't export any valid format bits. + */ + if (masks == 0) + return; + + bits = config & ~masks; + if (bits == 0) + return; + + bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf)); + + pr_warning("WARNING: event '%s' not valid (bits %s of config " + "'%llx' not supported by kernel)!\n", + name ?: "N/A", buf, config); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 8164388478c6..160b0f561771 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name); + #endif /* __PMU_H */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 71b753523fac..845dd46e3c61 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -36,3 +36,4 @@ util/symbol_fprintf.c util/units.c util/affinity.c util/rwsem.c +util/hashmap.c diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 0d5ad42812b9..552b590485bf 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3140,7 +3140,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sort__mode != SORT_MODE__MEMORY) + if (sort__mode != SORT_MODE__BRANCH) return -EINVAL; return __sort_dimension__add_output(list, sd); @@ -3152,7 +3152,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sort__mode != SORT_MODE__BRANCH) + if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; return __sort_dimension__add_output(list, sd); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index cce7a76d6473..7f09cdaf5b60 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -983,7 +983,7 @@ static void print_interval(struct perf_stat_config *config, if (config->interval_clear) puts(CONSOLE_CLEAR); - sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep); + sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 5d8af29447f4..c400f8dde017 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -13,6 +13,7 @@ #include "evlist.h" #include "evsel.h" #include "thread_map.h" +#include "hashmap.h" #include <linux/zalloc.h> void update_stats(struct stats *stats, u64 val) @@ -277,18 +278,29 @@ void evlist__save_aggr_prev_raw_counts(struct evlist *evlist) } } -static void zero_per_pkg(struct evsel *counter) +static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused) { - if (counter->per_pkg_mask) - memset(counter->per_pkg_mask, 0, cpu__max_cpu()); + uint64_t *key = (uint64_t *) __key; + + return *key & 0xffffffff; +} + +static bool pkg_id_equal(const void *__key1, const void *__key2, + void *ctx __maybe_unused) +{ + uint64_t *key1 = (uint64_t *) __key1; + uint64_t *key2 = (uint64_t *) __key2; + + return *key1 == *key2; } static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, int cpu, bool *skip) { - unsigned long *mask = counter->per_pkg_mask; + struct hashmap *mask = counter->per_pkg_mask; struct perf_cpu_map *cpus = evsel__cpus(counter); - int s; + int s, d, ret = 0; + uint64_t *key; *skip = false; @@ -299,7 +311,7 @@ static int check_per_pkg(struct evsel *counter, return 0; if (!mask) { - mask = zalloc(cpu__max_cpu()); + mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); if (!mask) return -ENOMEM; @@ -321,8 +333,25 @@ static int check_per_pkg(struct evsel *counter, if (s < 0) return -1; - *skip = test_and_set_bit(s, mask) == 1; - return 0; + /* + * On multi-die system, die_id > 0. On no-die system, die_id = 0. + * We use hashmap(socket, die) to check the used socket+die pair. + */ + d = cpu_map__get_die(cpus, cpu, NULL).die; + if (d < 0) + return -1; + + key = malloc(sizeof(*key)); + if (!key) + return -ENOMEM; + + *key = (uint64_t)d << 32 | s; + if (hashmap__find(mask, (void *)key, NULL)) + *skip = true; + else + ret = hashmap__add(mask, (void *)key, (void *)1); + + return ret; } static int @@ -422,7 +451,7 @@ int perf_stat_process_counter(struct perf_stat_config *config, } if (counter->per_pkg) - zero_per_pkg(counter); + evsel__zero_per_pkg(counter); ret = process_counter_maps(config, counter); if (ret) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index b698046ec2db..dff178103ce5 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, while (!io.eof) { static const char anonstr[] = "//anon"; - size_t size; + size_t size, aligned_size; /* ensure null termination since stack will be reused. */ event->mmap2.filename[0] = '\0'; @@ -484,11 +484,12 @@ out: } size = strlen(event->mmap2.filename) + 1; - size = PERF_ALIGN(size, sizeof(u64)); + aligned_size = PERF_ALIGN(size, sizeof(u64)); event->mmap2.len -= event->mmap.start; event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + (sizeof(event->mmap2.filename) - aligned_size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size + + (aligned_size - size)); event->mmap2.header.size += machine->id_hdr_size; event->mmap2.pid = tgid; event->mmap2.tid = pid; @@ -758,7 +759,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, for (i = 0; i < n; i++) { char *end; pid_t _pid; - bool kernel_thread; + bool kernel_thread = false; _pid = strtol(dirent[i]->d_name, &end, 10); if (*end) diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index f507dff713c9..8a01af783310 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -361,6 +361,7 @@ static int read_saved_cmdline(struct tep_handle *pevent) pr_debug("error reading saved cmdlines\n"); goto out; } + buf[ret] = '\0'; parse_saved_cmdline(pevent, buf, size); ret = 0; diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 3cc91ad048ea..43beb169631d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s if (dso != NULL) { __dsos__add(&machine->dsos, dso); dso__set_long_name(dso, long_name, false); + /* Put dso here because __dsos_add already got it */ + dso__put(dso); } return dso; |