diff options
Diffstat (limited to 'tools/perf')
57 files changed, 482 insertions, 255 deletions
diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 7902a5681fc8..b8fc7d972be9 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -35,7 +35,7 @@ endif # Only pass canonical directory names as the output directory: # ifneq ($(O),) - FULL_O := $(shell readlink -f $(O) || echo $(O)) + FULL_O := $(shell cd $(PWD); readlink -f $(O) || echo $(O)) endif # diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 53e6f32c8bd7..45997e10a335 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -224,8 +224,17 @@ strip-libs = $(filter-out -l%,$(1)) PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) +# Python 3.8 changed the output of `python-config --ldflags` to not include the +# '-lpythonX.Y' flag unless '--embed' is also passed. The feature check for +# libpython fails if that flag is not included in LDFLAGS +ifeq ($(shell $(PYTHON_CONFIG_SQ) --ldflags --embed 2>&1 1>/dev/null; echo $$?), 0) + PYTHON_CONFIG_LDFLAGS := --ldflags --embed +else + PYTHON_CONFIG_LDFLAGS := --ldflags +endif + ifdef PYTHON_CONFIG - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null) PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c index f64516d5b23e..4708e185e7f5 100644 --- a/tools/perf/arch/arm/annotate/instructions.c +++ b/tools/perf/arch/arm/annotate/instructions.c @@ -35,7 +35,7 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused) arm = zalloc(sizeof(*arm)); if (!arm) - return -1; + return ENOMEM; #define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)" err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED); @@ -57,5 +57,5 @@ out_free_call: regfree(&arm->call_insn); out_free_arm: free(arm); - return -1; + return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; } diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 1ce6bdbda561..b9d471a0babd 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -54,7 +54,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct perf_evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -72,12 +72,12 @@ struct auxtrace_record evsel->attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -94,7 +94,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 8f70a1b282df..223e2f161f41 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -94,7 +94,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) arm = zalloc(sizeof(*arm)); if (!arm) - return -1; + return ENOMEM; /* bl, blr */ err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED); @@ -117,5 +117,5 @@ out_free_call: regfree(&arm->call_insn); out_free_arm: free(arm); - return -1; + return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; } diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 0b242664f5ea..e46be9ef5a68 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <sys/types.h> +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> @@ -31,7 +32,7 @@ get_cpuid(char *buffer, size_t sz) buffer[nb-1] = '\0'; return 0; } - return -1; + return ENOBUFS; } char * diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 89bb8f2c54ce..a50e70baf918 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -164,8 +164,10 @@ static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused) if (!arch->initialized) { arch->initialized = true; arch->associate_instruction_ops = s390__associate_ins_ops; - if (cpuid) - err = s390__cpuid_parse(arch, cpuid); + if (cpuid) { + if (s390__cpuid_parse(arch, cpuid)) + err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; + } } return err; diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index 3db85cd2069e..0a155af3224d 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -8,6 +8,7 @@ */ #include <sys/types.h> +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <string.h> @@ -53,7 +54,7 @@ int get_cpuid(char *buffer, size_t sz) sysinfo = fopen(SYSINFO, "r"); if (sysinfo == NULL) - return -1; + return errno; while ((read = getline(&line, &line_sz, sysinfo)) != -1) { if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) { @@ -88,7 +89,7 @@ int get_cpuid(char *buffer, size_t sz) /* Missing manufacturer, type or model information should not happen */ if (!manufacturer[0] || !type[0] || !model[0]) - return -1; + return EINVAL; /* * Scan /proc/service_levels and return the CPU-MF counter facility @@ -132,14 +133,14 @@ skip_sysinfo: else nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type, model); - return (nbytes >= sz) ? -1 : 0; + return (nbytes >= sz) ? ENOBUFS : 0; } char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) { char *buf = malloc(128); - if (buf && get_cpuid(buf, 128) < 0) + if (buf && get_cpuid(buf, 128)) zfree(&buf); return buf; } diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 44f5aba78210..7eb5621c021d 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -196,8 +196,10 @@ static int x86__annotate_init(struct arch *arch, char *cpuid) if (arch->initialized) return 0; - if (cpuid) - err = x86__cpuid_parse(arch, cpuid); + if (cpuid) { + if (x86__cpuid_parse(arch, cpuid)) + err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; + } arch->initialized = true; return err; diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index af9a9f2600be..a089af60906a 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <sys/types.h> +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> @@ -57,7 +58,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt) buffer[nb-1] = '\0'; return 0; } - return -1; + return ENOBUFS; } int diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index fddb3ced9db6..4aa6de1aa67d 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -2,6 +2,10 @@ #ifndef BENCH_H #define BENCH_H +#include <sys/time.h> + +extern struct timeval bench__start, bench__end, bench__runtime; + /* * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 2af067859966..8a383c3e0967 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -33,7 +33,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool done, __verbose, randomize; /* @@ -92,8 +91,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void nest_epollfd(void) @@ -359,7 +358,7 @@ int bench_epoll_ctl(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index fe85448abd45..235e3aa28aad 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -88,7 +88,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool wdone, done, __verbose, randomize, nonblocking; /* @@ -274,8 +273,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -285,7 +284,7 @@ static void print_summary(void) printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static int do_threads(struct worker *worker, struct cpu_map *cpu) @@ -477,7 +476,7 @@ int bench_epoll_wait(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); @@ -517,7 +516,7 @@ int bench_epoll_wait(int argc, const char **argv) qsort(worker, nthreads, sizeof(struct worker), cmpworker); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 9aa3a674829b..ee9b28065109 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -35,7 +35,7 @@ static unsigned int nfutexes = 1024; static bool fshared = false, done = false, silent = false; static int futex_flag = 0; -struct timeval start, end, runtime; +struct timeval bench__start, bench__end, bench__runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -101,8 +101,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -112,7 +112,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } int bench_futex_hash(int argc, const char **argv) @@ -159,7 +159,7 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); for (i = 0; i < nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); @@ -202,7 +202,7 @@ int bench_futex_hash(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) { if (nfutexes == 1) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 8e9c4753e304..017609ae3590 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -35,7 +35,6 @@ static bool silent = false, multi = false; static bool done = false, fshared = false; static unsigned int nthreads = 0; static int futex_flag = 0; -struct timeval start, end, runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -62,7 +61,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static void toggle_done(int sig __maybe_unused, @@ -71,8 +70,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void *workerfn(void *arg) @@ -183,7 +182,7 @@ int bench_futex_lock_pi(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); create_threads(worker, thread_attr, cpu); pthread_attr_destroy(&thread_attr); @@ -209,7 +208,7 @@ int bench_futex_lock_pi(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index e8181ad7d088..e62006342b18 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -42,7 +42,7 @@ static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; -static unsigned int ncpus, threads_starting, nthreads = 0; +static unsigned int threads_starting, nthreads = 0; static int futex_flag = 0; static const struct option options[] = { @@ -140,7 +140,7 @@ int bench_futex_wake(int argc, const char **argv) sigaction(SIGINT, &act, NULL); if (!nthreads) - nthreads = ncpus; + nthreads = cpu->nr; worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index 0251dd348124..4864fc67d01b 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -222,12 +222,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info * return 0; } -static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst) +static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst) { - u64 cycle_start = 0ULL, cycle_end = 0ULL; - memcpy_t fn = r->fn.memcpy; - int i; - /* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */ memset(src, 0, size); @@ -236,6 +232,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, vo * to not measure page fault overhead: */ fn(dst, src, size); +} + +static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + memcpy_t fn = r->fn.memcpy; + int i; + + memcpy_prefault(fn, size, src, dst); cycle_start = get_cycles(); for (i = 0; i < nr_loops; ++i) @@ -251,11 +256,7 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size, void memcpy_t fn = r->fn.memcpy; int i; - /* - * We prefault the freshly allocated memory range here, - * to not measure page fault overhead: - */ - fn(dst, src, size); + memcpy_prefault(fn, size, src, dst); BUG_ON(gettimeofday(&tv_start, NULL)); for (i = 0; i < nr_loops; ++i) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 9e6cc868bdb4..d1811190b702 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -587,8 +587,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused, { struct c2c_hist_entry *c2c_left; struct c2c_hist_entry *c2c_right; - unsigned int tot_hitm_left; - unsigned int tot_hitm_right; + uint64_t tot_hitm_left; + uint64_t tot_hitm_right; c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); @@ -621,7 +621,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused, \ \ c2c_left = container_of(left, struct c2c_hist_entry, he); \ c2c_right = container_of(right, struct c2c_hist_entry, he); \ - return c2c_left->stats.__f - c2c_right->stats.__f; \ + return (uint64_t) c2c_left->stats.__f - \ + (uint64_t) c2c_right->stats.__f; \ } #define STAT_FN(__f) \ @@ -674,7 +675,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused, c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); - return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats); + return (uint64_t) llc_miss(&c2c_left->stats) - + (uint64_t) llc_miss(&c2c_right->stats); } static uint64_t total_records(struct c2c_stats *stats) @@ -2627,6 +2629,7 @@ static int build_cl_output(char *cl_sort, bool no_source) bool add_sym = false; bool add_dso = false; bool add_src = false; + int ret = 0; if (!buf) return -ENOMEM; @@ -2645,7 +2648,8 @@ static int build_cl_output(char *cl_sort, bool no_source) add_dso = true; } else if (strcmp(tok, "offset")) { pr_err("unrecognized sort token: %s\n", tok); - return -EINVAL; + ret = -EINVAL; + goto err; } } @@ -2668,13 +2672,15 @@ static int build_cl_output(char *cl_sort, bool no_source) add_sym ? "symbol," : "", add_dso ? "dso," : "", add_src ? "cl_srcline," : "", - "node") < 0) - return -ENOMEM; + "node") < 0) { + ret = -ENOMEM; + goto err; + } c2c.show_src = add_src; - +err: free(buf); - return 0; + return ret; } static int setup_coalesce(const char *coalesce, bool no_source) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b80eee455111..315222cee00a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -687,6 +687,7 @@ static char *compact_gfp_flags(char *gfp_flags) new = realloc(new_flags, len + strlen(cpt) + 2); if (new == NULL) { free(new_flags); + free(orig_flags); return NULL; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index dbb6f737a3e2..32cea4ca69c2 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -699,14 +699,15 @@ static int process_sample_event(struct perf_tool *tool, static int cpu_isa_config(struct perf_kvm_stat *kvm) { - char buf[64], *cpuid; + char buf[128], *cpuid; int err; if (kvm->live) { err = get_cpuid(buf, sizeof(buf)); if (err != 0) { - pr_err("Failed to look up CPU type\n"); - return err; + pr_err("Failed to look up CPU type: %s\n", + str_error_r(err, buf, sizeof(buf))); + return -err; } cpuid = buf; } else diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 2c376f5b2120..e3cfaab86c7a 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -363,6 +363,9 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs) for (k = 0; k < pev->ntevs; k++) { struct probe_trace_event *tev = &pev->tevs[k]; + /* Skipped events have no event name */ + if (!tev->event) + continue; /* We use tev's name for showing new events */ show_perf_probe_event(tev->group, tev->event, pev, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1ca533f06a4c..f063465ee253 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -170,24 +170,23 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, { struct hist_entry *he = iter->he; struct report *rep = arg; - struct branch_info *bi; + struct branch_info *bi = he->branch_info; struct perf_sample *sample = iter->sample; struct perf_evsel *evsel = iter->evsel; int err; + branch_type_count(&rep->brtype_stat, &bi->flags, + bi->from.addr, bi->to.addr); + if (!ui__has_annotation() && !rep->symbol_ipc) return 0; - bi = he->branch_info; err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); - branch_type_count(&rep->brtype_stat, &bi->flags, - bi->from.addr, bi->to.addr); - out: return err; } @@ -385,6 +384,13 @@ static int report__setup_sample_type(struct report *rep) PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; +#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT) + if (dwarf_callchain_users) { + ui__warning("Please install libunwind or libdw " + "development packages during the perf build.\n"); + } +#endif + return 0; } @@ -442,8 +448,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report if (rep->time_str) ret += fprintf(fp, " (time slices: %s)", rep->time_str); - if (symbol_conf.show_ref_callgraph && - strstr(evname, "call-graph=no")) { + if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) { ret += fprintf(fp, ", show reference callgraph"); } @@ -1011,6 +1016,7 @@ int cmd_report(int argc, const char **argv) struct stat st; bool has_br_stack = false; int branch_mode = -1; + int last_key = 0; bool branch_call_mode = false; #define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" @@ -1369,7 +1375,8 @@ repeat: sort_order = sort_tmp; } - if (setup_sorting(session->evlist) < 0) { + if ((last_key != K_SWITCH_INPUT_DATA) && + (setup_sorting(session->evlist) < 0)) { if (sort_order) parse_options_usage(report_usage, options, "s", 1); if (field_order) @@ -1444,6 +1451,7 @@ repeat: ret = __cmd_report(&report); if (ret == K_SWITCH_INPUT_DATA) { perf_session__delete(session); + last_key = K_SWITCH_INPUT_DATA; goto repeat; } else ret = 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 4380474c8c35..b218c44e7226 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -437,7 +437,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if (PRINT_FIELD(BRSTACKINSN) && + if (PRINT_FIELD(BRSTACKINSN) && !allow_user_set && !(perf_evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) { pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" @@ -1052,7 +1052,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, continue; insn = 0; - for (off = 0;; off += ilen) { + for (off = 0; off < (unsigned)len; off += ilen) { uint64_t ip = start + off; printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); @@ -1063,6 +1063,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += print_srccode(thread, x.cpumode, ip); break; } else { + ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip, dump_insn(&x, ip, buffer + off, len - off, &ilen)); if (ilen == 0) @@ -1072,6 +1073,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, insn++; } } + if (off != end - start) + printed += fprintf(fp, "\tmismatch of LBR data and executable\n"); } /* @@ -1112,6 +1115,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, goto out; } for (off = 0; off <= end - start; off += ilen) { + ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off, dump_insn(&x, start + off, buffer + off, len - off, &ilen)); if (ilen == 0) @@ -3496,11 +3500,6 @@ int cmd_script(int argc, const char **argv) } } - if (script.time_str && reltime) { - fprintf(stderr, "Don't combine --reltime with --time\n"); - return -1; - } - if (itrace_synth_opts.callchain && itrace_synth_opts.callchain_sz > scripting_max_stack) scripting_max_stack = itrace_synth_opts.callchain_sz; @@ -3760,10 +3759,11 @@ int cmd_script(int argc, const char **argv) goto out_delete; if (script.time_str) { - err = perf_time__parse_for_ranges(script.time_str, session, + err = perf_time__parse_for_ranges_reltime(script.time_str, session, &script.ptime_range, &script.range_size, - &script.range_num); + &script.range_num, + reltime); if (err < 0) goto out_delete; } diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 68618152ea2c..89e070727e1b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index ed5423d8a95f..2734bb8afff0 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -446,12 +446,12 @@ static struct fixed { const char *name; const char *event; } fixed[] = { - { "inst_retired.any", "event=0xc0" }, - { "inst_retired.any_p", "event=0xc0" }, - { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" }, - { "cpu_clk_unhalted.thread", "event=0x3c" }, - { "cpu_clk_unhalted.core", "event=0x3c" }, - { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" }, + { "inst_retired.any", "event=0xc0,period=2000003" }, + { "inst_retired.any_p", "event=0xc0,period=2000003" }, + { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" }, + { "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" }, + { "cpu_clk_unhalted.core", "event=0x3c,period=2000003" }, + { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" }, { NULL, NULL}, }; @@ -754,6 +754,7 @@ static int process_mapfile(FILE *outfp, char *fpath) char *line, *p; int line_num; char *tblname; + int ret = 0; pr_info("%s: Processing mapfile %s\n", prog, fpath); @@ -765,6 +766,7 @@ static int process_mapfile(FILE *outfp, char *fpath) if (!mapfp) { pr_info("%s: Error %s opening %s\n", prog, strerror(errno), fpath); + free(line); return -1; } @@ -791,7 +793,8 @@ static int process_mapfile(FILE *outfp, char *fpath) /* TODO Deal with lines longer than 16K */ pr_info("%s: Mapfile %s: line %d too long, aborting\n", prog, fpath, line_num); - return -1; + ret = -1; + goto out; } line[strlen(line)-1] = '\0'; @@ -821,7 +824,9 @@ static int process_mapfile(FILE *outfp, char *fpath) out: print_mapping_table_suffix(outfp); - return 0; + fclose(mapfp); + free(line); + return ret; } /* @@ -1118,6 +1123,7 @@ int main(int argc, char *argv[]) goto empty_map; } else if (rc < 0) { /* Make build fail */ + fclose(eventsfp); free_arch_std_events(); return 1; } else if (rc) { @@ -1130,6 +1136,7 @@ int main(int argc, char *argv[]) goto empty_map; } else if (rc < 0) { /* Make build fail */ + fclose(eventsfp); free_arch_std_events(); return 1; } else if (rc) { @@ -1147,6 +1154,8 @@ int main(int argc, char *argv[]) if (process_mapfile(eventsfp, mapfile)) { pr_info("%s: Error processing mapfile %s\n", prog, mapfile); /* Make build fail */ + fclose(eventsfp); + free_arch_std_events(); return 1; } diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index affed7d149be..b9a038b27d42 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -686,7 +686,8 @@ class CallGraphModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " GROUP BY comm_id, thread_id, call_path_id" " ORDER BY comm_id, thread_id, call_path_id") @@ -834,7 +835,8 @@ class CallTreeModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " ORDER BY comm_id, thread_id, call_time, calls.id") def FindPath(self, query): @@ -900,6 +902,7 @@ class TreeWindowBase(QMdiSubWindow): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index 57fc544aedb0..92226772d3c4 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -21,7 +21,7 @@ #include "perf.h" #include "cloexec.h" -volatile long the_var; +static volatile long the_var; static noinline int test_function(void) { diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index caedb5ec1523..0f32a9c11023 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -48,14 +48,6 @@ asm ( "__test_function:\n" "incq (%rdi)\n" "ret\n"); -#elif defined (__aarch64__) -extern void __test_function(volatile long *ptr); -asm ( - ".globl __test_function\n" - "__test_function:\n" - "str x30, [x0]\n" - "ret\n"); - #else static void __test_function(volatile long *ptr) { @@ -301,10 +293,15 @@ bool test__bp_signal_is_supported(void) * stepping into the SIGIO handler and getting stuck on the * breakpointed instruction. * + * Since arm64 has the same issue with arm for the single-step + * handling, this case also gets suck on the breakpointed + * instruction. + * * Just disable the test for these architectures until these * issues are resolved. */ -#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \ + defined(__aarch64__) return false; #else return true; diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index a693bcf017ea..44c16fd11bf6 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -20,12 +20,11 @@ static void sigsegv_handler(int sig __maybe_unused) static void the_hook(void *_hook_flags) { int *hook_flags = _hook_flags; - int *p = NULL; *hook_flags = 1234; /* Generate a segfault, test perf_hooks__recover */ - *p = 0; + raise(SIGSEGV); } int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused) diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index e92fa6029ac7..3986fd162a7e 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -48,6 +48,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused struct cpu_map *cpus; struct thread_map *threads; struct perf_mmap *md; + int retry_count = 0; signal(SIGCHLD, sig_handler); @@ -105,6 +106,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused if (perf_evlist__mmap(evlist, 128) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, str_error_r(errno, sbuf, sizeof(sbuf))); + err = -1; goto out_delete_evlist; } @@ -126,6 +128,13 @@ retry: out_init: if (!exited || !nr_exit) { perf_evlist__poll(evlist, -1); + + if (retry_count++ > 1000) { + pr_debug("Failed after retrying 1000 times\n"); + err = -1; + goto out_free_maps; + } + goto retry; } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index c1dd9b54dc6e..6cfd5eee2a95 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2216,6 +2216,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } +static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->res_samples : NULL; +} + /* Check whether the browser is for 'top' or 'report' */ static inline bool is_report_browser(void *timer) { @@ -3043,6 +3048,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } + actions->ms.map = map; top = pstack__peek(browser->pstack); if (top == &browser->hists->dso_filter) { /* @@ -3158,16 +3164,16 @@ skip_annotation: &options[nr_options], NULL, NULL, evsel); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_NORMAL); + hist_browser__selected_res_sample(browser), + evsel, A_NORMAL); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_ASM); + hist_browser__selected_res_sample(browser), + evsel, A_ASM); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_SOURCE); + hist_browser__selected_res_sample(browser), + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 9c486831465c..4d15bb50b854 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1620,6 +1620,19 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map * case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF: scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation"); break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP: + scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions."); + break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING: + scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization."); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE: + scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF: + scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.", + dso->long_name); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -1651,7 +1664,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil build_id_path = strdup(filename); if (!build_id_path) - return -1; + return ENOMEM; /* * old style build-id cache has name of XX/XXXXXXX.. while @@ -1702,13 +1715,13 @@ static int symbol__disassemble_bpf(struct symbol *sym, char tpath[PATH_MAX]; size_t buf_size; int nr_skip = 0; - int ret = -1; char *buf; bfd *bfdf; + int ret; FILE *s; if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) - return -1; + return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, sym->name, sym->start, sym->end - sym->start); @@ -1721,8 +1734,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, assert(bfd_check_format(bfdf, bfd_object)); s = open_memstream(&buf, &buf_size); - if (!s) + if (!s) { + ret = errno; goto out; + } init_disassemble_info(&info, s, (fprintf_ftype) fprintf); @@ -1731,8 +1746,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id); - if (!info_node) + if (!info_node) { + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; goto out; + } info_linear = info_node->info_linear; sub_id = dso->bpf_prog.sub_id; @@ -2060,11 +2077,11 @@ int symbol__annotate(struct symbol *sym, struct map *map, int err; if (!arch_name) - return -1; + return errno; args.arch = arch = arch__find(arch_name); if (arch == NULL) - return -ENOTSUP; + return ENOTSUP; if (parch) *parch = arch; @@ -2960,7 +2977,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev notes->offsets = zalloc(size * sizeof(struct annotation_line *)); if (notes->offsets == NULL) - return -1; + return ENOMEM; if (perf_evsel__is_group_event(evsel)) nr_pcnt = evsel->nr_members; @@ -2986,7 +3003,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev out_free_offsets: zfree(¬es->offsets); - return -1; + return err; } #define ANNOTATION__CFG(n) \ diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 5bc0cf655d37..2004e2cf0211 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -370,6 +370,10 @@ enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START, SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP, + SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE, + SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF, __SYMBOL_ANNOTATE_ERRNO__END, }; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e059976d9d93..01d76a990cf5 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -41,6 +41,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO] = 'D', [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', + [DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO] = 'x', [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o', [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', @@ -123,6 +124,21 @@ int dso__read_binary_type_filename(const struct dso *dso, snprintf(filename + len, size - len, "%s", dso->long_name); break; + case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: + /* + * Ubuntu can mixup /usr/lib with /lib, putting debuginfo in + * /usr/lib/debug/lib when it is expected to be in + * /usr/lib/debug/usr/lib + */ + if (strlen(dso->long_name) < 9 || + strncmp(dso->long_name, "/usr/lib/", 9)) { + ret = -1; + break; + } + len = __symbol__join_symfs(filename, size, "/usr/lib/debug"); + snprintf(filename + len, size - len, "%s", dso->long_name + 4); + break; + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: { const char *last_slash; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 6e3f63781e51..560c492c44b1 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -27,6 +27,7 @@ enum dso_binary_type { DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 218bfea8f8a8..41b0650e0d86 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -307,20 +307,50 @@ bool die_is_func_def(Dwarf_Die *dw_die) } /** + * die_entrypc - Returns entry PC (the lowest address) of a DIE + * @dw_die: a DIE + * @addr: where to store entry PC + * + * Since dwarf_entrypc() does not return entry PC if the DIE has only address + * range, we have to use this to retrieve the lowest address from the address + * range attribute. + */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) +{ + Dwarf_Addr base, end; + + if (!addr) + return -EINVAL; + + if (dwarf_entrypc(dw_die, addr) == 0) + return 0; + + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; +} + +/** * die_is_func_instance - Ensure that this DIE is an instance of a subprogram * @dw_die: a DIE * * Ensure that this DIE is an instance (which has an entry address). - * This returns true if @dw_die is a function instance. If not, you need to - * call die_walk_instances() to find actual instances. + * This returns true if @dw_die is a function instance. If not, the @dw_die + * must be a prototype. You can use die_walk_instances() to find actual + * instances. **/ bool die_is_func_instance(Dwarf_Die *dw_die) { Dwarf_Addr tmp; + Dwarf_Attribute attr_mem; + int tag = dwarf_tag(dw_die); - /* Actually gcc optimizes non-inline as like as inlined */ - return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; + if (tag != DW_TAG_subprogram && + tag != DW_TAG_inlined_subroutine) + return false; + + return dwarf_entrypc(dw_die, &tmp) == 0 || + dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL; } + /** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure @@ -597,6 +627,9 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) Dwarf_Die *origin; int tmp; + if (!die_is_func_instance(inst)) + return DIE_FIND_CB_CONTINUE; + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); if (attr == NULL) return DIE_FIND_CB_CONTINUE; @@ -668,15 +701,14 @@ static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { fname = die_get_call_file(in_die); lineno = die_get_call_lineno(in_die); - if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + if (fname && lineno > 0 && die_entrypc(in_die, &addr) == 0) { lw->retval = lw->callback(fname, lineno, addr, lw->data); if (lw->retval != 0) return DIE_FIND_CB_END; } + if (!lw->recursive) + return DIE_FIND_CB_SIBLING; } - if (!lw->recursive) - /* Don't need to search recursively */ - return DIE_FIND_CB_SIBLING; if (addr) { fname = dwarf_decl_file(in_die); @@ -709,7 +741,7 @@ static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, /* Handle function declaration line */ fname = dwarf_decl_file(sp_die); if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && - dwarf_entrypc(sp_die, &addr) == 0) { + die_entrypc(sp_die, &addr) == 0) { lw.retval = callback(fname, lineno, addr, data); if (lw.retval != 0) goto done; @@ -723,6 +755,10 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) { struct __line_walk_param *lw = data; + /* + * Since inlined function can include another inlined function in + * the same file, we need to walk in it recursively. + */ lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); if (lw->retval != 0) return DWARF_CB_ABORT; @@ -747,11 +783,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) Dwarf_Lines *lines; Dwarf_Line *line; Dwarf_Addr addr; - const char *fname, *decf = NULL; + const char *fname, *decf = NULL, *inf = NULL; int lineno, ret = 0; int decl = 0, inl; Dwarf_Die die_mem, *cu_die; size_t nlines, i; + bool flag; /* Get the CU die */ if (dwarf_tag(rt_die) != DW_TAG_compile_unit) { @@ -782,6 +819,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) "Possible error in debuginfo.\n"); continue; } + /* Skip end-of-sequence */ + if (dwarf_lineendsequence(line, &flag) != 0 || flag) + continue; + /* Skip Non statement line-info */ + if (dwarf_linebeginstatement(line, &flag) != 0 || !flag) + continue; /* Filter lines based on address */ if (rt_die != cu_die) { /* @@ -791,13 +834,21 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (!dwarf_haspc(rt_die, addr)) continue; + if (die_find_inlinefunc(rt_die, addr, &die_mem)) { + /* Call-site check */ + inf = die_get_call_file(&die_mem); + if ((inf && !strcmp(inf, decf)) && + die_get_call_lineno(&die_mem) == lineno) + goto found; + dwarf_decl_line(&die_mem, &inl); if (inl != decl || decf != dwarf_decl_file(&die_mem)) continue; } } +found: /* Get source line */ fname = dwarf_linesrc(line, NULL, NULL); @@ -812,8 +863,9 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (rt_die != cu_die) /* - * Don't need walk functions recursively, because nested - * inlined functions don't have lines of the specified DIE. + * Don't need walk inlined functions recursively, because + * inner inlined functions don't have the lines of the + * specified function. */ ret = __die_walk_funclines(rt_die, false, callback, data); else { @@ -988,7 +1040,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die, bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; @@ -1051,7 +1103,7 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 0489b0cf8e2c..fb6ca502c18e 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -27,6 +27,9 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Get DW_AT_linkage_name (should be NULL for C binary) */ const char *die_get_linkage_name(Dwarf_Die *dw_die); +/* Get the lowest PC in DIE (including range list) */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr); + /* Ensure that this DIE is a subprogram and definition (not declaration) */ bool die_is_func_def(Dwarf_Die *dw_die); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6a3eaf7d9353..725bf9270762 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -322,11 +322,11 @@ static const char *normalize_arch(char *arch) const char *perf_env__arch(struct perf_env *env) { - struct utsname uts; char *arch_name; if (!env || !env->arch) { /* Assume local operation */ - if (uname(&uts) < 0) + static struct utsname uts = { .machine[0] = '\0', }; + if (uts.machine[0] == '\0' && uname(&uts) < 0) return NULL; arch_name = uts.machine; } else diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index ecc68e73c414..fba6ba96d911 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1262,8 +1262,10 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) continue; if (WARN_ONCE(cnt >= size, - "failed to write MEM_TOPOLOGY, way too many nodes\n")) + "failed to write MEM_TOPOLOGY, way too many nodes\n")) { + closedir(dir); return -1; + } ret = memory_node__read(&nodes[cnt++], idx); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 966c248d6a3a..06d2981f0855 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1581,7 +1581,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 76ff6c6d03b8..490b1c88f76a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -331,10 +331,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format) list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list) #define hists__for_each_format(hists, format) \ - perf_hpp_list__for_each_format((hists)->hpp_list, fmt) + perf_hpp_list__for_each_format((hists)->hpp_list, format) #define hists__for_each_sort_list(hists, format) \ - perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt) + perf_hpp_list__for_each_sort_list((hists)->hpp_list, format) extern struct perf_hpp_fmt perf_hpp__format[]; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9d189e90fbdc..b030de6eb546 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1120,6 +1120,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (intel_pt_fup_event(decoder)) return 0; return -EAGAIN; @@ -1783,17 +1784,13 @@ next: } if (decoder->set_fup_mwait) no_tip = true; + if (no_tip) + decoder->pkt_state = INTEL_PT_STATE_FUP_NO_TIP; + else + decoder->pkt_state = INTEL_PT_STATE_FUP; err = intel_pt_walk_fup(decoder); - if (err != -EAGAIN) { - if (err) - return err; - if (no_tip) - decoder->pkt_state = - INTEL_PT_STATE_FUP_NO_TIP; - else - decoder->pkt_state = INTEL_PT_STATE_FUP; - return 0; - } + if (err != -EAGAIN) + return err; if (no_tip) { no_tip = false; break; @@ -2382,15 +2379,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_tip(decoder); break; case INTEL_PT_STATE_FUP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_fup_tip(decoder); - else if (!err) - decoder->pkt_state = INTEL_PT_STATE_FUP; break; case INTEL_PT_STATE_FUP_NO_TIP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 081fe4bdebaa..68a5c9b0d06a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -743,24 +743,6 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, return machine__process_ksymbol_register(machine, event, sample); } -static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename) -{ - const char *dup_filename; - - if (!filename || !dso || !dso->long_name) - return; - if (dso->long_name[0] != '[') - return; - if (!strchr(filename, '/')) - return; - - dup_filename = strdup(filename); - if (!dup_filename) - return; - - dso__set_long_name(dso, dup_filename, true); -} - struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename) { @@ -772,15 +754,8 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, return NULL; map = map_groups__find_by_name(&machine->kmaps, m.name); - if (map) { - /* - * If the map's dso is an offline module, give dso__load() - * a chance to find the file path of that module by fixing - * long_name. - */ - dso__adjust_kmod_long_name(map->dso, filename); + if (map) goto out; - } dso = machine__findnew_module_dso(machine, &m, filename); if (dso == NULL) @@ -1241,9 +1216,9 @@ static char *get_kernel_version(const char *root_dir) return NULL; tmp = fgets(version, sizeof(version), file); - if (!tmp) - *version = '\0'; fclose(file); + if (!tmp) + return NULL; name = strstr(version, prefix); if (!name) @@ -2370,7 +2345,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (callchain_param.order != ORDER_CALLEE) { + if (chain && callchain_param.order != ORDER_CALLEE) { err = find_prev_cpumode(chain, thread, cursor, parent, root_al, &cpumode, chain->nr - first_call); if (err) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 3fc32c7075d1..b7c20d14a611 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "symbol.h" +#include <assert.h> #include <errno.h> #include <inttypes.h> #include <limits.h> @@ -86,7 +87,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) return true; } - if (!strncmp(filename, "/system/lib/", 11)) { + if (!strncmp(filename, "/system/lib/", 12)) { char *ndk, *app; const char *arch; size_t ndk_length; @@ -630,7 +631,7 @@ bool map_groups__empty(struct map_groups *mg) struct map_groups *map_groups__new(struct machine *machine) { - struct map_groups *mg = malloc(sizeof(*mg)); + struct map_groups *mg = zalloc(sizeof(*mg)); if (mg != NULL) map_groups__init(mg, machine); @@ -841,6 +842,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp } after->start = map->end; + after->pgoff += map->end - pos->start; + assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end)); __map_groups__insert(pos->groups, after); if (verbose >= 2 && !use_browser) map__fprintf(after, fp); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index cf0b9b81c5aa..717422c4193c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1344,8 +1344,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + struct perf_evsel_config_term *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &config_terms, list) { + list_del_init(&pos->list); + free(pos); + } return -EINVAL; + } evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index cb9c246c8962..2f41b10698ad 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -37,7 +37,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); static inline const char *perf_reg_name(int id __maybe_unused) { - return NULL; + return "unknown"; } static inline int perf_reg_value(u64 *valp __maybe_unused, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 2ebf8673f8e9..787e5971519d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -100,7 +100,7 @@ void exit_probe_symbol_maps(void) symbol__exit(); } -static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) +static struct ref_reloc_sym *kernel_get_ref_reloc_sym(struct map **pmap) { /* kmap->ref_reloc_sym should be set if host_machine is initialized */ struct kmap *kmap; @@ -112,6 +112,10 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) kmap = map__kmap(map); if (!kmap) return NULL; + + if (pmap) + *pmap = map; + return kmap->ref_reloc_sym; } @@ -123,7 +127,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, struct map *map; /* ref_reloc_sym is just a label. Need a special fix*/ - reloc_sym = kernel_get_ref_reloc_sym(); + reloc_sym = kernel_get_ref_reloc_sym(NULL); if (reloc_sym && strcmp(name, reloc_sym->name) == 0) *addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; else { @@ -230,21 +234,22 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) static bool kprobe_blacklist__listed(unsigned long address); static bool kprobe_warn_out_range(const char *symbol, unsigned long address) { - u64 etext_addr = 0; - int ret; - - /* Get the address of _etext for checking non-probable text symbol */ - ret = kernel_get_symbol_address_by_name("_etext", &etext_addr, - false, false); + struct map *map; + bool ret = false; - if (ret == 0 && etext_addr < address) - pr_warning("%s is out of .text, skip it.\n", symbol); - else if (kprobe_blacklist__listed(address)) + map = kernel_get_module_map(NULL); + if (map) { + ret = address <= map->start || map->end < address; + if (ret) + pr_warning("%s is out of .text, skip it.\n", symbol); + map__put(map); + } + if (!ret && kprobe_blacklist__listed(address)) { pr_warning("%s is blacklisted function, skip it.\n", symbol); - else - return false; + ret = true; + } - return true; + return ret; } /* @@ -743,6 +748,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, int ntevs) { struct ref_reloc_sym *reloc_sym; + struct map *map; char *tmp; int i, skipped = 0; @@ -751,7 +757,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, return post_process_offline_probe_trace_events(tevs, ntevs, symbol_conf.vmlinux_name); - reloc_sym = kernel_get_ref_reloc_sym(); + reloc_sym = kernel_get_ref_reloc_sym(&map); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); return -EINVAL; @@ -762,9 +768,13 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, continue; if (tevs[i].point.retprobe && !kretprobe_offset_is_supported()) continue; - /* If we found a wrong one, mark it by NULL symbol */ + /* + * If we found a wrong one, mark it by NULL symbol. + * Since addresses in debuginfo is same as objdump, we need + * to convert it to addresses on memory. + */ if (kprobe_warn_out_range(tevs[i].point.symbol, - tevs[i].point.address)) { + map__objdump_2mem(map, tevs[i].point.address))) { tmp = NULL; skipped++; } else { @@ -1745,8 +1755,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) fmt1_str = strtok_r(argv0_str, ":", &fmt); fmt2_str = strtok_r(NULL, "/", &fmt); fmt3_str = strtok_r(NULL, " \t", &fmt); - if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL - || fmt3_str == NULL) { + if (fmt1_str == NULL || fmt2_str == NULL || fmt3_str == NULL) { semantic_error("Failed to parse event name: %s\n", argv[0]); ret = -EINVAL; goto out; @@ -2911,7 +2920,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, /* Note that the symbols in the kmodule are not relocated */ if (!pev->uprobes && !pev->target && (!pp->retprobe || kretprobe_offset_is_supported())) { - reloc_sym = kernel_get_ref_reloc_sym(); + reloc_sym = kernel_get_ref_reloc_sym(NULL); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); ret = -EINVAL; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 6b40cc691a2d..8f4cf2e2b5aa 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -100,6 +100,7 @@ enum dso_binary_type distro_dwarf_types[] = { DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -598,38 +599,31 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, const char *function, struct probe_trace_point *tp) { - Dwarf_Addr eaddr, highaddr; + Dwarf_Addr eaddr; GElf_Sym sym; const char *symbol; /* Verify the address is correct */ - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", + if (!dwarf_haspc(sp_die, paddr)) { + pr_warning("Specified offset is out of %s\n", dwarf_diename(sp_die)); return -EINVAL; } - symbol = dwarf_diename(sp_die); - if (!symbol) { - /* Try to get the symbol name from symtab */ + if (dwarf_entrypc(sp_die, &eaddr) == 0) { + /* If the DIE has entrypc, use it. */ + symbol = dwarf_diename(sp_die); + } else { + /* Try to get actual symbol name and address from symtab */ symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); - if (!symbol) { - pr_warning("Failed to find symbol at 0x%lx\n", - (unsigned long)paddr); - return -ENOENT; - } eaddr = sym.st_value; } + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + tp->offset = (unsigned long)(paddr - eaddr); tp->address = (unsigned long)paddr; tp->symbol = strdup(symbol); @@ -750,6 +744,16 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) return 0; } +/* Return innermost DIE */ +static int find_inner_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; +} + /* Find an appropriate scope fits to given conditions */ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) { @@ -761,8 +765,13 @@ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) .die_mem = die_mem, .found = false, }; + int ret; - cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + ret = cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, + &fsp); + if (!ret && !fsp.found) + cu_walk_functions_at(&pf->cu_die, pf->addr, + find_inner_scope_cb, &fsp); return fsp.found ? die_mem : NULL; } @@ -936,7 +945,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ - if (dwarf_entrypc(in_die, &addr) != 0) { + if (die_entrypc(in_die, &addr) != 0) { pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); return -ENOENT; @@ -988,7 +997,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = find_probe_point_by_line(pf); } else if (die_is_func_instance(sp_die)) { /* Instances always have the entry address */ - dwarf_entrypc(sp_die, &pf->addr); + die_entrypc(sp_die, &pf->addr); /* But in some case the entry address is 0 */ if (pf->addr == 0) { pr_debug("%s has no entry PC. Skipped\n", @@ -1400,6 +1409,18 @@ error: return DIE_FIND_CB_END; } +static bool available_var_finder_overlap(struct available_var_finder *af) +{ + int i; + + for (i = 0; i < af->nvls; i++) { + if (af->pf.addr == af->vls[i].point.address) + return true; + } + return false; + +} + /* Add a found vars into available variables list */ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1410,6 +1431,14 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) Dwarf_Die die_mem; int ret; + /* + * For some reason (e.g. different column assigned to same address), + * this callback can be called with the address which already passed. + * Ignore it first. + */ + if (available_var_finder_overlap(af)) + return 0; + /* Check number of tevs */ if (af->nvls == af->max_vls) { pr_warning("Too many( > %d) probe point found.\n", af->max_vls); @@ -1553,7 +1582,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, /* Get function entry information */ func = basefunc = dwarf_diename(&spdie); if (!func || - dwarf_entrypc(&spdie, &baseaddr) != 0 || + die_entrypc(&spdie, &baseaddr) != 0 || dwarf_decl_line(&spdie, &baseline) != 0) { lineno = 0; goto post; @@ -1570,7 +1599,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { /* There is an inline function */ - if (dwarf_entrypc(&indie, &_addr) == 0 && + if (die_entrypc(&indie, &_addr) == 0 && _addr == addr) { /* * addr is at an inline function entry. diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 61aa7f3df915..6a0dcaee3f3e 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -539,10 +539,11 @@ static int perl_stop_script(void) static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.pl", outfile); @@ -603,8 +604,11 @@ sub print_backtrace\n\ }\n\n\ "); + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); - while ((event = trace_find_next_event(pevent, event))) { + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index c3bcc5947afb..8fc2c3e5b83c 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1603,10 +1603,11 @@ static int python_stop_script(void) static int python_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.py", outfile); @@ -1651,7 +1652,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); - while ((event = trace_find_next_event(pevent, event))) { + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); + + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 10ca1533937e..e0615e321f15 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -191,16 +191,30 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) bfd_vma pc, vma; bfd_size_type size; struct a2l_data *a2l = data; + flagword flags; if (a2l->found) return; - if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) +#ifdef bfd_get_section_flags + flags = bfd_get_section_flags(abfd, section); +#else + flags = bfd_section_flags(section); +#endif + if ((flags & SEC_ALLOC) == 0) return; pc = a2l->addr; +#ifdef bfd_get_section_vma vma = bfd_get_section_vma(abfd, section); +#else + vma = bfd_section_vma(section); +#endif +#ifdef bfd_get_section_size size = bfd_get_section_size(section); +#else + size = bfd_section_size(section); +#endif if (pc < vma || pc >= vma + size) return; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 94bed4031def..5280e84b9318 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -648,7 +648,7 @@ static void print_aggr(struct perf_stat_config *config, int s; bool first; - if (!(config->aggr_map || config->aggr_get_id)) + if (!config->aggr_map || !config->aggr_get_id) return; aggr_update_shadow(config, evlist); @@ -1120,7 +1120,7 @@ static void print_percore(struct perf_stat_config *config, int s; bool first = true; - if (!(config->aggr_map || config->aggr_get_id)) + if (!config->aggr_map || !config->aggr_get_id) return; for (s = 0; s < config->aggr_map->nr; s++) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index e2ce6021e6c4..17cd7e4a645e 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -358,8 +358,10 @@ int perf_stat_process_counter(struct perf_stat_config *config, * interval mode, otherwise overall avg running * averages will be shown for each interval. */ - if (config->interval) - init_stats(ps->res_stats); + if (config->interval) { + for (i = 0; i < 3; i++) + init_stats(&ps->res_stats[i]); + } if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3b49eb4e3ed9..ad893b4bd526 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -70,6 +70,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -1432,6 +1433,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: return !kmod && dso->kernel == DSO_TYPE_USER; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 20663a460df3..ff07ea319406 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -398,53 +398,75 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, return (i == num) ? true : false; } -int perf_time__parse_for_ranges(const char *time_str, +int perf_time__parse_for_ranges_reltime(const char *time_str, struct perf_session *session, struct perf_time_interval **ranges, - int *range_size, int *range_num) + int *range_size, int *range_num, + bool reltime) { + bool has_percent = strchr(time_str, '%'); struct perf_time_interval *ptime_range; - int size, num, ret; + int size, num, ret = -EINVAL; ptime_range = perf_time__range_alloc(time_str, &size); if (!ptime_range) return -ENOMEM; - if (perf_time__parse_str(ptime_range, time_str) != 0) { + if (has_percent || reltime) { if (session->evlist->first_sample_time == 0 && session->evlist->last_sample_time == 0) { pr_err("HINT: no first/last sample time found in perf data.\n" "Please use latest perf binary to execute 'perf record'\n" "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n"); - ret = -EINVAL; goto error; } + } + if (has_percent) { num = perf_time__percent_parse_str( ptime_range, size, time_str, session->evlist->first_sample_time, session->evlist->last_sample_time); - if (num < 0) { - pr_err("Invalid time string\n"); - ret = -EINVAL; - goto error; - } + if (num < 0) + goto error_invalid; } else { + if (perf_time__parse_str(ptime_range, time_str)) + goto error_invalid; num = 1; } + if (reltime) { + int i; + + for (i = 0; i < num; i++) { + ptime_range[i].start += session->evlist->first_sample_time; + ptime_range[i].end += session->evlist->first_sample_time; + } + } + *range_size = size; *range_num = num; *ranges = ptime_range; return 0; +error_invalid: + pr_err("Invalid time string\n"); error: free(ptime_range); return ret; } +int perf_time__parse_for_ranges(const char *time_str, + struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num) +{ + return perf_time__parse_for_ranges_reltime(time_str, session, ranges, + range_size, range_num, false); +} + int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) { u64 sec = timestamp / NSEC_PER_SEC; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index 72a42ea1d513..e07b698172f5 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -25,6 +25,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, struct perf_session; +int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num, + bool reltime); + int perf_time__parse_for_ranges(const char *str, struct perf_session *session, struct perf_time_interval **ranges, int *range_size, int *range_num); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index d388f80d8703..fc9cffb4087d 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -176,8 +176,10 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) continue; - if (!match_pat(d->d_name, pat)) - return -2; + if (!match_pat(d->d_name, pat)) { + ret = -2; + break; + } scnprintf(namebuf, sizeof(namebuf), "%s/%s", path, d->d_name); |