diff options
Diffstat (limited to 'tools/perf')
56 files changed, 409 insertions, 153 deletions
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 32f4a898e3f2..05c10eb56a0c 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -114,7 +114,7 @@ Given a $HOME/.perfconfig like this: [report] # Defaults - sort-order = comm,dso,symbol + sort_order = comm,dso,symbol percent-limit = 0 queue-size = 0 children = true diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index e30d20fb482d..849b3be15bd8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -294,6 +294,8 @@ ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1) BIONIC := 1 + CFLAGS += -DLACKS_SIGQUEUE_PROTOTYPE + CFLAGS += -DLACKS_OPEN_MEMSTREAM_PROTOTYPE EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) endif @@ -686,18 +688,20 @@ endif ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd +else + # we are on a system that requires -liberty and (maybe) -lz + # to link against -lbfd; test each case individually here # call all detections now so we get correct # status in VF output - $(call feature_check,liberty) - $(call feature_check,liberty-z) - $(call feature_check,cplus-demangle) + $(call feature_check,libbfd-liberty) + $(call feature_check,libbfd-liberty-z) - ifeq ($(feature-liberty), 1) - EXTLIBS += -liberty + ifeq ($(feature-libbfd-liberty), 1) + EXTLIBS += -lbfd -liberty else - ifeq ($(feature-liberty-z), 1) - EXTLIBS += -liberty -lz + ifeq ($(feature-libbfd-liberty-z), 1) + EXTLIBS += -lbfd -liberty -lz endif endif endif @@ -707,24 +711,24 @@ ifdef NO_DEMANGLE else ifdef HAVE_CPLUS_DEMANGLE_SUPPORT EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else - ifneq ($(feature-libbfd), 1) - ifneq ($(feature-liberty), 1) - ifneq ($(feature-liberty-z), 1) - # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT - # or any of 'bfd iberty z' trinity - ifeq ($(feature-cplus-demangle), 1) - EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT - else - msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) - CFLAGS += -DNO_DEMANGLE - endif - endif + ifeq ($(filter -liberty,$(EXTLIBS)),) + $(call feature_check,cplus-demangle) + + # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT + # or any of 'bfd iberty z' trinity + ifeq ($(feature-cplus-demangle), 1) + EXTLIBS += -liberty + else + msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) + CFLAGS += -DNO_DEMANGLE endif endif endif + + ifneq ($(filter -liberty,$(EXTLIBS)),) + CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT + endif endif ifneq ($(filter -lbfd,$(EXTLIBS)),) diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 82657c01a3b8..5f69fd0b745a 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -200,3 +200,13 @@ int perf_env__lookup_objdump(struct perf_env *env, const char **path) return perf_env__lookup_binutils_path(env, "objdump", path); } + +/* + * Some architectures have a single address space for kernel and user addresses, + * which makes it possible to determine if an address is in kernel space or user + * space. + */ +bool perf_env__single_address_space(struct perf_env *env) +{ + return strcmp(perf_env__arch(env), "sparc"); +} diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h index 2167001b18c5..c298a446d1f6 100644 --- a/tools/perf/arch/common.h +++ b/tools/perf/arch/common.h @@ -5,5 +5,6 @@ #include "../util/env.h" int perf_env__lookup_objdump(struct perf_env *env, const char **path); +bool perf_env__single_address_space(struct perf_env *env); #endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index db0ba8caf5a2..ba8ecaf52200 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -524,10 +524,21 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, struct perf_evsel *evsel) { int err; + char c; if (!evsel) return 0; + /* + * If supported, force pass-through config term (pt=1) even if user + * sets pt=0, which avoids senseless kernel errors. + */ + if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + !(evsel->attr.config & 1)) { + pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); + evsel->attr.config |= 1; + } + err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", evsel->attr.config); diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index b32409a0e546..081353d7b095 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -156,7 +156,7 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) if (strstr(cpuid, "Intel")) { kvm->exit_reasons = vmx_exit_reasons; kvm->exit_reasons_isa = "VMX"; - } else if (strstr(cpuid, "AMD")) { + } else if (strstr(cpuid, "AMD") || strstr(cpuid, "Hygon")) { kvm->exit_reasons = svm_exit_reasons; kvm->exit_reasons_isa = "SVM"; } else diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 44195514b19e..fa56fde6e8d8 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -38,6 +38,10 @@ #include <numa.h> #include <numaif.h> +#ifndef RUSAGE_THREAD +# define RUSAGE_THREAD 1 +#endif + /* * Regular printout to the terminal, supressed if -q is specified: */ diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f3aa9d02a5ab..763c2edf52e7 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2055,6 +2055,12 @@ static int setup_nodes(struct perf_session *session) if (!set) return -ENOMEM; + nodes[node] = set; + + /* empty node, skip */ + if (cpu_map__empty(map)) + continue; + for (cpu = 0; cpu < map->nr; cpu++) { set_bit(map->map[cpu], set); @@ -2063,8 +2069,6 @@ static int setup_nodes(struct perf_session *session) cpu2node[map->map[cpu]] = node; } - - nodes[node] = set; } setup_nodes_header(); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ba481d73f910..53c11fc0855e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -727,8 +727,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, if (PRINT_FIELD(DSO)) { memset(&alf, 0, sizeof(alf)); memset(&alt, 0, sizeof(alt)); - thread__find_map(thread, sample->cpumode, from, &alf); - thread__find_map(thread, sample->cpumode, to, &alt); + thread__find_map_fb(thread, sample->cpumode, from, &alf); + thread__find_map_fb(thread, sample->cpumode, to, &alt); } printed += fprintf(fp, " 0x%"PRIx64, from); @@ -774,8 +774,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_symbol(thread, sample->cpumode, from, &alf); - thread__find_symbol(thread, sample->cpumode, to, &alt); + thread__find_symbol_fb(thread, sample->cpumode, from, &alf); + thread__find_symbol_fb(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); if (PRINT_FIELD(DSO)) { @@ -819,11 +819,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - if (thread__find_map(thread, sample->cpumode, from, &alf) && + if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - if (thread__find_map(thread, sample->cpumode, to, &alt) && + if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); @@ -1589,13 +1589,8 @@ static void perf_sample__fprint_metric(struct perf_script *script, .force_header = false, }; struct perf_evsel *ev2; - static bool init; u64 val; - if (!init) { - perf_stat__init_shadow_stats(); - init = true; - } if (!evsel->stats) perf_evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) @@ -1658,7 +1653,7 @@ static void process_event(struct perf_script *script, return; } - if (PRINT_FIELD(TRACE)) { + if (PRINT_FIELD(TRACE) && sample->raw_data) { event_format__fprintf(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size, fp); } @@ -2214,6 +2209,8 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); + perf_stat__init_shadow_stats(); + /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d097b5b47eb8..40720150ccd8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1961,7 +1961,7 @@ static int parse_metric_groups(const struct option *opt, return metricgroup__parse_groups(opt, str, &metric_events); } -static const struct option stat_options[] = { +static struct option stat_options[] = { OPT_BOOLEAN('T', "transaction", &transaction_run, "hardware transaction statistics"), OPT_CALLBACK('e', "event", &evsel_list, "event", @@ -2847,6 +2847,12 @@ int cmd_stat(int argc, const char **argv) return -ENOMEM; parse_events__shrink_config_terms(); + + /* String-parsing callback-based options would segfault when negated */ + set_option_flag(stat_options, 'e', "event", PARSE_OPT_NONEG); + set_option_flag(stat_options, 'M', "metrics", PARSE_OPT_NONEG); + set_option_flag(stat_options, 'G', "cgroup", PARSE_OPT_NONEG); + argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands, (const char **) stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index a827919c6263..775b99833e51 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -43,6 +43,10 @@ #include "util/data.h" #include "util/debug.h" +#ifdef LACKS_OPEN_MEMSTREAM_PROTOTYPE +FILE *open_memstream(char **ptr, size_t *sizeloc); +#endif + #define SUPPORT_OLD_POWER_EVENTS 1 #define PWR_EVENT_EXIT -1 diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d21d8751e749..33eefc33e0ea 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1491,8 +1491,9 @@ int cmd_top(int argc, const char **argv) annotation_config__init(); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); - if (symbol__init(NULL) < 0) - return -1; + status = symbol__init(NULL); + if (status < 0) + goto out_delete_evlist; sort__setup_elide(stdout); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 22ab8e67c760..3f43aedb384d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2263,19 +2263,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 466540ee8ea7..c72cc73a6b09 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -14,6 +14,7 @@ include/uapi/linux/sched.h include/uapi/linux/stat.h include/uapi/linux/vhost.h include/uapi/sound/asound.h +include/linux/bits.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 36c903faed0b..71e9737f4614 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -73,7 +73,7 @@ }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", - "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 36c903faed0b..71e9737f4614 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -73,7 +73,7 @@ }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", - "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ff9b60b99f52..44090a9a19f3 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -116,7 +116,7 @@ class Event(dict): if not self.has_key(t) or not other.has_key(t): continue if not data_equal(self[t], other[t]): - log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) + log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) # Test file description needs to have following sections: # [config] diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index a467615c5a0e..910e25e64188 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -291,12 +291,20 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused bool test__bp_signal_is_supported(void) { -/* - * The powerpc so far does not have support to even create - * instruction breakpoint using the perf event interface. - * Once it's there we can release this. - */ -#if defined(__powerpc__) || defined(__s390x__) + /* + * PowerPC and S390 do not support creation of instruction + * breakpoints using the perf_event interface. + * + * ARM requires explicit rounding down of the instruction + * pointer in Thumb mode, and then requires the single-step + * to be handled explicitly in the overflow handler to avoid + * stepping into the SIGIO handler and getting stuck on the + * breakpointed instruction. + * + * Just disable the test for these architectures until these + * issues are resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) return false; #else return true; diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 699561fa512c..926a8e1b5e94 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | FIELD_IS_SIGNED); + is_signed = !!(field->flags & FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); @@ -43,7 +43,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "prev_comm", 16, true)) + if (perf_evsel__test_field(evsel, "prev_comm", 16, false)) ret = -1; if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) @@ -55,7 +55,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true)) ret = -1; - if (perf_evsel__test_field(evsel, "next_comm", 16, true)) + if (perf_evsel__test_field(evsel, "next_comm", 16, false)) ret = -1; if (perf_evsel__test_field(evsel, "next_pid", 4, true)) @@ -73,7 +73,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "comm", 16, true)) + if (perf_evsel__test_field(evsel, "comm", 16, false)) ret = -1; if (perf_evsel__test_field(evsel, "pid", 4, true)) @@ -85,5 +85,6 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; + perf_evsel__delete(evsel); return ret; } diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 01f0706995a9..9acc1e80b936 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -19,7 +19,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) const char *p; const char **other; double val; - int ret; + int i, ret; struct parse_ctx ctx; int num_other; @@ -56,6 +56,9 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ")); TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO")); TEST_ASSERT_VAL("find other", other[3] == NULL); + + for (i = 0; i < num_other; i++) + free((void *)other[i]); free((void *)other); return 0; diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index c531e6deb104..493ecb611540 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -45,7 +45,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int if (IS_ERR(evsel)) { tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat"); pr_debug("%s\n", errbuf); - goto out_thread_map_delete; + goto out_cpu_map_delete; } if (perf_evsel__open(evsel, cpus, threads) < 0) { @@ -119,6 +119,8 @@ out_close_fd: perf_evsel__close_fd(evsel); out_evsel_delete: perf_evsel__delete(evsel); +out_cpu_map_delete: + cpu_map__put(cpus); out_thread_map_delete: thread_map__put(threads); return err; diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 1c16e56cd93e..7cb99b433888 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -13,7 +13,8 @@ add_probe_vfs_getname() { local verbose=$1 if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string" + perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" fi } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 28cd6a17491b..dfee110b3a58 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1862,6 +1862,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, struct annotation_options *options, struct arch **parch) { + struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { .privsize = privsize, .evsel = evsel, @@ -1892,6 +1893,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, args.ms.map = map; args.ms.sym = sym; + notes->start = map__rip_2objdump(map, sym->start); return symbol__disassemble(sym, &args); } @@ -2746,8 +2748,6 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev symbol__calc_percent(sym, evsel); - notes->start = map__rip_2objdump(map, sym->start); - annotation__set_offsets(notes, size); annotation__mark_jump_targets(notes, sym); annotation__compute_ipc(notes, size); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index db1511359c5e..40c93d8158b5 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1273,9 +1273,9 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm, } /* padding must be written by fn() e.g. record__process_auxtrace() */ - padding = size & 7; + padding = size & (PERF_AUXTRACE_RECORD_ALIGNMENT - 1); if (padding) - padding = 8 - padding; + padding = PERF_AUXTRACE_RECORD_ALIGNMENT - padding; memset(&ev, 0, sizeof(ev)); ev.auxtrace.header.type = PERF_RECORD_AUXTRACE; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 71fc3bd74299..136c5f95f9bf 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -38,6 +38,9 @@ struct record_opts; struct auxtrace_info_event; struct events_stats; +/* Auxtrace records must have the same alignment as perf event records */ +#define PERF_AUXTRACE_RECORD_ALIGNMENT 8 + enum auxtrace_type { PERF_AUXTRACE_UNKNOWN, PERF_AUXTRACE_INTEL_PT, diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 04b1d53e4bf9..1d352621bd48 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -183,6 +183,7 @@ char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size) return bf; } +/* The caller is responsible to free the returned buffer. */ char *build_id_cache__origname(const char *sbuild_id) { char *linkname; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 32ef7bdca1cf..dc2212e12184 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -766,6 +766,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, cnode->cycles_count += node->branch_flags.cycles; cnode->iter_count += node->nr_loop_iter; cnode->iter_cycles += node->iter_cycles; + cnode->from_count++; } } @@ -1345,10 +1346,10 @@ static int branch_to_str(char *bf, int bfsize, static int branch_from_str(char *bf, int bfsize, u64 branch_count, u64 cycles_count, u64 iter_count, - u64 iter_cycles) + u64 iter_cycles, u64 from_count) { int printed = 0, i = 0; - u64 cycles; + u64 cycles, v = 0; cycles = cycles_count / branch_count; if (cycles) { @@ -1357,14 +1358,16 @@ static int branch_from_str(char *bf, int bfsize, bf + printed, bfsize - printed); } - if (iter_count) { - printed += count_pri64_printf(i++, "iter", - iter_count, - bf + printed, bfsize - printed); + if (iter_count && from_count) { + v = iter_count / from_count; + if (v) { + printed += count_pri64_printf(i++, "iter", + v, bf + printed, bfsize - printed); - printed += count_pri64_printf(i++, "avg_cycles", - iter_cycles / iter_count, - bf + printed, bfsize - printed); + printed += count_pri64_printf(i++, "avg_cycles", + iter_cycles / iter_count, + bf + printed, bfsize - printed); + } } if (i) @@ -1377,6 +1380,7 @@ static int counts_str_build(char *bf, int bfsize, u64 branch_count, u64 predicted_count, u64 abort_count, u64 cycles_count, u64 iter_count, u64 iter_cycles, + u64 from_count, struct branch_type_stat *brtype_stat) { int printed; @@ -1389,7 +1393,8 @@ static int counts_str_build(char *bf, int bfsize, predicted_count, abort_count, brtype_stat); } else { printed = branch_from_str(bf, bfsize, branch_count, - cycles_count, iter_count, iter_cycles); + cycles_count, iter_count, iter_cycles, + from_count); } if (!printed) @@ -1402,13 +1407,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, u64 branch_count, u64 predicted_count, u64 abort_count, u64 cycles_count, u64 iter_count, u64 iter_cycles, + u64 from_count, struct branch_type_stat *brtype_stat) { char str[256]; counts_str_build(str, sizeof(str), branch_count, predicted_count, abort_count, cycles_count, - iter_count, iter_cycles, brtype_stat); + iter_count, iter_cycles, from_count, brtype_stat); if (fp) return fprintf(fp, "%s", str); @@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist, u64 branch_count, predicted_count; u64 abort_count, cycles_count; u64 iter_count, iter_cycles; + u64 from_count; branch_count = clist->branch_count; predicted_count = clist->predicted_count; @@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist, cycles_count = clist->cycles_count; iter_count = clist->iter_count; iter_cycles = clist->iter_cycles; + from_count = clist->from_count; return callchain_counts_printf(fp, bf, bfsize, branch_count, predicted_count, abort_count, cycles_count, iter_count, iter_cycles, - &clist->brtype_stat); + from_count, &clist->brtype_stat); } static void free_callchain_node(struct callchain_node *node) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 154560b1eb65..99d38ac019b8 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -118,6 +118,7 @@ struct callchain_list { bool has_children; }; u64 branch_count; + u64 from_count; u64 predicted_count; u64 abort_count; u64 cycles_count; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 5ac157056cdf..9bb742accfa5 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -628,11 +628,10 @@ static int collect_config(const char *var, const char *value, } ret = set_value(item, value); - return ret; out_free: free(key); - return -1; + return ret; } int perf_config_set__collect(struct perf_config_set *set, const char *file_name, diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..383674f448fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (!cpu_list) return cpu_map__read_all_cpu_map(); - if (!isdigit(*cpu_list)) + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') goto out; while (isdigit(*cpu_list)) { @@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else + else if (*cpu_list != '\0') cpus = cpu_map__default_new(); + else + cpus = cpu_map__dummy_new(); invalid: free(tmp_cpus); out: diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index ca577658e890..7b5e15cc6b71 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1005,7 +1005,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) } swap_packet: - if (etmq->etm->synth_opts.last_branch) { + if (etm->sample_branches || etm->synth_opts.last_branch) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index bbed90e5d9bb..cee717a3794f 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -295,7 +295,7 @@ static int decompress_kmodule(struct dso *dso, const char *name, unlink(tmpbuf); if (pathname && (fd >= 0)) - strncpy(pathname, tmpbuf, len); + strlcpy(pathname, tmpbuf, len); return fd; } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 59f38c7693f8..4c23779e271a 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -166,7 +166,7 @@ const char *perf_env__arch(struct perf_env *env) struct utsname uts; char *arch_name; - if (!env) { /* Assume local operation */ + if (!env || !env->arch) { /* Assume local operation */ if (uname(&uts) < 0) return NULL; arch_name = uts.machine; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index bc646185f8d9..aa9c7df120ca 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1576,6 +1576,24 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return al->map; } +/* + * For branch stacks or branch samples, the sample cpumode might not be correct + * because it applies only to the sample 'ip' and not necessary to 'addr' or + * branch stack addresses. If possible, use a fallback to deal with those cases. + */ +struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) +{ + struct map *map = thread__find_map(thread, cpumode, addr, al); + struct machine *machine = thread->mg->machine; + u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr); + + if (map || addr_cpumode == cpumode) + return map; + + return thread__find_map(thread, addr_cpumode, addr, al); +} + struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { @@ -1585,6 +1603,15 @@ struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, return al->sym; } +struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al) +{ + al->sym = NULL; + if (thread__find_map_fb(thread, cpumode, addr, al)) + al->sym = map__find_symbol(al->map, al->addr); + return al->sym; +} + /* * Callers need to drop the reference to al->thread, obtained in * machine__findnew_thread() @@ -1678,7 +1705,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - thread__find_map(thread, sample->cpumode, sample->addr, al); + thread__find_map_fb(thread, sample->cpumode, sample->addr, al); al->cpu = sample->cpu; al->sym = NULL; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index be440df29615..819aa4491b53 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -34,6 +34,10 @@ #include <linux/log2.h> #include <linux/err.h> +#ifdef LACKS_SIGQUEUE_PROTOTYPE +int sigqueue(pid_t pid, int sig, const union sigval value); +#endif + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index e7dbdcc8d465..b65ad5a273eb 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1274,6 +1274,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); assert(evsel->evlist == NULL); + perf_evsel__free_counts(evsel); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 3cadc252dd89..bd9226bc5945 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2636,6 +2636,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) struct perf_header *header = &session->header; int fd = perf_data__fd(session->data); struct stat st; + time_t stctime; int ret, bit; hd.fp = fp; @@ -2645,7 +2646,8 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - fprintf(fp, "# captured on : %s", ctime(&st.st_ctime)); + stctime = st.st_ctime; + fprintf(fp, "# captured on : %s", ctime(&stctime)); fprintf(fp, "# header version : %u\n", header->version); fprintf(fp, "# data offset : %" PRIu64 "\n", header->data_offset); @@ -3521,7 +3523,7 @@ perf_event__synthesize_event_update_unit(struct perf_tool *tool, if (ev == NULL) return -ENOMEM; - strncpy(ev->data, evsel->unit, size); + strlcpy(ev->data, evsel->unit, size + 1); err = process(tool, (union perf_event *)ev, NULL, NULL); free(ev); return err; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 828cb9794c76..e1e94b44d588 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1048,8 +1048,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); - if (err) + if (err) { + map__put(alm); return err; + } err = iter->ops->prepare_entry(iter, al); if (err) 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 d404bed7003a..4357141c7c92 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -26,6 +26,7 @@ #include "../cache.h" #include "../util.h" +#include "../auxtrace.h" #include "intel-pt-insn-decoder.h" #include "intel-pt-pkt-decoder.h" @@ -57,6 +58,7 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_NO_IP, INTEL_PT_STATE_ERR_RESYNC, INTEL_PT_STATE_IN_SYNC, + INTEL_PT_STATE_TNT_CONT, INTEL_PT_STATE_TNT, INTEL_PT_STATE_TIP, INTEL_PT_STATE_TIP_PGD, @@ -71,8 +73,9 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) case INTEL_PT_STATE_NO_IP: case INTEL_PT_STATE_ERR_RESYNC: case INTEL_PT_STATE_IN_SYNC: - case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: return true; + case INTEL_PT_STATE_TNT: case INTEL_PT_STATE_TIP: case INTEL_PT_STATE_TIP_PGD: case INTEL_PT_STATE_FUP: @@ -250,19 +253,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d)) decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n / decoder->tsc_ctc_ratio_d; - - /* - * Allow for timestamps appearing to backwards because a TSC - * packet has slipped past a MTC packet, so allow 2 MTC ticks - * or ... - */ - decoder->tsc_slip = multdiv(2 << decoder->mtc_shift, - decoder->tsc_ctc_ratio_n, - decoder->tsc_ctc_ratio_d); } - /* ... or 0x100 paranoia */ - if (decoder->tsc_slip < 0x100) - decoder->tsc_slip = 0x100; + + /* + * A TSC packet can slip past MTC packets so that the timestamp appears + * to go backwards. One estimate is that can be up to about 40 CPU + * cycles, which is certainly less than 0x1000 TSC ticks, but accept + * slippage an order of magnitude more to be on the safe side. + */ + decoder->tsc_slip = 0x10000; intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift); intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n); @@ -891,16 +890,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder) timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; if (decoder->continuous_period) { - if (masked_timestamp != decoder->last_masked_timestamp) + if (masked_timestamp > decoder->last_masked_timestamp) return 1; } else { timestamp += 1; masked_timestamp = timestamp & decoder->period_mask; - if (masked_timestamp != decoder->last_masked_timestamp) { + if (masked_timestamp > decoder->last_masked_timestamp) { decoder->last_masked_timestamp = masked_timestamp; decoder->continuous_period = true; } } + + if (masked_timestamp < decoder->last_masked_timestamp) + return decoder->period_ticks; + return decoder->period_ticks - (timestamp - masked_timestamp); } @@ -929,7 +932,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder) case INTEL_PT_PERIOD_TICKS: timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; - decoder->last_masked_timestamp = masked_timestamp; + if (masked_timestamp > decoder->last_masked_timestamp) + decoder->last_masked_timestamp = masked_timestamp; + else + decoder->last_masked_timestamp += decoder->period_ticks; break; case INTEL_PT_PERIOD_NONE: case INTEL_PT_PERIOD_MTC: @@ -1252,7 +1258,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return -ENOENT; } decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->tnt.payload <<= 1; decoder->state.from_ip = decoder->ip; @@ -1283,7 +1291,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) { decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (decoder->tnt.payload & BIT63) { decoder->tnt.payload <<= 1; @@ -1303,8 +1313,11 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return 0; } decoder->ip += intel_pt_insn.length; - if (!decoder->tnt.count) + if (!decoder->tnt.count) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; return -EAGAIN; + } decoder->tnt.payload <<= 1; continue; } @@ -1389,7 +1402,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) { intel_pt_log("ERROR: Buffer overflow\n"); intel_pt_clear_tx_flags(decoder); - decoder->cbr = 0; decoder->timestamp_insn_cnt = 0; decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; decoder->overflow = true; @@ -2353,6 +2365,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_trace(decoder); break; case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: err = intel_pt_walk_tnt(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); @@ -2559,6 +2572,34 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2) } } +#define MAX_PADDING (PERF_AUXTRACE_RECORD_ALIGNMENT - 1) + +/** + * adj_for_padding - adjust overlap to account for padding. + * @buf_b: second buffer + * @buf_a: first buffer + * @len_a: size of first buffer + * + * @buf_a might have up to 7 bytes of padding appended. Adjust the overlap + * accordingly. + * + * Return: A pointer into @buf_b from where non-overlapped data starts + */ +static unsigned char *adj_for_padding(unsigned char *buf_b, + unsigned char *buf_a, size_t len_a) +{ + unsigned char *p = buf_b - MAX_PADDING; + unsigned char *q = buf_a + len_a - MAX_PADDING; + int i; + + for (i = MAX_PADDING; i; i--, p++, q++) { + if (*p != *q) + break; + } + + return p; +} + /** * intel_pt_find_overlap_tsc - determine start of non-overlapped trace data * using TSC. @@ -2609,8 +2650,11 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, /* Same TSC, so buffers are consecutive */ if (!cmp && rem_b >= rem_a) { + unsigned char *start; + *consecutive = true; - return buf_b + len_b - (rem_b - rem_a); + start = buf_b + len_b - (rem_b - rem_a); + return adj_for_padding(start, buf_a, len_a); } if (cmp < 0) return buf_b; /* tsc_a < tsc_b => no overlap */ @@ -2673,7 +2717,7 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, found = memmem(buf_a, len_a, buf_b, len_a); if (found) { *consecutive = true; - return buf_b + len_a; + return adj_for_padding(buf_b + len_a, buf_a, len_a); } /* Try again at next PSB in buffer 'a' */ diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 4f48bc11a29c..ff2c41ea94c8 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2507,6 +2507,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event, } pt->timeless_decoding = intel_pt_timeless_decoding(pt); + if (pt->timeless_decoding && !pt->tc.time_mult) + pt->tc.time_mult = 1; pt->have_tsc = intel_pt_have_tsc(pt); pt->sampling_mode = false; pt->est_tsc = !pt->timeless_decoding; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8ee8ab39d8ac..076718a7b3ea 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1358,6 +1358,20 @@ static void machine__set_kernel_mmap(struct machine *machine, machine->vmlinux_map->end = ~0ULL; } +static void machine__update_kernel_mmap(struct machine *machine, + u64 start, u64 end) +{ + struct map *map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + machine__set_kernel_mmap(machine, start, end); + + map_groups__insert(&machine->kmaps, map); + map__put(map); +} + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); @@ -1390,17 +1404,11 @@ int machine__create_kernel_maps(struct machine *machine) goto out_put; } - /* we have a real start address now, so re-order the kmaps */ - map = machine__kernel_map(machine); - - map__get(map); - map_groups__remove(&machine->kmaps, map); - - /* assume it's the last in the kmaps */ - machine__set_kernel_mmap(machine, addr, ~0ULL); - - map_groups__insert(&machine->kmaps, map); - map__put(map); + /* + * we have a real start address now, so re-order the kmaps + * assume it's the last in the kmaps + */ + machine__update_kernel_mmap(machine, addr, ~0ULL); } if (machine__create_extra_kernel_maps(machine, kernel)) @@ -1536,7 +1544,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__set_kernel_mmap(machine, event->mmap.start, + machine__update_kernel_mmap(machine, event->mmap.start, event->mmap.start + event->mmap.len); /* @@ -1988,7 +1996,7 @@ static void save_iterations(struct iterations *iter, { int i; - iter->nr_loop_iter = nr; + iter->nr_loop_iter++; iter->cycles = 0; for (i = 0; i < nr; i++) @@ -2575,6 +2583,33 @@ int machine__get_kernel_start(struct machine *machine) return err; } +u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr) +{ + u8 addr_cpumode = cpumode; + bool kernel_ip; + + if (!machine->single_address_space) + goto out; + + kernel_ip = machine__kernel_ip(machine, addr); + switch (cpumode) { + case PERF_RECORD_MISC_KERNEL: + case PERF_RECORD_MISC_USER: + addr_cpumode = kernel_ip ? PERF_RECORD_MISC_KERNEL : + PERF_RECORD_MISC_USER; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + case PERF_RECORD_MISC_GUEST_USER: + addr_cpumode = kernel_ip ? PERF_RECORD_MISC_GUEST_KERNEL : + PERF_RECORD_MISC_GUEST_USER; + break; + default: + break; + } +out: + return addr_cpumode; +} + struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { return dsos__findnew(&machine->dsos, filename); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index d856b85862e2..ebde3ea70225 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -42,6 +42,7 @@ struct machine { u16 id_hdr_size; bool comm_exec; bool kptr_restrict_warned; + bool single_address_space; char *root_dir; char *mmap_name; struct threads threads[THREADS__TABLE_SIZE]; @@ -99,6 +100,8 @@ static inline bool machine__kernel_ip(struct machine *machine, u64 ip) return ip >= kernel_start; } +u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr); + struct thread *machine__find_thread(struct machine *machine, pid_t pid, pid_t tid); struct comm *machine__thread_exec_comm(struct machine *machine, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f8cd3e7c9186..1a7c76d2baa8 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2263,6 +2263,7 @@ static bool is_event_supported(u8 type, unsigned config) perf_evsel__delete(evsel); } + thread_map__put(tmap); return ret; } @@ -2333,6 +2334,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, printf(" %-50s [%s]\n", buf, "SDT event"); free(buf); } + free(path); } else printf(" %-50s [%s]\n", nd->s, "SDT event"); if (nd2) { @@ -2454,7 +2456,7 @@ restart: if (!name_only && strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else - strncpy(name, syms->symbol, MAX_NAME_LEN); + strlcpy(name, syms->symbol, MAX_NAME_LEN); evt_list[evt_i] = strdup(name); if (evt_list[evt_i] == NULL) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7e49baad304d..36cfc64c3824 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -145,7 +145,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * int fd, ret = -1; char path[PATH_MAX]; - snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + scnprintf(path, PATH_MAX, "%s/%s.scale", dir, name); fd = open(path, O_RDONLY); if (fd == -1) @@ -175,7 +175,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n ssize_t sret; int fd; - snprintf(path, PATH_MAX, "%s/%s.unit", dir, name); + scnprintf(path, PATH_MAX, "%s/%s.unit", dir, name); fd = open(path, O_RDONLY); if (fd == -1) @@ -205,7 +205,7 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name) char path[PATH_MAX]; int fd; - snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name); + scnprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name); fd = open(path, O_RDONLY); if (fd == -1) @@ -223,7 +223,7 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, char path[PATH_MAX]; int fd; - snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name); + scnprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name); fd = open(path, O_RDONLY); if (fd == -1) @@ -773,10 +773,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; + + /* + * uncore alias may be from different PMU + * with common prefix + */ + if (pmu_is_uncore(name) && + !strncmp(pname, name, strlen(pname))) + goto new_alias; + if (strcmp(pname, name)) continue; } +new_alias: /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index f119eb628dbb..a22e1f538aea 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -157,8 +157,10 @@ static struct map *kernel_get_module_map(const char *module) if (module && strchr(module, '/')) return dso__new_map(module); - if (!module) - module = "kernel"; + if (!module) { + pos = machine__kernel_map(host_machine); + return map__get(pos); + } for (pos = maps__first(maps); pos; pos = map__next(pos)) { /* short_name is "[module]" */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index b76088fadf3d..6a6548890d5a 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -424,7 +424,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target, if (target && build_id_cache__cached(target)) { /* This is a cached buildid */ - strncpy(sbuildid, target, SBUILD_ID_SIZE); + strlcpy(sbuildid, target, SBUILD_ID_SIZE); dir_name = build_id_cache__linkname(sbuildid, NULL, 0); goto found; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index ce501ba14b08..69f5f6142dcf 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -939,7 +939,8 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, file = PyFile_FromFile(fp, "perf", "r", NULL); #else - file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1); + file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, + NULL, NULL, NULL, 0); #endif if (file == NULL) goto free_list; diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index d2c78ffd9fee..910f2621d211 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -294,6 +294,11 @@ static bool s390_cpumsf_validate(int machine_type, *dsdes = 85; *bsdes = 32; break; + case 2964: + case 2965: + *dsdes = 112; + *bsdes = 32; + break; default: /* Illegal trailer entry */ return false; @@ -499,7 +504,7 @@ static int s390_cpumsf_samples(struct s390_cpumsf_queue *sfq, u64 *ts) aux_ts = get_trailer_time(buf); if (!aux_ts) { pr_err("[%#08" PRIx64 "] Invalid AUX trailer entry TOD clock base\n", - sfq->buffer->data_offset); + (s64)sfq->buffer->data_offset); aux_ts = ~0ULL; goto out; } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index dfc6093f118c..9569cc06e0a7 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -494,14 +494,14 @@ static PyObject *python_process_brstack(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "cycles", PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles)); - thread__find_map(thread, sample->cpumode, - br->entries[i].from, &al); + thread__find_map_fb(thread, sample->cpumode, + br->entries[i].from, &al); dsoname = get_dsoname(al.map); pydict_set_item_string_decref(pyelem, "from_dsoname", _PyUnicode_FromString(dsoname)); - thread__find_map(thread, sample->cpumode, - br->entries[i].to, &al); + thread__find_map_fb(thread, sample->cpumode, + br->entries[i].to, &al); dsoname = get_dsoname(al.map); pydict_set_item_string_decref(pyelem, "to_dsoname", _PyUnicode_FromString(dsoname)); @@ -576,14 +576,14 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample, if (!pyelem) Py_FatalError("couldn't create Python dictionary"); - thread__find_symbol(thread, sample->cpumode, - br->entries[i].from, &al); + thread__find_symbol_fb(thread, sample->cpumode, + br->entries[i].from, &al); get_symoff(al.sym, &al, true, bf, sizeof(bf)); pydict_set_item_string_decref(pyelem, "from", _PyUnicode_FromString(bf)); - thread__find_symbol(thread, sample->cpumode, - br->entries[i].to, &al); + thread__find_symbol_fb(thread, sample->cpumode, + br->entries[i].to, &al); get_symoff(al.sym, &al, true, bf, sizeof(bf)); pydict_set_item_string_decref(pyelem, "to", _PyUnicode_FromString(bf)); @@ -733,8 +733,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize( - (const char *)&evsel->attr, sizeof(evsel->attr))); + pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->attr, sizeof(evsel->attr))); pydict_set_item_string_decref(dict_sample, "pid", _PyLong_FromLong(sample->pid)); @@ -1494,34 +1493,40 @@ static void _free_command_line(wchar_t **command_line, int num) static int python_start_script(const char *script, int argc, const char **argv) { struct tables *tables = &tables_global; + PyMODINIT_FUNC (*initfunc)(void); #if PY_MAJOR_VERSION < 3 const char **command_line; #else wchar_t **command_line; #endif - char buf[PATH_MAX]; + /* + * Use a non-const name variable to cope with python 2.6's + * PyImport_AppendInittab prototype + */ + char buf[PATH_MAX], name[19] = "perf_trace_context"; int i, err = 0; FILE *fp; #if PY_MAJOR_VERSION < 3 + initfunc = initperf_trace_context; command_line = malloc((argc + 1) * sizeof(const char *)); command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; #else + initfunc = PyInit_perf_trace_context; command_line = malloc((argc + 1) * sizeof(wchar_t *)); command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); #endif + PyImport_AppendInittab(name, initfunc); Py_Initialize(); #if PY_MAJOR_VERSION < 3 - initperf_trace_context(); PySys_SetArgv(argc + 1, (char **)command_line); #else - PyInit_perf_trace_context(); PySys_SetArgv(argc + 1, command_line); #endif diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8b9369303561..11086097fc9f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -24,6 +24,7 @@ #include "thread.h" #include "thread-stack.h" #include "stat.h" +#include "arch/common.h" static int perf_session__deliver_event(struct perf_session *session, union perf_event *event, @@ -150,6 +151,9 @@ struct perf_session *perf_session__new(struct perf_data *data, session->machines.host.env = &perf_env; } + session->machines.host.single_address_space = + perf_env__single_address_space(session->machines.host.env); + if (!data || perf_data__is_write(data)) { /* * In O_RDONLY mode this will be performed when reading the diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index b284276ec963..46daa22b86e3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -229,8 +229,14 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) if (sym_l == sym_r) return 0; - if (sym_l->inlined || sym_r->inlined) - return strcmp(sym_l->name, sym_r->name); + if (sym_l->inlined || sym_r->inlined) { + int ret = strcmp(sym_l->name, sym_r->name); + + if (ret) + return ret; + if ((sym_l->start <= sym_r->end) && (sym_l->end >= sym_r->start)) + return 0; + } if (sym_l->start != sym_r->start) return (int64_t)(sym_r->start - sym_l->start); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index e767c4a9d4d2..af3f9b9f1e8b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -104,7 +104,7 @@ static struct symbol *new_inline_sym(struct dso *dso, } else { /* create a fake symbol for the inline frame */ inline_sym = symbol__new(base_sym ? base_sym->start : 0, - base_sym ? base_sym->end : 0, + base_sym ? (base_sym->end - base_sym->start) : 0, base_sym ? base_sym->binding : 0, base_sym ? base_sym->type : 0, funcname); diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 1cbada2dc6be..f735ee038713 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -334,7 +334,7 @@ static char *cpu_model(void) if (file) { while (fgets(buf, 255, file)) { if (strstr(buf, "model name")) { - strncpy(cpu_m, &buf[13], 255); + strlcpy(cpu_m, &buf[13], 255); break; } } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 6e70cc00c161..a701a8a48f00 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -87,6 +87,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -111,7 +116,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__filter(GElf_Sym *sym) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index d188b7588152..0715f972a275 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -709,6 +709,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct } pos->start -= curr_map->start - curr_map->pgoff; + if (pos->end > curr_map->end) + pos->end = curr_map->end; if (pos->end) pos->end -= curr_map->start - curr_map->pgoff; symbols__insert(&curr_map->dso->symbols, pos); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 07606aa6998d..4e2c3cbdea4b 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -94,9 +94,13 @@ struct thread *thread__main_thread(struct machine *machine, struct thread *threa struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); +struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al); struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); +struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al); |