diff options
Diffstat (limited to 'tools/perf')
51 files changed, 1966 insertions, 374 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index c71b0f36d9e..d460049cae8 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -184,9 +184,10 @@ following filters are defined: - in_tx: only when the target is in a hardware transaction - no_tx: only when the target is not in a hardware transaction - abort_tx: only when the target is a hardware transaction abort + - cond: conditional branches + -The option requires at least one branch type among any, any_call, any_ret, ind_call. +The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. The privilege levels may be omitted, in which case, the privilege levels of the associated event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege levels are subject to permissions. When sampling on multiple events, branch stack sampling diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index cefdf430d1b..d2b59af62bc 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,22 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. + If --mem-mode option is used, following sort keys are also available + (incompatible with --branch-stack): + symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. + + - symbol_daddr: name of data symbol being executed on at the time of sample + - dso_daddr: name of library or module containing the data being executed + on at the time of sample + - locked: whether the bus was locked at the time of sample + - tlb: type of tlb access for the data at the time of sample + - mem: type of memory access for the data at the time of sample + - snoop: type of snoop (if any) for the data at the time of sample + - dcacheline: the cacheline the data address is on at the time of sample + + And default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this @@ -260,6 +276,13 @@ OPTIONS Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. +--mem-mode:: + Use the data addresses of samples in addition to instruction addresses + to build the histograms. To generate meaningful output, the perf.data + file must have been obtained using perf record -d -W and using a + special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See + 'perf mem' for simpler access. + --percent-limit:: Do not show entries which have an overhead under that percent. (Default: 0). diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt index bc5990c33dc..5e0f986dff3 100644 --- a/tools/perf/Documentation/perf-timechart.txt +++ b/tools/perf/Documentation/perf-timechart.txt @@ -43,27 +43,6 @@ TIMECHART OPTIONS --symfs=<directory>:: Look for files with symbols relative to this directory. - -EXAMPLES --------- - -$ perf timechart record git pull - - [ perf record: Woken up 13 times to write data ] - [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ] - -$ perf timechart - - Written 10.2 seconds of trace to output.svg. - -Record system-wide timechart: - - $ perf timechart record - - then generate timechart and highlight 'gcc' tasks: - - $ perf timechart --highlight gcc - -n:: --proc-num:: Print task info for at least given number of tasks. @@ -88,6 +67,26 @@ RECORD OPTIONS --callchain:: Do call-graph (stack chain/backtrace) recording +EXAMPLES +-------- + +$ perf timechart record git pull + + [ perf record: Woken up 13 times to write data ] + [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ] + +$ perf timechart + + Written 10.2 seconds of trace to output.svg. + +Record system-wide timechart: + + $ perf timechart record + + then generate timechart and highlight 'gcc' tasks: + + $ perf timechart --highlight gcc + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index dcfa54c851e..180ae02137a 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -119,7 +119,7 @@ Default is to monitor all CPUS. --fields=:: Specify output field - multiple keys can be specified in CSV format. Following fields are available: - overhead, overhead_sys, overhead_us, sample and period. + overhead, overhead_sys, overhead_us, overhead_children, sample and period. Also it can contain any sort key(s). By default, every sort keys not specified in --field will be appended @@ -161,6 +161,12 @@ Default is to monitor all CPUS. Setup and enable call-graph (stack chain/backtrace) recording, implies -g. +--children:: + Accumulate callchain of children to parent entry so that then can + show up in the output. The output will have a new "Children" column + and will be sorted on the data. It requires -g/--call-graph option + enabled. + --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. This is a trade-off diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 02f0a4dd1a8..9670a16fa57 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -400,6 +400,7 @@ LIB_OBJS += $(OUTPUT)tests/hists_common.o LIB_OBJS += $(OUTPUT)tests/hists_link.o LIB_OBJS += $(OUTPUT)tests/hists_filter.o LIB_OBJS += $(OUTPUT)tests/hists_output.o +LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o LIB_OBJS += $(OUTPUT)tests/python-use.o LIB_OBJS += $(OUTPUT)tests/bp_signal.o LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o @@ -788,8 +789,8 @@ help: @echo '' @echo 'Perf install targets:' @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed' - @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular' - @echo ' path like make prefix=/usr/local install install-doc' + @echo ' HINT: use "prefix" or "DESTDIR" to install to a particular' + @echo ' path like "make prefix=/usr/local install install-doc"' @echo ' install - install compiled binaries' @echo ' install-doc - install *all* documentation' @echo ' install-man - install manpage documentation' @@ -814,17 +815,20 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html $(DOC_TARGETS): $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) +TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol +TAG_FILES= ../../include/uapi/linux/perf_event.h + TAGS: - $(RM) TAGS - $(FIND) . -name '*.[hcS]' -print | xargs etags -a + $(QUIET_GEN)$(RM) TAGS; \ + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES) tags: - $(RM) tags - $(FIND) . -name '*.[hcS]' -print | xargs ctags -a + $(QUIET_GEN)$(RM) tags; \ + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES) cscope: - $(RM) cscope* - $(FIND) . -name '*.[hcS]' -print | xargs cscope -b + $(QUIET_GEN)$(RM) cscope*; \ + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES) ### Detect prefix changes TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\ diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6a3af0013d6..16c7c11ad06 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -72,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool, if (ret) return ret; - if (&inject->output.is_pipe) + if (!inject->output.is_pipe) return 0; return perf_event__repipe_synth(tool, event); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index cdcd4eb3a57..c63fa292507 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -288,6 +288,13 @@ static void cleanup_params(void) memset(¶ms, 0, sizeof(params)); } +static void pr_err_with_code(const char *msg, int err) +{ + pr_err("%s", msg); + pr_debug(" Reason: %s (Code: %d)", strerror(-err), err); + pr_err("\n"); +} + static int __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) { @@ -379,7 +386,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) } ret = parse_probe_event_argv(argc, argv); if (ret < 0) { - pr_err(" Error: Parse Error. (%d)\n", ret); + pr_err_with_code(" Error: Command Parse Error.", ret); return ret; } } @@ -419,8 +426,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) } ret = show_perf_probe_events(); if (ret < 0) - pr_err(" Error: Failed to show event list. (%d)\n", - ret); + pr_err_with_code(" Error: Failed to show event list.", ret); return ret; } if (params.show_funcs) { @@ -445,8 +451,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) strfilter__delete(params.filter); params.filter = NULL; if (ret < 0) - pr_err(" Error: Failed to show functions." - " (%d)\n", ret); + pr_err_with_code(" Error: Failed to show functions.", ret); return ret; } @@ -464,7 +469,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) ret = show_line_range(¶ms.line_range, params.target); if (ret < 0) - pr_err(" Error: Failed to show lines. (%d)\n", ret); + pr_err_with_code(" Error: Failed to show lines.", ret); return ret; } if (params.show_vars) { @@ -485,7 +490,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) strfilter__delete(params.filter); params.filter = NULL; if (ret < 0) - pr_err(" Error: Failed to show vars. (%d)\n", ret); + pr_err_with_code(" Error: Failed to show vars.", ret); return ret; } #endif @@ -493,7 +498,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) if (params.dellist) { ret = del_perf_probe_events(params.dellist); if (ret < 0) { - pr_err(" Error: Failed to delete events. (%d)\n", ret); + pr_err_with_code(" Error: Failed to delete events.", ret); return ret; } } @@ -504,7 +509,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) params.target, params.force_add); if (ret < 0) { - pr_err(" Error: Failed to add events. (%d)\n", ret); + pr_err_with_code(" Error: Failed to add events.", ret); return ret; } } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e4c85b8f46c..378b85b731a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -454,7 +454,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (done) break; err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1); - if (err < 0 && errno == EINTR) + /* + * Propagate error, only if there's any. Ignore positive + * number of returned events and interrupt error. + */ + if (err > 0 || (err < 0 && errno == EINTR)) err = 0; waking++; } @@ -544,6 +548,7 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX), BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX), BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX), + BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND), BRANCH_END }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6cac509212e..21d830bafff 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -80,14 +80,59 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static void report__inc_stats(struct report *rep, - struct hist_entry *he __maybe_unused) +static void report__inc_stats(struct report *rep, struct hist_entry *he) { /* - * We cannot access @he at this time. Just assume it's a new entry. - * It'll be fixed once we have a callback mechanism in hist_iter. + * The @he is either of a newly created one or an existing one + * merging current sample. We only want to count a new one so + * checking ->nr_events being 1. */ - rep->nr_entries++; + if (he->stat.nr_events == 1) + rep->nr_entries++; +} + +static int hist_iter__report_callback(struct hist_entry_iter *iter, + struct addr_location *al, bool single, + void *arg) +{ + int err = 0; + struct report *rep = arg; + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + struct mem_info *mi; + struct branch_info *bi; + + report__inc_stats(rep, he); + + if (!ui__has_annotation()) + return 0; + + if (sort__mode == SORT_MODE__BRANCH) { + bi = he->branch_info; + err = addr_map_symbol__inc_samples(&bi->from, evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bi->to, evsel->idx); + + } else if (rep->mem_mode) { + mi = he->mem_info; + err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx); + if (err) + goto out; + + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + + } else if (symbol_conf.cumulate_callchain) { + if (single) + err = hist_entry__inc_addr_samples(he, evsel->idx, + al->addr); + } else { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + } + +out: + return err; } static int process_sample_event(struct perf_tool *tool, @@ -100,6 +145,7 @@ static int process_sample_event(struct perf_tool *tool, struct addr_location al; struct hist_entry_iter iter = { .hide_unresolved = rep->hide_unresolved, + .add_entry_cb = hist_iter__report_callback, }; int ret; @@ -127,9 +173,8 @@ static int process_sample_event(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - report__inc_stats(rep, NULL); - - ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack); + ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack, + rep); if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 12e2e1227e4..377971dc89a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -196,6 +196,12 @@ static void perf_top__record_precise_ip(struct perf_top *top, pthread_mutex_unlock(¬es->lock); + /* + * This function is now called with he->hists->lock held. + * Release it before going to sleep. + */ + pthread_mutex_unlock(&he->hists->lock); + if (err == -ERANGE && !he->ms.map->erange_warned) ui__warn_map_erange(he->ms.map, sym, ip); else if (err == -ENOMEM) { @@ -203,6 +209,8 @@ static void perf_top__record_precise_ip(struct perf_top *top, sym->name); sleep(1); } + + pthread_mutex_lock(&he->hists->lock); } static void perf_top__show_details(struct perf_top *top) @@ -238,24 +246,6 @@ out_unlock: pthread_mutex_unlock(¬es->lock); } -static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, - struct addr_location *al, - struct perf_sample *sample) -{ - struct hist_entry *he; - - pthread_mutex_lock(&evsel->hists.lock); - he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, - sample->period, sample->weight, - sample->transaction, true); - pthread_mutex_unlock(&evsel->hists.lock); - if (he == NULL) - return NULL; - - hists__inc_nr_samples(&evsel->hists, he->filtered); - return he; -} - static void perf_top__print_sym_table(struct perf_top *top) { char bf[160]; @@ -659,6 +649,26 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym) return 0; } +static int hist_iter__top_callback(struct hist_entry_iter *iter, + struct addr_location *al, bool single, + void *arg) +{ + struct perf_top *top = arg; + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + + if (sort__has_sym && single) { + u64 ip = al->addr; + + if (al->map) + ip = al->map->unmap_ip(al->map, ip); + + perf_top__record_precise_ip(top, he, evsel->idx, ip); + } + + return 0; +} + static void perf_event__process_sample(struct perf_tool *tool, const union perf_event *event, struct perf_evsel *evsel, @@ -666,8 +676,6 @@ static void perf_event__process_sample(struct perf_tool *tool, struct machine *machine) { struct perf_top *top = container_of(tool, struct perf_top, tool); - struct symbol *parent = NULL; - u64 ip = sample->ip; struct addr_location al; int err; @@ -742,25 +750,23 @@ static void perf_event__process_sample(struct perf_tool *tool, } if (al.sym == NULL || !al.sym->ignore) { - struct hist_entry *he; + struct hist_entry_iter iter = { + .add_entry_cb = hist_iter__top_callback, + }; - err = sample__resolve_callchain(sample, &parent, evsel, &al, - top->max_stack); - if (err) - return; + if (symbol_conf.cumulate_callchain) + iter.ops = &hist_iter_cumulative; + else + iter.ops = &hist_iter_normal; - he = perf_evsel__add_hist_entry(evsel, &al, sample); - if (he == NULL) { - pr_err("Problem incrementing symbol period, skipping event\n"); - return; - } + pthread_mutex_lock(&evsel->hists.lock); - err = hist_entry__append_callchain(he, sample); - if (err) - return; + err = hist_entry_iter__add(&iter, &al, evsel, sample, + top->max_stack, top); + if (err < 0) + pr_err("Problem incrementing symbol period, skipping event\n"); - if (sort__has_sym) - perf_top__record_precise_ip(top, he, evsel->idx, ip); + pthread_mutex_unlock(&evsel->hists.lock); } return; @@ -998,6 +1004,10 @@ static int perf_top_config(const char *var, const char *value, void *cb) if (!strcmp(var, "top.call-graph")) return record_parse_callchain(value, &top->record_opts); + if (!strcmp(var, "top.children")) { + symbol_conf.cumulate_callchain = perf_config_bool(var, value); + return 0; + } return perf_default_config(var, value, cb); } @@ -1092,6 +1102,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK(0, "call-graph", &top.record_opts, "mode[,dump_size]", record_callchain_help, &parse_callchain_opt), + OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, + "Accumulate callchains of children and show total overhead as well"), OPT_INTEGER(0, "max-stack", &top.max_stack, "Set the maximum stack depth when parsing the callchain. " "Default: " __stringify(PERF_MAX_STACK_DEPTH)), @@ -1197,6 +1209,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) top.sym_evsel = perf_evlist__first(top.evlist); + if (!symbol_conf.use_callchain) { + symbol_conf.cumulate_callchain = false; + perf_hpp__cancel_cumulate(); + } + symbol_conf.priv_size = sizeof(struct annotation); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 729bbdf5cec..f30ac5e5d27 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -299,7 +299,11 @@ else NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 else - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); + ifneq ($(filter s% -static%,$(LDFLAGS),),) + msg := $(error No static glibc found, please install glibc-static); + else + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]); + endif endif else ifndef NO_LIBDW_DWARF_UNWIND @@ -447,6 +451,7 @@ else ifneq ($(feature-libperl), 1) CFLAGS += -DNO_LIBPERL NO_LIBPERL := 1 + msg := $(warning Missing perl devel files. Disabling perl scripting support, consider installing perl-ExtUtils-Embed); else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) @@ -599,7 +604,7 @@ endif # Make the path relative to DESTDIR, not to prefix ifndef DESTDIR -prefix = $(HOME) +prefix ?= $(HOME) endif bindir_relative = bin bindir = $(prefix)/$(bindir_relative) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 431798a4110..95c58fc1528 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -458,6 +458,7 @@ int main(int argc, const char **argv) /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); + cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE); cmd = perf_extract_argv0_path(argv[0]); if (!cmd) @@ -481,14 +482,18 @@ int main(int argc, const char **argv) fprintf(stderr, "cannot handle %s internally", cmd); goto out; } -#ifdef HAVE_LIBAUDIT_SUPPORT if (!prefixcmp(cmd, "trace")) { +#ifdef HAVE_LIBAUDIT_SUPPORT set_buildid_dir(); setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv, NULL); - } +#else + fprintf(stderr, + "trace command not available: missing audit-libs devel package at build time.\n"); + goto out; #endif + } /* Look for flags.. */ argv++; argc--; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 831f52cae19..6f8b01bc603 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -3,6 +3,8 @@ * * Builtin regression testing command: ever growing number of sanity tests */ +#include <unistd.h> +#include <string.h> #include "builtin.h" #include "intlist.h" #include "tests.h" @@ -50,10 +52,18 @@ static struct test { .func = test__pmu, }, { - .desc = "Test dso data interface", + .desc = "Test dso data read", .func = test__dso_data, }, { + .desc = "Test dso data cache", + .func = test__dso_data_cache, + }, + { + .desc = "Test dso data reopen", + .func = test__dso_data_reopen, + }, + { .desc = "roundtrip evsel->name check", .func = test__perf_evsel__roundtrip_name_test, }, @@ -140,6 +150,10 @@ static struct test { .func = test__hists_output, }, { + .desc = "Test cumulation of child hist entries", + .func = test__hists_cumulate, + }, + { .func = NULL, }, }; @@ -168,6 +182,34 @@ static bool perf_test__matches(int curr, int argc, const char *argv[]) return false; } +static int run_test(struct test *test) +{ + int status, err = -1, child = fork(); + + if (child < 0) { + pr_err("failed to fork test: %s\n", strerror(errno)); + return -1; + } + + if (!child) { + pr_debug("test child forked, pid %d\n", getpid()); + err = test->func(); + exit(err); + } + + wait(&status); + + if (WIFEXITED(status)) { + err = WEXITSTATUS(status); + pr_debug("test child finished with %d\n", err); + } else if (WIFSIGNALED(status)) { + err = -1; + pr_debug("test child interrupted\n"); + } + + return err; +} + static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { int i = 0; @@ -196,7 +238,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) } pr_debug("\n--- start ---\n"); - err = tests[curr].func(); + err = run_test(&tests[curr]); pr_debug("---- end ----\n%s:", tests[curr].desc); switch (err) { diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 3e6cb171e3d..630808cd7cc 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -1,22 +1,27 @@ -#include "util.h" - #include <stdlib.h> #include <linux/types.h> #include <sys/stat.h> #include <fcntl.h> #include <string.h> - +#include <sys/time.h> +#include <sys/resource.h> +#include <api/fs/fs.h> +#include "util.h" #include "machine.h" #include "symbol.h" #include "tests.h" static char *test_file(int size) { - static char buf_templ[] = "/tmp/test-XXXXXX"; +#define TEMPL "/tmp/perf-test-XXXXXX" + static char buf_templ[sizeof(TEMPL)]; char *templ = buf_templ; int fd, i; unsigned char *buf; + strcpy(buf_templ, TEMPL); +#undef TEMPL + fd = mkstemp(templ); if (fd < 0) { perror("mkstemp failed"); @@ -150,3 +155,204 @@ int test__dso_data(void) unlink(file); return 0; } + +static long open_files_cnt(void) +{ + char path[PATH_MAX]; + struct dirent *dent; + DIR *dir; + long nr = 0; + + scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint()); + pr_debug("fd path: %s\n", path); + + dir = opendir(path); + TEST_ASSERT_VAL("failed to open fd directory", dir); + + while ((dent = readdir(dir)) != NULL) { + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + nr++; + } + + closedir(dir); + return nr - 1; +} + +static struct dso **dsos; + +static int dsos__create(int cnt, int size) +{ + int i; + + dsos = malloc(sizeof(dsos) * cnt); + TEST_ASSERT_VAL("failed to alloc dsos array", dsos); + + for (i = 0; i < cnt; i++) { + char *file; + + file = test_file(size); + TEST_ASSERT_VAL("failed to get dso file", file); + + dsos[i] = dso__new(file); + TEST_ASSERT_VAL("failed to get dso", dsos[i]); + } + + return 0; +} + +static void dsos__delete(int cnt) +{ + int i; + + for (i = 0; i < cnt; i++) { + struct dso *dso = dsos[i]; + + unlink(dso->name); + dso__delete(dso); + } + + free(dsos); +} + +static int set_fd_limit(int n) +{ + struct rlimit rlim; + + if (getrlimit(RLIMIT_NOFILE, &rlim)) + return -1; + + pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n); + + rlim.rlim_cur = n; + return setrlimit(RLIMIT_NOFILE, &rlim); +} + +int test__dso_data_cache(void) +{ + struct machine machine; + long nr_end, nr = open_files_cnt(); + int dso_cnt, limit, i, fd; + + memset(&machine, 0, sizeof(machine)); + + /* set as system limit */ + limit = nr * 4; + TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit)); + + /* and this is now our dso open FDs limit + 1 extra */ + dso_cnt = limit / 2 + 1; + TEST_ASSERT_VAL("failed to create dsos\n", + !dsos__create(dso_cnt, TEST_FILE_SIZE)); + + for (i = 0; i < (dso_cnt - 1); i++) { + struct dso *dso = dsos[i]; + + /* + * Open dsos via dso__data_fd or dso__data_read_offset. + * Both opens the data file and keep it open. + */ + if (i % 2) { + fd = dso__data_fd(dso, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + } else { + #define BUFSIZE 10 + u8 buf[BUFSIZE]; + ssize_t n; + + n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE); + TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE); + } + } + + /* open +1 dso over the allowed limit */ + fd = dso__data_fd(dsos[i], &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + + /* should force the first one to be closed */ + TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1); + + /* cleanup everything */ + dsos__delete(dso_cnt); + + /* Make sure we did not leak any file descriptor. */ + nr_end = open_files_cnt(); + pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end); + TEST_ASSERT_VAL("failed leadking files", nr == nr_end); + return 0; +} + +int test__dso_data_reopen(void) +{ + struct machine machine; + long nr_end, nr = open_files_cnt(); + int fd, fd_extra; + +#define dso_0 (dsos[0]) +#define dso_1 (dsos[1]) +#define dso_2 (dsos[2]) + + memset(&machine, 0, sizeof(machine)); + + /* + * Test scenario: + * - create 3 dso objects + * - set process file descriptor limit to current + * files count + 3 + * - test that the first dso gets closed when we + * reach the files count limit + */ + + /* Make sure we are able to open 3 fds anyway */ + TEST_ASSERT_VAL("failed to set file limit", + !set_fd_limit((nr + 3))); + + TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE)); + + /* open dso_0 */ + fd = dso__data_fd(dso_0, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + + /* open dso_1 */ + fd = dso__data_fd(dso_1, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + + /* + * open extra file descriptor and we just + * reached the files count limit + */ + fd_extra = open("/dev/null", O_RDONLY); + TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0); + + /* open dso_2 */ + fd = dso__data_fd(dso_2, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + + /* + * dso_0 should get closed, because we reached + * the file descriptor limit + */ + TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1); + + /* open dso_0 */ + fd = dso__data_fd(dso_0, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + + /* + * dso_1 should get closed, because we reached + * the file descriptor limit + */ + TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1); + + /* cleanup everything */ + close(fd_extra); + dsos__delete(3); + + /* Make sure we did not leak any file descriptor. */ + nr_end = open_files_cnt(); + pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end); + TEST_ASSERT_VAL("failed leadking files", nr == nr_end); + return 0; +} diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 108f0cd49f4..96adb730b74 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -15,7 +15,7 @@ static int mmap_handler(struct perf_tool *tool __maybe_unused, struct perf_sample *sample __maybe_unused, struct machine *machine) { - return machine__process_mmap_event(machine, event, NULL); + return machine__process_mmap2_event(machine, event, NULL); } static int init_live_machine(struct machine *machine) diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index e4e01aadc3b..a62c0913451 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -12,9 +12,9 @@ static struct { u32 pid; const char *comm; } fake_threads[] = { - { 100, "perf" }, - { 200, "perf" }, - { 300, "bash" }, + { FAKE_PID_PERF1, "perf" }, + { FAKE_PID_PERF2, "perf" }, + { FAKE_PID_BASH, "bash" }, }; static struct { @@ -22,15 +22,15 @@ static struct { u64 start; const char *filename; } fake_mmap_info[] = { - { 100, 0x40000, "perf" }, - { 100, 0x50000, "libc" }, - { 100, 0xf0000, "[kernel]" }, - { 200, 0x40000, "perf" }, - { 200, 0x50000, "libc" }, - { 200, 0xf0000, "[kernel]" }, - { 300, 0x40000, "bash" }, - { 300, 0x50000, "libc" }, - { 300, 0xf0000, "[kernel]" }, + { FAKE_PID_PERF1, FAKE_MAP_PERF, "perf" }, + { FAKE_PID_PERF1, FAKE_MAP_LIBC, "libc" }, + { FAKE_PID_PERF1, FAKE_MAP_KERNEL, "[kernel]" }, + { FAKE_PID_PERF2, FAKE_MAP_PERF, "perf" }, + { FAKE_PID_PERF2, FAKE_MAP_LIBC, "libc" }, + { FAKE_PID_PERF2, FAKE_MAP_KERNEL, "[kernel]" }, + { FAKE_PID_BASH, FAKE_MAP_BASH, "bash" }, + { FAKE_PID_BASH, FAKE_MAP_LIBC, "libc" }, + { FAKE_PID_BASH, FAKE_MAP_KERNEL, "[kernel]" }, }; struct fake_sym { @@ -40,27 +40,30 @@ struct fake_sym { }; static struct fake_sym perf_syms[] = { - { 700, 100, "main" }, - { 800, 100, "run_command" }, - { 900, 100, "cmd_record" }, + { FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" }, + { FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "run_command" }, + { FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "cmd_record" }, }; static struct fake_sym bash_syms[] = { - { 700, 100, "main" }, - { 800, 100, "xmalloc" }, - { 900, 100, "xfree" }, + { FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" }, + { FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "xmalloc" }, + { FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "xfree" }, }; static struct fake_sym libc_syms[] = { { 700, 100, "malloc" }, { 800, 100, "free" }, { 900, 100, "realloc" }, + { FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "malloc" }, + { FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "free" }, + { FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "realloc" }, }; static struct fake_sym kernel_syms[] = { - { 700, 100, "schedule" }, - { 800, 100, "page_fault" }, - { 900, 100, "sys_perf_event_open" }, + { FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "schedule" }, + { FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "page_fault" }, + { FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "sys_perf_event_open" }, }; static struct { @@ -102,7 +105,7 @@ struct machine *setup_fake_machine(struct machines *machines) .pid = fake_mmap_info[i].pid, .tid = fake_mmap_info[i].pid, .start = fake_mmap_info[i].start, - .len = 0x1000ULL, + .len = FAKE_MAP_LENGTH, .pgoff = 0ULL, }, }; @@ -193,10 +196,11 @@ void print_hists_out(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); if (!he->filtered) { - pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"\n", + pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"/%"PRIu64"\n", i, thread__comm_str(he->thread), he->thread->tid, he->ms.map->dso->short_name, - he->ms.sym->name, he->stat.period); + he->ms.sym->name, he->stat.period, + he->stat_acc ? he->stat_acc->period : 0); } i++; diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h index 1415ae69d7b..888254e8665 100644 --- a/tools/perf/tests/hists_common.h +++ b/tools/perf/tests/hists_common.h @@ -4,6 +4,34 @@ struct machine; struct machines; +#define FAKE_PID_PERF1 100 +#define FAKE_PID_PERF2 200 +#define FAKE_PID_BASH 300 + +#define FAKE_MAP_PERF 0x400000 +#define FAKE_MAP_BASH 0x400000 +#define FAKE_MAP_LIBC 0x500000 +#define FAKE_MAP_KERNEL 0xf00000 +#define FAKE_MAP_LENGTH 0x100000 + +#define FAKE_SYM_OFFSET1 700 +#define FAKE_SYM_OFFSET2 800 +#define FAKE_SYM_OFFSET3 900 +#define FAKE_SYM_LENGTH 100 + +#define FAKE_IP_PERF_MAIN FAKE_MAP_PERF + FAKE_SYM_OFFSET1 +#define FAKE_IP_PERF_RUN_COMMAND FAKE_MAP_PERF + FAKE_SYM_OFFSET2 +#define FAKE_IP_PERF_CMD_RECORD FAKE_MAP_PERF + FAKE_SYM_OFFSET3 +#define FAKE_IP_BASH_MAIN FAKE_MAP_BASH + FAKE_SYM_OFFSET1 +#define FAKE_IP_BASH_XMALLOC FAKE_MAP_BASH + FAKE_SYM_OFFSET2 +#define FAKE_IP_BASH_XFREE FAKE_MAP_BASH + FAKE_SYM_OFFSET3 +#define FAKE_IP_LIBC_MALLOC FAKE_MAP_LIBC + FAKE_SYM_OFFSET1 +#define FAKE_IP_LIBC_FREE FAKE_MAP_LIBC + FAKE_SYM_OFFSET2 +#define FAKE_IP_LIBC_REALLOC FAKE_MAP_LIBC + FAKE_SYM_OFFSET3 +#define FAKE_IP_KERNEL_SCHEDULE FAKE_MAP_KERNEL + FAKE_SYM_OFFSET1 +#define FAKE_IP_KERNEL_PAGE_FAULT FAKE_MAP_KERNEL + FAKE_SYM_OFFSET2 +#define FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN FAKE_MAP_KERNEL + FAKE_SYM_OFFSET3 + /* * The setup_fake_machine() provides a test environment which consists * of 3 processes that have 3 mappings and in turn, have 3 symbols @@ -13,7 +41,7 @@ struct machines; * ............. ............. ................... * perf: 100 perf main * perf: 100 perf run_command - * perf: 100 perf comd_record + * perf: 100 perf cmd_record * perf: 100 libc malloc * perf: 100 libc free * perf: 100 libc realloc @@ -22,7 +50,7 @@ struct machines; * perf: 100 [kernel] sys_perf_event_open * perf: 200 perf main * perf: 200 perf run_command - * perf: 200 perf comd_record + * perf: 200 perf cmd_record * perf: 200 libc malloc * perf: 200 libc free * perf: 200 libc realloc diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c new file mode 100644 index 00000000000..0ac240db2e2 --- /dev/null +++ b/tools/perf/tests/hists_cumulate.c @@ -0,0 +1,726 @@ +#include "perf.h" +#include "util/debug.h" +#include "util/symbol.h" +#include "util/sort.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/thread.h" +#include "util/parse-events.h" +#include "tests/tests.h" +#include "tests/hists_common.h" + +struct sample { + u32 pid; + u64 ip; + struct thread *thread; + struct map *map; + struct symbol *sym; +}; + +/* For the numbers, see hists_common.c */ +static struct sample fake_samples[] = { + /* perf [kernel] schedule() */ + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, }, + /* perf [perf] main() */ + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, }, + /* perf [perf] cmd_record() */ + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, }, + /* perf [libc] malloc() */ + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, }, + /* perf [libc] free() */ + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, }, + /* perf [perf] main() */ + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, + /* perf [kernel] page_fault() */ + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, + /* bash [bash] main() */ + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_MAIN, }, + /* bash [bash] xmalloc() */ + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XMALLOC, }, + /* bash [kernel] page_fault() */ + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, +}; + +/* + * Will be casted to struct ip_callchain which has all 64 bit entries + * of nr and ips[]. + */ +static u64 fake_callchains[][10] = { + /* schedule => run_command => main */ + { 3, FAKE_IP_KERNEL_SCHEDULE, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, }, + /* main */ + { 1, FAKE_IP_PERF_MAIN, }, + /* cmd_record => run_command => main */ + { 3, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, }, + /* malloc => cmd_record => run_command => main */ + { 4, FAKE_IP_LIBC_MALLOC, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, + FAKE_IP_PERF_MAIN, }, + /* free => cmd_record => run_command => main */ + { 4, FAKE_IP_LIBC_FREE, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, + FAKE_IP_PERF_MAIN, }, + /* main */ + { 1, FAKE_IP_PERF_MAIN, }, + /* page_fault => sys_perf_event_open => run_command => main */ + { 4, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, + FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, }, + /* main */ + { 1, FAKE_IP_BASH_MAIN, }, + /* xmalloc => malloc => xmalloc => malloc => xmalloc => main */ + { 6, FAKE_IP_BASH_XMALLOC, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, + FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, FAKE_IP_BASH_MAIN, }, + /* page_fault => malloc => main */ + { 3, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_MAIN, }, +}; + +static int add_hist_entries(struct hists *hists, struct machine *machine) +{ + struct addr_location al; + struct perf_evsel *evsel = hists_to_evsel(hists); + struct perf_sample sample = { .period = 1000, }; + size_t i; + + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { + const union perf_event event = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + }; + struct hist_entry_iter iter = { + .hide_unresolved = false, + }; + + if (symbol_conf.cumulate_callchain) + iter.ops = &hist_iter_cumulative; + else + iter.ops = &hist_iter_normal; + + sample.pid = fake_samples[i].pid; + sample.tid = fake_samples[i].pid; + sample.ip = fake_samples[i].ip; + sample.callchain = (struct ip_callchain *)fake_callchains[i]; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample) < 0) + goto out; + + if (hist_entry_iter__add(&iter, &al, evsel, &sample, + PERF_MAX_STACK_DEPTH, NULL) < 0) + goto out; + + fake_samples[i].thread = al.thread; + fake_samples[i].map = al.map; + fake_samples[i].sym = al.sym; + } + + return TEST_OK; + +out: + pr_debug("Not enough memory for adding a hist entry\n"); + return TEST_FAIL; +} + +static void del_hist_entries(struct hists *hists) +{ + struct hist_entry *he; + struct rb_root *root_in; + struct rb_root *root_out; + struct rb_node *node; + + if (sort__need_collapse) + root_in = &hists->entries_collapsed; + else + root_in = hists->entries_in; + + root_out = &hists->entries; + + while (!RB_EMPTY_ROOT(root_out)) { + node = rb_first(root_out); + + he = rb_entry(node, struct hist_entry, rb_node); + rb_erase(node, root_out); + rb_erase(&he->rb_node_in, root_in); + hist_entry__free(he); + } +} + +typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); + +#define COMM(he) (thread__comm_str(he->thread)) +#define DSO(he) (he->ms.map->dso->short_name) +#define SYM(he) (he->ms.sym->name) +#define CPU(he) (he->cpu) +#define PID(he) (he->thread->tid) +#define DEPTH(he) (he->callchain->max_depth) +#define CDSO(cl) (cl->ms.map->dso->short_name) +#define CSYM(cl) (cl->ms.sym->name) + +struct result { + u64 children; + u64 self; + const char *comm; + const char *dso; + const char *sym; +}; + +struct callchain_result { + u64 nr; + struct { + const char *dso; + const char *sym; + } node[10]; +}; + +static int do_test(struct hists *hists, struct result *expected, size_t nr_expected, + struct callchain_result *expected_callchain, size_t nr_callchain) +{ + char buf[32]; + size_t i, c; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + struct callchain_node *cnode; + struct callchain_list *clist; + + /* + * adding and deleting hist entries must be done outside of this + * function since TEST_ASSERT_VAL() returns in case of failure. + */ + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("use callchain: %d, cumulate callchain: %d\n", + symbol_conf.use_callchain, + symbol_conf.cumulate_callchain); + print_hists_out(hists); + } + + root = &hists->entries; + for (node = rb_first(root), i = 0; + node && (he = rb_entry(node, struct hist_entry, rb_node)); + node = rb_next(node), i++) { + scnprintf(buf, sizeof(buf), "Invalid hist entry #%zd", i); + + TEST_ASSERT_VAL("Incorrect number of hist entry", + i < nr_expected); + TEST_ASSERT_VAL(buf, he->stat.period == expected[i].self && + !strcmp(COMM(he), expected[i].comm) && + !strcmp(DSO(he), expected[i].dso) && + !strcmp(SYM(he), expected[i].sym)); + + if (symbol_conf.cumulate_callchain) + TEST_ASSERT_VAL(buf, he->stat_acc->period == expected[i].children); + + if (!symbol_conf.use_callchain) + continue; + + /* check callchain entries */ + root = &he->callchain->node.rb_root; + cnode = rb_entry(rb_first(root), struct callchain_node, rb_node); + + c = 0; + list_for_each_entry(clist, &cnode->val, list) { + scnprintf(buf, sizeof(buf), "Invalid callchain entry #%zd/%zd", i, c); + + TEST_ASSERT_VAL("Incorrect number of callchain entry", + c < expected_callchain[i].nr); + TEST_ASSERT_VAL(buf, + !strcmp(CDSO(clist), expected_callchain[i].node[c].dso) && + !strcmp(CSYM(clist), expected_callchain[i].node[c].sym)); + c++; + } + /* TODO: handle multiple child nodes properly */ + TEST_ASSERT_VAL("Incorrect number of callchain entry", + c <= expected_callchain[i].nr); + } + TEST_ASSERT_VAL("Incorrect number of hist entry", + i == nr_expected); + TEST_ASSERT_VAL("Incorrect number of callchain entry", + !symbol_conf.use_callchain || nr_expected == nr_callchain); + return 0; +} + +/* NO callchain + NO children */ +static int test1(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + /* + * expected output: + * + * Overhead Command Shared Object Symbol + * ======== ======= ============= ============== + * 20.00% perf perf [.] main + * 10.00% bash [kernel] [k] page_fault + * 10.00% bash bash [.] main + * 10.00% bash bash [.] xmalloc + * 10.00% perf [kernel] [k] page_fault + * 10.00% perf [kernel] [k] schedule + * 10.00% perf libc [.] free + * 10.00% perf libc [.] malloc + * 10.00% perf perf [.] cmd_record + */ + struct result expected[] = { + { 0, 2000, "perf", "perf", "main" }, + { 0, 1000, "bash", "[kernel]", "page_fault" }, + { 0, 1000, "bash", "bash", "main" }, + { 0, 1000, "bash", "bash", "xmalloc" }, + { 0, 1000, "perf", "[kernel]", "page_fault" }, + { 0, 1000, "perf", "[kernel]", "schedule" }, + { 0, 1000, "perf", "libc", "free" }, + { 0, 1000, "perf", "libc", "malloc" }, + { 0, 1000, "perf", "perf", "cmd_record" }, + }; + + symbol_conf.use_callchain = false; + symbol_conf.cumulate_callchain = false; + + setup_sorting(); + callchain_register_param(&callchain_param); + + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* callcain + NO children */ +static int test2(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + /* + * expected output: + * + * Overhead Command Shared Object Symbol + * ======== ======= ============= ============== + * 20.00% perf perf [.] main + * | + * --- main + * + * 10.00% bash [kernel] [k] page_fault + * | + * --- page_fault + * malloc + * main + * + * 10.00% bash bash [.] main + * | + * --- main + * + * 10.00% bash bash [.] xmalloc + * | + * --- xmalloc + * malloc + * xmalloc <--- NOTE: there's a cycle + * malloc + * xmalloc + * main + * + * 10.00% perf [kernel] [k] page_fault + * | + * --- page_fault + * sys_perf_event_open + * run_command + * main + * + * 10.00% perf [kernel] [k] schedule + * | + * --- schedule + * run_command + * main + * + * 10.00% perf libc [.] free + * | + * --- free + * cmd_record + * run_command + * main + * + * 10.00% perf libc [.] malloc + * | + * --- malloc + * cmd_record + * run_command + * main + * + * 10.00% perf perf [.] cmd_record + * | + * --- cmd_record + * run_command + * main + * + */ + struct result expected[] = { + { 0, 2000, "perf", "perf", "main" }, + { 0, 1000, "bash", "[kernel]", "page_fault" }, + { 0, 1000, "bash", "bash", "main" }, + { 0, 1000, "bash", "bash", "xmalloc" }, + { 0, 1000, "perf", "[kernel]", "page_fault" }, + { 0, 1000, "perf", "[kernel]", "schedule" }, + { 0, 1000, "perf", "libc", "free" }, + { 0, 1000, "perf", "libc", "malloc" }, + { 0, 1000, "perf", "perf", "cmd_record" }, + }; + struct callchain_result expected_callchain[] = { + { + 1, { { "perf", "main" }, }, + }, + { + 3, { { "[kernel]", "page_fault" }, + { "libc", "malloc" }, + { "bash", "main" }, }, + }, + { + 1, { { "bash", "main" }, }, + }, + { + 6, { { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "bash", "main" }, }, + }, + { + 4, { { "[kernel]", "page_fault" }, + { "[kernel]", "sys_perf_event_open" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 3, { { "[kernel]", "schedule" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "libc", "free" }, + { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "libc", "malloc" }, + { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 3, { { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + }; + + symbol_conf.use_callchain = true; + symbol_conf.cumulate_callchain = false; + + setup_sorting(); + callchain_register_param(&callchain_param); + + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + err = do_test(hists, expected, ARRAY_SIZE(expected), + expected_callchain, ARRAY_SIZE(expected_callchain)); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* NO callchain + children */ +static int test3(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + /* + * expected output: + * + * Children Self Command Shared Object Symbol + * ======== ======== ======= ============= ======================= + * 70.00% 20.00% perf perf [.] main + * 50.00% 0.00% perf perf [.] run_command + * 30.00% 10.00% bash bash [.] main + * 30.00% 10.00% perf perf [.] cmd_record + * 20.00% 0.00% bash libc [.] malloc + * 10.00% 10.00% bash [kernel] [k] page_fault + * 10.00% 10.00% perf [kernel] [k] schedule + * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open + * 10.00% 10.00% perf [kernel] [k] page_fault + * 10.00% 10.00% perf libc [.] free + * 10.00% 10.00% perf libc [.] malloc + * 10.00% 10.00% bash bash [.] xmalloc + */ + struct result expected[] = { + { 7000, 2000, "perf", "perf", "main" }, + { 5000, 0, "perf", "perf", "run_command" }, + { 3000, 1000, "bash", "bash", "main" }, + { 3000, 1000, "perf", "perf", "cmd_record" }, + { 2000, 0, "bash", "libc", "malloc" }, + { 1000, 1000, "bash", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, + { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, + { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "libc", "free" }, + { 1000, 1000, "perf", "libc", "malloc" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, + }; + + symbol_conf.use_callchain = false; + symbol_conf.cumulate_callchain = true; + + setup_sorting(); + callchain_register_param(&callchain_param); + + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* callchain + children */ +static int test4(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + /* + * expected output: + * + * Children Self Command Shared Object Symbol + * ======== ======== ======= ============= ======================= + * 70.00% 20.00% perf perf [.] main + * | + * --- main + * + * 50.00% 0.00% perf perf [.] run_command + * | + * --- run_command + * main + * + * 30.00% 10.00% bash bash [.] main + * | + * --- main + * + * 30.00% 10.00% perf perf [.] cmd_record + * | + * --- cmd_record + * run_command + * main + * + * 20.00% 0.00% bash libc [.] malloc + * | + * --- malloc + * | + * |--50.00%-- xmalloc + * | main + * --50.00%-- main + * + * 10.00% 10.00% bash [kernel] [k] page_fault + * | + * --- page_fault + * malloc + * main + * + * 10.00% 10.00% perf [kernel] [k] schedule + * | + * --- schedule + * run_command + * main + * + * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open + * | + * --- sys_perf_event_open + * run_command + * main + * + * 10.00% 10.00% perf [kernel] [k] page_fault + * | + * --- page_fault + * sys_perf_event_open + * run_command + * main + * + * 10.00% 10.00% perf libc [.] free + * | + * --- free + * cmd_record + * run_command + * main + * + * 10.00% 10.00% perf libc [.] malloc + * | + * --- malloc + * cmd_record + * run_command + * main + * + * 10.00% 10.00% bash bash [.] xmalloc + * | + * --- xmalloc + * malloc + * xmalloc <--- NOTE: there's a cycle + * malloc + * xmalloc + * main + * + */ + struct result expected[] = { + { 7000, 2000, "perf", "perf", "main" }, + { 5000, 0, "perf", "perf", "run_command" }, + { 3000, 1000, "bash", "bash", "main" }, + { 3000, 1000, "perf", "perf", "cmd_record" }, + { 2000, 0, "bash", "libc", "malloc" }, + { 1000, 1000, "bash", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, + { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, + { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "libc", "free" }, + { 1000, 1000, "perf", "libc", "malloc" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, + }; + struct callchain_result expected_callchain[] = { + { + 1, { { "perf", "main" }, }, + }, + { + 2, { { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 1, { { "bash", "main" }, }, + }, + { + 3, { { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "bash", "main" }, + { "bash", "main" }, }, + }, + { + 3, { { "[kernel]", "page_fault" }, + { "libc", "malloc" }, + { "bash", "main" }, }, + }, + { + 3, { { "[kernel]", "schedule" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 3, { { "[kernel]", "sys_perf_event_open" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "[kernel]", "page_fault" }, + { "[kernel]", "sys_perf_event_open" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "libc", "free" }, + { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 4, { { "libc", "malloc" }, + { "perf", "cmd_record" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { + 6, { { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "bash", "main" }, }, + }, + }; + + symbol_conf.use_callchain = true; + symbol_conf.cumulate_callchain = true; + + setup_sorting(); + callchain_register_param(&callchain_param); + + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + err = do_test(hists, expected, ARRAY_SIZE(expected), + expected_callchain, ARRAY_SIZE(expected_callchain)); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +int test__hists_cumulate(void) +{ + int err = TEST_FAIL; + struct machines machines; + struct machine *machine; + struct perf_evsel *evsel; + struct perf_evlist *evlist = perf_evlist__new(); + size_t i; + test_fn_t testcases[] = { + test1, + test2, + test3, + test4, + }; + + TEST_ASSERT_VAL("No memory", evlist); + + err = parse_events(evlist, "cpu-clock"); + if (err) + goto out; + + machines__init(&machines); + + /* setup threads/dso/map/symbols also */ + machine = setup_fake_machine(&machines); + if (!machine) + goto out; + + if (verbose > 1) + machine__fprintf(machine, stderr); + + evsel = perf_evlist__first(evlist); + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + err = testcases[i](evsel, machine); + if (err < 0) + break; + } + +out: + /* tear down everything */ + perf_evlist__delete(evlist); + machines__exit(&machines); + + return err; +} diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 76b02e1de70..821f581fd93 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -21,25 +21,25 @@ struct sample { /* For the numbers, see hists_common.c */ static struct sample fake_samples[] = { /* perf [kernel] schedule() */ - { .pid = 100, .ip = 0xf0000 + 700, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, }, /* perf [perf] main() */ - { .pid = 100, .ip = 0x40000 + 700, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, }, /* perf [libc] malloc() */ - { .pid = 100, .ip = 0x50000 + 700, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, }, /* perf [perf] main() */ - { .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */ + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* will be merged */ /* perf [perf] cmd_record() */ - { .pid = 200, .ip = 0x40000 + 900, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, }, /* perf [kernel] page_fault() */ - { .pid = 200, .ip = 0xf0000 + 800, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, /* bash [bash] main() */ - { .pid = 300, .ip = 0x40000 + 700, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_MAIN, }, /* bash [bash] xmalloc() */ - { .pid = 300, .ip = 0x40000 + 800, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XMALLOC, }, /* bash [libc] malloc() */ - { .pid = 300, .ip = 0x50000 + 700, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_LIBC_MALLOC, }, /* bash [kernel] page_fault() */ - { .pid = 300, .ip = 0xf0000 + 800, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, }; static int add_hist_entries(struct perf_evlist *evlist, @@ -47,7 +47,7 @@ static int add_hist_entries(struct perf_evlist *evlist, { struct perf_evsel *evsel; struct addr_location al; - struct perf_sample sample = { .cpu = 0, }; + struct perf_sample sample = { .period = 100, }; size_t i; /* @@ -75,14 +75,13 @@ static int add_hist_entries(struct perf_evlist *evlist, sample.pid = fake_samples[i].pid; sample.tid = fake_samples[i].pid; sample.ip = fake_samples[i].ip; - sample.period = 100; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) goto out; if (hist_entry_iter__add(&iter, &al, evsel, &sample, - PERF_MAX_STACK_DEPTH) < 0) + PERF_MAX_STACK_DEPTH, NULL) < 0) goto out; fake_samples[i].thread = al.thread; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index ca6693b37cd..d4b34b0f50a 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -21,41 +21,41 @@ struct sample { /* For the numbers, see hists_common.c */ static struct sample fake_common_samples[] = { /* perf [kernel] schedule() */ - { .pid = 100, .ip = 0xf0000 + 700, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, }, /* perf [perf] main() */ - { .pid = 200, .ip = 0x40000 + 700, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* perf [perf] cmd_record() */ - { .pid = 200, .ip = 0x40000 + 900, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, }, /* bash [bash] xmalloc() */ - { .pid = 300, .ip = 0x40000 + 800, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XMALLOC, }, /* bash [libc] malloc() */ - { .pid = 300, .ip = 0x50000 + 700, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_LIBC_MALLOC, }, }; static struct sample fake_samples[][5] = { { /* perf [perf] run_command() */ - { .pid = 100, .ip = 0x40000 + 800, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_RUN_COMMAND, }, /* perf [libc] malloc() */ - { .pid = 100, .ip = 0x50000 + 700, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, }, /* perf [kernel] page_fault() */ - { .pid = 100, .ip = 0xf0000 + 800, }, + { .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, /* perf [kernel] sys_perf_event_open() */ - { .pid = 200, .ip = 0xf0000 + 900, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, }, /* bash [libc] free() */ - { .pid = 300, .ip = 0x50000 + 800, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_LIBC_FREE, }, }, { /* perf [libc] free() */ - { .pid = 200, .ip = 0x50000 + 800, }, + { .pid = FAKE_PID_PERF2, .ip = FAKE_IP_LIBC_FREE, }, /* bash [libc] malloc() */ - { .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */ + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_LIBC_MALLOC, }, /* will be merged */ /* bash [bash] xfee() */ - { .pid = 300, .ip = 0x40000 + 900, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XFREE, }, /* bash [libc] realloc() */ - { .pid = 300, .ip = 0x50000 + 900, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_LIBC_REALLOC, }, /* bash [kernel] page_fault() */ - { .pid = 300, .ip = 0xf0000 + 800, }, + { .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, }, }; @@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) struct perf_evsel *evsel; struct addr_location al; struct hist_entry *he; - struct perf_sample sample = { .cpu = 0, }; + struct perf_sample sample = { .period = 1, }; size_t i = 0, k; /* diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 1308f88a916..e3bbd6c54c1 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -22,25 +22,25 @@ struct sample { /* For the numbers, see hists_common.c */ static struct sample fake_samples[] = { /* perf [kernel] schedule() */ - { .cpu = 0, .pid = 100, .ip = 0xf0000 + 700, }, + { .cpu = 0, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, }, /* perf [perf] main() */ - { .cpu = 1, .pid = 100, .ip = 0x40000 + 700, }, + { .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, }, /* perf [perf] cmd_record() */ - { .cpu = 1, .pid = 100, .ip = 0x40000 + 900, }, + { .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, }, /* perf [libc] malloc() */ - { .cpu = 1, .pid = 100, .ip = 0x50000 + 700, }, + { .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, }, /* perf [libc] free() */ - { .cpu = 2, .pid = 100, .ip = 0x50000 + 800, }, + { .cpu = 2, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, }, /* perf [perf] main() */ - { .cpu = 2, .pid = 200, .ip = 0x40000 + 700, }, + { .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* perf [kernel] page_fault() */ - { .cpu = 2, .pid = 200, .ip = 0xf0000 + 800, }, + { .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, /* bash [bash] main() */ - { .cpu = 3, .pid = 300, .ip = 0x40000 + 700, }, + { .cpu = 3, .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_MAIN, }, /* bash [bash] xmalloc() */ - { .cpu = 0, .pid = 300, .ip = 0x40000 + 800, }, + { .cpu = 0, .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XMALLOC, }, /* bash [kernel] page_fault() */ - { .cpu = 1, .pid = 300, .ip = 0xf0000 + 800, }, + { .cpu = 1, .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, }, }; static int add_hist_entries(struct hists *hists, struct machine *machine) @@ -71,7 +71,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) goto out; if (hist_entry_iter__add(&iter, &al, evsel, &sample, - PERF_MAX_STACK_DEPTH) < 0) + PERF_MAX_STACK_DEPTH, NULL) < 0) goto out; fake_samples[i].thread = al.thread; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 2f92d6e7ee0..69a71ff84e0 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -205,8 +205,7 @@ $(run): ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)" >> $@ 2>&1; \ $(call test,$@) && \ - rm -f $@ \ - rm -rf $$TMP_DEST + rm -rf $@ $$TMP_DEST || (cat $@ ; false) $(run_O): $(call clean) @@ -217,9 +216,7 @@ $(run_O): ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)" >> $@ 2>&1; \ $(call test_O,$@) && \ - rm -f $@ && \ - rm -rf $$TMP_O \ - rm -rf $$TMP_DEST + rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false) tarpkg: @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \ diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index d76c0e2e663..ed64790a395 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -28,6 +28,8 @@ int test__syscall_open_tp_fields(void); int test__pmu(void); int test__attr(void); int test__dso_data(void); +int test__dso_data_cache(void); +int test__dso_data_reopen(void); int test__parse_events(void); int test__hists_link(void); int test__python_use(void); @@ -45,6 +47,7 @@ int test__hists_filter(void); int test__mmap_thread_lookup(void); int test__thread_mg_share(void); int test__hists_output(void); +int test__hists_cumulate(void); #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index d11541d4d7d..3ccf6e14f89 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -194,7 +194,7 @@ int ui_browser__warning(struct ui_browser *browser, int timeout, ui_helpline__vpush(format, args); va_end(args); } else { - while ((key == ui__question_window("Warning!", text, + while ((key = ui__question_window("Warning!", text, "Press any key...", timeout)) == K_RESIZE) ui_browser__handle_resize(browser); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 5905acde5f1..04a229aa5c0 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -17,6 +17,7 @@ #include "../util.h" #include "../ui.h" #include "map.h" +#include "annotate.h" struct hist_browser { struct ui_browser b; @@ -1593,13 +1594,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, bi->to.sym->name) > 0) annotate_t = nr_options++; } else { - if (browser->selection != NULL && browser->selection->sym != NULL && - !browser->selection->map->dso->annotate_warned && - asprintf(&options[nr_options], "Annotate %s", - browser->selection->sym->name) > 0) - annotate = nr_options++; + !browser->selection->map->dso->annotate_warned) { + struct annotation *notes; + + notes = symbol__annotation(browser->selection->sym); + + if (notes->src && + asprintf(&options[nr_options], "Annotate %s", + browser->selection->sym->name) > 0) + annotate = nr_options++; + } } if (thread != NULL && @@ -1656,6 +1662,7 @@ retry_popup_menu: if (choice == annotate || choice == annotate_t || choice == annotate_f) { struct hist_entry *he; + struct annotation *notes; int err; do_annotate: if (!objdump_path && perf_session_env__lookup_objdump(env)) @@ -1679,6 +1686,10 @@ do_annotate: he->ms.map = he->branch_info->to.map; } + notes = symbol__annotation(he->ms.sym); + if (!notes->src) + continue; + /* * Don't let this be freed, say, by hists__decay_entry. */ @@ -1706,14 +1717,14 @@ zoom_dso: zoom_out_dso: ui_helpline__pop(); browser->hists->dso_filter = NULL; - sort_dso.elide = false; + perf_hpp__set_elide(HISTC_DSO, false); } else { if (dso == NULL) continue; ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"", dso->kernel ? "the Kernel" : dso->short_name); browser->hists->dso_filter = dso; - sort_dso.elide = true; + perf_hpp__set_elide(HISTC_DSO, true); pstack__push(fstack, &browser->hists->dso_filter); } hists__filter_by_dso(hists); @@ -1725,13 +1736,13 @@ zoom_thread: zoom_out_thread: ui_helpline__pop(); browser->hists->thread_filter = NULL; - sort_thread.elide = false; + perf_hpp__set_elide(HISTC_THREAD, false); } else { ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", thread->comm_set ? thread__comm_str(thread) : "", thread->tid); browser->hists->thread_filter = thread; - sort_thread.elide = true; + perf_hpp__set_elide(HISTC_THREAD, false); pstack__push(fstack, &browser->hists->thread_filter); } hists__filter_by_thread(hists); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 03d6812d25d..6ca60e482cd 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -198,6 +198,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, if (perf_hpp__should_skip(fmt)) continue; + /* + * XXX no way to determine where symcol column is.. + * Just use last column for now. + */ + if (perf_hpp__is_sort_entry(fmt)) + sym_col = col_idx; + fmt->header(fmt, &hpp, hists_to_evsel(hists)); gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), @@ -253,7 +260,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, if (symbol_conf.use_callchain && sort__has_sym) { if (callchain_param.mode == CHAIN_GRAPH_REL) - total = h->stat.period; + total = symbol_conf.cumulate_callchain ? + h->stat_acc->period : h->stat.period; perf_gtk__add_callchain(&h->sorted_chain, store, &iter, sym_col, total); diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 8ca638754ac..498adb23c02 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -513,6 +513,9 @@ void perf_hpp__column_disable(unsigned col) void perf_hpp__cancel_cumulate(void) { + if (field_order) + return; + perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC); perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead; } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 475d2f5c7e1..90122abd372 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -271,7 +271,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, { switch (callchain_param.mode) { case CHAIN_GRAPH_REL: - return callchain__fprintf_graph(fp, &he->sorted_chain, he->stat.period, + return callchain__fprintf_graph(fp, &he->sorted_chain, + symbol_conf.cumulate_callchain ? + he->stat_acc->period : he->stat.period, left_margin); break; case CHAIN_GRAPH_ABS: diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 64453d63b97..819f10414f0 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1,3 +1,6 @@ +#include <asm/bug.h> +#include <sys/time.h> +#include <sys/resource.h> #include "symbol.h" #include "dso.h" #include "machine.h" @@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } -static int open_dso(struct dso *dso, struct machine *machine) +/* + * Global list of open DSOs and the counter. + */ +static LIST_HEAD(dso__data_open); +static long dso__data_open_cnt; + +static void dso__list_add(struct dso *dso) +{ + list_add_tail(&dso->data.open_entry, &dso__data_open); + dso__data_open_cnt++; +} + +static void dso__list_del(struct dso *dso) +{ + list_del(&dso->data.open_entry); + WARN_ONCE(dso__data_open_cnt <= 0, + "DSO data fd counter out of bounds."); + dso__data_open_cnt--; +} + +static void close_first_dso(void); + +static int do_open(char *name) +{ + int fd; + + do { + fd = open(name, O_RDONLY); + if (fd >= 0) + return fd; + + pr_debug("dso open failed, mmap: %s\n", strerror(errno)); + if (!dso__data_open_cnt || errno != EMFILE) + break; + + close_first_dso(); + } while (1); + + return -1; +} + +static int __open_dso(struct dso *dso, struct machine *machine) { int fd; char *root_dir = (char *)""; @@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine) return -EINVAL; } - fd = open(name, O_RDONLY); + fd = do_open(name); free(name); return fd; } +static void check_data_close(void); + +/** + * dso_close - Open DSO data file + * @dso: dso object + * + * Open @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static int open_dso(struct dso *dso, struct machine *machine) +{ + int fd = __open_dso(dso, machine); + + if (fd > 0) { + dso__list_add(dso); + /* + * Check if we crossed the allowed number + * of opened DSOs and close one if needed. + */ + check_data_close(); + } + + return fd; +} + +static void close_data_fd(struct dso *dso) +{ + if (dso->data.fd >= 0) { + close(dso->data.fd); + dso->data.fd = -1; + dso->data.file_size = 0; + dso__list_del(dso); + } +} + +/** + * dso_close - Close DSO data file + * @dso: dso object + * + * Close @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static void close_dso(struct dso *dso) +{ + close_data_fd(dso); +} + +static void close_first_dso(void) +{ + struct dso *dso; + + dso = list_first_entry(&dso__data_open, struct dso, data.open_entry); + close_dso(dso); +} + +static rlim_t get_fd_limit(void) +{ + struct rlimit l; + rlim_t limit = 0; + + /* Allow half of the current open fd limit. */ + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (l.rlim_cur == RLIM_INFINITY) + limit = l.rlim_cur; + else + limit = l.rlim_cur / 2; + } else { + pr_err("failed to get fd limit\n"); + limit = 1; + } + + return limit; +} + +static bool may_cache_fd(void) +{ + static rlim_t limit; + + if (!limit) + limit = get_fd_limit(); + + if (limit == RLIM_INFINITY) + return true; + + return limit > (rlim_t) dso__data_open_cnt; +} + +/* + * Check and close LRU dso if we crossed allowed limit + * for opened dso file descriptors. The limit is half + * of the RLIMIT_NOFILE files opened. +*/ +static void check_data_close(void) +{ + bool cache_fd = may_cache_fd(); + + if (!cache_fd) + close_first_dso(); +} + +/** + * dso__data_close - Close DSO data file + * @dso: dso object + * + * External interface to close @dso's data file descriptor. + */ +void dso__data_close(struct dso *dso) +{ + close_dso(dso); +} + +/** + * dso__data_fd - Get dso's data file descriptor + * @dso: dso object + * @machine: machine object + * + * External interface to find dso's file, open it and + * returns file descriptor. + */ int dso__data_fd(struct dso *dso, struct machine *machine) { enum dso_binary_type binary_type_data[] = { @@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine) }; int i = 0; - if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) - return open_dso(dso, machine); + if (dso->data.fd >= 0) + return dso->data.fd; + + if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) { + dso->data.fd = open_dso(dso, machine); + return dso->data.fd; + } do { int fd; @@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine) fd = open_dso(dso, machine); if (fd >= 0) - return fd; + return dso->data.fd = fd; } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND); @@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset, } static ssize_t -dso_cache__read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size) { struct dso_cache *cache; ssize_t ret; - int fd; - - fd = dso__data_fd(dso, machine); - if (fd < 0) - return -1; do { u64 cache_offset; @@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine, cache_offset = offset & DSO__DATA_CACHE_MASK; ret = -EINVAL; - if (-1 == lseek(fd, cache_offset, SEEK_SET)) + if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET)) break; - ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE); + ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE); if (ret <= 0) break; cache->offset = cache_offset; cache->size = ret; - dso_cache__insert(&dso->cache, cache); + dso_cache__insert(&dso->data.cache, cache); ret = dso_cache__memcpy(cache, offset, data, size); @@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine, if (ret <= 0) free(cache); - close(fd); return ret; } -static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t dso_cache_read(struct dso *dso, u64 offset, + u8 *data, ssize_t size) { struct dso_cache *cache; - cache = dso_cache__find(&dso->cache, offset); + cache = dso_cache__find(&dso->data.cache, offset); if (cache) return dso_cache__memcpy(cache, offset, data, size); else - return dso_cache__read(dso, machine, offset, data, size); + return dso_cache__read(dso, offset, data, size); } -ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +/* + * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks + * in the rb_tree. Any read to already cached data is served + * by cached data. + */ +static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size) { ssize_t r = 0; u8 *p = data; @@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, do { ssize_t ret; - ret = dso_cache_read(dso, machine, offset, p, size); + ret = dso_cache_read(dso, offset, p, size); if (ret < 0) return ret; @@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, return r; } +static int data_file_size(struct dso *dso) +{ + struct stat st; + + if (!dso->data.file_size) { + if (fstat(dso->data.fd, &st)) { + pr_err("dso mmap failed, fstat: %s\n", strerror(errno)); + return -1; + } + dso->data.file_size = st.st_size; + } + + return 0; +} + +static ssize_t data_read_offset(struct dso *dso, u64 offset, + u8 *data, ssize_t size) +{ + if (data_file_size(dso)) + return -1; + + /* Check the offset sanity. */ + if (offset > dso->data.file_size) + return -1; + + if (offset + size < offset) + return -1; + + return cached_read(dso, offset, data, size); +} + +/** + * dso__data_read_offset - Read data from dso file offset + * @dso: dso object + * @machine: machine object + * @offset: file offset + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso file offset. Open + * dso data file and use cached_read to get the data. + */ +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + if (dso__data_fd(dso, machine) < 0) + return -1; + + return data_read_offset(dso, offset, data, size); +} + +/** + * dso__data_read_addr - Read data from dso address + * @dso: dso object + * @machine: machine object + * @add: virtual memory address + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso address. + */ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size) @@ -473,7 +699,8 @@ struct dso *dso__new(const char *name) dso__set_short_name(dso, dso->name, false); for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; - dso->cache = RB_ROOT; + dso->data.cache = RB_ROOT; + dso->data.fd = -1; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; @@ -485,6 +712,7 @@ struct dso *dso__new(const char *name) dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; INIT_LIST_HEAD(&dso->node); + INIT_LIST_HEAD(&dso->data.open_entry); } return dso; @@ -506,7 +734,8 @@ void dso__delete(struct dso *dso) dso->long_name_allocated = false; } - dso_cache__free(&dso->cache); + dso__data_close(dso); + dso_cache__free(&dso->data.cache); dso__free_a2l(dso); zfree(&dso->symsrc_filename); free(dso); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 38efe95a7fd..ad553ba257b 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -76,7 +76,6 @@ struct dso { struct list_head node; struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; - struct rb_root cache; void *a2l; char *symsrc_filename; unsigned int a2l_fails; @@ -99,6 +98,15 @@ struct dso { const char *long_name; u16 long_name_len; u16 short_name_len; + + /* dso data file */ + struct { + struct rb_root cache; + int fd; + size_t file_size; + struct list_head open_entry; + } data; + char name[0]; }; @@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); +/* + * The dso__data_* external interface provides following functions: + * dso__data_fd + * dso__data_close + * dso__data_read_offset + * dso__data_read_addr + * + * Please refer to the dso.c object code for each function and + * arguments documentation. Following text tries to explain the + * dso file descriptor caching. + * + * The dso__data* interface allows caching of opened file descriptors + * to speed up the dso data accesses. The idea is to leave the file + * descriptor opened ideally for the whole life of the dso object. + * + * The current usage of the dso__data_* interface is as follows: + * + * Get DSO's fd: + * int fd = dso__data_fd(dso, machine); + * USE 'fd' SOMEHOW + * + * Read DSO's data: + * n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE); + * n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE); + * + * Eventually close DSO's fd: + * dso__data_close(dso); + * + * It is not necessary to close the DSO object data file. Each time new + * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once + * it is crossed, the oldest opened DSO object is closed. + * + * The dso__delete function calls close_dso function to ensure the + * data file descriptor gets closed/unmapped before the dso object + * is freed. + * + * TODO +*/ int dso__data_fd(struct dso *dso, struct machine *machine); +void dso__data_close(struct dso *dso); + ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7defd77105d..cc66c4049e0 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -747,14 +747,17 @@ struct __find_variable_param { static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) { struct __find_variable_param *fvp = data; + Dwarf_Attribute attr; int tag; tag = dwarf_tag(die_mem); if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && - die_compare_name(die_mem, fvp->name)) + die_compare_name(die_mem, fvp->name) && + /* Does the DIE have location information or external instance? */ + (dwarf_attr(die_mem, DW_AT_external, &attr) || + dwarf_attr(die_mem, DW_AT_location, &attr))) return DIE_FIND_CB_END; - if (dwarf_haspc(die_mem, fvp->addr)) return DIE_FIND_CB_CONTINUE; else diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 65795b835b3..d0281bdfa58 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,4 +1,5 @@ #include <linux/types.h> +#include <sys/mman.h> #include "event.h" #include "debug.h" #include "hist.h" @@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, return -1; } - event->header.type = PERF_RECORD_MMAP; + event->header.type = PERF_RECORD_MMAP2; while (1) { char bf[BUFSIZ]; char prot[5]; char execname[PATH_MAX]; char anonstr[] = "//anon"; + unsigned int ino; size_t size; ssize_t n; @@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", - &event->mmap.start, &event->mmap.len, prot, - &event->mmap.pgoff, - execname); + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + /* * Anon maps don't have the execname. */ - if (n < 4) + if (n < 7) continue; + + event->mmap2.ino = (u64)ino; + /* * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c */ @@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, else event->header.misc = PERF_RECORD_MISC_GUEST_USER; + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; + if (prot[2] != 'x') { if (!mmap_data || prot[0] != 'r') continue; @@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, anonstr); size = strlen(execname) + 1; - memcpy(event->mmap.filename, execname, size); + memcpy(event->mmap2.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.len -= event->mmap.start; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.pid = tgid; - event->mmap.tid = pid; + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; if (process(tool, event, &synth_sample, machine) != 0) { rc = -1; @@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 - " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n", + " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n", event->mmap2.pid, event->mmap2.tid, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, - (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x', + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', event->mmap2.filename); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index d970232cb27..e5dd40addb3 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -7,6 +7,7 @@ #include "../perf.h" #include "map.h" #include "build-id.h" +#include "perf_regs.h" struct mmap_event { struct perf_event_header header; @@ -27,6 +28,8 @@ struct mmap2_event { u32 min; u64 ino; u64 ino_generation; + u32 prot; + u32 flags; char filename[PATH_MAX]; }; @@ -87,6 +90,10 @@ struct regs_dump { u64 abi; u64 mask; u64 *regs; + + /* Cached values/mask filled by first register access. */ + u64 cache_regs[PERF_REGS_MAX]; + u64 cache_mask; }; struct stack_dump { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5c28d82b76c..8606175fe1e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) } /* - * We default some events to a 1 default interval. But keep + * We default some events to have a default interval. But keep * it a weak assumption overridable by the user. */ - if (!attr->sample_period || (opts->user_freq != UINT_MAX && + if (!attr->sample_period || (opts->user_freq != UINT_MAX || opts->user_interval != ULLONG_MAX)) { if (opts->freq) { perf_evsel__set_sample_bit(evsel, PERIOD); @@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) perf_evsel__set_sample_bit(evsel, WEIGHT); attr->mmap = track; + attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; if (opts->sample_transaction) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c6f5f5251aa..30df6187ee0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -128,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen + 1); } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, @@ -439,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .map = al->map, .sym = al->sym, }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, + .cpu = al->cpu, + .cpumode = al->cpumode, + .ip = al->addr, + .level = al->level, .stat = { .nr_events = 1, .period = period, @@ -517,27 +520,16 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al } static int -iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +iter_finish_mem_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { struct perf_evsel *evsel = iter->evsel; struct hist_entry *he = iter->he; - struct mem_info *mx; int err = -EINVAL; if (he == NULL) goto out; - if (ui__has_annotation()) { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - goto out; - - mx = he->mem_info; - err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); - if (err) - goto out; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); err = hist_entry__append_callchain(he, iter->sample); @@ -575,6 +567,9 @@ static int iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, struct addr_location *al __maybe_unused) { + /* to avoid calling callback function */ + iter->he = NULL; + return 0; } @@ -599,7 +594,7 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) static int iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct branch_info *bi, *bx; + struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; struct hist_entry *he = NULL; int i = iter->curr; @@ -619,17 +614,6 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a if (he == NULL) return -ENOMEM; - if (ui__has_annotation()) { - bx = he->branch_info; - err = addr_map_symbol__inc_samples(&bx->from, evsel->idx); - if (err) - goto out; - - err = addr_map_symbol__inc_samples(&bx->to, evsel->idx); - if (err) - goto out; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); out: @@ -673,9 +657,9 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location } static int -iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +iter_finish_normal_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { - int err; struct hist_entry *he = iter->he; struct perf_evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; @@ -685,12 +669,6 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) iter->he = NULL; - if (ui__has_annotation()) { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - return err; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); return hist_entry__append_callchain(he, sample); @@ -746,13 +724,6 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, */ callchain_cursor_commit(&callchain_cursor); - /* - * The iter->he will be over-written after ->add_next_entry() - * called so inc stats for the original entry now. - */ - if (ui__has_annotation()) - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - hists__inc_nr_samples(&evsel->hists, he->filtered); return err; @@ -802,8 +773,11 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, * It's possible that it has cycles or recursive calls. */ for (i = 0; i < iter->curr; i++) { - if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) + if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) { + /* to avoid calling callback function */ + iter->he = NULL; return 0; + } } he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, @@ -863,7 +837,7 @@ const struct hist_iter_ops hist_iter_cumulative = { int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, - int max_stack_depth) + int max_stack_depth, void *arg) { int err, err2; @@ -883,10 +857,22 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, if (err) goto out; + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, true, arg); + if (err) + goto out; + } + while (iter->ops->next_entry(iter, al)) { err = iter->ops->add_next_entry(iter, al); if (err) break; + + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, false, arg); + if (err) + goto out; + } } out: diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 99ad3cb433f..742f49a8572 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -72,6 +72,7 @@ enum hist_column { HISTC_MEM_TLB, HISTC_MEM_LVL, HISTC_MEM_SNOOP, + HISTC_MEM_DCACHELINE, HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; @@ -119,6 +120,9 @@ struct hist_entry_iter { void *priv; const struct hist_iter_ops *ops; + /* user-defined callback function (optional) */ + int (*add_entry_cb)(struct hist_entry_iter *iter, + struct addr_location *al, bool single, void *arg); }; extern const struct hist_iter_ops hist_iter_normal; @@ -135,7 +139,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, bool sample_self); int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, - int max_stack_depth); + int max_stack_depth, void *arg); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); @@ -202,6 +206,7 @@ struct perf_hpp_fmt { struct list_head list; struct list_head sort_list; + bool elide; }; extern struct list_head perf_hpp__list; @@ -249,7 +254,12 @@ void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); -bool perf_hpp__should_skip(struct perf_hpp_fmt *format); + +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +{ + return format->elide; +} + void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); typedef u64 (*hpp_field_fn)(struct hist_entry *he); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7409ac8de51..c73e1fc12e5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -496,18 +496,6 @@ struct process_args { u64 start; }; -static int symbol__in_kernel(void *arg, const char *name, - char type __maybe_unused, u64 start) -{ - struct process_args *args = arg; - - if (strchr(name, '[')) - return 0; - - args->start = start; - return 1; -} - static void machine__get_kallsyms_filename(struct machine *machine, char *buf, size_t bufsz) { @@ -517,27 +505,41 @@ static void machine__get_kallsyms_filename(struct machine *machine, char *buf, scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir); } -/* Figure out the start address of kernel map from /proc/kallsyms */ -static u64 machine__get_kernel_start_addr(struct machine *machine) +const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; + +/* Figure out the start address of kernel map from /proc/kallsyms. + * Returns the name of the start symbol in *symbol_name. Pass in NULL as + * symbol_name if it's not that important. + */ +static u64 machine__get_kernel_start_addr(struct machine *machine, + const char **symbol_name) { char filename[PATH_MAX]; - struct process_args args; + int i; + const char *name; + u64 addr = 0; machine__get_kallsyms_filename(machine, filename, PATH_MAX); if (symbol__restricted_filename(filename, "/proc/kallsyms")) return 0; - if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) - return 0; + for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { + addr = kallsyms__get_function_start(filename, name); + if (addr) + break; + } + + if (symbol_name) + *symbol_name = name; - return args.start; + return addr; } int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { enum map_type type; - u64 start = machine__get_kernel_start_addr(machine); + u64 start = machine__get_kernel_start_addr(machine, NULL); for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -852,23 +854,11 @@ static int machine__create_modules(struct machine *machine) return 0; } -const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; - int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); - char filename[PATH_MAX]; const char *name; - u64 addr = 0; - int i; - - machine__get_kallsyms_filename(machine, filename, PATH_MAX); - - for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr = kallsyms__get_function_start(filename, name); - if (addr) - break; - } + u64 addr = machine__get_kernel_start_addr(machine, &name); if (!addr) return -1; @@ -1060,6 +1050,8 @@ int machine__process_mmap2_event(struct machine *machine, event->mmap2.pid, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, + event->mmap2.prot, + event->mmap2.flags, event->mmap2.filename, type); if (map == NULL) @@ -1105,7 +1097,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(&machine->user_dsos, event->mmap.start, event->mmap.len, event->mmap.pgoff, - event->mmap.pid, 0, 0, 0, 0, + event->mmap.pid, 0, 0, 0, 0, 0, 0, event->mmap.filename, type); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8ccbb32eda2..25c571f4cba 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -138,7 +138,7 @@ void map__init(struct map *map, enum map_type type, struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, char *filename, + u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type) { struct map *map = malloc(sizeof(*map)); @@ -157,6 +157,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, map->min = d_min; map->ino = ino; map->ino_generation = ino_gen; + map->prot = prot; + map->flags = flags; if ((anon || no_dso) && type == MAP__FUNCTION) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index ae2d4511058..7758c72522e 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -35,6 +35,8 @@ struct map { bool referenced; bool erange_warned; u32 priv; + u32 prot; + u32 flags; u64 pgoff; u64 reloc; u32 maj, min; /* only valid for MMAP2 record */ @@ -118,7 +120,7 @@ void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, + u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index a3539ef30b1..43168fb0d9a 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,11 +1,15 @@ #include <errno.h> #include "perf_regs.h" +#include "event.h" int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { int i, idx = 0; u64 mask = regs->mask; + if (regs->cache_mask & (1 << id)) + goto out; + if (!(mask & (1 << id))) return -EINVAL; @@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) idx++; } - *valp = regs->regs[idx]; + regs->cache_mask |= (1 << id); + regs->cache_regs[id] = regs->regs[idx]; + +out: + *valp = regs->cache_regs[id]; return 0; } diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 79c78f74e0c..980dbf76bc9 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -2,7 +2,8 @@ #define __PERF_REGS_H #include <linux/types.h> -#include "event.h" + +struct regs_dump; #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> @@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); #else #define PERF_REGS_MASK 0 +#define PERF_REGS_MAX 0 static inline const char *perf_reg_name(int id __maybe_unused) { diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 0d1542f33d8..9a0a1839a37 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module) ret = debuginfo__find_line_range(dinfo, lr); debuginfo__delete(dinfo); - if (ret == 0) { + if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); return -ENOENT; } else if (ret < 0) { - pr_warning("Debuginfo analysis failed. (%d)\n", ret); + pr_warning("Debuginfo analysis failed.\n"); return ret; } @@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module) ret = get_real_path(tmp, lr->comp_dir, &lr->path); free(tmp); /* Free old path */ if (ret < 0) { - pr_warning("Failed to find source file. (%d)\n", ret); + pr_warning("Failed to find source file path.\n"); return ret; } @@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo, ret = debuginfo__find_available_vars_at(dinfo, pev, &vls, max_vls, externs); if (ret <= 0) { - pr_err("Failed to find variables at %s (%d)\n", buf, ret); + if (ret == 0 || ret == -ENOENT) { + pr_err("Failed to find the address of %s\n", buf); + ret = -ENOENT; + } else + pr_warning("Debuginfo analysis failed.\n"); goto end; } + /* Some variables are found */ fprintf(stdout, "Available variables at %s\n", buf); for (i = 0; i < ret; i++) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 56276211763..98e30476641 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -511,12 +511,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, &pf->sp_die, pf->tvar); - if (ret == -ENOENT) + if (ret == -ENOENT || ret == -EINVAL) pr_err("Failed to find the location of %s at this address.\n" " Perhaps, it has been optimized out.\n", pf->pvar->var); else if (ret == -ENOTSUP) pr_err("Sorry, we don't support this variable location yet.\n"); - else if (pf->pvar->field) { + else if (ret == 0 && pf->pvar->field) { ret = convert_variable_fields(vr_die, pf->pvar->var, pf->pvar->field, &pf->tvar->ref, &die_mem); @@ -573,14 +573,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) { /* Search again in global variables */ if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) + pr_warning("Failed to find '%s' in this function.\n", + pf->pvar->var); ret = -ENOENT; } if (ret >= 0) ret = convert_variable(&vr_die, pf); - if (ret < 0) - pr_warning("Failed to find '%s' in this function.\n", - pf->pvar->var); return ret; } @@ -1281,7 +1280,11 @@ out: return ret; } -/* Find available variables at given probe point */ +/* + * Find available variables at given probe point + * Return the number of found probe points. Return 0 if there is no + * matched probe point. Return <0 if an error occurs. + */ int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e108207c5de..af7da565a75 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: + case PRINT_BITMASK: break; case PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cd9774df375..1c419321f70 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_FUNC: + case PRINT_BITMASK: /* we should warn... */ return; } @@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s=", f->name); if (f->flags & FIELD_IS_STRING || f->flags & FIELD_IS_FLAG || + f->flags & FIELD_IS_ARRAY || f->flags & FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); else if (f->flags & FIELD_IS_SIGNED) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9da8931d239..1ec57dd8228 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,3 +1,4 @@ +#include <sys/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } +static inline u64 cl_address(u64 address) +{ + /* return the cacheline of the address */ + return (address & ~(cacheline_size - 1)); +} + +static int64_t +sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + u64 l, r; + struct map *l_map, *r_map; + + if (!left->mem_info) return -1; + if (!right->mem_info) return 1; + + /* group event types together */ + if (left->cpumode > right->cpumode) return -1; + if (left->cpumode < right->cpumode) return 1; + + l_map = left->mem_info->daddr.map; + r_map = right->mem_info->daddr.map; + + /* if both are NULL, jump to sort on al_addr instead */ + if (!l_map && !r_map) + goto addr; + + if (!l_map) return -1; + if (!r_map) return 1; + + if (l_map->maj > r_map->maj) return -1; + if (l_map->maj < r_map->maj) return 1; + + if (l_map->min > r_map->min) return -1; + if (l_map->min < r_map->min) return 1; + + if (l_map->ino > r_map->ino) return -1; + if (l_map->ino < r_map->ino) return 1; + + if (l_map->ino_generation > r_map->ino_generation) return -1; + if (l_map->ino_generation < r_map->ino_generation) return 1; + + /* + * Addresses with no major/minor numbers are assumed to be + * anonymous in userspace. Sort those on pid then address. + * + * The kernel and non-zero major/minor mapped areas are + * assumed to be unity mapped. Sort those on address. + */ + + if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && + (!(l_map->flags & MAP_SHARED)) && + !l_map->maj && !l_map->min && !l_map->ino && + !l_map->ino_generation) { + /* userspace anonymous */ + + if (left->thread->pid_ > right->thread->pid_) return -1; + if (left->thread->pid_ < right->thread->pid_) return 1; + } + +addr: + /* al_addr does all the right addr - start + offset calculations */ + l = cl_address(left->mem_info->daddr.al_addr); + r = cl_address(right->mem_info->daddr.al_addr); + + if (l > r) return -1; + if (l < r) return 1; + + return 0; +} + +static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + + uint64_t addr = 0; + struct map *map = NULL; + struct symbol *sym = NULL; + char level = he->level; + + if (he->mem_info) { + addr = cl_address(he->mem_info->daddr.al_addr); + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; + + /* print [s] for shared data mmaps */ + if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && + map && (map->type == MAP__VARIABLE) && + (map->flags & MAP_SHARED) && + (map->maj || map->min || map->ino || + map->ino_generation)) + level = 's'; + else if (!map) + level = 'X'; + } + return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, + width); +} + struct sort_entry sort_mispredict = { .se_header = "Branch Mispredicted", .se_cmp = sort__mispredict_cmp, @@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = { .se_width_idx = HISTC_MEM_SNOOP, }; +struct sort_entry sort_mem_dcacheline = { + .se_header = "Data Cacheline", + .se_cmp = sort__dcacheline_cmp, + .se_snprintf = hist_entry__dcacheline_snprintf, + .se_width_idx = HISTC_MEM_DCACHELINE, +}; + static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb), DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), + DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), }; #undef DIM @@ -1157,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); + hse->hpp.elide = false; return hse; } @@ -1364,27 +1472,64 @@ static int __setup_sorting(void) return ret; } -bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +void perf_hpp__set_elide(int idx, bool elide) { - if (perf_hpp__is_sort_entry(format)) { - struct hpp_sort_entry *hse; + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; - hse = container_of(format, struct hpp_sort_entry, hpp); - return hse->se->elide; + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (hse->se->se_width_idx == idx) { + fmt->elide = elide; + break; + } } - return false; } -static void sort_entry__setup_elide(struct sort_entry *se, - struct strlist *list, - const char *list_name, FILE *fp) +static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp) { if (list && strlist__nr_entries(list) == 1) { if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - se->elide = true; + return true; } + return false; +} + +static bool get_elide(int idx, FILE *output) +{ + switch (idx) { + case HISTC_SYMBOL: + return __get_elide(symbol_conf.sym_list, "symbol", output); + case HISTC_DSO: + return __get_elide(symbol_conf.dso_list, "dso", output); + case HISTC_COMM: + return __get_elide(symbol_conf.comm_list, "comm", output); + default: + break; + } + + if (sort__mode != SORT_MODE__BRANCH) + return false; + + switch (idx) { + case HISTC_SYMBOL_FROM: + return __get_elide(symbol_conf.sym_from_list, "sym_from", output); + case HISTC_SYMBOL_TO: + return __get_elide(symbol_conf.sym_to_list, "sym_to", output); + case HISTC_DSO_FROM: + return __get_elide(symbol_conf.dso_from_list, "dso_from", output); + case HISTC_DSO_TO: + return __get_elide(symbol_conf.dso_to_list, "dso_to", output); + default: + break; + } + + return false; } void sort__setup_elide(FILE *output) @@ -1392,39 +1537,12 @@ void sort__setup_elide(FILE *output) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "dso", output); - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, - "comm", output); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, - "symbol", output); - - if (sort__mode == SORT_MODE__BRANCH) { - sort_entry__setup_elide(&sort_dso_from, - symbol_conf.dso_from_list, - "dso_from", output); - sort_entry__setup_elide(&sort_dso_to, - symbol_conf.dso_to_list, - "dso_to", output); - sort_entry__setup_elide(&sort_sym_from, - symbol_conf.sym_from_list, - "sym_from", output); - sort_entry__setup_elide(&sort_sym_to, - symbol_conf.sym_to_list, - "sym_to", output); - } else if (sort__mode == SORT_MODE__MEMORY) { - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "symbol_daddr", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "dso_daddr", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "mem", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "local_weight", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "tlb", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "snoop", output); + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + fmt->elide = get_elide(hse->se->se_width_idx, output); } /* @@ -1435,8 +1553,7 @@ void sort__setup_elide(FILE *output) if (!perf_hpp__is_sort_entry(fmt)) continue; - hse = container_of(fmt, struct hpp_sort_entry, hpp); - if (!hse->se->elide) + if (!fmt->elide) return; } @@ -1444,8 +1561,7 @@ void sort__setup_elide(FILE *output) if (!perf_hpp__is_sort_entry(fmt)) continue; - hse = container_of(fmt, struct hpp_sort_entry, hpp); - hse->se->elide = false; + fmt->elide = false; } } @@ -1582,6 +1698,9 @@ void reset_output_field(void) sort__has_sym = 0; sort__has_dso = 0; + field_order = NULL; + sort_order = NULL; + reset_dimensions(); perf_hpp__reset_output_field(); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 426b873e16f..041f0c9cea2 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -89,6 +89,7 @@ struct hist_entry { u64 ip; u64 transaction; s32 cpu; + u8 cpumode; struct hist_entry_diff diff; @@ -185,6 +186,7 @@ enum sort_type { SORT_MEM_TLB, SORT_MEM_LVL, SORT_MEM_SNOOP, + SORT_MEM_DCACHELINE, }; /* @@ -202,7 +204,6 @@ struct sort_entry { int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; - bool elide; }; extern struct sort_entry sort_thread; @@ -213,6 +214,7 @@ int setup_output_field(void); void reset_output_field(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +void perf_hpp__set_elide(int idx, bool elide); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 95e24977993..7b9096f29cd 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -29,11 +29,12 @@ int vmlinux_path__nr_entries; char **vmlinux_path; struct symbol_conf symbol_conf = { - .use_modules = true, - .try_vmlinux_path = true, - .annotate_src = true, - .demangle = true, - .symfs = "", + .use_modules = true, + .try_vmlinux_path = true, + .annotate_src = true, + .demangle = true, + .cumulate_callchain = true, + .symfs = "", }; static enum dso_binary_type binary_type_symtab[] = { diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index bd5768d74f0..25578b98f5c 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, /* Check the .eh_frame section for unwinding info */ offset = elf_section_offset(fd, ".eh_frame_hdr"); - close(fd); if (offset) ret = unwind_spec_ehframe(dso, machine, offset, @@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso, /* Check the .debug_frame section for unwinding info */ *offset = elf_section_offset(fd, ".debug_frame"); - close(fd); if (*offset) return 0; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 7fff6be07f0..95aefa78bb0 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -17,6 +17,7 @@ * XXX We need to find a better place for these things... */ unsigned int page_size; +int cacheline_size; bool test_attr__enabled; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b03da44e94e..66864364ccb 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -304,6 +304,7 @@ char *rtrim(char *s); void dump_stack(void); extern unsigned int page_size; +extern int cacheline_size; void get_term_dimensions(struct winsize *ws); |