diff options
Diffstat (limited to 'tools/perf')
128 files changed, 3279 insertions, 1548 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 40399c3d97d6..812f904193e8 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -1,6 +1,7 @@ PERF-CFLAGS PERF-GUI-VARS PERF-VERSION-FILE +FEATURE-DUMP perf perf-read-vdso32 perf-read-vdsox32 diff --git a/tools/perf/Build b/tools/perf/Build index 976e03849f6d..b77370ef7005 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -18,6 +18,7 @@ perf-y += builtin-lock.o perf-y += builtin-kvm.o perf-y += builtin-inject.o perf-y += builtin-mem.o +perf-y += builtin-data.o perf-$(CONFIG_AUDIT) += builtin-trace.o perf-$(CONFIG_LIBELF) += builtin-probe.o diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 0294c57b1f5e..dd07b55f58d8 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -12,9 +12,9 @@ SYNOPSIS DESCRIPTION ----------- -This command manages the build-id cache. It can add and remove files to/from -the cache. In the future it should as well purge older entries, set upper -limits for the space used by the cache, etc. +This command manages the build-id cache. It can add, remove, update and purge +files to/from the cache. In the future it should as well set upper limits for +the space used by the cache, etc. OPTIONS ------- @@ -36,14 +36,24 @@ OPTIONS actually made. -r:: --remove=:: - Remove specified file from the cache. + Remove a cached binary which has same build-id of specified file + from the cache. +-p:: +--purge=:: + Purge all cached binaries including older caches which have specified + path from the cache. -M:: --missing=:: List missing build ids in the cache for the specified file. -u:: ---update:: - Update specified file of the cache. It can be used to update kallsyms - kernel dso to vmlinux in order to support annotation. +--update=:: + Update specified file of the cache. Note that this doesn't remove + older entires since those may be still needed for annotating old + (or remote) perf.data. Only if there is already a cache which has + exactly same build-id, that is replaced by new one. It can be used + to update kallsyms and kernel dso to vmlinux in order to support + annotation. + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt new file mode 100644 index 000000000000..be8fa1a0a97e --- /dev/null +++ b/tools/perf/Documentation/perf-data.txt @@ -0,0 +1,40 @@ +perf-data(1) +============== + +NAME +---- +perf-data - Data file related processing + +SYNOPSIS +-------- +[verse] +'perf data' [<common options>] <command> [<options>]", + +DESCRIPTION +----------- +Data file related processing. + +COMMANDS +-------- +convert:: + Converts perf data file into another format (only CTF [1] format is support by now). + It's possible to set data-convert debug variable to get debug messages from conversion, + like: + perf --debug data-convert data convert ... + +OPTIONS for 'convert' +--------------------- +--to-ctf:: + Triggers the CTF conversion, specify the path of CTF data directory. + +-i:: + Specify input perf data file path. + +-v:: +--verbose:: + Be more verbose (show counter open errors, etc). + +SEE ALSO +-------- +linkperf:perf[1] +[1] Common Trace Format - http://www.efficios.com/ctf diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index e463caa3eb49..d1deb573877f 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -20,12 +20,20 @@ If no parameters are passed it will assume perf.data.old and perf.data. The differential profile is displayed only for events matching both specified perf.data files. +If no parameters are passed the samples will be sorted by dso and symbol. +As the perf.data files could come from different binaries, the symbols addresses +could vary. So perf diff is based on the comparison of the files and +symbols name. + OPTIONS ------- -D:: --dump-raw-trace:: Dump raw trace in ASCII. +--kallsyms=<file>:: + kallsyms pathname + -m:: --modules:: Load module symbols. WARNING: use only with -k and LIVE kernel diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 7c8fbbf3f61c..150253cc3c97 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -25,6 +25,10 @@ OPTIONS --input=<file>:: Select the input file (default: perf.data unless stdin is a fifo) +-v:: +--verbose:: + Be more verbose. (show symbol address, etc) + --caller:: Show per-callsite statistics diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 3e2aec94f806..4692d277980b 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -127,6 +127,12 @@ To limit the list use: One or more types can be used at the same time, listing the events for the types specified. +Support raw format: + +. '--raw-dump', shows the raw-dump of all the events. +. '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of + a certain kind of events. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1], diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 1c7e50f62b1f..355c4f5569b5 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -55,6 +55,11 @@ OPTIONS If you want to profile write accesses in [0x1000~1008), just set 'mem:0x1000/8:w'. + - a group of events surrounded by a pair of brace ("{event1,event2,...}"). + Each event is separated by commas and the group should be quoted to + prevent the shell interpretation. You also need to use --group on + "perf report" to view group events together. + --filter=<filter>:: Event filter. @@ -62,9 +67,6 @@ OPTIONS --all-cpus:: System-wide collection from all CPUs. --l:: - Scale counter values. - -p:: --pid=:: Record events on existing process ID (comma separated list). @@ -107,6 +109,10 @@ OPTIONS specification with appended unit character - B/K/M/G. The size is rounded up to have nearest pages power of two value. +--group:: + Put all events in a single event group. This precedes the --event + option and remains only for backward compatibility. See --event. + -g:: Enables call-graph (stack chain/backtrace) recording. @@ -241,6 +247,9 @@ Capture machine state (registers) at interrupt, i.e., on counter overflows for each sample. List of captured registers depends on the architecture. This option is off by default. +--running-time:: +Record running and enabled time for read events (:S) + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index dd7cccdde498..4879cf638824 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -40,6 +40,11 @@ OPTIONS Only consider symbols in these comms. CSV that understands file://filename entries. This option will affect the percentage of the overhead column. See --percentage for more info. +--pid=:: + Only show events for given process ID (comma separated list). + +--tid=:: + Only show events for given thread ID (comma separated list). -d:: --dsos=:: Only consider symbols in these dsos. CSV that understands diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index a21eec05bc42..79445750fcb3 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -193,6 +193,12 @@ OPTIONS Only display events for these comms. CSV that understands file://filename entries. +--pid=:: + Only show events for given process ID (comma separated list). + +--tid=:: + Only show events for given thread ID (comma separated list). + -I:: --show-info:: Display extended information about the perf.data file. This adds diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 7e1b1f2bb83c..ba03fd5d1a54 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -55,6 +55,9 @@ OPTIONS --uid=:: Record events in threads owned by uid. Name or number. +--filter-pids=:: + Filter out events for these pids and for 'trace' itself (comma separated list). + -v:: --verbose=:: Verbosity level. @@ -115,6 +118,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --syscalls:: Trace system calls. This options is enabled by default. +--event:: + Trace other events, see 'perf list' for a complete list. + PAGEFAULTS ---------- diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 1e8e400b4493..2b131776363e 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -13,11 +13,16 @@ SYNOPSIS OPTIONS ------- --debug:: - Setup debug variable (just verbose for now) in value + Setup debug variable (see list below) in value range (0, 10). Use like: --debug verbose # sets verbose = 1 --debug verbose=2 # sets verbose = 2 + List of debug variables allowed to set: + verbose - general debug messages + ordered-events - ordered events object debug messages + data-convert - data convert command debug messages + --buildid-dir:: Setup buildid cache directory. It has higher priority than buildid.dir config file option. diff --git a/tools/perf/Makefile b/tools/perf/Makefile index cb2e5868c8e8..c699dc35eef9 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -24,8 +24,8 @@ unexport MAKEFLAGS # (To override it, run 'make JOBS=1' and similar.) # ifeq ($(JOBS),) - JOBS := $(shell grep -c ^processor /proc/cpuinfo 2>/dev/null) - ifeq ($(JOBS),) + JOBS := $(shell egrep -c '^processor|^CPU' /proc/cpuinfo 2>/dev/null) + ifeq ($(JOBS),0) JOBS := 1 endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index efc5158738f4..e9925e6ad1d0 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -68,7 +68,11 @@ include config/utilities.mak # for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode # # Define NO_ZLIB if you do not want to support compressed kernel modules - +# +# Define NO_LIBBABELTRACE if you do not want libbabeltrace support +# for CTF data format. +# +# Define NO_LZMA if you do not want to support compressed (xz) kernel modules ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -519,14 +523,14 @@ $(INSTALL_DOC_TARGETS): # config-clean: $(call QUIET_CLEAN, config) - $(Q)$(MAKE) -C config/feature-checks clean >/dev/null + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) .config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 - $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* + $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 6c14afe8c1b1..db1d3a29d97f 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -289,7 +289,7 @@ static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault) memcpy_t fn = r->fn.memcpy; int i; - memcpy_alloc_mem(&src, &dst, len); + memcpy_alloc_mem(&dst, &src, len); if (prefault) fn(dst, src, len); @@ -312,7 +312,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t len, void *src = NULL, *dst = NULL; int i; - memcpy_alloc_mem(&src, &dst, len); + memcpy_alloc_mem(&dst, &src, len); if (prefault) fn(dst, src, len); diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 747f86103599..71bf7451c0ca 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -208,7 +208,7 @@ static int __cmd_annotate(struct perf_annotate *ann) goto out; } - ret = perf_session__process_events(session, &ann->tool); + ret = perf_session__process_events(session); if (ret) goto out; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index d929d9544664..d47a0cdc71c9 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -196,9 +196,8 @@ static int build_id_cache__add_file(const char *filename) build_id__sprintf(build_id, sizeof(build_id), sbuild_id); err = build_id_cache__add_s(sbuild_id, filename, false, false); - if (verbose) - pr_info("Adding %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Adding %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } @@ -216,9 +215,33 @@ static int build_id_cache__remove_file(const char *filename) build_id__sprintf(build_id, sizeof(build_id), sbuild_id); err = build_id_cache__remove_s(sbuild_id); - if (verbose) - pr_info("Removing %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Removing %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); + + return err; +} + +static int build_id_cache__purge_path(const char *pathname) +{ + struct strlist *list; + struct str_node *pos; + int err; + + err = build_id_cache__list_build_ids(pathname, &list); + if (err) + goto out; + + strlist__for_each(pos, list) { + err = build_id_cache__remove_s(pos->s); + pr_debug("Removing %s %s: %s\n", pos->s, pathname, + err ? "FAIL" : "Ok"); + if (err) + break; + } + strlist__delete(list); + +out: + pr_debug("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok"); return err; } @@ -255,7 +278,7 @@ static int build_id_cache__update_file(const char *filename) u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - int err; + int err = 0; if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); @@ -263,13 +286,14 @@ static int build_id_cache__update_file(const char *filename) } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__remove_s(sbuild_id); + if (build_id_cache__cached(sbuild_id)) + err = build_id_cache__remove_s(sbuild_id); + if (!err) err = build_id_cache__add_s(sbuild_id, filename, false, false); - if (verbose) - pr_info("Updating %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Updating %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } @@ -283,6 +307,7 @@ int cmd_buildid_cache(int argc, const char **argv, bool force = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, + *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, *kcore_filename = NULL; @@ -300,6 +325,8 @@ int cmd_buildid_cache(int argc, const char **argv, "file", "kcore file to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), + OPT_STRING('p', "purge", &purge_name_list_str, "path list", + "path(s) to remove (remove old caches too)"), OPT_STRING('M', "missing", &missing_filename, "file", "to find missing build ids in the cache"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -316,6 +343,11 @@ int cmd_buildid_cache(int argc, const char **argv, argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); + if (argc || (!add_name_list_str && !kcore_filename && + !remove_name_list_str && !purge_name_list_str && + !missing_filename && !update_name_list_str)) + usage_with_options(buildid_cache_usage, buildid_cache_options); + if (missing_filename) { file.path = missing_filename; file.force = force; @@ -366,6 +398,24 @@ int cmd_buildid_cache(int argc, const char **argv, } } + if (purge_name_list_str) { + list = strlist__new(true, purge_name_list_str); + if (list) { + strlist__for_each(pos, list) + if (build_id_cache__purge_path(pos->s)) { + if (errno == ENOENT) { + pr_debug("%s wasn't in the cache\n", + pos->s); + continue; + } + pr_warning("Couldn't remove %s: %s\n", + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); + } + + strlist__delete(list); + } + } + if (missing_filename) ret = build_id_cache__fprintf_missing(session, stdout); diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index ed3873b3e238..feb420f74c2d 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -74,7 +74,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits) * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID */ if (with_hits || perf_data_file__is_pipe(&file)) - perf_session__process_events(session, &build_id__mark_dso_hit_ops); + perf_session__process_events(session); perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits); perf_session__delete(session); diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c new file mode 100644 index 000000000000..709152a7b408 --- /dev/null +++ b/tools/perf/builtin-data.c @@ -0,0 +1,121 @@ +#include <linux/compiler.h> +#include "builtin.h" +#include "perf.h" +#include "debug.h" +#include "parse-options.h" +#include "data-convert-bt.h" + +typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix); + +struct data_cmd { + const char *name; + const char *summary; + data_cmd_fn_t fn; +}; + +static struct data_cmd data_cmds[]; + +#define for_each_cmd(cmd) \ + for (cmd = data_cmds; cmd && cmd->name; cmd++) + +static const struct option data_options[] = { + OPT_END() +}; + +static const char * const data_subcommands[] = { "convert", NULL }; + +static const char *data_usage[] = { + "perf data [<common options>] <command> [<options>]", + NULL +}; + +static void print_usage(void) +{ + struct data_cmd *cmd; + + printf("Usage:\n"); + printf("\t%s\n\n", data_usage[0]); + printf("\tAvailable commands:\n"); + + for_each_cmd(cmd) { + printf("\t %s\t- %s\n", cmd->name, cmd->summary); + } + + printf("\n"); +} + +static const char * const data_convert_usage[] = { + "perf data convert [<options>]", + NULL +}; + +static int cmd_data_convert(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + const char *to_ctf = NULL; + const struct option options[] = { + OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_STRING('i', "input", &input_name, "file", "input file name"), +#ifdef HAVE_LIBBABELTRACE_SUPPORT + OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"), +#endif + OPT_END() + }; + +#ifndef HAVE_LIBBABELTRACE_SUPPORT + pr_err("No conversion support compiled in.\n"); + return -1; +#endif + + argc = parse_options(argc, argv, options, + data_convert_usage, 0); + if (argc) { + usage_with_options(data_convert_usage, options); + return -1; + } + + if (to_ctf) { +#ifdef HAVE_LIBBABELTRACE_SUPPORT + return bt_convert__perf2ctf(input_name, to_ctf); +#else + pr_err("The libbabeltrace support is not compiled in.\n"); + return -1; +#endif + } + + return 0; +} + +static struct data_cmd data_cmds[] = { + { "convert", "converts data file between formats", cmd_data_convert }, + { .name = NULL, }, +}; + +int cmd_data(int argc, const char **argv, const char *prefix) +{ + struct data_cmd *cmd; + const char *cmdstr; + + /* No command specified. */ + if (argc < 2) + goto usage; + + argc = parse_options_subcommand(argc, argv, data_options, data_subcommands, data_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc < 1) + goto usage; + + cmdstr = argv[0]; + + for_each_cmd(cmd) { + if (strcmp(cmd->name, cmdstr)) + continue; + + return cmd->fn(argc, argv, prefix); + } + + pr_err("Unknown command: %s\n", cmdstr); +usage: + print_usage(); + return -1; +} diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 74aada554b12..df6307b4050a 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -747,7 +747,7 @@ static int __cmd_diff(void) goto out_delete; } - ret = perf_session__process_events(d->session, &tool); + ret = perf_session__process_events(d->session); if (ret) { pr_err("Failed to process %s\n", d->file.path); goto out_delete; @@ -791,6 +791,8 @@ static const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, + "file", "kallsyms pathname"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", @@ -802,7 +804,7 @@ static const struct option options[] = { OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..." " Please refer the man page for the complete list."), - OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator", + OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added between " "columns '.' is reserved."), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 25d20628212e..36486eade1ef 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -437,7 +437,18 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) HELP_FORMAT_INFO), OPT_END(), }; - const char * const builtin_help_usage[] = { + const char * const builtin_help_subcommands[] = { + "buildid-cache", "buildid-list", "diff", "evlist", "help", "list", + "record", "report", "bench", "stat", "timechart", "top", "annotate", + "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data", +#ifdef HAVE_LIBELF_SUPPORT + "probe", +#endif +#ifdef HAVE_LIBAUDIT_SUPPORT + "trace", +#endif + NULL }; + const char *builtin_help_usage[] = { "perf help [--all] [--man|--web|--info] [command]", NULL }; @@ -448,8 +459,8 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) perf_config(perf_help_config, &help_format); - argc = parse_options(argc, argv, builtin_help_options, - builtin_help_usage, 0); + argc = parse_options_subcommand(argc, argv, builtin_help_options, + builtin_help_subcommands, builtin_help_usage, 0); if (show_all) { printf("\n usage: %s\n\n", perf_usage_string); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index a13641e066f5..ea46df25368c 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -53,6 +53,13 @@ static int perf_event__repipe_synth(struct perf_tool *tool, return 0; } +static int perf_event__repipe_oe_synth(struct perf_tool *tool, + union perf_event *event, + struct ordered_events *oe __maybe_unused) +{ + return perf_event__repipe_synth(tool, event); +} + static int perf_event__repipe_op2_synth(struct perf_tool *tool, union perf_event *event, struct perf_session *session @@ -359,8 +366,6 @@ static int __cmd_inject(struct perf_inject *inject) } else if (inject->sched_stat) { struct perf_evsel *evsel; - inject->tool.ordered_events = true; - evlist__for_each(session->evlist, evsel) { const char *name = perf_evsel__name(evsel); @@ -379,7 +384,7 @@ static int __cmd_inject(struct perf_inject *inject) if (!file_out->is_pipe) lseek(fd, session->header.data_offset, SEEK_SET); - ret = perf_session__process_events(session, &inject->tool); + ret = perf_session__process_events(session); if (!file_out->is_pipe) { if (inject->build_ids) @@ -408,7 +413,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .unthrottle = perf_event__repipe, .attr = perf_event__repipe_attr, .tracing_data = perf_event__repipe_op2_synth, - .finished_round = perf_event__repipe_op2_synth, + .finished_round = perf_event__repipe_oe_synth, .build_id = perf_event__repipe_op2_synth, .id_index = perf_event__repipe_op2_synth, }, @@ -458,6 +463,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } + inject.tool.ordered_events = inject.sched_stat; + file.path = inject.input_name; inject.session = perf_session__new(&file, true, &inject.tool); if (inject.session == NULL) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index f295141025bc..64d3623d45a0 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -20,6 +20,7 @@ #include <linux/rbtree.h> #include <linux/string.h> +#include <locale.h> struct alloc_stat; typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); @@ -275,10 +276,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session, struct rb_node *next; struct machine *machine = &session->machines.host; - printf("%.102s\n", graph_dotted_line); + printf("%.105s\n", graph_dotted_line); printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); printf(" Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag\n"); - printf("%.102s\n", graph_dotted_line); + printf("%.105s\n", graph_dotted_line); next = rb_first(root); @@ -304,7 +305,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session, snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr); printf(" %-34s |", buf); - printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n", + printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %9lu | %6.3f%%\n", (unsigned long long)data->bytes_alloc, (unsigned long)data->bytes_alloc / data->hit, (unsigned long long)data->bytes_req, @@ -317,21 +318,21 @@ static void __print_result(struct rb_root *root, struct perf_session *session, } if (n_lines == -1) - printf(" ... | ... | ... | ... | ... | ... \n"); + printf(" ... | ... | ... | ... | ... | ... \n"); - printf("%.102s\n", graph_dotted_line); + printf("%.105s\n", graph_dotted_line); } static void print_summary(void) { printf("\nSUMMARY\n=======\n"); - printf("Total bytes requested: %lu\n", total_requested); - printf("Total bytes allocated: %lu\n", total_allocated); - printf("Total bytes wasted on internal fragmentation: %lu\n", + printf("Total bytes requested: %'lu\n", total_requested); + printf("Total bytes allocated: %'lu\n", total_allocated); + printf("Total bytes wasted on internal fragmentation: %'lu\n", total_allocated - total_requested); printf("Internal fragmentation: %f%%\n", fragmentation(total_requested, total_allocated)); - printf("Cross CPU allocations: %lu/%lu\n", nr_cross_allocs, nr_allocs); + printf("Cross CPU allocations: %'lu/%'lu\n", nr_cross_allocs, nr_allocs); } static void print_result(struct perf_session *session) @@ -426,7 +427,7 @@ static int __cmd_kmem(struct perf_session *session) } setup_pager(); - err = perf_session__process_events(session, &perf_kmem); + err = perf_session__process_events(session); if (err != 0) goto out; sort_result(); @@ -559,6 +560,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg) { char *tok; char *str = strdup(arg); + char *pos = str; if (!str) { pr_err("%s: strdup failed\n", __func__); @@ -566,7 +568,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg) } while (true) { - tok = strsep(&str, ","); + tok = strsep(&pos, ","); if (!tok) break; if (sort_dimension__add(tok, sort_list) < 0) { @@ -662,6 +664,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) const char * const default_sort_order = "frag,hit,bytes"; const struct option kmem_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL, "show per-callsite statistics", parse_caller_opt), OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL, @@ -703,6 +707,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) symbol__init(&session->header.env); if (!strcmp(argv[0], "stat")) { + setlocale(LC_ALL, ""); + if (cpu__setup_cpunode_map()) goto out_delete; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 0894a817f67e..643722f40075 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -18,6 +18,7 @@ #include "util/stat.h" #include "util/top.h" #include "util/data.h" +#include "util/ordered-events.h" #include <sys/prctl.h> #ifdef HAVE_TIMERFD_SUPPORT @@ -730,9 +731,9 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, return -1; } - err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0); + err = perf_session__queue_event(kvm->session, event, &sample, 0); /* - * FIXME: Here we can't consume the event, as perf_session_queue_event will + * FIXME: Here we can't consume the event, as perf_session__queue_event will * point to it, and it'll get possibly overwritten by the kernel. */ perf_evlist__mmap_consume(kvm->evlist, idx); @@ -783,8 +784,10 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm) /* flush queue after each round in which we processed events */ if (ntotal) { - kvm->session->ordered_events.next_flush = flush_time; - err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session); + struct ordered_events *oe = &kvm->session->ordered_events; + + oe->next_flush = flush_time; + err = ordered_events__flush(oe, OE_FLUSH__ROUND); if (err) { if (kvm->lost_events) pr_info("\nLost events: %" PRIu64 "\n\n", @@ -1066,7 +1069,7 @@ static int read_events(struct perf_kvm_stat *kvm) if (ret < 0) return ret; - return perf_session__process_events(kvm->session, &kvm->tool); + return perf_session__process_events(kvm->session); } static int parse_target_str(struct perf_kvm_stat *kvm) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index ad8018e26aa0..af5bd0514108 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -36,41 +36,36 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) setup_pager(); - if (raw_dump) { - print_events(NULL, true); - return 0; - } - if (!raw_dump) printf("\nList of pre-defined events (to be used in -e):\n\n"); if (argc == 0) { - print_events(NULL, false); + print_events(NULL, raw_dump); return 0; } for (i = 0; i < argc; ++i) { - if (i) - putchar('\n'); - if (strncmp(argv[i], "tracepoint", 10) == 0) - print_tracepoint_events(NULL, NULL, false); + if (strcmp(argv[i], "tracepoint") == 0) + print_tracepoint_events(NULL, NULL, raw_dump); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) - print_events_type(PERF_TYPE_HARDWARE); + print_symbol_events(NULL, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); else if (strcmp(argv[i], "sw") == 0 || strcmp(argv[i], "software") == 0) - print_events_type(PERF_TYPE_SOFTWARE); + print_symbol_events(NULL, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) - print_hwcache_events(NULL, false); + print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) - print_pmu_events(NULL, false); + print_pmu_events(NULL, raw_dump); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; if (sep == NULL) { - print_events(argv[i], false); + print_events(argv[i], raw_dump); continue; } sep_idx = sep - argv[i]; @@ -79,7 +74,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) return -1; s[sep_idx] = '\0'; - print_tracepoint_events(s, s + sep_idx + 1, false); + print_tracepoint_events(s, s + sep_idx + 1, raw_dump); free(s); } } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index e7ec71589da6..7893a9bba2a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -878,7 +878,7 @@ static int __cmd_report(bool display_info) if (select_key()) goto out_delete; - err = perf_session__process_events(session, &eops); + err = perf_session__process_events(session); if (err) goto out_delete; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 9b5663950a4d..b4dcf0bfc029 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -141,7 +141,7 @@ static int report_raw_events(struct perf_mem *mem) printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); - err = perf_session__process_events(session, &mem->tool); + err = perf_session__process_events(session); if (err) return err; @@ -286,7 +286,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) "input file name"), OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", "list of cpus to profile"), - OPT_STRING('x', "field-separator", &symbol_conf.field_sep, + OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added" " between columns '.' is reserved."), diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d0d02a811ecd..18aad239b401 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -161,8 +161,9 @@ try_again: } } - if (perf_evlist__apply_filters(evlist)) { - error("failed to set filter with %d (%s)\n", errno, + if (perf_evlist__apply_filters(evlist, &pos)) { + error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pos->filter, perf_evsel__name(pos), errno, strerror_r(errno, msg, sizeof(msg))); rc = -1; goto out; @@ -225,7 +226,7 @@ static int process_buildids(struct record *rec) */ symbol_conf.ignore_vmlinux_buildid = true; - return perf_session__process_events(session, &rec->tool); + return perf_session__process_events(session); } static void perf_event__synthesize_guest_os(struct machine *machine, void *data) @@ -343,7 +344,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); - session = perf_session__new(file, false, NULL); + session = perf_session__new(file, false, tool); if (session == NULL) { pr_err("Perf session creation failed.\n"); return -1; @@ -839,6 +840,8 @@ struct option __record_options[] = { "use per-thread mmaps"), OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs, "Sample machine registers on interrupt"), + OPT_BOOLEAN(0, "running-time", &record.opts.running_time, + "Record running/enabled time of read (:S) events"), OPT_END() }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0ba5f07906fb..b5b2ad4ca9c4 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -304,7 +304,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report if (rep->mem_mode) { ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events); - ret += fprintf(fp, "\n# Sort order : %s", sort_order); + ret += fprintf(fp, "\n# Sort order : %s", sort_order ? : default_mem_sort_order); } else ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); return ret + fprintf(fp, "\n#\n"); @@ -482,7 +482,7 @@ static int __cmd_report(struct report *rep) if (ret) return ret; - ret = perf_session__process_events(session, &rep->tool); + ret = perf_session__process_events(session); if (ret) return ret; @@ -669,6 +669,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "only consider symbols in these dsos"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", "only consider symbols in these comms"), + OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]", + "only consider symbols in these pids"), + OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", + "only consider symbols in these tids"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter", @@ -676,7 +680,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str, "width[,width...]", "don't try to adjust column width, use these fixed values"), - OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator", + OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added between " "columns '.' is reserved."), OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved, @@ -768,7 +772,7 @@ repeat: * 0/1 means the user chose a mode. */ if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) && - branch_call_mode == -1) { + !branch_call_mode) { sort__mode = SORT_MODE__BRANCH; symbol_conf.cumulate_callchain = false; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 891c3930080e..3b3a5bb97059 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -831,7 +831,7 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) return -1; } - atoms->thread = thread; + atoms->thread = thread__get(thread); INIT_LIST_HEAD(&atoms->work_list); __thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid); return 0; @@ -1439,8 +1439,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ return err; } -static int perf_sched__read_events(struct perf_sched *sched, - struct perf_session **psession) +static int perf_sched__read_events(struct perf_sched *sched) { const struct perf_evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, @@ -1454,6 +1453,7 @@ static int perf_sched__read_events(struct perf_sched *sched, .path = input_name, .mode = PERF_DATA_MODE_READ, }; + int rc = -1; session = perf_session__new(&file, false, &sched->tool); if (session == NULL) { @@ -1467,27 +1467,21 @@ static int perf_sched__read_events(struct perf_sched *sched, goto out_delete; if (perf_session__has_traces(session, "record -R")) { - int err = perf_session__process_events(session, &sched->tool); + int err = perf_session__process_events(session); if (err) { pr_err("Failed to process events, error %d", err); goto out_delete; } - sched->nr_events = session->stats.nr_events[0]; - sched->nr_lost_events = session->stats.total_lost; - sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->evlist->stats.nr_events[0]; + sched->nr_lost_events = session->evlist->stats.total_lost; + sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST]; } - if (psession) - *psession = session; - else - perf_session__delete(session); - - return 0; - + rc = 0; out_delete: perf_session__delete(session); - return -1; + return rc; } static void print_bad_events(struct perf_sched *sched) @@ -1515,12 +1509,10 @@ static void print_bad_events(struct perf_sched *sched) static int perf_sched__lat(struct perf_sched *sched) { struct rb_node *next; - struct perf_session *session; setup_pager(); - /* save session -- references to threads are held in work_list */ - if (perf_sched__read_events(sched, &session)) + if (perf_sched__read_events(sched)) return -1; perf_sched__sort_lat(sched); @@ -1537,6 +1529,7 @@ static int perf_sched__lat(struct perf_sched *sched) work_list = rb_entry(next, struct work_atoms, node); output_lat_thread(sched, work_list); next = rb_next(next); + thread__zput(work_list->thread); } printf(" -----------------------------------------------------------------------------------------------------------------\n"); @@ -1548,7 +1541,6 @@ static int perf_sched__lat(struct perf_sched *sched) print_bad_events(sched); printf("\n"); - perf_session__delete(session); return 0; } @@ -1557,7 +1549,7 @@ static int perf_sched__map(struct perf_sched *sched) sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); setup_pager(); - if (perf_sched__read_events(sched, NULL)) + if (perf_sched__read_events(sched)) return -1; print_bad_events(sched); return 0; @@ -1572,7 +1564,7 @@ static int perf_sched__replay(struct perf_sched *sched) test_calibrations(sched); - if (perf_sched__read_events(sched, NULL)) + if (perf_sched__read_events(sched)) return -1; printf("nr_run_events: %ld\n", sched->nr_run_events); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ce304dfd962a..662366ceb572 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -800,7 +800,7 @@ static int __cmd_script(struct perf_script *script) script->tool.mmap2 = process_mmap2_event; } - ret = perf_session__process_events(script->session, &script->tool); + ret = perf_session__process_events(script->session); if (debug_mode) pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); @@ -1562,6 +1562,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", "only display events for these comms"), + OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]", + "only consider symbols in these pids"), + OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", + "only consider symbols in these tids"), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, @@ -1572,7 +1576,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Show the mmap events"), OPT_END() }; - const char * const script_usage[] = { + const char * const script_subcommands[] = { "record", "report", NULL }; + const char *script_usage[] = { "perf script [<options>]", "perf script [<options>] record <script> [<record-options>] <command>", "perf script [<options>] report <script> [script-args]", @@ -1586,7 +1591,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) setup_scripting(); - argc = parse_options(argc, argv, options, script_usage, + argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, PARSE_OPT_STOP_AT_NON_OPTION); file.path = input_name; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index e598e4e98170..f7b8218785f6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -353,39 +353,40 @@ static struct perf_evsel *nth_evsel(int n) * more semantic information such as miss/hit ratios, * instruction rates, etc: */ -static void update_shadow_stats(struct perf_evsel *counter, u64 *count) +static void update_shadow_stats(struct perf_evsel *counter, u64 *count, + int cpu) { if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK)) - update_stats(&runtime_nsecs_stats[0], count[0]); + update_stats(&runtime_nsecs_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_stats(&runtime_cycles_stats[0], count[0]); + update_stats(&runtime_cycles_stats[cpu], count[0]); else if (transaction_run && perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX))) - update_stats(&runtime_cycles_in_tx_stats[0], count[0]); + update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]); else if (transaction_run && perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START))) - update_stats(&runtime_transaction_stats[0], count[0]); + update_stats(&runtime_transaction_stats[cpu], count[0]); else if (transaction_run && perf_evsel__cmp(counter, nth_evsel(T_ELISION_START))) - update_stats(&runtime_elision_stats[0], count[0]); + update_stats(&runtime_elision_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_stats(&runtime_stalled_cycles_front_stats[0], count[0]); + update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_stats(&runtime_stalled_cycles_back_stats[0], count[0]); + update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_stats(&runtime_branches_stats[0], count[0]); + update_stats(&runtime_branches_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_stats(&runtime_cacherefs_stats[0], count[0]); + update_stats(&runtime_cacherefs_stats[cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_stats(&runtime_l1_dcache_stats[0], count[0]); + update_stats(&runtime_l1_dcache_stats[cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_stats(&runtime_l1_icache_stats[0], count[0]); + update_stats(&runtime_l1_icache_stats[cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_stats(&runtime_ll_cache_stats[0], count[0]); + update_stats(&runtime_ll_cache_stats[cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_stats(&runtime_dtlb_cache_stats[0], count[0]); + update_stats(&runtime_dtlb_cache_stats[cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_stats(&runtime_itlb_cache_stats[0], count[0]); + update_stats(&runtime_itlb_cache_stats[cpu], count[0]); } static void zero_per_pkg(struct perf_evsel *counter) @@ -447,7 +448,8 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, perf_evsel__compute_deltas(evsel, cpu, count); perf_counts_values__scale(count, scale, NULL); evsel->counts->cpu[cpu] = *count; - update_shadow_stats(evsel, count->values); + if (aggr_mode == AGGR_NONE) + update_shadow_stats(evsel, count->values, cpu); break; case AGGR_GLOBAL: aggr->val += count->val; @@ -495,7 +497,7 @@ static int read_counter_aggr(struct perf_evsel *counter) /* * Save the full runtime - to allow normalization during printout: */ - update_shadow_stats(counter, count); + update_shadow_stats(counter, count, 0); return 0; } @@ -510,6 +512,9 @@ static int read_counter(struct perf_evsel *counter) int ncpus = perf_evsel__nr_cpus(counter); int cpu, thread; + if (!counter->supported) + return -ENOENT; + if (counter->system_wide) nthreads = 1; @@ -679,8 +684,9 @@ static int __run_perf_stat(int argc, const char **argv) unit_width = l; } - if (perf_evlist__apply_filters(evsel_list)) { - error("failed to set filter with %d (%s)\n", errno, + if (perf_evlist__apply_filters(evsel_list, &counter)) { + error("failed to set filter \"%s\" on event %s with %d (%s)\n", + counter->filter, perf_evsel__name(counter), errno, strerror_r(errno, msg, sizeof(msg))); return -1; } @@ -766,6 +772,19 @@ static int run_perf_stat(int argc, const char **argv) return ret; } +static void print_running(u64 run, u64 ena) +{ + if (csv_output) { + fprintf(output, "%s%" PRIu64 "%s%.2f", + csv_sep, + run, + csv_sep, + ena ? 100.0 * run / ena : 100.0); + } else if (run != ena) { + fprintf(output, " (%.2f%%)", 100.0 * run / ena); + } +} + static void print_noise_pct(double total, double avg) { double pct = rel_stddev_stats(total, avg); @@ -1076,6 +1095,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) if (total) { ratio = avg / total; fprintf(output, " # %5.2f insns per cycle ", ratio); + } else { + fprintf(output, " "); } total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]); total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu])); @@ -1145,6 +1166,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) if (total) { ratio = avg / total; fprintf(output, " # %8.3f GHz ", ratio); + } else { + fprintf(output, " "); } } else if (transaction_run && perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) { @@ -1249,6 +1272,7 @@ static void print_aggr(char *prefix) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); + print_running(run, ena); fputc('\n', output); continue; } @@ -1259,13 +1283,10 @@ static void print_aggr(char *prefix) else abs_printout(id, nr, counter, uval); - if (!csv_output) { + if (!csv_output) print_noise(counter, 1.0); - if (run != ena) - fprintf(output, " (%.2f%%)", - 100.0 * run / ena); - } + print_running(run, ena); fputc('\n', output); } } @@ -1281,11 +1302,15 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) double avg = avg_stats(&ps->res_stats[0]); int scaled = counter->counts->scaled; double uval; + double avg_enabled, avg_running; + + avg_enabled = avg_stats(&ps->res_stats[1]); + avg_running = avg_stats(&ps->res_stats[2]); if (prefix) fprintf(output, "%s", prefix); - if (scaled == -1) { + if (scaled == -1 || !counter->supported) { fprintf(output, "%*s%s", csv_output ? 0 : 18, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, @@ -1300,6 +1325,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) if (counter->cgrp) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); + print_running(avg_running, avg_enabled); fputc('\n', output); return; } @@ -1313,19 +1339,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) print_noise(counter, avg); - if (csv_output) { - fputc('\n', output); - return; - } - - if (scaled) { - double avg_enabled, avg_running; - - avg_enabled = avg_stats(&ps->res_stats[1]); - avg_running = avg_stats(&ps->res_stats[2]); - - fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled); - } + print_running(avg_running, avg_enabled); fprintf(output, "\n"); } @@ -1367,6 +1381,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); + print_running(run, ena); fputc('\n', output); continue; } @@ -1378,13 +1393,10 @@ static void print_counter(struct perf_evsel *counter, char *prefix) else abs_printout(cpu, 0, counter, uval); - if (!csv_output) { + if (!csv_output) print_noise(counter, 1.0); + print_running(run, ena); - if (run != ena) - fprintf(output, " (%.2f%%)", - 100.0 * run / ena); - } fputc('\n', output); } } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index f3bb1a4bf060..494b3bbe5ea4 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -1623,7 +1623,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name) goto out_delete; } - ret = perf_session__process_events(session, &tchart->tool); + ret = perf_session__process_events(session); if (ret) goto out_delete; @@ -1958,7 +1958,8 @@ int cmd_timechart(int argc, const char **argv, parse_time), OPT_END() }; - const char * const timechart_usage[] = { + const char * const timechart_subcommands[] = { "record", NULL }; + const char *timechart_usage[] = { "perf timechart [<options>] {record}", NULL }; @@ -1976,8 +1977,8 @@ int cmd_timechart(int argc, const char **argv, "perf timechart record [<options>]", NULL }; - argc = parse_options(argc, argv, timechart_options, timechart_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, timechart_options, timechart_subcommands, + timechart_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (tchart.power_only && tchart.tasks_only) { pr_err("-P and -T options cannot be used at the same time.\n"); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c4c7eac69de4..1cb3436276d1 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -716,7 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!machine) { pr_err("%u unprocessable samples recorded.\r", - top->session->stats.nr_unprocessable_samples++); + top->session->evlist->stats.nr_unprocessable_samples++); return; } @@ -757,8 +757,10 @@ static void perf_event__process_sample(struct perf_tool *tool, al.map == machine->vmlinux_maps[MAP__FUNCTION] && RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { if (symbol_conf.vmlinux_name) { - ui__warning("The %s file can't be used.\n%s", - symbol_conf.vmlinux_name, msg); + char serr[256]; + dso__strerror_load(al.map->dso, serr, sizeof(serr)); + ui__warning("The %s file can't be used: %s\n%s", + symbol_conf.vmlinux_name, serr, msg); } else { ui__warning("A vmlinux file was not found.\n%s", msg); @@ -856,7 +858,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) hists__inc_nr_events(evsel__hists(evsel), event->header.type); machine__process_event(machine, event, &sample); } else - ++session->stats.nr_unknown_events; + ++session->evlist->stats.nr_unknown_events; next_event: perf_evlist__mmap_consume(top->evlist, idx); } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index b1c1df9bfb26..bcc98ce3e5b8 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -52,7 +52,9 @@ struct tp_field { #define TP_UINT_FIELD(bits) \ static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - return *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ + return value; \ } TP_UINT_FIELD(8); @@ -63,7 +65,8 @@ TP_UINT_FIELD(64); #define TP_UINT_FIELD__SWAPPED(bits) \ static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - u##bits value = *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ return bswap_##bits(value);\ } @@ -1132,6 +1135,8 @@ static struct syscall_fmt *syscall_fmt__find(const char *name) struct syscall { struct event_format *tp_format; + int nr_args; + struct format_field *args; const char *name; bool filtered; bool is_exit; @@ -1229,6 +1234,10 @@ struct trace { const char *last_vfs_getname; struct intlist *tid_list; struct intlist *pid_list; + struct { + size_t nr; + pid_t *entries; + } filter_pids; double duration_filter; double runtime_ms; struct { @@ -1435,14 +1444,14 @@ static int syscall__set_arg_fmts(struct syscall *sc) struct format_field *field; int idx = 0; - sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *)); + sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *)); if (sc->arg_scnprintf == NULL) return -1; if (sc->fmt) sc->arg_parm = sc->fmt->arg_parm; - for (field = sc->tp_format->format.fields->next; field; field = field->next) { + for (field = sc->args; field; field = field->next) { if (sc->fmt && sc->fmt->arg_scnprintf[idx]) sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; else if (field->flags & FIELD_IS_POINTER) @@ -1508,18 +1517,37 @@ static int trace__read_syscall_info(struct trace *trace, int id) if (sc->tp_format == NULL) return -1; + sc->args = sc->tp_format->format.fields; + sc->nr_args = sc->tp_format->format.nr_fields; + /* drop nr field - not relevant here; does not exist on older kernels */ + if (sc->args && strcmp(sc->args->name, "nr") == 0) { + sc->args = sc->args->next; + --sc->nr_args; + } + sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); return syscall__set_arg_fmts(sc); } +/* + * args is to be interpreted as a series of longs but we need to handle + * 8-byte unaligned accesses. args points to raw_data within the event + * and raw_data is guaranteed to be 8-byte unaligned because it is + * preceded by raw_size which is a u32. So we need to copy args to a temp + * variable to read it. Most notably this avoids extended load instructions + * on unaligned addresses + */ + static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, - unsigned long *args, struct trace *trace, + unsigned char *args, struct trace *trace, struct thread *thread) { size_t printed = 0; + unsigned char *p; + unsigned long val; - if (sc->tp_format != NULL) { + if (sc->args != NULL) { struct format_field *field; u8 bit = 1; struct syscall_arg arg = { @@ -1529,16 +1557,21 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, .thread = thread, }; - for (field = sc->tp_format->format.fields->next; field; + for (field = sc->args; field; field = field->next, ++arg.idx, bit <<= 1) { if (arg.mask & bit) continue; + + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * arg.idx; + memcpy(&val, p, sizeof(val)); + /* * Suppress this argument if its value is zero and * and we don't have a string associated in an * strarray for it. */ - if (args[arg.idx] == 0 && + if (val == 0 && !(sc->arg_scnprintf && sc->arg_scnprintf[arg.idx] == SCA_STRARRAY && sc->arg_parm[arg.idx])) @@ -1547,23 +1580,26 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, printed += scnprintf(bf + printed, size - printed, "%s%s: ", printed ? ", " : "", field->name); if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) { - arg.val = args[arg.idx]; + arg.val = val; if (sc->arg_parm) arg.parm = sc->arg_parm[arg.idx]; printed += sc->arg_scnprintf[arg.idx](bf + printed, size - printed, &arg); } else { printed += scnprintf(bf + printed, size - printed, - "%ld", args[arg.idx]); + "%ld", val); } } } else { int i = 0; while (i < 6) { + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * i; + memcpy(&val, p, sizeof(val)); printed += scnprintf(bf + printed, size - printed, "%sarg%d: %ld", - printed ? ", " : "", i, args[i]); + printed ? ", " : "", i, val); ++i; } } @@ -1698,7 +1734,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, return -1; } - printed += trace__printf_interrupted_entry(trace, sample); + if (!trace->summary_only) + trace__printf_interrupted_entry(trace, sample); ttrace->entry_time = sample->time; msg = ttrace->entry_str; @@ -1715,7 +1752,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, } else ttrace->entry_pending = true; - trace->current = thread; + if (trace->current != thread) { + thread__put(trace->current); + trace->current = thread__get(thread); + } return 0; } @@ -1840,7 +1880,11 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, { trace__printf_interrupted_entry(trace, sample); trace__fprintf_tstamp(trace, sample->time, trace->output); - fprintf(trace->output, "(%9.9s): %s:", " ", evsel->name); + + if (trace->trace_syscalls) + fprintf(trace->output, "( ): "); + + fprintf(trace->output, "%s:", evsel->name); if (evsel->tp_format) { event_format__fprintf(evsel->tp_format, sample->cpu, @@ -2084,10 +2128,39 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist, return 0; } +static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) +{ + const u32 type = event->header.type; + struct perf_evsel *evsel; + + if (!trace->full_time && trace->base_time == 0) + trace->base_time = sample->time; + + if (type != PERF_RECORD_SAMPLE) { + trace__process_event(trace, trace->host, event, sample); + return; + } + + evsel = perf_evlist__id2evsel(trace->evlist, sample->id); + if (evsel == NULL) { + fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id); + return; + } + + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + sample->raw_data == NULL) { + fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", + perf_evsel__name(evsel), sample->tid, + sample->cpu, sample->raw_size); + } else { + tracepoint_handler handler = evsel->handler; + handler(trace, evsel, event, sample); + } +} + static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = trace->evlist; - struct perf_evsel *evsel; int err = -1, i; unsigned long before; const bool forks = argc > 0; @@ -2147,6 +2220,22 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_open; + /* + * Better not use !target__has_task() here because we need to cover the + * case where no threads were specified in the command line, but a + * workload was, and in that case we will fill in the thread_map when + * we fork the workload in perf_evlist__prepare_workload. + */ + if (trace->filter_pids.nr > 0) + err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries); + else if (evlist->threads->map[0] == -1) + err = perf_evlist__set_filter_pid(evlist, getpid()); + + if (err < 0) { + printf("err=%d,%s\n", -err, strerror(-err)); + exit(1); + } + err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false); if (err < 0) goto out_error_mmap; @@ -2166,8 +2255,6 @@ again: union perf_event *event; while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { - const u32 type = event->header.type; - tracepoint_handler handler; struct perf_sample sample; ++trace->nr_events; @@ -2178,30 +2265,7 @@ again: goto next_event; } - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample.time; - - if (type != PERF_RECORD_SAMPLE) { - trace__process_event(trace, trace->host, event, &sample); - continue; - } - - evsel = perf_evlist__id2evsel(evlist, sample.id); - if (evsel == NULL) { - fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - goto next_event; - } - - if (evsel->attr.type == PERF_TYPE_TRACEPOINT && - sample.raw_data == NULL) { - fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", - perf_evsel__name(evsel), sample.tid, - sample.cpu, sample.raw_size); - goto next_event; - } - - handler = evsel->handler; - handler(trace, evsel, event, &sample); + trace__handle_event(trace, event, &sample); next_event: perf_evlist__mmap_consume(evlist, i); @@ -2224,6 +2288,8 @@ next_event: } out_disable: + thread__zput(trace->current); + perf_evlist__disable(evlist); if (!err) { @@ -2353,7 +2419,7 @@ static int trace__replay(struct trace *trace) setup_pager(); - err = perf_session__process_events(session, &trace->tool); + err = perf_session__process_events(session); if (err) pr_err("Failed to process events, error %d", err); @@ -2478,6 +2544,38 @@ static int trace__set_duration(const struct option *opt, const char *str, return 0; } +static int trace__set_filter_pids(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int ret = -1; + size_t i; + struct trace *trace = opt->value; + /* + * FIXME: introduce a intarray class, plain parse csv and create a + * { int nr, int entries[] } struct... + */ + struct intlist *list = intlist__new(str); + + if (list == NULL) + return -1; + + i = trace->filter_pids.nr = intlist__nr_entries(list) + 1; + trace->filter_pids.entries = calloc(i, sizeof(pid_t)); + + if (trace->filter_pids.entries == NULL) + goto out; + + trace->filter_pids.entries[0] = getpid(); + + for (i = 1; i < trace->filter_pids.nr; ++i) + trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i; + + intlist__delete(list); + ret = 0; +out: + return ret; +} + static int trace__open_output(struct trace *trace, const char *filename) { struct stat st; @@ -2522,7 +2620,7 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { - const char * const trace_usage[] = { + const char *trace_usage[] = { "perf trace [<options>] [<command>]", "perf trace [<options>] -- <command> [<options>]", "perf trace record [<options>] [<command>]", @@ -2568,6 +2666,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "trace events on existing process id"), OPT_STRING('t', "tid", &trace.opts.target.tid, "tid", "trace events on existing thread id"), + OPT_CALLBACK(0, "filter-pids", &trace, "float", + "show only events with duration > N.M ms", trace__set_filter_pids), OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide, "system-wide collection from all CPUs"), OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu", @@ -2595,9 +2695,13 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), OPT_END() }; + const char * const trace_subcommands[] = { "record", NULL }; int err; char bf[BUFSIZ]; + signal(SIGSEGV, sighandler_dump_stack); + signal(SIGFPE, sighandler_dump_stack); + trace.evlist = perf_evlist__new(); if (trace.evlist == NULL) return -ENOMEM; @@ -2607,8 +2711,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) goto out; } - argc = parse_options(argc, argv, trace_options, trace_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands, + trace_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (trace.trace_pgfaults) { trace.opts.sample_address = true; diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index b210d62907e4..3688ad29085f 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -37,6 +37,7 @@ extern int cmd_test(int argc, const char **argv, const char *prefix); extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_inject(int argc, const char **argv, const char *prefix); extern int cmd_mem(int argc, const char **argv, const char *prefix); +extern int cmd_data(int argc, const char **argv, const char *prefix); extern int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 0906fc401c52..00fcaf8a5b8d 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -7,6 +7,7 @@ perf-archive mainporcelain common perf-bench mainporcelain common perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common +perf-data mainporcelain common perf-diff mainporcelain common perf-evlist mainporcelain common perf-inject mainporcelain common diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index b97a7b903a23..cd121dfc4de9 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -15,7 +15,6 @@ $(shell echo -n > .config-detected) detected = $(shell echo "$(1)=y" >> .config-detected) detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected) -LIB_INCLUDE := $(srctree)/tools/lib/ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) include $(src-perf)/config/Makefile.arch @@ -96,6 +95,17 @@ ifndef NO_LIBELF FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw endif +ifndef NO_LIBBABELTRACE + # for linking with debug library, run like: + # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ + ifdef LIBBABELTRACE_DIR + LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include + LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib + endif + FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) + FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +endif + # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -166,121 +176,7 @@ LDFLAGS += -Wl,-z,noexecstack EXTLIBS = -lpthread -lrt -lm -ldl -ifneq ($(OUTPUT),) - OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/ - $(shell mkdir -p $(OUTPUT_FEATURES)) -endif - -feature_check = $(eval $(feature_check_code)) -define feature_check_code - feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0) -endef - -feature_set = $(eval $(feature_set_code)) -define feature_set_code - feature-$(1) := 1 -endef - -# -# Build the feature check binaries in parallel, ignore errors, ignore return value and suppress output: -# - -# -# Note that this is not a complete list of all feature tests, just -# those that are typically built on a fully configured system. -# -# [ Feature tests not mentioned here have to be built explicitly in -# the rule that uses them - an example for that is the 'bionic' -# feature check. ] -# -CORE_FEATURE_TESTS = \ - backtrace \ - dwarf \ - fortify-source \ - sync-compare-and-swap \ - glibc \ - gtk2 \ - gtk2-infobar \ - libaudit \ - libbfd \ - libelf \ - libelf-getphdrnum \ - libelf-mmap \ - libnuma \ - libperl \ - libpython \ - libpython-version \ - libslang \ - libunwind \ - pthread-attr-setaffinity-np \ - stackprotector-all \ - timerfd \ - libdw-dwarf-unwind \ - zlib - -LIB_FEATURE_TESTS = \ - dwarf \ - glibc \ - gtk2 \ - libaudit \ - libbfd \ - libelf \ - libnuma \ - libperl \ - libpython \ - libslang \ - libunwind \ - libdw-dwarf-unwind \ - zlib - -VF_FEATURE_TESTS = \ - backtrace \ - fortify-source \ - sync-compare-and-swap \ - gtk2-infobar \ - libelf-getphdrnum \ - libelf-mmap \ - libpython-version \ - pthread-attr-setaffinity-np \ - stackprotector-all \ - timerfd \ - libunwind-debug-frame \ - bionic \ - liberty \ - liberty-z \ - cplus-demangle \ - compile-32 \ - compile-x32 - -# Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. -# If in the future we need per-feature checks/flags for features not -# mentioned in this list we need to refactor this ;-). -set_test_all_flags = $(eval $(set_test_all_flags_code)) -define set_test_all_flags_code - FEATURE_CHECK_CFLAGS-all += $(FEATURE_CHECK_CFLAGS-$(1)) - FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1)) -endef - -$(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat))) - -# -# Special fast-path for the 'all features are available' case: -# -$(call feature_check,all,$(MSG)) - -# -# Just in case the build freshly failed, make sure we print the -# feature matrix: -# -ifeq ($(feature-all), 1) - # - # test-all.c passed - just set all the core feature flags to 1: - # - $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat))) -else - $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(addsuffix .bin,$(CORE_FEATURE_TESTS)) >/dev/null 2>&1) - $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat))) -endif +include $(srctree)/tools/build/Makefile.feature ifeq ($(feature-stackprotector-all), 1) CFLAGS += -fstack-protector-all @@ -309,7 +205,7 @@ endif CFLAGS += -I$(src-perf)/util CFLAGS += -I$(src-perf) -CFLAGS += -I$(LIB_INCLUDE) +CFLAGS += -I$(srctree)/tools/lib/ CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE @@ -518,7 +414,7 @@ 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); + msg := $(warning Missing perl devel files. Disabling perl scripting support, please install perl-ExtUtils-Embed/libperl-dev); else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) @@ -535,22 +431,21 @@ endif disable-python = $(eval $(disable-python_code)) define disable-python_code CFLAGS += -DNO_LIBPYTHON - $(if $(1),$(warning No $(1) was found)) - $(warning Python support will not be built) + $(warning $1) NO_LIBPYTHON := 1 endef ifdef NO_LIBPYTHON - $(call disable-python) + $(call disable-python,Python support disabled by user) else ifndef PYTHON - $(call disable-python,python interpreter) + $(call disable-python,No python interpreter was found: disables Python support - please install python-devel/python-dev) else PYTHON_WORD := $(call shell-wordify,$(PYTHON)) ifndef PYTHON_CONFIG - $(call disable-python,python-config tool) + $(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev) else PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) @@ -562,7 +457,7 @@ else FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) ifneq ($(feature-libpython), 1) - $(call disable-python,Python.h (for Python 2.x)) + $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev) else ifneq ($(feature-libpython-version), 1) @@ -623,7 +518,7 @@ else EXTLIBS += -liberty CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else - msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling) + msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) CFLAGS += -DNO_DEMANGLE endif endif @@ -646,6 +541,17 @@ ifndef NO_ZLIB endif endif +ifndef NO_LZMA + ifeq ($(feature-lzma), 1) + CFLAGS += -DHAVE_LZMA_SUPPORT + EXTLIBS += -llzma + $(call detected,CONFIG_LZMA) + else + msg := $(warning No liblzma found, disables xz kernel module decompression, please install xz-devel/liblzma-dev); + NO_LZMA := 1 + endif +endif + ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT @@ -676,7 +582,7 @@ ifeq (${IS_64_BIT}, 1) NO_PERF_READ_VDSO32 := 1 endif endif - ifneq (${IS_X86_64}, 1) + ifneq ($(ARCH), x86) NO_PERF_READ_VDSOX32 := 1 endif ifndef NO_PERF_READ_VDSOX32 @@ -692,6 +598,19 @@ else NO_PERF_READ_VDSOX32 := 1 endif +ifndef NO_LIBBABELTRACE + $(call feature_check,libbabeltrace) + ifeq ($(feature-libbabeltrace), 1) + CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS) + LDFLAGS += $(LIBBABELTRACE_LDFLAGS) + EXTLIBS += -lbabeltrace-ctf + $(call detected,CONFIG_LIBBABELTRACE) + else + msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev); + NO_LIBBABELTRACE := 1 + endif +endif + # Among the variables below, these: # perfexecdir # template_dir @@ -724,7 +643,7 @@ sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif ifndef lib -ifeq ($(IS_X86_64),1) +ifeq ($(ARCH)$(IS_64_BIT), x861) lib = lib64 else lib = lib @@ -760,84 +679,18 @@ plugindir=$(libdir)/traceevent/plugins plugindir_SQ= $(subst ','\'',$(plugindir)) endif -# -# Print the result of the feature test: -# -feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG)) - -define feature_print_status_code - ifeq ($(feature-$(1)), 1) - MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) - else - MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) - endif -endef - -feature_print_var = $(eval $(feature_print_var_code)) $(info $(MSG)) -define feature_print_var_code +print_var = $(eval $(print_var_code)) $(info $(MSG)) +define print_var_code MSG = $(shell printf '...%30s: %s' $(1) $($(1))) endef -feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG)) -define feature_print_text_code - MSG = $(shell printf '...%30s: %s' $(1) $(2)) -endef - -PERF_FEATURES := $(foreach feat,$(LIB_FEATURE_TESTS),feature-$(feat)($(feature-$(feat)))) -PERF_FEATURES_FILE := $(shell touch $(OUTPUT)PERF-FEATURES; cat $(OUTPUT)PERF-FEATURES) - -ifeq ($(dwarf-post-unwind),1) - PERF_FEATURES += dwarf-post-unwind($(dwarf-post-unwind-text)) -endif - -# The $(display_lib) controls the default detection message -# output. It's set if: -# - detected features differes from stored features from -# last build (in PERF-FEATURES file) -# - one of the $(LIB_FEATURE_TESTS) is not detected -# - VF is enabled - -ifneq ("$(PERF_FEATURES)","$(PERF_FEATURES_FILE)") - $(shell echo "$(PERF_FEATURES)" > $(OUTPUT)PERF-FEATURES) - display_lib := 1 -endif - -feature_check = $(eval $(feature_check_code)) -define feature_check_code - ifneq ($(feature-$(1)), 1) - display_lib := 1 - endif -endef - -$(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_check,$(feat))) - ifeq ($(VF),1) - display_lib := 1 - display_vf := 1 -endif - -ifeq ($(display_lib),1) - $(info ) - $(info Auto-detecting system features:) - $(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_print_status,$(feat),)) - - ifeq ($(dwarf-post-unwind),1) - $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) - endif -endif - -ifeq ($(display_vf),1) - $(foreach feat,$(VF_FEATURE_TESTS),$(call feature_print_status,$(feat),)) - $(info ) - $(call feature_print_var,prefix) - $(call feature_print_var,bindir) - $(call feature_print_var,libdir) - $(call feature_print_var,sysconfdir) - $(call feature_print_var,LIBUNWIND_DIR) - $(call feature_print_var,LIBDW_DIR) -endif - -ifeq ($(display_lib),1) + $(call print_var,prefix) + $(call print_var,bindir) + $(call print_var,libdir) + $(call print_var,sysconfdir) + $(call print_var,LIBUNWIND_DIR) + $(call print_var,LIBDW_DIR) $(info ) endif diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index ff95a68741d1..e11fbd6fae78 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -1,28 +1,15 @@ +ifndef ARCH +ARCH := $(shell uname -m 2>/dev/null || echo not) +endif -uname_M := $(shell uname -m 2>/dev/null || echo not) - -RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ - -e s/arm.*/arm/ -e s/sa110/arm/ \ +ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ + -e s/sun4u/sparc/ -e s/sparc64/sparc/ \ + -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ -e s/tile.*/tile/ ) -# Additional ARCH settings for x86 -ifeq ($(RAW_ARCH),i386) - ARCH ?= x86 -endif - -ifeq ($(RAW_ARCH),x86_64) - ARCH ?= x86 - - ifneq (, $(findstring m32,$(CFLAGS))) - RAW_ARCH := x86_32 - endif -endif - -ARCH ?= $(RAW_ARCH) - LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) IS_64_BIT := 1 diff --git a/tools/perf/config/feature-checks/.gitignore b/tools/perf/config/feature-checks/.gitignore deleted file mode 100644 index 80f3da0c3515..000000000000 --- a/tools/perf/config/feature-checks/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -*.d -*.bin diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile deleted file mode 100644 index b32ff3372514..000000000000 --- a/tools/perf/config/feature-checks/Makefile +++ /dev/null @@ -1,155 +0,0 @@ - -FILES= \ - test-all.bin \ - test-backtrace.bin \ - test-bionic.bin \ - test-dwarf.bin \ - test-fortify-source.bin \ - test-sync-compare-and-swap.bin \ - test-glibc.bin \ - test-gtk2.bin \ - test-gtk2-infobar.bin \ - test-hello.bin \ - test-libaudit.bin \ - test-libbfd.bin \ - test-liberty.bin \ - test-liberty-z.bin \ - test-cplus-demangle.bin \ - test-libelf.bin \ - test-libelf-getphdrnum.bin \ - test-libelf-mmap.bin \ - test-libnuma.bin \ - test-libperl.bin \ - test-libpython.bin \ - test-libpython-version.bin \ - test-libslang.bin \ - test-libunwind.bin \ - test-libunwind-debug-frame.bin \ - test-pthread-attr-setaffinity-np.bin \ - test-stackprotector-all.bin \ - test-timerfd.bin \ - test-libdw-dwarf-unwind.bin \ - test-compile-32.bin \ - test-compile-x32.bin \ - test-zlib.bin - -CC := $(CROSS_COMPILE)gcc -MD -PKG_CONFIG := $(CROSS_COMPILE)pkg-config - -all: $(FILES) - -BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS) - -############################### - -test-all.bin: - $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz - -test-hello.bin: - $(BUILD) - -test-pthread-attr-setaffinity-np.bin: - $(BUILD) -D_GNU_SOURCE -Werror -lpthread - -test-stackprotector-all.bin: - $(BUILD) -Werror -fstack-protector-all - -test-fortify-source.bin: - $(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2 - -test-bionic.bin: - $(BUILD) - -test-libelf.bin: - $(BUILD) -lelf - -test-glibc.bin: - $(BUILD) - -test-dwarf.bin: - $(BUILD) -ldw - -test-libelf-mmap.bin: - $(BUILD) -lelf - -test-libelf-getphdrnum.bin: - $(BUILD) -lelf - -test-libnuma.bin: - $(BUILD) -lnuma - -test-libunwind.bin: - $(BUILD) -lelf - -test-libunwind-debug-frame.bin: - $(BUILD) -lelf - -test-libaudit.bin: - $(BUILD) -laudit - -test-libslang.bin: - $(BUILD) -I/usr/include/slang -lslang - -test-gtk2.bin: - $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) - -test-gtk2-infobar.bin: - $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) - -grep-libs = $(filter -l%,$(1)) -strip-libs = $(filter-out -l%,$(1)) - -PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) -PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` -FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) - -test-libperl.bin: - $(BUILD) $(FLAGS_PERL_EMBED) - -test-libpython.bin: - $(BUILD) - -test-libpython-version.bin: - $(BUILD) - -test-libbfd.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl - -test-liberty.bin: - $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty - -test-liberty-z.bin: - $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz - -test-cplus-demangle.bin: - $(BUILD) -liberty - -test-backtrace.bin: - $(BUILD) - -test-timerfd.bin: - $(BUILD) - -test-libdw-dwarf-unwind.bin: - $(BUILD) - -test-sync-compare-and-swap.bin: - $(BUILD) -Werror - -test-compile-32.bin: - $(CC) -m32 -o $(OUTPUT)$@ test-compile.c - -test-compile-x32.bin: - $(CC) -mx32 -o $(OUTPUT)$@ test-compile.c - -test-zlib.bin: - $(BUILD) -lz - --include *.d - -############################### - -clean: - rm -f $(FILES) *.d diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c deleted file mode 100644 index 6d4d09323922..000000000000 --- a/tools/perf/config/feature-checks/test-all.c +++ /dev/null @@ -1,131 +0,0 @@ -/* - * test-all.c: Try to build all the main testcases at once. - * - * A well-configured system will have all the prereqs installed, so we can speed - * up auto-detection on such systems. - */ - -/* - * Quirk: Python and Perl headers cannot be in arbitrary places, so keep - * these 3 testcases at the top: - */ -#define main main_test_libpython -# include "test-libpython.c" -#undef main - -#define main main_test_libpython_version -# include "test-libpython-version.c" -#undef main - -#define main main_test_libperl -# include "test-libperl.c" -#undef main - -#define main main_test_hello -# include "test-hello.c" -#undef main - -#define main main_test_libelf -# include "test-libelf.c" -#undef main - -#define main main_test_libelf_mmap -# include "test-libelf-mmap.c" -#undef main - -#define main main_test_glibc -# include "test-glibc.c" -#undef main - -#define main main_test_dwarf -# include "test-dwarf.c" -#undef main - -#define main main_test_libelf_getphdrnum -# include "test-libelf-getphdrnum.c" -#undef main - -#define main main_test_libunwind -# include "test-libunwind.c" -#undef main - -#define main main_test_libaudit -# include "test-libaudit.c" -#undef main - -#define main main_test_libslang -# include "test-libslang.c" -#undef main - -#define main main_test_gtk2 -# include "test-gtk2.c" -#undef main - -#define main main_test_gtk2_infobar -# include "test-gtk2-infobar.c" -#undef main - -#define main main_test_libbfd -# include "test-libbfd.c" -#undef main - -#define main main_test_backtrace -# include "test-backtrace.c" -#undef main - -#define main main_test_libnuma -# include "test-libnuma.c" -#undef main - -#define main main_test_timerfd -# include "test-timerfd.c" -#undef main - -#define main main_test_stackprotector_all -# include "test-stackprotector-all.c" -#undef main - -#define main main_test_libdw_dwarf_unwind -# include "test-libdw-dwarf-unwind.c" -#undef main - -#define main main_test_sync_compare_and_swap -# include "test-sync-compare-and-swap.c" -#undef main - -#define main main_test_zlib -# include "test-zlib.c" -#undef main - -#define main main_test_pthread_attr_setaffinity_np -# include "test-pthread_attr_setaffinity_np.c" -#undef main - -int main(int argc, char *argv[]) -{ - main_test_libpython(); - main_test_libpython_version(); - main_test_libperl(); - main_test_hello(); - main_test_libelf(); - main_test_libelf_mmap(); - main_test_glibc(); - main_test_dwarf(); - main_test_libelf_getphdrnum(); - main_test_libunwind(); - main_test_libaudit(); - main_test_libslang(); - main_test_gtk2(argc, argv); - main_test_gtk2_infobar(argc, argv); - main_test_libbfd(); - main_test_backtrace(); - main_test_libnuma(); - main_test_timerfd(); - main_test_stackprotector_all(); - main_test_libdw_dwarf_unwind(); - main_test_sync_compare_and_swap(argc, argv); - main_test_zlib(); - main_test_pthread_attr_setaffinity_np(); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-backtrace.c b/tools/perf/config/feature-checks/test-backtrace.c deleted file mode 100644 index 7124aa1dc8fb..000000000000 --- a/tools/perf/config/feature-checks/test-backtrace.c +++ /dev/null @@ -1,13 +0,0 @@ -#include <execinfo.h> -#include <stdio.h> - -int main(void) -{ - void *backtrace_fns[10]; - size_t entries; - - entries = backtrace(backtrace_fns, 10); - backtrace_symbols_fd(backtrace_fns, entries, 1); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-bionic.c b/tools/perf/config/feature-checks/test-bionic.c deleted file mode 100644 index eac24e9513eb..000000000000 --- a/tools/perf/config/feature-checks/test-bionic.c +++ /dev/null @@ -1,6 +0,0 @@ -#include <android/api-level.h> - -int main(void) -{ - return __ANDROID_API__; -} diff --git a/tools/perf/config/feature-checks/test-compile.c b/tools/perf/config/feature-checks/test-compile.c deleted file mode 100644 index 31dbf45bf99c..000000000000 --- a/tools/perf/config/feature-checks/test-compile.c +++ /dev/null @@ -1,4 +0,0 @@ -int main(void) -{ - return 0; -} diff --git a/tools/perf/config/feature-checks/test-cplus-demangle.c b/tools/perf/config/feature-checks/test-cplus-demangle.c deleted file mode 100644 index 610c686e0009..000000000000 --- a/tools/perf/config/feature-checks/test-cplus-demangle.c +++ /dev/null @@ -1,14 +0,0 @@ -extern int printf(const char *format, ...); -extern char *cplus_demangle(const char *, int); - -int main(void) -{ - char symbol[4096] = "FieldName__9ClassNameFd"; - char *tmp; - - tmp = cplus_demangle(symbol, 0); - - printf("demangled symbol: {%s}\n", tmp); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-dwarf.c b/tools/perf/config/feature-checks/test-dwarf.c deleted file mode 100644 index 3fc1801ce4a9..000000000000 --- a/tools/perf/config/feature-checks/test-dwarf.c +++ /dev/null @@ -1,10 +0,0 @@ -#include <dwarf.h> -#include <elfutils/libdw.h> -#include <elfutils/version.h> - -int main(void) -{ - Dwarf *dbg = dwarf_begin(0, DWARF_C_READ); - - return (long)dbg; -} diff --git a/tools/perf/config/feature-checks/test-fortify-source.c b/tools/perf/config/feature-checks/test-fortify-source.c deleted file mode 100644 index c9f398d87868..000000000000 --- a/tools/perf/config/feature-checks/test-fortify-source.c +++ /dev/null @@ -1,6 +0,0 @@ -#include <stdio.h> - -int main(void) -{ - return puts("hi"); -} diff --git a/tools/perf/config/feature-checks/test-glibc.c b/tools/perf/config/feature-checks/test-glibc.c deleted file mode 100644 index b0820345cd98..000000000000 --- a/tools/perf/config/feature-checks/test-glibc.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <gnu/libc-version.h> - -int main(void) -{ - const char *version = gnu_get_libc_version(); - - return (long)version; -} diff --git a/tools/perf/config/feature-checks/test-gtk2-infobar.c b/tools/perf/config/feature-checks/test-gtk2-infobar.c deleted file mode 100644 index 397b4646d066..000000000000 --- a/tools/perf/config/feature-checks/test-gtk2-infobar.c +++ /dev/null @@ -1,11 +0,0 @@ -#pragma GCC diagnostic ignored "-Wstrict-prototypes" -#include <gtk/gtk.h> -#pragma GCC diagnostic error "-Wstrict-prototypes" - -int main(int argc, char *argv[]) -{ - gtk_init(&argc, &argv); - gtk_info_bar_new(); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-gtk2.c b/tools/perf/config/feature-checks/test-gtk2.c deleted file mode 100644 index 6bd80e509439..000000000000 --- a/tools/perf/config/feature-checks/test-gtk2.c +++ /dev/null @@ -1,10 +0,0 @@ -#pragma GCC diagnostic ignored "-Wstrict-prototypes" -#include <gtk/gtk.h> -#pragma GCC diagnostic error "-Wstrict-prototypes" - -int main(int argc, char *argv[]) -{ - gtk_init(&argc, &argv); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-hello.c b/tools/perf/config/feature-checks/test-hello.c deleted file mode 100644 index c9f398d87868..000000000000 --- a/tools/perf/config/feature-checks/test-hello.c +++ /dev/null @@ -1,6 +0,0 @@ -#include <stdio.h> - -int main(void) -{ - return puts("hi"); -} diff --git a/tools/perf/config/feature-checks/test-libaudit.c b/tools/perf/config/feature-checks/test-libaudit.c deleted file mode 100644 index afc019f08641..000000000000 --- a/tools/perf/config/feature-checks/test-libaudit.c +++ /dev/null @@ -1,10 +0,0 @@ -#include <libaudit.h> - -extern int printf(const char *format, ...); - -int main(void) -{ - printf("error message: %s\n", audit_errno_to_name(0)); - - return audit_open(); -} diff --git a/tools/perf/config/feature-checks/test-libbfd.c b/tools/perf/config/feature-checks/test-libbfd.c deleted file mode 100644 index 24059907e990..000000000000 --- a/tools/perf/config/feature-checks/test-libbfd.c +++ /dev/null @@ -1,15 +0,0 @@ -#include <bfd.h> - -extern int printf(const char *format, ...); - -int main(void) -{ - char symbol[4096] = "FieldName__9ClassNameFd"; - char *tmp; - - tmp = bfd_demangle(0, symbol, 0); - - printf("demangled symbol: {%s}\n", tmp); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c deleted file mode 100644 index f676a3ff442a..000000000000 --- a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c +++ /dev/null @@ -1,13 +0,0 @@ - -#include <elfutils/libdwfl.h> - -int main(void) -{ - /* - * This function is guarded via: __nonnull_attribute__ (1, 2). - * Passing '1' as arguments value. This code is never executed, - * only compiled. - */ - dwfl_thread_getframes((void *) 1, (void *) 1, NULL); - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libelf-getphdrnum.c b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c deleted file mode 100644 index d710459306c3..000000000000 --- a/tools/perf/config/feature-checks/test-libelf-getphdrnum.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <libelf.h> - -int main(void) -{ - size_t dst; - - return elf_getphdrnum(0, &dst); -} diff --git a/tools/perf/config/feature-checks/test-libelf-mmap.c b/tools/perf/config/feature-checks/test-libelf-mmap.c deleted file mode 100644 index 564427d7ef18..000000000000 --- a/tools/perf/config/feature-checks/test-libelf-mmap.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <libelf.h> - -int main(void) -{ - Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0); - - return (long)elf; -} diff --git a/tools/perf/config/feature-checks/test-libelf.c b/tools/perf/config/feature-checks/test-libelf.c deleted file mode 100644 index 08db322d8957..000000000000 --- a/tools/perf/config/feature-checks/test-libelf.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <libelf.h> - -int main(void) -{ - Elf *elf = elf_begin(0, ELF_C_READ, 0); - - return (long)elf; -} diff --git a/tools/perf/config/feature-checks/test-libnuma.c b/tools/perf/config/feature-checks/test-libnuma.c deleted file mode 100644 index 4763d9cd587d..000000000000 --- a/tools/perf/config/feature-checks/test-libnuma.c +++ /dev/null @@ -1,9 +0,0 @@ -#include <numa.h> -#include <numaif.h> - -int main(void) -{ - numa_available(); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libperl.c b/tools/perf/config/feature-checks/test-libperl.c deleted file mode 100644 index 8871f6a0fdb4..000000000000 --- a/tools/perf/config/feature-checks/test-libperl.c +++ /dev/null @@ -1,9 +0,0 @@ -#include <EXTERN.h> -#include <perl.h> - -int main(void) -{ - perl_alloc(); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libpython-version.c b/tools/perf/config/feature-checks/test-libpython-version.c deleted file mode 100644 index facea122d812..000000000000 --- a/tools/perf/config/feature-checks/test-libpython-version.c +++ /dev/null @@ -1,10 +0,0 @@ -#include <Python.h> - -#if PY_VERSION_HEX >= 0x03000000 - #error -#endif - -int main(void) -{ - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libpython.c b/tools/perf/config/feature-checks/test-libpython.c deleted file mode 100644 index b24b28ad6324..000000000000 --- a/tools/perf/config/feature-checks/test-libpython.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <Python.h> - -int main(void) -{ - Py_Initialize(); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libslang.c b/tools/perf/config/feature-checks/test-libslang.c deleted file mode 100644 index 22ff22ed94d1..000000000000 --- a/tools/perf/config/feature-checks/test-libslang.c +++ /dev/null @@ -1,6 +0,0 @@ -#include <slang.h> - -int main(void) -{ - return SLsmg_init_smg(); -} diff --git a/tools/perf/config/feature-checks/test-libunwind-debug-frame.c b/tools/perf/config/feature-checks/test-libunwind-debug-frame.c deleted file mode 100644 index 0ef8087a104a..000000000000 --- a/tools/perf/config/feature-checks/test-libunwind-debug-frame.c +++ /dev/null @@ -1,16 +0,0 @@ -#include <libunwind.h> -#include <stdlib.h> - -extern int -UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, - unw_word_t ip, unw_word_t segbase, - const char *obj_name, unw_word_t start, - unw_word_t end); - -#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) - -int main(void) -{ - dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0); - return 0; -} diff --git a/tools/perf/config/feature-checks/test-libunwind.c b/tools/perf/config/feature-checks/test-libunwind.c deleted file mode 100644 index 43b9369bcab7..000000000000 --- a/tools/perf/config/feature-checks/test-libunwind.c +++ /dev/null @@ -1,27 +0,0 @@ -#include <libunwind.h> -#include <stdlib.h> - -extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, - unw_word_t ip, - unw_dyn_info_t *di, - unw_proc_info_t *pi, - int need_unwind_info, void *arg); - - -#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) - -static unw_accessors_t accessors; - -int main(void) -{ - unw_addr_space_t addr_space; - - addr_space = unw_create_addr_space(&accessors, 0); - if (addr_space) - return 0; - - unw_init_remote(NULL, addr_space, NULL); - dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c deleted file mode 100644 index 0a0d3ecb4e8a..000000000000 --- a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c +++ /dev/null @@ -1,14 +0,0 @@ -#include <stdint.h> -#include <pthread.h> - -int main(void) -{ - int ret = 0; - pthread_attr_t thread_attr; - - pthread_attr_init(&thread_attr); - /* don't care abt exact args, just the API itself in libpthread */ - ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL); - - return ret; -} diff --git a/tools/perf/config/feature-checks/test-stackprotector-all.c b/tools/perf/config/feature-checks/test-stackprotector-all.c deleted file mode 100644 index c9f398d87868..000000000000 --- a/tools/perf/config/feature-checks/test-stackprotector-all.c +++ /dev/null @@ -1,6 +0,0 @@ -#include <stdio.h> - -int main(void) -{ - return puts("hi"); -} diff --git a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c deleted file mode 100644 index c34d4ca4af56..000000000000 --- a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c +++ /dev/null @@ -1,14 +0,0 @@ -#include <stdint.h> - -volatile uint64_t x; - -int main(int argc, char *argv[]) -{ - uint64_t old, new = argc; - - argv = argv; - do { - old = __sync_val_compare_and_swap(&x, 0, 0); - } while (!__sync_bool_compare_and_swap(&x, old, new)); - return old == new; -} diff --git a/tools/perf/config/feature-checks/test-timerfd.c b/tools/perf/config/feature-checks/test-timerfd.c deleted file mode 100644 index 8c5c083b4d3c..000000000000 --- a/tools/perf/config/feature-checks/test-timerfd.c +++ /dev/null @@ -1,18 +0,0 @@ -/* - * test for timerfd functions used by perf-kvm-stat-live - */ -#include <sys/timerfd.h> - -int main(void) -{ - struct itimerspec new_value; - - int fd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK); - if (fd < 0) - return 1; - - if (timerfd_settime(fd, 0, &new_value, NULL) != 0) - return 1; - - return 0; -} diff --git a/tools/perf/config/feature-checks/test-zlib.c b/tools/perf/config/feature-checks/test-zlib.c deleted file mode 100644 index e111fff6240e..000000000000 --- a/tools/perf/config/feature-checks/test-zlib.c +++ /dev/null @@ -1,9 +0,0 @@ -#include <zlib.h> - -int main(void) -{ - z_stream zs; - - inflateInit(&zs); - return 0; -} diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak index 7076a62d0ff7..c16ce833079c 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -175,6 +175,5 @@ _ge-abspath = $(if $(is-executable),$(1)) define get-executable-or-default $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) endef -_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2))) -_gea_warn = $(warning The path '$(1)' is not executable.) +_ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2))) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 33569847fdcc..3ba80b2359cc 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -47,8 +47,16 @@ __my_reassemble_comp_words_by_ref() done } -type _get_comp_words_by_ref &>/dev/null || -_get_comp_words_by_ref() +# Define preload_get_comp_words_by_ref="false", if the function +# __perf_get_comp_words_by_ref() is required instead. +preload_get_comp_words_by_ref="true" + +if [ $preload_get_comp_words_by_ref = "true" ]; then + type _get_comp_words_by_ref &>/dev/null || + preload_get_comp_words_by_ref="false" +fi +[ $preload_get_comp_words_by_ref = "true" ] || +__perf_get_comp_words_by_ref() { local exclude cur_ words_ cword_ if [ "$1" = "-n" ]; then @@ -76,8 +84,16 @@ _get_comp_words_by_ref() done } -type __ltrim_colon_completions &>/dev/null || -__ltrim_colon_completions() +# Define preload__ltrim_colon_completions="false", if the function +# __perf__ltrim_colon_completions() is required instead. +preload__ltrim_colon_completions="true" + +if [ $preload__ltrim_colon_completions = "true" ]; then + type __ltrim_colon_completions &>/dev/null || + preload__ltrim_colon_completions="false" +fi +[ $preload__ltrim_colon_completions = "true" ] || +__perf__ltrim_colon_completions() { if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then # Remove colon-word prefix from COMPREPLY items @@ -97,7 +113,32 @@ __perfcomp () __perfcomp_colon () { __perfcomp "$1" "$2" - __ltrim_colon_completions $cur + if [ $preload__ltrim_colon_completions = "true" ]; then + __ltrim_colon_completions $cur + else + __perf__ltrim_colon_completions $cur + fi +} + +__perf_prev_skip_opts () +{ + local i cmd_ cmds_ + + let i=cword-1 + cmds_=$($cmd $1 --list-cmds) + prev_skip_opts=() + while [ $i -ge 0 ]; do + if [[ ${words[i]} == $1 ]]; then + return + fi + for cmd_ in $cmds_; do + if [[ ${words[i]} == $cmd_ ]]; then + prev_skip_opts=${words[i]} + return + fi + done + ((i--)) + done } __perf_main () @@ -107,29 +148,36 @@ __perf_main () cmd=${words[0]} COMPREPLY=() + # Skip options backward and find the last perf command + __perf_prev_skip_opts # List perf subcommands or long options - if [ $cword -eq 1 ]; then + if [ -z $prev_skip_opts ]; then if [[ $cur == --* ]]; then - __perfcomp '--help --version \ - --exec-path --html-path --paginate --no-pager \ - --perf-dir --work-tree --debugfs-dir' -- "$cur" + cmds=$($cmd --list-opts) else cmds=$($cmd --list-cmds) - __perfcomp "$cmds" "$cur" fi + __perfcomp "$cmds" "$cur" # List possible events for -e option - elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then + elif [[ $prev == @("-e"|"--event") && + $prev_skip_opts == @(record|stat|top) ]]; then evts=$($cmd list --raw-dump) __perfcomp_colon "$evts" "$cur" - # List subcommands for perf commands - elif [[ $prev == @(kvm|kmem|mem|lock|sched) ]]; then - subcmds=$($cmd $prev --list-cmds) - __perfcomp_colon "$subcmds" "$cur" - # List long option names - elif [[ $cur == --* ]]; then - subcmd=${words[1]} - opts=$($cmd $subcmd --list-opts) - __perfcomp "$opts" "$cur" + else + # List subcommands for perf commands + if [[ $prev_skip_opts == @(kvm|kmem|mem|lock|sched| + |data|help|script|test|timechart|trace) ]]; then + subcmds=$($cmd $prev_skip_opts --list-cmds) + __perfcomp_colon "$subcmds" "$cur" + fi + # List long option names + if [[ $cur == --* ]]; then + subcmd=$prev_skip_opts + __perf_prev_skip_opts $subcmd + subcmd=$subcmd" "$prev_skip_opts + opts=$($cmd $subcmd --list-opts) + __perfcomp "$opts" "$cur" + fi fi } @@ -198,7 +246,11 @@ type perf &>/dev/null && _perf() { local cur words cword prev - _get_comp_words_by_ref -n =: cur words cword prev + if [ $preload_get_comp_words_by_ref = "true" ]; then + _get_comp_words_by_ref -n =: cur words cword prev + else + __perf_get_comp_words_by_ref -n =: cur words cword prev + fi __perf_main } && diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 3700a7faca6c..b857fcbd00cf 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,6 +13,7 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" +#include "util/parse-options.h" #include "util/debug.h" #include <api/fs/debugfs.h> #include <pthread.h> @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { #endif { "inject", cmd_inject, 0 }, { "mem", cmd_mem, 0 }, + { "data", cmd_data, 0 }, }; struct pager_config { @@ -124,6 +126,23 @@ static void commit_pager_choice(void) } } +struct option options[] = { + OPT_ARGUMENT("help", "help"), + OPT_ARGUMENT("version", "version"), + OPT_ARGUMENT("exec-path", "exec-path"), + OPT_ARGUMENT("html-path", "html-path"), + OPT_ARGUMENT("paginate", "paginate"), + OPT_ARGUMENT("no-pager", "no-pager"), + OPT_ARGUMENT("perf-dir", "perf-dir"), + OPT_ARGUMENT("work-tree", "work-tree"), + OPT_ARGUMENT("debugfs-dir", "debugfs-dir"), + OPT_ARGUMENT("buildid-dir", "buildid-dir"), + OPT_ARGUMENT("list-cmds", "list-cmds"), + OPT_ARGUMENT("list-opts", "list-opts"), + OPT_ARGUMENT("debug", "debug"), + OPT_END() +}; + static int handle_options(const char ***argv, int *argc, int *envchanged) { int handled = 0; @@ -222,6 +241,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) struct cmd_struct *p = commands+i; printf("%s ", p->cmd); } + putchar('\n'); + exit(0); + } else if (!strcmp(cmd, "--list-opts")) { + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(options)-1; i++) { + struct option *p = options+i; + printf("--%s ", p->long_name); + } + putchar('\n'); exit(0); } else if (!strcmp(cmd, "--debug")) { if (*argc < 2) { diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 1dabb8553499..c38a085a5571 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -29,7 +29,7 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } -#define MAX_NR_CPUS 256 +#define MAX_NR_CPUS 1024 extern const char *input_name; extern bool perf_host, perf_guest; @@ -53,6 +53,7 @@ struct record_opts { bool sample_time; bool period; bool sample_intr_regs; + bool running_time; unsigned int freq; unsigned int mmap_pages; unsigned int user_freq; diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 2de01a4b4084..6a8801b32017 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -30,6 +30,7 @@ perf-y += keep-tracking.o perf-y += code-reading.o perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o +perf-y += kmod-path.o perf-$(CONFIG_X86) += perf-time-to-tsc.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 4b7d9ab0f049..4f4098167112 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -167,6 +167,10 @@ static struct test { .func = test__fdarray__add, }, { + .desc = "Test kmod_path__parse function", + .func = test__kmod_path__parse, + }, + { .func = NULL, }, }; @@ -291,7 +295,7 @@ static int perf_test__list(int argc, const char **argv) int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) { - const char * const test_usage[] = { + const char *test_usage[] = { "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", NULL, }; @@ -302,13 +306,14 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) "be more verbose (show symbol address, etc)"), OPT_END() }; + const char * const test_subcommands[] = { "list", NULL }; struct intlist *skiplist = NULL; int ret = hists__init(); if (ret < 0) return ret; - argc = parse_options(argc, argv, test_options, test_usage, 0); + argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) return perf_test__list(argc, argv); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c new file mode 100644 index 000000000000..e8d7cbb9320c --- /dev/null +++ b/tools/perf/tests/kmod-path.c @@ -0,0 +1,73 @@ +#include <stdbool.h> +#include "tests.h" +#include "dso.h" +#include "debug.h" + +static int test(const char *path, bool alloc_name, bool alloc_ext, + bool kmod, bool comp, const char *name, const char *ext) +{ + struct kmod_path m; + + memset(&m, 0x0, sizeof(m)); + + TEST_ASSERT_VAL("kmod_path__parse", + !__kmod_path__parse(&m, path, alloc_name, alloc_ext)); + + pr_debug("%s - alloc name %d, alloc ext %d, kmod %d, comp %d, name '%s', ext '%s'\n", + path, alloc_name, alloc_ext, m.kmod, m.comp, m.name, m.ext); + + TEST_ASSERT_VAL("wrong kmod", m.kmod == kmod); + TEST_ASSERT_VAL("wrong comp", m.comp == comp); + + if (ext) + TEST_ASSERT_VAL("wrong ext", m.ext && !strcmp(ext, m.ext)); + else + TEST_ASSERT_VAL("wrong ext", !m.ext); + + if (name) + TEST_ASSERT_VAL("wrong name", m.name && !strcmp(name, m.name)); + else + TEST_ASSERT_VAL("wrong name", !m.name); + + free(m.name); + free(m.ext); + return 0; +} + +#define T(path, an, ae, k, c, n, e) \ + TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e)) + +int test__kmod_path__parse(void) +{ + /* path alloc_name alloc_ext kmod comp name ext */ + T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL); + T("/xxxx/xxxx/x-x.ko", false , true , true, false, NULL , NULL); + T("/xxxx/xxxx/x-x.ko", true , false , true, false, "[x_x]", NULL); + T("/xxxx/xxxx/x-x.ko", false , false , true, false, NULL , NULL); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); + T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); + T("/xxxx/xxxx/x.ko.gz", true , false , true, true, "[x]", NULL); + T("/xxxx/xxxx/x.ko.gz", false , false , true, true, NULL , NULL); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("/xxxx/xxxx/x.gz", true , true , false, true, "x.gz" ,"gz"); + T("/xxxx/xxxx/x.gz", false , true , false, true, NULL ,"gz"); + T("/xxxx/xxxx/x.gz", true , false , false, true, "x.gz" , NULL); + T("/xxxx/xxxx/x.gz", false , false , false, true, NULL , NULL); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("x.gz", true , true , false, true, "x.gz", "gz"); + T("x.gz", false , true , false, true, NULL , "gz"); + T("x.gz", true , false , false, true, "x.gz", NULL); + T("x.gz", false , false , false, true, NULL , NULL); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("x.ko.gz", true , true , true, true, "[x]", "gz"); + T("x.ko.gz", false , true , true, true, NULL , "gz"); + T("x.ko.gz", true , false , true, true, "[x]", NULL); + T("x.ko.gz", false , false , true, true, NULL , NULL); + + return 0; +} diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 75709d2b17b4..bff85324f799 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -5,7 +5,7 @@ include config/Makefile.arch # FIXME looks like x86 is the only arch running tests ;-) # we need some IS_(32/64) flag to make this generic -ifeq ($(IS_X86_64),1) +ifeq ($(ARCH)$(IS_64_BIT), x861) lib = lib64 else lib = lib diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 00e776a87a9c..52758a33f64c 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -51,6 +51,7 @@ int test__hists_cumulate(void); int test__switch_tracking(void); int test__fdarray__filter(void); int test__fdarray__add(void); +int test__kmod_path__parse(void); #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 9d32e3c0cfee..e5250eb2dd57 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -829,10 +829,16 @@ out: return key; } +int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, + struct hist_browser_timer *hbt) +{ + return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt); +} + int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt) { - return symbol__tui_annotate(he->ms.sym, he->ms.map, evsel, hbt); + return map_symbol__tui_annotate(&he->ms, evsel, hbt); } static void annotate_browser__mark_jump_targets(struct annotate_browser *browser, diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 788506eef567..995b7a8596b1 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -48,6 +48,24 @@ static bool hist_browser__has_filter(struct hist_browser *hb) return hists__has_filter(hb->hists) || hb->min_pcnt; } +static int hist_browser__get_folding(struct hist_browser *browser) +{ + struct rb_node *nd; + struct hists *hists = browser->hists; + int unfolded_rows = 0; + + for (nd = rb_first(&hists->entries); + (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL; + nd = rb_next(nd)) { + struct hist_entry *he = + rb_entry(nd, struct hist_entry, rb_node); + + if (he->ms.unfolded) + unfolded_rows += he->nr_rows; + } + return unfolded_rows; +} + static u32 hist_browser__nr_entries(struct hist_browser *hb) { u32 nr_entries; @@ -57,6 +75,7 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb) else nr_entries = hb->hists->nr_entries; + hb->nr_callchain_rows = hist_browser__get_folding(hb); return nr_entries + hb->nr_callchain_rows; } @@ -492,6 +511,7 @@ static void hist_browser__show_callchain_entry(struct hist_browser *browser, { int color, width; char folded_sign = callchain_list__folded(chain); + bool show_annotated = browser->show_dso && chain->ms.sym && symbol__annotation(chain->ms.sym)->src; color = HE_COLORSET_NORMAL; width = browser->b.width - (offset + 2); @@ -504,7 +524,8 @@ static void hist_browser__show_callchain_entry(struct hist_browser *browser, ui_browser__set_color(&browser->b, color); hist_browser__gotorc(browser, row, 0); slsmg_write_nstring(" ", offset); - slsmg_printf("%c ", folded_sign); + slsmg_printf("%c", folded_sign); + ui_browser__write_graph(&browser->b, show_annotated ? SLSMG_RARROW_CHAR : ' '); slsmg_write_nstring(str, width); } @@ -1467,7 +1488,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, perf_hpp__set_user_width(symbol_conf.col_width_list_str); while (1) { - const struct thread *thread = NULL; + struct thread *thread = NULL; const struct dso *dso = NULL; int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, @@ -1593,28 +1614,30 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (!sort__has_sym) goto add_exit_option; + if (browser->selection == NULL) + goto skip_annotation; + if (sort__mode == SORT_MODE__BRANCH) { bi = browser->he_selection->branch_info; - if (browser->selection != NULL && - bi && - bi->from.sym != NULL && + + if (bi == NULL) + goto skip_annotation; + + if (bi->from.sym != NULL && !bi->from.map->dso->annotate_warned && - asprintf(&options[nr_options], "Annotate %s", - bi->from.sym->name) > 0) + asprintf(&options[nr_options], "Annotate %s", bi->from.sym->name) > 0) { annotate_f = nr_options++; + } - if (browser->selection != NULL && - bi && - bi->to.sym != NULL && + if (bi->to.sym != NULL && !bi->to.map->dso->annotate_warned && (bi->to.sym != bi->from.sym || bi->to.map->dso != bi->from.map->dso) && - asprintf(&options[nr_options], "Annotate %s", - bi->to.sym->name) > 0) + asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) { annotate_t = nr_options++; + } } else { - if (browser->selection != NULL && - browser->selection->sym != NULL && + if (browser->selection->sym != NULL && !browser->selection->map->dso->annotate_warned) { struct annotation *notes; @@ -1622,11 +1645,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (notes->src && asprintf(&options[nr_options], "Annotate %s", - browser->selection->sym->name) > 0) + browser->selection->sym->name) > 0) { annotate = nr_options++; + } } } - +skip_annotation: if (thread != NULL && asprintf(&options[nr_options], "Zoom %s %s(%d) thread", (browser->hists->thread_filter ? "out of" : "into"), @@ -1682,6 +1706,7 @@ retry_popup_menu: if (choice == annotate || choice == annotate_t || choice == annotate_f) { struct hist_entry *he; struct annotation *notes; + struct map_symbol ms; int err; do_annotate: if (!objdump_path && perf_session_env__lookup_objdump(env)) @@ -1691,30 +1716,21 @@ do_annotate: if (he == NULL) continue; - /* - * we stash the branch_info symbol + map into the - * the ms so we don't have to rewrite all the annotation - * code to use branch_info. - * in branch mode, the ms struct is not used - */ if (choice == annotate_f) { - he->ms.sym = he->branch_info->from.sym; - he->ms.map = he->branch_info->from.map; - } else if (choice == annotate_t) { - he->ms.sym = he->branch_info->to.sym; - he->ms.map = he->branch_info->to.map; + ms.map = he->branch_info->from.map; + ms.sym = he->branch_info->from.sym; + } else if (choice == annotate_t) { + ms.map = he->branch_info->to.map; + ms.sym = he->branch_info->to.sym; + } else { + ms = *browser->selection; } - notes = symbol__annotation(he->ms.sym); + notes = symbol__annotation(ms.sym); if (!notes->src) continue; - /* - * Don't let this be freed, say, by hists__decay_entry. - */ - he->used = true; - err = hist_entry__tui_annotate(he, evsel, hbt); - he->used = false; + err = map_symbol__tui_annotate(&ms, evsel, hbt); /* * offer option to annotate the other branch source or target * (if they exists) when returning from annotate @@ -1754,13 +1770,13 @@ zoom_thread: pstack__remove(fstack, &browser->hists->thread_filter); zoom_out_thread: ui_helpline__pop(); - browser->hists->thread_filter = NULL; + thread__zput(browser->hists->thread_filter); 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; + browser->hists->thread_filter = thread__get(thread); perf_hpp__set_elide(HISTC_THREAD, false); pstack__push(fstack, &browser->hists->thread_filter); } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 32f9327b1a97..797490a40075 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -71,7 +71,7 @@ libperf-y += stat.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o -libperf-y += tsc.o +libperf-$(CONFIG_X86) += tsc.o libperf-y += cloexec.o libperf-y += thread-stack.o @@ -88,10 +88,13 @@ libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o + libperf-y += scripting-engines/ libperf-$(CONFIG_PERF_REGS) += perf_regs.o libperf-$(CONFIG_ZLIB) += zlib.o +libperf-$(CONFIG_LZMA) += lzma.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 61bf9128e1f2..7f5bdfc9bc87 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -30,6 +30,8 @@ static int disasm_line__parse(char *line, char **namep, char **rawp); static void ins__delete(struct ins_operands *ops) { + if (ops == NULL) + return; zfree(&ops->source.raw); zfree(&ops->source.name); zfree(&ops->target.raw); @@ -1008,6 +1010,32 @@ fallback: } filename = symfs_filename; } + } else if (dso__needs_decompress(dso)) { + char tmp[PATH_MAX]; + struct kmod_path m; + int fd; + bool ret; + + if (kmod_path__parse_ext(&m, symfs_filename)) + goto out_free_filename; + + snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX"); + + fd = mkstemp(tmp); + if (fd < 0) { + free(m.ext); + goto out_free_filename; + } + + ret = decompress_to_file(m.ext, symfs_filename, fd); + + free(m.ext); + close(fd); + + if (!ret) + goto out_free_filename; + + strcpy(symfs_filename, tmp); } snprintf(command, sizeof(command), @@ -1027,7 +1055,7 @@ fallback: file = popen(command, "r"); if (!file) - goto out_free_filename; + goto out_remove_tmp; while (!feof(file)) if (symbol__parse_objdump_line(sym, map, file, privsize, @@ -1042,6 +1070,10 @@ fallback: delete_last_nop(sym); pclose(file); + +out_remove_tmp: + if (dso__needs_decompress(dso)) + unlink(symfs_filename); out_free_filename: if (delete_extract) kcore_extract__delete(&kce); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index adbc36028636..f7fb2587df69 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -61,8 +61,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, if (thread) { rb_erase(&thread->rb_node, &machine->threads); - machine->last_match = NULL; - thread__delete(thread); + if (machine->last_match == thread) + thread__zput(machine->last_match); + thread__put(thread); } return 0; @@ -281,41 +282,100 @@ void disable_buildid_cache(void) no_buildid_cache = true; } +static char *build_id_cache__dirname_from_path(const char *name, + bool is_kallsyms, bool is_vdso) +{ + char *realname = (char *)name, *filename; + bool slash = is_kallsyms || is_vdso; + + if (!slash) { + realname = realpath(name, NULL); + if (!realname) + return NULL; + } + + if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "", + is_vdso ? DSO__NAME_VDSO : realname) < 0) + filename = NULL; + + if (!slash) + free(realname); + + return filename; +} + +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result) +{ + struct strlist *list; + char *dir_name; + DIR *dir; + struct dirent *d; + int ret = 0; + + list = strlist__new(true, NULL); + dir_name = build_id_cache__dirname_from_path(pathname, false, false); + if (!list || !dir_name) { + ret = -ENOMEM; + goto out; + } + + /* List up all dirents */ + dir = opendir(dir_name); + if (!dir) { + ret = -errno; + goto out; + } + + while ((d = readdir(dir)) != NULL) { + if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) + continue; + strlist__add(list, d->d_name); + } + closedir(dir); + +out: + free(dir_name); + if (ret) + strlist__delete(list); + else + *result = list; + + return ret; +} + int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; - char *realname, *filename = zalloc(size), + char *realname = NULL, *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *targetname, *tmp; - int len, err = -1; - bool slash = is_kallsyms || is_vdso; + int err = -1; - if (is_kallsyms) { - if (symbol_conf.kptr_restrict) { - pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - err = 0; - goto out_free; - } - realname = (char *) name; - } else + if (!is_kallsyms) { realname = realpath(name, NULL); + if (!realname) + goto out_free; + } - if (realname == NULL || filename == NULL || linkname == NULL) + dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso); + if (!dir_name) goto out_free; - len = scnprintf(filename, size, "%s%s%s", - buildid_dir, slash ? "/" : "", - is_vdso ? DSO__NAME_VDSO : realname); - if (mkdir_p(filename, 0755)) + if (mkdir_p(dir_name, 0755)) goto out_free; - snprintf(filename + len, size - len, "/%s", sbuild_id); + if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) { + filename = NULL; + goto out_free; + } if (access(filename, F_OK)) { if (is_kallsyms) { if (copyfile("/proc/kallsyms", filename)) goto out_free; - } else if (link(realname, filename) && copyfile(name, filename)) + } else if (link(realname, filename) && errno != EEXIST && + copyfile(name, filename)) goto out_free; } @@ -337,6 +397,7 @@ out_free: if (!is_kallsyms) free(realname); free(filename); + free(dir_name); free(linkname); return err; } @@ -352,6 +413,18 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); } +bool build_id_cache__cached(const char *sbuild_id) +{ + bool ret = false; + char *filename = build_id__filename(sbuild_id, NULL, 0); + + if (filename && !access(filename, F_OK)) + ret = true; + free(filename); + + return ret; +} + int build_id_cache__remove_s(const char *sbuild_id) { const size_t size = PATH_MAX; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 31b3c6332a1a..85011222cc14 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -4,6 +4,7 @@ #define BUILD_ID_SIZE 20 #include "tool.h" +#include "strlist.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; @@ -22,6 +23,9 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result); +bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 47b78b3f0325..85b523885f9d 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -7,6 +7,12 @@ static unsigned long flag = PERF_FLAG_FD_CLOEXEC; +int __weak sched_getcpu(void) +{ + errno = ENOSYS; + return -1; +} + static int perf_flag_probe(void) { /* use 'safest' configuration as used in perf_evsel__fallback() */ @@ -25,6 +31,10 @@ static int perf_flag_probe(void) if (cpu < 0) cpu = 0; + /* + * Using -1 for the pid is a workaround to avoid gratuitous jump label + * changes. + */ while (1) { /* check cloexec flag */ fd = sys_perf_event_open(&attr, pid, cpu, -1, @@ -47,16 +57,24 @@ static int perf_flag_probe(void) err, strerror_r(err, sbuf, sizeof(sbuf))); /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ - fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + while (1) { + fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + if (fd < 0 && pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + break; + } err = errno; + if (fd >= 0) + close(fd); + if (WARN_ONCE(fd < 0 && err != EBUSY, "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", err, strerror_r(err, sbuf, sizeof(sbuf)))) return -1; - close(fd); - return 0; } diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index 94a5a7d829d5..68888c29b04a 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -3,4 +3,10 @@ unsigned long perf_event_open_cloexec_flag(void); +#ifdef __GLIBC_PREREQ +#if !__GLIBC_PREREQ(2, 6) +extern int sched_getcpu(void) __THROW; +#endif +#endif + #endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c new file mode 100644 index 000000000000..c6d62268cc2a --- /dev/null +++ b/tools/perf/util/data-convert-bt.c @@ -0,0 +1,856 @@ +/* + * CTF writing support via babeltrace. + * + * Copyright (C) 2014, Jiri Olsa <jolsa@redhat.com> + * Copyright (C) 2014, Sebastian Andrzej Siewior <bigeasy@linutronix.de> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include <linux/compiler.h> +#include <babeltrace/ctf-writer/writer.h> +#include <babeltrace/ctf-writer/clock.h> +#include <babeltrace/ctf-writer/stream.h> +#include <babeltrace/ctf-writer/event.h> +#include <babeltrace/ctf-writer/event-types.h> +#include <babeltrace/ctf-writer/event-fields.h> +#include <babeltrace/ctf/events.h> +#include <traceevent/event-parse.h> +#include "asm/bug.h" +#include "data-convert-bt.h" +#include "session.h" +#include "util.h" +#include "debug.h" +#include "tool.h" +#include "evlist.h" +#include "evsel.h" +#include "machine.h" + +#define pr_N(n, fmt, ...) \ + eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) + +#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__) +#define pr2(fmt, ...) pr_N(2, pr_fmt(fmt), ##__VA_ARGS__) + +#define pr_time2(t, fmt, ...) pr_time_N(2, debug_data_convert, t, pr_fmt(fmt), ##__VA_ARGS__) + +struct evsel_priv { + struct bt_ctf_event_class *event_class; +}; + +struct ctf_writer { + /* writer primitives */ + struct bt_ctf_writer *writer; + struct bt_ctf_stream *stream; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_clock *clock; + + /* data types */ + union { + struct { + struct bt_ctf_field_type *s64; + struct bt_ctf_field_type *u64; + struct bt_ctf_field_type *s32; + struct bt_ctf_field_type *u32; + struct bt_ctf_field_type *string; + struct bt_ctf_field_type *u64_hex; + }; + struct bt_ctf_field_type *array[6]; + } data; +}; + +struct convert { + struct perf_tool tool; + struct ctf_writer writer; + + u64 events_size; + u64 events_count; +}; + +static int value_set(struct bt_ctf_field_type *type, + struct bt_ctf_event *event, + const char *name, u64 val) +{ + struct bt_ctf_field *field; + bool sign = bt_ctf_field_type_integer_get_signed(type); + int ret; + + field = bt_ctf_field_create(type); + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + if (sign) { + ret = bt_ctf_field_signed_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } else { + ret = bt_ctf_field_unsigned_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } + + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) { + pr_err("failed to set payload %s\n", name); + goto err; + } + + pr2(" SET [%s = %" PRIu64 "]\n", name, val); + +err: + bt_ctf_field_put(field); + return ret; +} + +#define __FUNC_VALUE_SET(_name, _val_type) \ +static __maybe_unused int value_set_##_name(struct ctf_writer *cw, \ + struct bt_ctf_event *event, \ + const char *name, \ + _val_type val) \ +{ \ + struct bt_ctf_field_type *type = cw->data._name; \ + return value_set(type, event, name, (u64) val); \ +} + +#define FUNC_VALUE_SET(_name) __FUNC_VALUE_SET(_name, _name) + +FUNC_VALUE_SET(s32) +FUNC_VALUE_SET(u32) +FUNC_VALUE_SET(s64) +FUNC_VALUE_SET(u64) +__FUNC_VALUE_SET(u64_hex, u64) + +static struct bt_ctf_field_type* +get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field) +{ + unsigned long flags = field->flags; + + if (flags & FIELD_IS_STRING) + return cw->data.string; + + if (!(flags & FIELD_IS_SIGNED)) { + /* unsigned long are mostly pointers */ + if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER) + return cw->data.u64_hex; + } + + if (flags & FIELD_IS_SIGNED) { + if (field->size == 8) + return cw->data.s64; + else + return cw->data.s32; + } + + if (field->size == 8) + return cw->data.u64; + else + return cw->data.u32; +} + +static int add_tracepoint_field_value(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct perf_sample *sample, + struct format_field *fmtf) +{ + struct bt_ctf_field_type *type; + struct bt_ctf_field *array_field; + struct bt_ctf_field *field; + const char *name = fmtf->name; + void *data = sample->raw_data; + unsigned long long value_int; + unsigned long flags = fmtf->flags; + unsigned int n_items; + unsigned int i; + unsigned int offset; + unsigned int len; + int ret; + + offset = fmtf->offset; + len = fmtf->size; + if (flags & FIELD_IS_STRING) + flags &= ~FIELD_IS_ARRAY; + + if (flags & FIELD_IS_DYNAMIC) { + unsigned long long tmp_val; + + tmp_val = pevent_read_number(fmtf->event->pevent, + data + offset, len); + offset = tmp_val; + len = offset >> 16; + offset &= 0xffff; + } + + if (flags & FIELD_IS_ARRAY) { + + type = bt_ctf_event_class_get_field_by_name( + event_class, name); + array_field = bt_ctf_field_create(type); + bt_ctf_field_type_put(type); + if (!array_field) { + pr_err("Failed to create array type %s\n", name); + return -1; + } + + len = fmtf->size / fmtf->arraylen; + n_items = fmtf->arraylen; + } else { + n_items = 1; + array_field = NULL; + } + + type = get_tracepoint_field_type(cw, fmtf); + + for (i = 0; i < n_items; i++) { + if (!(flags & FIELD_IS_STRING)) + value_int = pevent_read_number( + fmtf->event->pevent, + data + offset + i * len, len); + + if (flags & FIELD_IS_ARRAY) + field = bt_ctf_field_array_get_field(array_field, i); + else + field = bt_ctf_field_create(type); + + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + if (flags & FIELD_IS_STRING) + ret = bt_ctf_field_string_set_value(field, + data + offset + i * len); + else if (!(flags & FIELD_IS_SIGNED)) + ret = bt_ctf_field_unsigned_integer_set_value( + field, value_int); + else + ret = bt_ctf_field_signed_integer_set_value( + field, value_int); + if (ret) { + pr_err("failed to set file value %s\n", name); + goto err_put_field; + } + if (!(flags & FIELD_IS_ARRAY)) { + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) { + pr_err("failed to set payload %s\n", name); + goto err_put_field; + } + } + bt_ctf_field_put(field); + } + if (flags & FIELD_IS_ARRAY) { + ret = bt_ctf_event_set_payload(event, name, array_field); + if (ret) { + pr_err("Failed add payload array %s\n", name); + return -1; + } + bt_ctf_field_put(array_field); + } + return 0; + +err_put_field: + bt_ctf_field_put(field); + return -1; +} + +static int add_tracepoint_fields_values(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct format_field *fields, + struct perf_sample *sample) +{ + struct format_field *field; + int ret; + + for (field = fields; field; field = field->next) { + ret = add_tracepoint_field_value(cw, event_class, event, sample, + field); + if (ret) + return -1; + } + return 0; +} + +static int add_tracepoint_values(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + struct format_field *common_fields = evsel->tp_format->format.common_fields; + struct format_field *fields = evsel->tp_format->format.fields; + int ret; + + ret = add_tracepoint_fields_values(cw, event_class, event, + common_fields, sample); + if (!ret) + ret = add_tracepoint_fields_values(cw, event_class, event, + fields, sample); + + return ret; +} + +static int add_generic_values(struct ctf_writer *cw, + struct bt_ctf_event *event, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 type = evsel->attr.sample_type; + int ret; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + + if (type & PERF_SAMPLE_IP) { + ret = value_set_u64_hex(cw, event, "perf_ip", sample->ip); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TID) { + ret = value_set_s32(cw, event, "perf_tid", sample->tid); + if (ret) + return -1; + + ret = value_set_s32(cw, event, "perf_pid", sample->pid); + if (ret) + return -1; + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) { + ret = value_set_u64(cw, event, "perf_id", sample->id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + ret = value_set_u64(cw, event, "perf_stream_id", sample->stream_id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_CPU) { + ret = value_set_u32(cw, event, "perf_cpu", sample->cpu); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_PERIOD) { + ret = value_set_u64(cw, event, "perf_period", sample->period); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_WEIGHT) { + ret = value_set_u64(cw, event, "perf_weight", sample->weight); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + ret = value_set_u64(cw, event, "perf_data_src", + sample->data_src); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + ret = value_set_u64(cw, event, "perf_transaction", + sample->transaction); + if (ret) + return -1; + } + + return 0; +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *_event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __maybe_unused) +{ + struct convert *c = container_of(tool, struct convert, tool); + struct evsel_priv *priv = evsel->priv; + struct ctf_writer *cw = &c->writer; + struct bt_ctf_event_class *event_class; + struct bt_ctf_event *event; + int ret; + + if (WARN_ONCE(!priv, "Failed to setup all events.\n")) + return 0; + + event_class = priv->event_class; + + /* update stats */ + c->events_count++; + c->events_size += _event->header.size; + + pr_time2(sample->time, "sample %" PRIu64 "\n", c->events_count); + + event = bt_ctf_event_create(event_class); + if (!event) { + pr_err("Failed to create an CTF event\n"); + return -1; + } + + bt_ctf_clock_set_time(cw->clock, sample->time); + + ret = add_generic_values(cw, event, evsel, sample); + if (ret) + return -1; + + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + ret = add_tracepoint_values(cw, event_class, event, + evsel, sample); + if (ret) + return -1; + } + + bt_ctf_stream_append_event(cw->stream, event); + bt_ctf_event_put(event); + return 0; +} + +static int add_tracepoint_fields_types(struct ctf_writer *cw, + struct format_field *fields, + struct bt_ctf_event_class *event_class) +{ + struct format_field *field; + int ret; + + for (field = fields; field; field = field->next) { + struct bt_ctf_field_type *type; + unsigned long flags = field->flags; + + pr2(" field '%s'\n", field->name); + + type = get_tracepoint_field_type(cw, field); + if (!type) + return -1; + + /* + * A string is an array of chars. For this we use the string + * type and don't care that it is an array. What we don't + * support is an array of strings. + */ + if (flags & FIELD_IS_STRING) + flags &= ~FIELD_IS_ARRAY; + + if (flags & FIELD_IS_ARRAY) + type = bt_ctf_field_type_array_create(type, field->arraylen); + + ret = bt_ctf_event_class_add_field(event_class, type, + field->name); + + if (flags & FIELD_IS_ARRAY) + bt_ctf_field_type_put(type); + + if (ret) { + pr_err("Failed to add field '%s\n", field->name); + return -1; + } + } + + return 0; +} + +static int add_tracepoint_types(struct ctf_writer *cw, + struct perf_evsel *evsel, + struct bt_ctf_event_class *class) +{ + struct format_field *common_fields = evsel->tp_format->format.common_fields; + struct format_field *fields = evsel->tp_format->format.fields; + int ret; + + ret = add_tracepoint_fields_types(cw, common_fields, class); + if (!ret) + ret = add_tracepoint_fields_types(cw, fields, class); + + return ret; +} + +static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, + struct bt_ctf_event_class *event_class) +{ + u64 type = evsel->attr.sample_type; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + +#define ADD_FIELD(cl, t, n) \ + do { \ + pr2(" field '%s'\n", n); \ + if (bt_ctf_event_class_add_field(cl, t, n)) { \ + pr_err("Failed to add field '%s;\n", n); \ + return -1; \ + } \ + } while (0) + + if (type & PERF_SAMPLE_IP) + ADD_FIELD(event_class, cw->data.u64_hex, "perf_ip"); + + if (type & PERF_SAMPLE_TID) { + ADD_FIELD(event_class, cw->data.s32, "perf_tid"); + ADD_FIELD(event_class, cw->data.s32, "perf_pid"); + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) + ADD_FIELD(event_class, cw->data.u64, "perf_id"); + + if (type & PERF_SAMPLE_STREAM_ID) + ADD_FIELD(event_class, cw->data.u64, "perf_stream_id"); + + if (type & PERF_SAMPLE_CPU) + ADD_FIELD(event_class, cw->data.u32, "perf_cpu"); + + if (type & PERF_SAMPLE_PERIOD) + ADD_FIELD(event_class, cw->data.u64, "perf_period"); + + if (type & PERF_SAMPLE_WEIGHT) + ADD_FIELD(event_class, cw->data.u64, "perf_weight"); + + if (type & PERF_SAMPLE_DATA_SRC) + ADD_FIELD(event_class, cw->data.u64, "perf_data_src"); + + if (type & PERF_SAMPLE_TRANSACTION) + ADD_FIELD(event_class, cw->data.u64, "perf_transaction"); + +#undef ADD_FIELD + return 0; +} + +static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) +{ + struct bt_ctf_event_class *event_class; + struct evsel_priv *priv; + const char *name = perf_evsel__name(evsel); + int ret; + + pr("Adding event '%s' (type %d)\n", name, evsel->attr.type); + + event_class = bt_ctf_event_class_create(name); + if (!event_class) + return -1; + + ret = add_generic_types(cw, evsel, event_class); + if (ret) + goto err; + + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + ret = add_tracepoint_types(cw, evsel, event_class); + if (ret) + goto err; + } + + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class); + if (ret) { + pr("Failed to add event class into stream.\n"); + goto err; + } + + priv = malloc(sizeof(*priv)); + if (!priv) + goto err; + + priv->event_class = event_class; + evsel->priv = priv; + return 0; + +err: + bt_ctf_event_class_put(event_class); + pr_err("Failed to add event '%s'.\n", name); + return -1; +} + +static int setup_events(struct ctf_writer *cw, struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel; + int ret; + + evlist__for_each(evlist, evsel) { + ret = add_event(cw, evsel); + if (ret) + return ret; + } + return 0; +} + +static int ctf_writer__setup_env(struct ctf_writer *cw, + struct perf_session *session) +{ + struct perf_header *header = &session->header; + struct bt_ctf_writer *writer = cw->writer; + +#define ADD(__n, __v) \ +do { \ + if (bt_ctf_writer_add_environment_field(writer, __n, __v)) \ + return -1; \ +} while (0) + + ADD("host", header->env.hostname); + ADD("sysname", "Linux"); + ADD("release", header->env.os_release); + ADD("version", header->env.version); + ADD("machine", header->env.arch); + ADD("domain", "kernel"); + ADD("tracer_name", "perf"); + +#undef ADD + return 0; +} + +static int ctf_writer__setup_clock(struct ctf_writer *cw) +{ + struct bt_ctf_clock *clock = cw->clock; + + bt_ctf_clock_set_description(clock, "perf clock"); + +#define SET(__n, __v) \ +do { \ + if (bt_ctf_clock_set_##__n(clock, __v)) \ + return -1; \ +} while (0) + + SET(frequency, 1000000000); + SET(offset_s, 0); + SET(offset, 0); + SET(precision, 10); + SET(is_absolute, 0); + +#undef SET + return 0; +} + +static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex) +{ + struct bt_ctf_field_type *type; + + type = bt_ctf_field_type_integer_create(size); + if (!type) + return NULL; + + if (sign && + bt_ctf_field_type_integer_set_signed(type, 1)) + goto err; + + if (hex && + bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL)) + goto err; + + pr2("Created type: INTEGER %d-bit %ssigned %s\n", + size, sign ? "un" : "", hex ? "hex" : ""); + return type; + +err: + bt_ctf_field_type_put(type); + return NULL; +} + +static void ctf_writer__cleanup_data(struct ctf_writer *cw) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cw->data.array); i++) + bt_ctf_field_type_put(cw->data.array[i]); +} + +static int ctf_writer__init_data(struct ctf_writer *cw) +{ +#define CREATE_INT_TYPE(type, size, sign, hex) \ +do { \ + (type) = create_int_type(size, sign, hex); \ + if (!(type)) \ + goto err; \ +} while (0) + + CREATE_INT_TYPE(cw->data.s64, 64, true, false); + CREATE_INT_TYPE(cw->data.u64, 64, false, false); + CREATE_INT_TYPE(cw->data.s32, 32, true, false); + CREATE_INT_TYPE(cw->data.u32, 32, false, false); + CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true); + + cw->data.string = bt_ctf_field_type_string_create(); + if (cw->data.string) + return 0; + +err: + ctf_writer__cleanup_data(cw); + pr_err("Failed to create data types.\n"); + return -1; +} + +static void ctf_writer__cleanup(struct ctf_writer *cw) +{ + ctf_writer__cleanup_data(cw); + + bt_ctf_clock_put(cw->clock); + bt_ctf_stream_put(cw->stream); + bt_ctf_stream_class_put(cw->stream_class); + bt_ctf_writer_put(cw->writer); + + /* and NULL all the pointers */ + memset(cw, 0, sizeof(*cw)); +} + +static int ctf_writer__init(struct ctf_writer *cw, const char *path) +{ + struct bt_ctf_writer *writer; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_stream *stream; + struct bt_ctf_clock *clock; + + /* CTF writer */ + writer = bt_ctf_writer_create(path); + if (!writer) + goto err; + + cw->writer = writer; + + /* CTF clock */ + clock = bt_ctf_clock_create("perf_clock"); + if (!clock) { + pr("Failed to create CTF clock.\n"); + goto err_cleanup; + } + + cw->clock = clock; + + if (ctf_writer__setup_clock(cw)) { + pr("Failed to setup CTF clock.\n"); + goto err_cleanup; + } + + /* CTF stream class */ + stream_class = bt_ctf_stream_class_create("perf_stream"); + if (!stream_class) { + pr("Failed to create CTF stream class.\n"); + goto err_cleanup; + } + + cw->stream_class = stream_class; + + /* CTF clock stream setup */ + if (bt_ctf_stream_class_set_clock(stream_class, clock)) { + pr("Failed to assign CTF clock to stream class.\n"); + goto err_cleanup; + } + + if (ctf_writer__init_data(cw)) + goto err_cleanup; + + /* CTF stream instance */ + stream = bt_ctf_writer_create_stream(writer, stream_class); + if (!stream) { + pr("Failed to create CTF stream.\n"); + goto err_cleanup; + } + + cw->stream = stream; + + /* CTF clock writer setup */ + if (bt_ctf_writer_add_clock(writer, clock)) { + pr("Failed to assign CTF clock to writer.\n"); + goto err_cleanup; + } + + return 0; + +err_cleanup: + ctf_writer__cleanup(cw); +err: + pr_err("Failed to setup CTF writer.\n"); + return -1; +} + +int bt_convert__perf2ctf(const char *input, const char *path) +{ + struct perf_session *session; + struct perf_data_file file = { + .path = input, + .mode = PERF_DATA_MODE_READ, + }; + struct convert c = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .comm = perf_event__process_comm, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, + .lost = perf_event__process_lost, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_events = true, + .ordering_requires_timestamps = true, + }, + }; + struct ctf_writer *cw = &c.writer; + int err = -1; + + /* CTF writer */ + if (ctf_writer__init(cw, path)) + return -1; + + /* perf.data session */ + session = perf_session__new(&file, 0, &c.tool); + if (!session) + goto free_writer; + + /* CTF writer env/clock setup */ + if (ctf_writer__setup_env(cw, session)) + goto free_session; + + /* CTF events setup */ + if (setup_events(cw, session)) + goto free_session; + + err = perf_session__process_events(session); + if (!err) + err = bt_ctf_stream_flush(cw->stream); + + fprintf(stderr, + "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", + file.path, path); + + fprintf(stderr, + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + (double) c.events_size / 1024.0 / 1024.0, + c.events_count); + + /* its all good */ +free_session: + perf_session__delete(session); + +free_writer: + ctf_writer__cleanup(cw); + return err; +} diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h new file mode 100644 index 000000000000..dda30c5d0792 --- /dev/null +++ b/tools/perf/util/data-convert-bt.h @@ -0,0 +1,8 @@ +#ifndef __DATA_CONVERT_BT_H +#define __DATA_CONVERT_BT_H +#ifdef HAVE_LIBBABELTRACE_SUPPORT + +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf); + +#endif /* HAVE_LIBBABELTRACE_SUPPORT */ +#endif /* __DATA_CONVERT_BT_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index ad60b2f20258..2da5581ec74d 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -20,6 +20,7 @@ int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; +int debug_data_convert; static int _eprintf(int level, int var, const char *fmt, va_list args) { @@ -147,6 +148,7 @@ static struct debug_variable { { .name = "verbose", .ptr = &verbose }, { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = "stderr", .ptr = &redirect_to_stderr}, + { .name = "data-convert", .ptr = &debug_data_convert }, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index be264d6f3b30..caac2fdc6105 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -12,6 +12,7 @@ extern int verbose; extern bool quiet, dump_trace; extern int debug_ordered_events; +extern int debug_data_convert; #ifndef pr_fmt #define pr_fmt(fmt) fmt diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 814554d1b857..fc0ddd5792a9 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -148,6 +148,9 @@ static const struct { #ifdef HAVE_ZLIB_SUPPORT { "gz", gzip_decompress_to_file }, #endif +#ifdef HAVE_LZMA_SUPPORT + { "xz", lzma_decompress_to_file }, +#endif { NULL, NULL }, }; @@ -162,32 +165,14 @@ bool is_supported_compression(const char *ext) return false; } -bool is_kmodule_extension(const char *ext) -{ - if (strncmp(ext, "ko", 2)) - return false; - - if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3))) - return true; - - return false; -} - -bool is_kernel_module(const char *pathname, bool *compressed) +bool is_kernel_module(const char *pathname) { - const char *ext = strrchr(pathname, '.'); + struct kmod_path m; - if (ext == NULL) - return false; - - if (is_supported_compression(ext + 1)) { - if (compressed) - *compressed = true; - ext -= 3; - } else if (compressed) - *compressed = false; + if (kmod_path__parse(&m, pathname)) + return NULL; - return is_kmodule_extension(ext + 1); + return m.kmod; } bool decompress_to_file(const char *ext, const char *filename, int output_fd) @@ -209,6 +194,72 @@ bool dso__needs_decompress(struct dso *dso) } /* + * Parses kernel module specified in @path and updates + * @m argument like: + * + * @comp - true if @path contains supported compression suffix, + * false otherwise + * @kmod - true if @path contains '.ko' suffix in right position, + * false otherwise + * @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name + * of the kernel module without suffixes, otherwise strudup-ed + * base name of @path + * @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string + * the compression suffix + * + * Returns 0 if there's no strdup error, -ENOMEM otherwise. + */ +int __kmod_path__parse(struct kmod_path *m, const char *path, + bool alloc_name, bool alloc_ext) +{ + const char *name = strrchr(path, '/'); + const char *ext = strrchr(path, '.'); + + memset(m, 0x0, sizeof(*m)); + name = name ? name + 1 : path; + + /* No extension, just return name. */ + if (ext == NULL) { + if (alloc_name) { + m->name = strdup(name); + return m->name ? 0 : -ENOMEM; + } + return 0; + } + + if (is_supported_compression(ext + 1)) { + m->comp = true; + ext -= 3; + } + + /* Check .ko extension only if there's enough name left. */ + if (ext > name) + m->kmod = !strncmp(ext, ".ko", 3); + + if (alloc_name) { + if (m->kmod) { + if (asprintf(&m->name, "[%.*s]", (int) (ext - name), name) == -1) + return -ENOMEM; + } else { + if (asprintf(&m->name, "%s", name) == -1) + return -ENOMEM; + } + + strxfrchar(m->name, '-', '_'); + } + + if (alloc_ext && m->comp) { + m->ext = strdup(ext + 4); + if (!m->ext) { + free((void *) m->name); + return -ENOMEM; + } + } + + return 0; +} + +/* * Global list of open DSOs and the counter. */ static LIST_HEAD(dso__data_open); @@ -1002,21 +1053,24 @@ struct dso *dsos__find(const struct dsos *dsos, const char *name, return dso__find_by_longname(&dsos->root, name); } -struct dso *__dsos__findnew(struct dsos *dsos, const char *name) +struct dso *dsos__addnew(struct dsos *dsos, const char *name) { - struct dso *dso = dsos__find(dsos, name, false); + struct dso *dso = dso__new(name); - if (!dso) { - dso = dso__new(name); - if (dso != NULL) { - dsos__add(dsos, dso); - dso__set_basename(dso); - } + if (dso != NULL) { + dsos__add(dsos, dso); + dso__set_basename(dso); } - return dso; } +struct dso *__dsos__findnew(struct dsos *dsos, const char *name) +{ + struct dso *dso = dsos__find(dsos, name, false); + + return dso ? dso : dsos__addnew(dsos, name); +} + size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { @@ -1083,3 +1137,36 @@ enum dso_type dso__type(struct dso *dso, struct machine *machine) return dso__type_fd(fd); } + +int dso__strerror_load(struct dso *dso, char *buf, size_t buflen) +{ + int idx, errnum = dso->load_errno; + /* + * This must have a same ordering as the enum dso_load_errno. + */ + static const char *dso_load__error_str[] = { + "Internal tools/perf/ library error", + "Invalid ELF file", + "Can not read build id", + "Mismatching build id", + "Decompression failure", + }; + + BUG_ON(buflen == 0); + + if (errnum >= 0) { + const char *err = strerror_r(errnum, buf, buflen); + + if (err != buf) + scnprintf(buf, buflen, "%s", err); + + return 0; + } + + if (errnum < __DSO_LOAD_ERRNO__START || errnum >= __DSO_LOAD_ERRNO__END) + return -1; + + idx = errnum - __DSO_LOAD_ERRNO__START; + scnprintf(buf, buflen, "%s", dso_load__error_str[idx]); + return 0; +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ced92841ff97..e0901b4ed8de 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -60,6 +60,31 @@ enum dso_type { DSO__TYPE_X32BIT, }; +enum dso_load_errno { + DSO_LOAD_ERRNO__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __DSO_LOAD_ERRNO__START = -10000, + + DSO_LOAD_ERRNO__INTERNAL_ERROR = __DSO_LOAD_ERRNO__START, + + /* for symsrc__init() */ + DSO_LOAD_ERRNO__INVALID_ELF, + DSO_LOAD_ERRNO__CANNOT_READ_BUILDID, + DSO_LOAD_ERRNO__MISMATCHING_BUILDID, + + /* for decompress_kmodule */ + DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE, + + __DSO_LOAD_ERRNO__END, +}; + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -113,6 +138,7 @@ struct dso { enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; enum dso_binary_type binary_type; + enum dso_load_errno load_errno; u8 adjust_symbols:1; u8 has_build_id:1; u8 has_srcline:1; @@ -139,7 +165,8 @@ struct dso { u32 status_seen; size_t file_size; struct list_head open_entry; - u64 frame_offset; + u64 debug_frame_offset; + u64 eh_frame_hdr_offset; } data; union { /* Tool specific area */ @@ -189,11 +216,24 @@ 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); bool is_supported_compression(const char *ext); -bool is_kmodule_extension(const char *ext); -bool is_kernel_module(const char *pathname, bool *compressed); +bool is_kernel_module(const char *pathname); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); +struct kmod_path { + char *name; + char *ext; + bool comp; + bool kmod; +}; + +int __kmod_path__parse(struct kmod_path *m, const char *path, + bool alloc_name, bool alloc_ext); + +#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) +#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) +#define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) + /* * The dso__data_* external interface provides following functions: * dso__data_fd @@ -249,6 +289,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name, const char *short_name, int dso_type); void dsos__add(struct dsos *dsos, struct dso *dso); +struct dso *dsos__addnew(struct dsos *dsos, const char *name); struct dso *dsos__find(const struct dsos *dsos, const char *name, bool cmp_short); struct dso *__dsos__findnew(struct dsos *dsos, const char *name); @@ -279,4 +320,6 @@ void dso__free_a2l(struct dso *dso); enum dso_type dso__type(struct dso *dso, struct machine *machine); +int dso__strerror_load(struct dso *dso, char *buf, size_t buflen); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6c6d044e959a..d5efa5092ce6 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -95,9 +95,7 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) return tgid; } -static pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, +static pid_t perf_event__prepare_comm(union perf_event *event, pid_t pid, struct machine *machine) { size_t size; @@ -124,6 +122,19 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, (sizeof(event->comm.comm) - size) + machine->id_hdr_size); event->comm.tid = pid; +out: + return tgid; +} + +static pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + pid_t tgid = perf_event__prepare_comm(event, pid, machine); + + if (tgid == -1) + goto out; if (process(tool, event, &synth_sample, machine) != 0) return -1; @@ -139,7 +150,6 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, { memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - /* this is really a clone event but we use fork to synthesize it */ event->fork.ppid = tgid; event->fork.ptid = tgid; event->fork.pid = tgid; @@ -368,19 +378,23 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (*end) continue; - tgid = perf_event__synthesize_comm(tool, comm_event, _pid, - process, machine); + tgid = perf_event__prepare_comm(comm_event, _pid, machine); if (tgid == -1) return -1; + if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + process, machine) < 0) + return -1; + /* + * Send the prepared comm event + */ + if (process(tool, comm_event, &synth_sample, machine) != 0) + return -1; + if (_pid == pid) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); - } else { - /* only fork the tid's map, to save time */ - rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - process, machine); } if (rc) @@ -615,7 +629,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) else s = ""; - return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); + return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a8b2c5726aba..82bf224bbee9 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1050,7 +1050,7 @@ out_delete_threads: return -1; } -int perf_evlist__apply_filters(struct perf_evlist *evlist) +int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) { struct perf_evsel *evsel; int err = 0; @@ -1062,8 +1062,10 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist) continue; err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter); - if (err) + if (err) { + *err_evsel = evsel; break; + } } return err; @@ -1085,6 +1087,38 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) return err; } +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids) +{ + char *filter; + int ret = -1; + size_t i; + + for (i = 0; i < npids; ++i) { + if (i == 0) { + if (asprintf(&filter, "common_pid != %d", pids[i]) < 0) + return -1; + } else { + char *tmp; + + if (asprintf(&tmp, "%s && common_pid != %d", filter, pids[i]) < 0) + goto out_free; + + free(filter); + filter = tmp; + } + } + + ret = perf_evlist__set_filter(evlist, filter); +out_free: + free(filter); + return ret; +} + +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid) +{ + return perf_evlist__set_filter_pids(evlist, 1, &pid); +} + bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { struct perf_evsel *pos; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c94a9e03ecf1..fb19c47b8aac 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -28,7 +28,7 @@ struct perf_mmap { int mask; int refcnt; unsigned int prev; - char event_copy[PERF_SAMPLE_MAX_SIZE]; + char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); }; struct perf_evlist { @@ -51,6 +51,7 @@ struct perf_evlist { struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; + struct events_stats stats; }; struct perf_evsel_str_handler { @@ -77,6 +78,8 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); @@ -149,7 +152,7 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct perf_evlist *evlist); +int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f93e5208c762..358e5954baa8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -734,6 +734,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_transaction) perf_evsel__set_sample_bit(evsel, TRANSACTION); + if (opts->running_time) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + } + /* * XXX see the function comment above * @@ -1909,7 +1915,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, value = *(u32 *)ptr; break; case 8: - value = *(u64 *)ptr; + memcpy(&value, ptr, sizeof(u64)); break; default: return 0; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1f407f7352a7..fb432153e2aa 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1266,7 +1266,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (!is_kernel_module(filename, NULL)) + if (!is_kernel_module(filename)) dso->kernel = dso_type; build_id__sprintf(dso->build_id, sizeof(dso->build_id), diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 70b48a65064c..cc22b9158b93 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -263,15 +263,9 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) while (next) { n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - /* - * We may be annotating this, for instance, so keep it here in - * case some it gets new samples, we'll eventually free it when - * the user stops browsing and it agains gets fully decayed. - */ if (((zap_user && n->level == '.') || (zap_kernel && n->level != '.') || - hists__decay_entry(hists, n)) && - !n->used) { + hists__decay_entry(hists, n))) { hists__delete_entry(hists, n); } } @@ -355,6 +349,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, callchain_init(he->callchain); INIT_LIST_HEAD(&he->pairs.node); + thread__get(he->thread); } return he; @@ -941,6 +936,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__delete(struct hist_entry *he) { + thread__zput(he->thread); zfree(&he->branch_info); zfree(&he->mem_info); zfree(&he->stat_acc); @@ -1169,6 +1165,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h /* force fold unfiltered entry for simplicity */ h->ms.unfolded = false; h->row_offset = 0; + h->nr_rows = 0; hists->stats.nr_non_filtered_samples += h->stat.nr_events; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2b690d028907..9f31b89a527a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -60,7 +60,7 @@ struct hists { struct rb_root entries_collapsed; u64 nr_entries; u64 nr_non_filtered_entries; - const struct thread *thread_filter; + struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; @@ -303,6 +303,9 @@ struct hist_browser_timer { #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" +int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, + struct hist_browser_timer *hbt); + int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -321,6 +324,12 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, { return 0; } +static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused) +{ + return 0; +} static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct perf_evsel *evsel __maybe_unused, diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c new file mode 100644 index 000000000000..95a1acb61245 --- /dev/null +++ b/tools/perf/util/lzma.c @@ -0,0 +1,95 @@ +#include <lzma.h> +#include <stdio.h> +#include <linux/compiler.h> +#include "util.h" +#include "debug.h" + +#define BUFSIZE 8192 + +static const char *lzma_strerror(lzma_ret ret) +{ + switch ((int) ret) { + case LZMA_MEM_ERROR: + return "Memory allocation failed"; + case LZMA_OPTIONS_ERROR: + return "Unsupported decompressor flags"; + case LZMA_FORMAT_ERROR: + return "The input is not in the .xz format"; + case LZMA_DATA_ERROR: + return "Compressed file is corrupt"; + case LZMA_BUF_ERROR: + return "Compressed file is truncated or otherwise corrupt"; + default: + return "Unknown error, possibly a bug"; + } +} + +int lzma_decompress_to_file(const char *input, int output_fd) +{ + lzma_action action = LZMA_RUN; + lzma_stream strm = LZMA_STREAM_INIT; + lzma_ret ret; + + u8 buf_in[BUFSIZE]; + u8 buf_out[BUFSIZE]; + FILE *infile; + + infile = fopen(input, "rb"); + if (!infile) { + pr_err("lzma: fopen failed on %s: '%s'\n", + input, strerror(errno)); + return -1; + } + + ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED); + if (ret != LZMA_OK) { + pr_err("lzma: lzma_stream_decoder failed %s (%d)\n", + lzma_strerror(ret), ret); + return -1; + } + + strm.next_in = NULL; + strm.avail_in = 0; + strm.next_out = buf_out; + strm.avail_out = sizeof(buf_out); + + while (1) { + if (strm.avail_in == 0 && !feof(infile)) { + strm.next_in = buf_in; + strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile); + + if (ferror(infile)) { + pr_err("lzma: read error: %s\n", strerror(errno)); + return -1; + } + + if (feof(infile)) + action = LZMA_FINISH; + } + + ret = lzma_code(&strm, action); + + if (strm.avail_out == 0 || ret == LZMA_STREAM_END) { + ssize_t write_size = sizeof(buf_out) - strm.avail_out; + + if (writen(output_fd, buf_out, write_size) != write_size) { + pr_err("lzma: write error: %s\n", strerror(errno)); + return -1; + } + + strm.next_out = buf_out; + strm.avail_out = sizeof(buf_out); + } + + if (ret != LZMA_OK) { + if (ret == LZMA_STREAM_END) + return 0; + + pr_err("lzma: failed %s\n", lzma_strerror(ret)); + return -1; + } + } + + fclose(infile); + return 0; +} diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9e0f60a7e7b3..e3353307330c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -14,6 +14,8 @@ #include "unwind.h" #include "linux/hash.h" +static void machine__remove_thread(struct machine *machine, struct thread *th); + static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -89,16 +91,6 @@ static void dsos__delete(struct dsos *dsos) } } -void machine__delete_dead_threads(struct machine *machine) -{ - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &machine->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } -} - void machine__delete_threads(struct machine *machine) { struct rb_node *nd = rb_first(&machine->threads); @@ -106,9 +98,8 @@ void machine__delete_threads(struct machine *machine) while (nd) { struct thread *t = rb_entry(nd, struct thread, rb_node); - rb_erase(&t->rb_node, &machine->threads); nd = rb_next(nd); - thread__delete(t); + machine__remove_thread(machine, t); } } @@ -361,9 +352,13 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * the full rbtree: */ th = machine->last_match; - if (th && th->tid == tid) { - machine__update_thread_pid(machine, th, pid); - return th; + if (th != NULL) { + if (th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; + } + + thread__zput(machine->last_match); } while (*p != NULL) { @@ -371,7 +366,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - machine->last_match = th; + machine->last_match = thread__get(th); machine__update_thread_pid(machine, th, pid); return th; } @@ -403,8 +398,11 @@ static struct thread *__machine__findnew_thread(struct machine *machine, thread__delete(th); return NULL; } - - machine->last_match = th; + /* + * It is now in the rbtree, get a ref + */ + thread__get(th); + machine->last_match = thread__get(th); } return th; @@ -462,30 +460,61 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, return 0; } +static struct dso* +machine__module_dso(struct machine *machine, struct kmod_path *m, + const char *filename) +{ + struct dso *dso; + + dso = dsos__find(&machine->kernel_dsos, m->name, true); + if (!dso) { + dso = dsos__addnew(&machine->kernel_dsos, m->name); + if (dso == NULL) + return NULL; + + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (m->kmod && m->comp) + dso->symtab_type++; + + dso__set_short_name(dso, strdup(m->name), true); + dso__set_long_name(dso, strdup(filename), true); + } + + return dso; +} + struct map *machine__new_module(struct machine *machine, u64 start, const char *filename) { - struct map *map; - struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); - bool compressed; + struct map *map = NULL; + struct dso *dso; + struct kmod_path m; - if (dso == NULL) + if (kmod_path__parse_name(&m, filename)) return NULL; - map = map__new2(start, dso, MAP__FUNCTION); - if (map == NULL) - return NULL; + map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION, + m.name); + if (map) + goto out; - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + dso = machine__module_dso(machine, &m, filename); + if (dso == NULL) + goto out; - /* _KMODULE_COMP should be next to _KMODULE */ - if (is_kernel_module(filename, &compressed) && compressed) - dso->symtab_type++; + map = map__new2(start, dso, MAP__FUNCTION); + if (map == NULL) + goto out; map_groups__insert(&machine->kmaps, map); + +out: + free(m.name); return map; } @@ -827,6 +856,39 @@ static char *get_kernel_version(const char *root_dir) return strdup(name); } +static bool is_kmod_dso(struct dso *dso) +{ + return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; +} + +static int map_groups__set_module_path(struct map_groups *mg, const char *path, + struct kmod_path *m) +{ + struct map *map; + char *long_name; + + map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name); + if (map == NULL) + return 0; + + long_name = strdup(path); + if (long_name == NULL) + return -ENOMEM; + + dso__set_long_name(map->dso, long_name, true); + dso__kernel_module_get_build_id(map->dso, ""); + + /* + * Full name could reveal us kmod compression, so + * we need to update the symtab_type if needed. + */ + if (m->comp && is_kmod_dso(map->dso)) + map->dso->symtab_type++; + + return 0; +} + static int map_groups__set_modules_path_dir(struct map_groups *mg, const char *dir_name, int depth) { @@ -865,35 +927,19 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, if (ret < 0) goto out; } else { - char *dot = strrchr(dent->d_name, '.'), - dso_name[PATH_MAX]; - struct map *map; - char *long_name; - - if (dot == NULL) - continue; + struct kmod_path m; - /* On some system, modules are compressed like .ko.gz */ - if (is_supported_compression(dot + 1) && - is_kmodule_extension(dot - 2)) - dot -= 3; + ret = kmod_path__parse_name(&m, dent->d_name); + if (ret) + goto out; - snprintf(dso_name, sizeof(dso_name), "[%.*s]", - (int)(dot - dent->d_name), dent->d_name); + if (m.kmod) + ret = map_groups__set_module_path(mg, path, &m); - strxfrchar(dso_name, '-', '_'); - map = map_groups__find_by_name(mg, MAP__FUNCTION, - dso_name); - if (map == NULL) - continue; + free(m.name); - long_name = strdup(path); - if (long_name == NULL) { - ret = -1; + if (ret) goto out; - } - dso__set_long_name(map->dso, long_name, true); - dso__kernel_module_get_build_id(map->dso, ""); } } @@ -1046,40 +1092,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine, strlen(kmmap_prefix) - 1) == 0; if (event->mmap.filename[0] == '/' || (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - - char short_module_name[1024]; - char *name, *dot; - - if (event->mmap.filename[0] == '/') { - name = strrchr(event->mmap.filename, '/'); - if (name == NULL) - goto out_problem; - - ++name; /* skip / */ - dot = strrchr(name, '.'); - if (dot == NULL) - goto out_problem; - /* On some system, modules are compressed like .ko.gz */ - if (is_supported_compression(dot + 1)) - dot -= 3; - if (!is_kmodule_extension(dot + 1)) - goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); - strxfrchar(short_module_name, '-', '_'); - } else - strcpy(short_module_name, event->mmap.filename); - map = machine__new_module(machine, event->mmap.start, event->mmap.filename); if (map == NULL) goto out_problem; - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - dso__set_short_name(map->dso, name, true); map->end = map->start + event->mmap.len; } else if (is_kernel_mmap) { const char *symbol_name = (event->mmap.filename + @@ -1092,7 +1109,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, struct dso *dso; list_for_each_entry(dso, &machine->kernel_dsos.head, node) { - if (is_kernel_module(dso->long_name, NULL)) + if (is_kernel_module(dso->long_name)) continue; kernel = dso; @@ -1238,13 +1255,17 @@ out_problem: static void machine__remove_thread(struct machine *machine, struct thread *th) { - machine->last_match = NULL; + if (machine->last_match == th) + thread__zput(machine->last_match); + rb_erase(&th->rb_node, &machine->threads); /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. + * Move it first to the dead_threads list, then drop the reference, + * if this is the last reference, then the thread__delete destructor + * will be called and we will remove it from the dead_threads list. */ list_add_tail(&th->node, &machine->dead_threads); + thread__put(th); } int machine__process_fork_event(struct machine *machine, union perf_event *event, diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index e8b7779a0a3f..e2faf3b47e7b 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -118,7 +118,6 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); -void machine__delete_dead_threads(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index fd4be94125fb..6002fa3fcf77 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -131,8 +131,8 @@ static struct ordered_event *alloc_event(struct ordered_events *oe, return new; } -struct ordered_event * -ordered_events__new(struct ordered_events *oe, u64 timestamp, +static struct ordered_event * +ordered_events__new_event(struct ordered_events *oe, u64 timestamp, union perf_event *event) { struct ordered_event *new; @@ -153,10 +153,38 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve free_dup_event(oe, event->event); } -static int __ordered_events__flush(struct perf_session *s, - struct perf_tool *tool) +int ordered_events__queue(struct ordered_events *oe, union perf_event *event, + struct perf_sample *sample, u64 file_offset) +{ + u64 timestamp = sample->time; + struct ordered_event *oevent; + + if (!timestamp || timestamp == ~0ULL) + return -ETIME; + + if (timestamp < oe->last_flush) { + pr_oe_time(timestamp, "out of order event\n"); + pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", + oe->last_flush_type); + + oe->evlist->stats.nr_unordered_events++; + } + + oevent = ordered_events__new_event(oe, timestamp, event); + if (!oevent) { + ordered_events__flush(oe, OE_FLUSH__HALF); + oevent = ordered_events__new_event(oe, timestamp, event); + } + + if (!oevent) + return -ENOMEM; + + oevent->file_offset = file_offset; + return 0; +} + +static int __ordered_events__flush(struct ordered_events *oe) { - struct ordered_events *oe = &s->ordered_events; struct list_head *head = &oe->events; struct ordered_event *tmp, *iter; struct perf_sample sample; @@ -166,7 +194,7 @@ static int __ordered_events__flush(struct perf_session *s, struct ui_progress prog; int ret; - if (!tool->ordered_events || !limit) + if (!limit) return 0; if (show_progress) @@ -179,12 +207,11 @@ static int __ordered_events__flush(struct perf_session *s, if (iter->timestamp > limit) break; - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); + ret = perf_evlist__parse_sample(oe->evlist, iter->event, &sample); if (ret) pr_err("Can't parse sample, err = %d\n", ret); else { - ret = perf_session__deliver_event(s, iter->event, &sample, tool, - iter->file_offset); + ret = oe->deliver(oe, iter, &sample); if (ret) return ret; } @@ -204,10 +231,8 @@ static int __ordered_events__flush(struct perf_session *s, return 0; } -int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, - enum oe_flush how) +int ordered_events__flush(struct ordered_events *oe, enum oe_flush how) { - struct ordered_events *oe = &s->ordered_events; static const char * const str[] = { "NONE", "FINAL", @@ -216,6 +241,9 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, }; int err; + if (oe->nr_events == 0) + return 0; + switch (how) { case OE_FLUSH__FINAL: oe->next_flush = ULLONG_MAX; @@ -248,7 +276,7 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, str[how], oe->nr_events); pr_oe_time(oe->max_timestamp, "max_timestamp\n"); - err = __ordered_events__flush(s, tool); + err = __ordered_events__flush(oe); if (!err) { if (how == OE_FLUSH__ROUND) @@ -264,13 +292,19 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, return err; } -void ordered_events__init(struct ordered_events *oe) +void ordered_events__init(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlist, struct perf_tool *tool, + ordered_events__deliver_t deliver) { INIT_LIST_HEAD(&oe->events); INIT_LIST_HEAD(&oe->cache); INIT_LIST_HEAD(&oe->to_free); oe->max_alloc_size = (u64) -1; oe->cur_alloc_size = 0; + oe->evlist = evlist; + oe->machines = machines; + oe->tool = tool; + oe->deliver = deliver; } void ordered_events__free(struct ordered_events *oe) diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index 7b8f9b011f38..173e13f28c08 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -2,9 +2,11 @@ #define __ORDERED_EVENTS_H #include <linux/types.h> -#include "tool.h" -struct perf_session; +struct perf_tool; +struct perf_evlist; +struct perf_sample; +struct machines; struct ordered_event { u64 timestamp; @@ -20,6 +22,12 @@ enum oe_flush { OE_FLUSH__HALF, }; +struct ordered_events; + +typedef int (*ordered_events__deliver_t)(struct ordered_events *oe, + struct ordered_event *event, + struct perf_sample *sample); + struct ordered_events { u64 last_flush; u64 next_flush; @@ -31,18 +39,23 @@ struct ordered_events { struct list_head to_free; struct ordered_event *buffer; struct ordered_event *last; + struct machines *machines; + struct perf_evlist *evlist; + struct perf_tool *tool; + ordered_events__deliver_t deliver; int buffer_idx; unsigned int nr_events; enum oe_flush last_flush_type; bool copy_on_queue; }; -struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, - union perf_event *event); +int ordered_events__queue(struct ordered_events *oe, union perf_event *event, + struct perf_sample *sample, u64 file_offset); void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); -int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, - enum oe_flush how); -void ordered_events__init(struct ordered_events *oe); +int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); +void ordered_events__init(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlsit, struct perf_tool *tool, + ordered_events__deliver_t deliver); void ordered_events__free(struct ordered_events *oe); static inline diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 109ba5c8c2e5..fe07573d5ed4 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -20,11 +20,6 @@ #define MAX_NAME_LEN 100 -struct event_symbol { - const char *symbol; - const char *alias; -}; - #ifdef PARSER_DEBUG extern int parse_events_debug; #endif @@ -39,7 +34,7 @@ static struct perf_pmu_event_symbol *perf_pmu_events_list; */ static int perf_pmu_events_list_num; -static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { +struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { .symbol = "cpu-cycles", .alias = "cycles", @@ -82,7 +77,7 @@ static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { }, }; -static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { +struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { [PERF_COUNT_SW_CPU_CLOCK] = { .symbol = "cpu-clock", .alias = "", @@ -1089,6 +1084,14 @@ static const char * const event_type_descriptors[] = { "Hardware breakpoint", }; +static int cmp_string(const void *a, const void *b) +{ + const char * const *as = a; + const char * const *bs = b; + + return strcmp(*as, *bs); +} + /* * Print the events from <debugfs_mount_point>/tracing/events */ @@ -1100,11 +1103,21 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; + char **evt_list = NULL; + unsigned int evt_i = 0, evt_num = 0; + bool evt_num_known = false; +restart: sys_dir = opendir(tracing_events_path); if (!sys_dir) return; + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_close_sys_dir; + } + for_each_subsystem(sys_dir, sys_dirent, sys_next) { if (subsys_glob != NULL && !strglobmatch(sys_dirent.d_name, subsys_glob)) @@ -1121,19 +1134,56 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, !strglobmatch(evt_dirent.d_name, event_glob)) continue; - if (name_only) { - printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name); + if (!evt_num_known) { + evt_num++; continue; } snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - printf(" %-50s [%s]\n", evt_path, - event_type_descriptors[PERF_TYPE_TRACEPOINT]); + + evt_list[evt_i] = strdup(evt_path); + if (evt_list[evt_i] == NULL) + goto out_close_evt_dir; + evt_i++; } closedir(evt_dir); } closedir(sys_dir); + + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + } + if (evt_num) + printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_close_evt_dir: + closedir(evt_dir); +out_close_sys_dir: + closedir(sys_dir); + + printf("FATAL: not enough memory to print %s\n", + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + if (evt_list) + goto out_free; } /* @@ -1214,38 +1264,19 @@ static bool is_event_supported(u8 type, unsigned config) return ret; } -static void __print_events_type(u8 type, struct event_symbol *syms, - unsigned max) -{ - char name[64]; - unsigned i; - - for (i = 0; i < max ; i++, syms++) { - if (!is_event_supported(type, i)) - continue; - - if (strlen(syms->alias)) - snprintf(name, sizeof(name), "%s OR %s", - syms->symbol, syms->alias); - else - snprintf(name, sizeof(name), "%s", syms->symbol); - - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); - } -} - -void print_events_type(u8 type) -{ - if (type == PERF_TYPE_SOFTWARE) - __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); - else - __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); -} - int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, printed = 0; + unsigned int type, op, i, evt_i = 0, evt_num = 0; char name[64]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + } for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { @@ -1263,27 +1294,66 @@ int print_hwcache_events(const char *event_glob, bool name_only) type | (op << 8) | (i << 16))) continue; - if (name_only) - printf("%s ", name); - else - printf(" %-50s [%s]\n", name, - event_type_descriptors[PERF_TYPE_HW_CACHE]); - ++printed; + if (!evt_num_known) { + evt_num++; + continue; + } + + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } } } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_HW_CACHE]); + } + if (evt_num) printf("\n"); - return printed; + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return evt_num; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[PERF_TYPE_HW_CACHE]); + if (evt_list) + goto out_free; + return evt_num; } -static void print_symbol_events(const char *event_glob, unsigned type, +void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) { - unsigned i, printed = 0; + unsigned int i, evt_i = 0, evt_num = 0; char name[MAX_NAME_LEN]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + syms -= max; + } for (i = 0; i < max; i++, syms++) { @@ -1295,23 +1365,49 @@ static void print_symbol_events(const char *event_glob, unsigned type, if (!is_event_supported(type, i)) continue; - if (name_only) { - printf("%s ", syms->symbol); + if (!evt_num_known) { + evt_num++; continue; } - if (strlen(syms->alias)) + if (!name_only && strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else strncpy(name, syms->symbol, MAX_NAME_LEN); - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); - - printed++; + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]); + } + if (evt_num) printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]); + if (evt_list) + goto out_free; } /* diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 39c3b57965d1..52a2dda4f954 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -116,7 +116,16 @@ void parse_events_update_lists(struct list_head *list_event, void parse_events_error(void *data, void *scanner, char const *msg); void print_events(const char *event_glob, bool name_only); -void print_events_type(u8 type); + +struct event_symbol { + const char *symbol; + const char *alias; +}; +extern struct event_symbol event_symbols_hw[]; +extern struct event_symbol event_symbols_sw[]; +void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max, + bool name_only); void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 4ee9a86705ed..01626be2a8eb 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -37,6 +37,7 @@ static int get_value(struct parse_opt_ctx_t *p, { const char *s, *arg = NULL; const int unset = flags & OPT_UNSET; + int err; if (unset && p->opt) return opterror(opt, "takes no value", flags); @@ -114,13 +115,29 @@ static int get_value(struct parse_opt_ctx_t *p, return 0; case OPTION_STRING: + err = 0; if (unset) *(const char **)opt->value = NULL; else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) *(const char **)opt->value = (const char *)opt->defval; else - return get_arg(p, opt, flags, (const char **)opt->value); - return 0; + err = get_arg(p, opt, flags, (const char **)opt->value); + + /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */ + if (opt->flags & PARSE_OPT_NOEMPTY) { + const char *val = *(const char **)opt->value; + + if (!val) + return err; + + /* Similar to unset if we are given an empty string. */ + if (val[0] == '\0') { + *(const char **)opt->value = NULL; + return 0; + } + } + + return err; case OPTION_CALLBACK: if (unset) @@ -505,15 +522,18 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o break; case PARSE_OPT_LIST_OPTS: while (options->type != OPTION_END) { - printf("--%s ", options->long_name); + if (options->long_name) + printf("--%s ", options->long_name); options++; } + putchar('\n'); exit(130); case PARSE_OPT_LIST_SUBCMDS: if (subcommands) { for (int i = 0; subcommands[i]; i++) printf("%s ", subcommands[i]); } + putchar('\n'); exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 97b153fb4999..59561fd86278 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -40,6 +40,7 @@ enum parse_opt_option_flags { PARSE_OPT_LASTARG_DEFAULT = 16, PARSE_OPT_DISABLED = 32, PARSE_OPT_EXCLUSIVE = 64, + PARSE_OPT_NOEMPTY = 128, }; struct option; @@ -122,6 +123,7 @@ struct option { #define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) } #define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) } #define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) } +#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9dfbed96bf39..8feac0774c41 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -80,6 +80,7 @@ static int init_symbol_maps(bool user_only) int ret; symbol_conf.sort_by_name = true; + symbol_conf.allow_aliases = true; ret = symbol__init(NULL); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); @@ -151,7 +152,7 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) sym = __find_kernel_function_by_name(name, &map); if (sym) return map->unmap_ip(map, sym->start) - - (reloc) ? 0 : map->reloc; + ((reloc) ? 0 : map->reloc); } return 0; } @@ -178,6 +179,25 @@ static struct map *kernel_get_module_map(const char *module) return NULL; } +static struct map *get_target_map(const char *target, bool user) +{ + /* Init maps of given executable or kernel */ + if (user) + return dso__new_map(target); + else + return kernel_get_module_map(target); +} + +static void put_target_map(struct map *map, bool user) +{ + if (map && user) { + /* Only the user map needs to be released */ + dso__delete(map->dso); + map__delete(map); + } +} + + static struct dso *kernel_get_module_dso(const char *module) { struct dso *dso; @@ -249,6 +269,13 @@ out: return ret; } +static void clear_perf_probe_point(struct perf_probe_point *pp) +{ + free(pp->file); + free(pp->function); + free(pp->lazy_line); +} + static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) { int i; @@ -258,6 +285,102 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) } #ifdef HAVE_DWARF_SUPPORT +/* + * Some binaries like glibc have special symbols which are on the symbol + * table, but not in the debuginfo. If we can find the address of the + * symbol from map, we can translate the address back to the probe point. + */ +static int find_alternative_probe_point(struct debuginfo *dinfo, + struct perf_probe_point *pp, + struct perf_probe_point *result, + const char *target, bool uprobes) +{ + struct map *map = NULL; + struct symbol *sym; + u64 address = 0; + int ret = -ENOENT; + + /* This can work only for function-name based one */ + if (!pp->function || pp->file) + return -ENOTSUP; + + map = get_target_map(target, uprobes); + if (!map) + return -EINVAL; + + /* Find the address of given function */ + map__for_each_symbol_by_name(map, pp->function, sym) { + if (uprobes) + address = sym->start; + else + address = map->unmap_ip(map, sym->start); + break; + } + if (!address) { + ret = -ENOENT; + goto out; + } + pr_debug("Symbol %s address found : %lx\n", pp->function, address); + + ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, + result); + if (ret <= 0) + ret = (!ret) ? -ENOENT : ret; + else { + result->offset += pp->offset; + result->line += pp->line; + ret = 0; + } + +out: + put_target_map(map, uprobes); + return ret; + +} + +static int get_alternative_probe_event(struct debuginfo *dinfo, + struct perf_probe_event *pev, + struct perf_probe_point *tmp, + const char *target) +{ + int ret; + + memcpy(tmp, &pev->point, sizeof(*tmp)); + memset(&pev->point, 0, sizeof(pev->point)); + ret = find_alternative_probe_point(dinfo, tmp, &pev->point, + target, pev->uprobes); + if (ret < 0) + memcpy(&pev->point, tmp, sizeof(*tmp)); + + return ret; +} + +static int get_alternative_line_range(struct debuginfo *dinfo, + struct line_range *lr, + const char *target, bool user) +{ + struct perf_probe_point pp = { .function = lr->function, + .file = lr->file, + .line = lr->start }; + struct perf_probe_point result; + int ret, len = 0; + + memset(&result, 0, sizeof(result)); + + if (lr->end != INT_MAX) + len = lr->end - lr->start; + ret = find_alternative_probe_point(dinfo, &pp, &result, + target, user); + if (!ret) { + lr->function = result.function; + lr->file = result.file; + lr->start = result.line; + if (lr->end != INT_MAX) + lr->end = lr->start + len; + clear_perf_probe_point(&pp); + } + return ret; +} /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module, bool silent) @@ -466,6 +589,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, int max_tevs, const char *target) { bool need_dwarf = perf_probe_event_need_dwarf(pev); + struct perf_probe_point tmp; struct debuginfo *dinfo; int ntevs, ret = 0; @@ -482,6 +606,20 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, /* Searching trace events corresponding to a probe event */ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs); + if (ntevs == 0) { /* Not found, retry with an alternative */ + ret = get_alternative_probe_event(dinfo, pev, &tmp, target); + if (!ret) { + ntevs = debuginfo__find_trace_events(dinfo, pev, + tevs, max_tevs); + /* + * Write back to the original probe_event for + * setting appropriate (user given) event name + */ + clear_perf_probe_point(&pev->point); + memcpy(&pev->point, &tmp, sizeof(tmp)); + } + } + debuginfo__delete(dinfo); if (ntevs > 0) { /* Succeeded to find trace events */ @@ -496,11 +634,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } if (ntevs == 0) { /* No error but failed to find probe point. */ - pr_warning("Probe point '%s' not found in debuginfo.\n", + pr_warning("Probe point '%s' not found.\n", synthesize_perf_probe_point(&pev->point)); - if (need_dwarf) - return -ENOENT; - return 0; + return -ENOENT; } /* Error path : ntevs < 0 */ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); @@ -533,7 +669,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir, else { if (access(raw_path, R_OK) == 0) { *new_path = strdup(raw_path); - return 0; + return *new_path ? 0 : -ENOMEM; } else return -errno; } @@ -549,9 +685,11 @@ static int get_real_path(const char *raw_path, const char *comp_dir, if (access(*new_path, R_OK) == 0) return 0; - if (!symbol_conf.source_prefix) + if (!symbol_conf.source_prefix) { /* In case of searching comp_dir, don't retry */ + zfree(new_path); return -errno; + } switch (errno) { case ENAMETOOLONG: @@ -623,7 +761,8 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) * Show line-range always requires debuginfo to find source file and * line number. */ -static int __show_line_range(struct line_range *lr, const char *module) +static int __show_line_range(struct line_range *lr, const char *module, + bool user) { int l = 1; struct int_node *ln; @@ -639,6 +778,11 @@ static int __show_line_range(struct line_range *lr, const char *module) return -ENOENT; ret = debuginfo__find_line_range(dinfo, lr); + if (!ret) { /* Not found, retry with an alternative */ + ret = get_alternative_line_range(dinfo, lr, module, user); + if (!ret) + ret = debuginfo__find_line_range(dinfo, lr); + } debuginfo__delete(dinfo); if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); @@ -651,7 +795,11 @@ static int __show_line_range(struct line_range *lr, const char *module) /* Convert source file path */ tmp = lr->path; ret = get_real_path(tmp, lr->comp_dir, &lr->path); - free(tmp); /* Free old path */ + + /* Free old path when new path is assigned */ + if (tmp != lr->path) + free(tmp); + if (ret < 0) { pr_warning("Failed to find source file path.\n"); return ret; @@ -708,7 +856,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user) ret = init_symbol_maps(user); if (ret < 0) return ret; - ret = __show_line_range(lr, module); + ret = __show_line_range(lr, module, user); exit_symbol_maps(); return ret; @@ -717,12 +865,13 @@ int show_line_range(struct line_range *lr, const char *module, bool user) static int show_available_vars_at(struct debuginfo *dinfo, struct perf_probe_event *pev, int max_vls, struct strfilter *_filter, - bool externs) + bool externs, const char *target) { char *buf; int ret, i, nvars; struct str_node *node; struct variable_list *vls = NULL, *vl; + struct perf_probe_point tmp; const char *var; buf = synthesize_perf_probe_point(&pev->point); @@ -732,6 +881,15 @@ static int show_available_vars_at(struct debuginfo *dinfo, ret = debuginfo__find_available_vars_at(dinfo, pev, &vls, max_vls, externs); + if (!ret) { /* Not found, retry with an alternative */ + ret = get_alternative_probe_event(dinfo, pev, &tmp, target); + if (!ret) { + ret = debuginfo__find_available_vars_at(dinfo, pev, + &vls, max_vls, externs); + /* Release the old probe_point */ + clear_perf_probe_point(&tmp); + } + } if (ret <= 0) { if (ret == 0 || ret == -ENOENT) { pr_err("Failed to find the address of %s\n", buf); @@ -794,7 +952,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, for (i = 0; i < npevs && ret >= 0; i++) ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter, - externs); + externs, module); debuginfo__delete(dinfo); out: @@ -1740,15 +1898,12 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, void clear_perf_probe_event(struct perf_probe_event *pev) { - struct perf_probe_point *pp = &pev->point; struct perf_probe_arg_field *field, *next; int i; free(pev->event); free(pev->group); - free(pp->file); - free(pp->function); - free(pp->lazy_line); + clear_perf_probe_point(&pev->point); for (i = 0; i < pev->nargs; i++) { free(pev->args[i].name); @@ -1903,6 +2058,95 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) return sl; } +struct kprobe_blacklist_node { + struct list_head list; + unsigned long start; + unsigned long end; + char *symbol; +}; + +static void kprobe_blacklist__delete(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + + while (!list_empty(blacklist)) { + node = list_first_entry(blacklist, + struct kprobe_blacklist_node, list); + list_del(&node->list); + free(node->symbol); + free(node); + } +} + +static int kprobe_blacklist__load(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + const char *__debugfs = debugfs_find_mountpoint(); + char buf[PATH_MAX], *p; + FILE *fp; + int ret; + + if (__debugfs == NULL) + return -ENOTSUP; + + ret = e_snprintf(buf, PATH_MAX, "%s/kprobes/blacklist", __debugfs); + if (ret < 0) + return ret; + + fp = fopen(buf, "r"); + if (!fp) + return -errno; + + ret = 0; + while (fgets(buf, PATH_MAX, fp)) { + node = zalloc(sizeof(*node)); + if (!node) { + ret = -ENOMEM; + break; + } + INIT_LIST_HEAD(&node->list); + list_add_tail(&node->list, blacklist); + if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + ret = -EINVAL; + break; + } + p = strchr(buf, '\t'); + if (p) { + p++; + if (p[strlen(p) - 1] == '\n') + p[strlen(p) - 1] = '\0'; + } else + p = (char *)"unknown"; + node->symbol = strdup(p); + if (!node->symbol) { + ret = -ENOMEM; + break; + } + pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + node->start, node->end, node->symbol); + ret++; + } + if (ret < 0) + kprobe_blacklist__delete(blacklist); + fclose(fp); + + return ret; +} + +static struct kprobe_blacklist_node * +kprobe_blacklist__find_by_address(struct list_head *blacklist, + unsigned long address) +{ + struct kprobe_blacklist_node *node; + + list_for_each_entry(node, blacklist, list) { + if (node->start <= address && address <= node->end) + return node; + } + + return NULL; +} + /* Show an event */ static int show_perf_probe_event(struct perf_probe_event *pev, const char *module) @@ -2108,6 +2352,27 @@ static int get_new_event_name(char *buf, size_t len, const char *base, return ret; } +/* Warn if the current kernel's uprobe implementation is old */ +static void warn_uprobe_event_compat(struct probe_trace_event *tev) +{ + int i; + char *buf = synthesize_probe_trace_command(tev); + + /* Old uprobe event doesn't support memory dereference */ + if (!tev->uprobes || tev->nargs == 0 || !buf) + goto out; + + for (i = 0; i < tev->nargs; i++) + if (strglobmatch(tev->args[i].value, "[$@+-]*")) { + pr_warning("Please upgrade your kernel to at least " + "3.14 to have access to feature %s\n", + tev->args[i].value); + break; + } +out: + free(buf); +} + static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs, bool allow_suffix) @@ -2117,6 +2382,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, char buf[64]; const char *event, *group; struct strlist *namelist; + LIST_HEAD(blacklist); + struct kprobe_blacklist_node *node; if (pev->uprobes) fd = open_uprobe_events(true); @@ -2134,11 +2401,25 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, pr_debug("Failed to get current event list.\n"); return -EIO; } + /* Get kprobe blacklist if exists */ + if (!pev->uprobes) { + ret = kprobe_blacklist__load(&blacklist); + if (ret < 0) + pr_debug("No kprobe blacklist support, ignored\n"); + } ret = 0; pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; + /* Ensure that the address is NOT blacklisted */ + node = kprobe_blacklist__find_by_address(&blacklist, + tev->point.address); + if (node) { + pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol); + continue; + } + if (pev->event) event = pev->event; else @@ -2188,14 +2469,18 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, */ allow_suffix = true; } + if (ret == -EINVAL && pev->uprobes) + warn_uprobe_event_compat(tev); - if (ret >= 0) { + /* Note that it is possible to skip all events because of blacklist */ + if (ret >= 0 && tev->event) { /* Show how to use the event. */ pr_info("\nYou can now use it in all perf tools, such as:\n\n"); pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } + kprobe_blacklist__delete(&blacklist); strlist__delete(namelist); close(fd); return ret; @@ -2207,8 +2492,7 @@ static int find_probe_functions(struct map *map, char *name) struct symbol *sym; map__for_each_symbol_by_name(map, name, sym) { - if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) - found++; + found++; } return found; @@ -2226,7 +2510,6 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int max_tevs, const char *target) { struct map *map = NULL; - struct kmap *kmap = NULL; struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; struct probe_trace_event *tev; @@ -2235,11 +2518,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int num_matched_functions; int ret, i; - /* Init maps of given executable or kernel */ - if (pev->uprobes) - map = dso__new_map(target); - else - map = kernel_get_module_map(target); + map = get_target_map(target, pev->uprobes); if (!map) { ret = -EINVAL; goto out; @@ -2263,8 +2542,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } if (!pev->uprobes && !pp->retprobe) { - kmap = map__kmap(map); - reloc_sym = kmap->ref_reloc_sym; + reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); ret = -EINVAL; @@ -2332,11 +2610,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } out: - if (map && pev->uprobes) { - /* Only when using uprobe(exec) map needs to be released */ - dso__delete(map->dso); - map__delete(map); - } + put_target_map(map, pev->uprobes); return ret; nomem_out: @@ -2576,8 +2850,7 @@ static struct strfilter *available_func_filter; static int filter_available_functions(struct map *map __maybe_unused, struct symbol *sym) { - if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && - strfilter__compare(available_func_filter, sym->name)) + if (strfilter__compare(available_func_filter, sym->name)) return 0; return 1; } diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index d14193518e4d..46f009aa486c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1345,11 +1345,8 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; - /* Adjust address with bias */ - addr += dbg->bias; - /* Find cu die */ - if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) { + if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 22ebc46226e7..8171fed4136e 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -214,6 +214,11 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; + case PRINT_INT_ARRAY: + define_event_symbols(event, ev_name, args->int_array.field); + define_event_symbols(event, ev_name, args->int_array.count); + define_event_symbols(event, ev_name, args->int_array.el_size); + break; case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 0c815a40a6e8..2ec5dfb5a456 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -231,6 +231,11 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; + case PRINT_INT_ARRAY: + define_event_symbols(event, ev_name, args->int_array.field); + define_event_symbols(event, ev_name, args->int_array.count); + define_event_symbols(event, ev_name, args->int_array.el_size); + break; case PRINT_STRING: break; case PRINT_TYPE: diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 504b7e664e6c..adf0740c563b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -16,6 +16,12 @@ #include "perf_regs.h" #include "asm/bug.h" +static int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset); + static int perf_session__open(struct perf_session *session) { struct perf_data_file *file = session->file; @@ -86,6 +92,14 @@ static void perf_session__set_comm_exec(struct perf_session *session) machines__set_comm_exec(&session->machines, comm_exec); } +static int ordered_events__deliver_event(struct ordered_events *oe, + struct ordered_event *event, + struct perf_sample *sample) +{ + return machines__deliver_event(oe->machines, oe->evlist, event->event, + sample, oe->tool, event->file_offset); +} + struct perf_session *perf_session__new(struct perf_data_file *file, bool repipe, struct perf_tool *tool) { @@ -95,7 +109,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out; session->repipe = repipe; - ordered_events__init(&session->ordered_events); machines__init(&session->machines); if (file) { @@ -126,6 +139,9 @@ struct perf_session *perf_session__new(struct perf_data_file *file, tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; + } else { + ordered_events__init(&session->ordered_events, &session->machines, + session->evlist, tool, ordered_events__deliver_event); } return session; @@ -138,11 +154,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, return NULL; } -static void perf_session__delete_dead_threads(struct perf_session *session) -{ - machine__delete_dead_threads(&session->machines.host); -} - static void perf_session__delete_threads(struct perf_session *session) { machine__delete_threads(&session->machines.host); @@ -167,7 +178,6 @@ static void perf_session_env__delete(struct perf_session_env *env) void perf_session__delete(struct perf_session *session) { perf_session__destroy_kernel_maps(session); - perf_session__delete_dead_threads(session); perf_session__delete_threads(session); perf_session_env__delete(&session->header.env); machines__exit(&session->machines); @@ -215,10 +225,17 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused, return 0; } +static int process_build_id_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) + struct ordered_events *oe __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -226,7 +243,7 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, static int process_finished_round(struct perf_tool *tool, union perf_event *event, - struct perf_session *session); + struct ordered_events *oe); static int process_id_index_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, @@ -264,7 +281,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) - tool->build_id = process_finished_round_stub; + tool->build_id = process_build_id_stub; if (tool->finished_round == NULL) { if (tool->ordered_events) tool->finished_round = process_finished_round; @@ -514,43 +531,17 @@ static perf_event__swap_op perf_event__swap_ops[] = { * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(struct perf_tool *tool, +static int process_finished_round(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_session *session) + struct ordered_events *oe) { - return ordered_events__flush(session, tool, OE_FLUSH__ROUND); + return ordered_events__flush(oe, OE_FLUSH__ROUND); } -int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_tool *tool, struct perf_sample *sample, - u64 file_offset) +int perf_session__queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset) { - struct ordered_events *oe = &s->ordered_events; - u64 timestamp = sample->time; - struct ordered_event *new; - - if (!timestamp || timestamp == ~0ULL) - return -ETIME; - - if (timestamp < oe->last_flush) { - pr_oe_time(timestamp, "out of order event\n"); - pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", - oe->last_flush_type); - - s->stats.nr_unordered_events++; - } - - new = ordered_events__new(oe, timestamp, event); - if (!new) { - ordered_events__flush(s, tool, OE_FLUSH__HALF); - new = ordered_events__new(oe, timestamp, event); - } - - if (!new) - return -ENOMEM; - - new->file_offset = file_offset; - return 0; + return ordered_events__queue(&s->ordered_events, event, sample, file_offset); } static void callchain__lbr_callstack_printf(struct perf_sample *sample) @@ -688,14 +679,14 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_session__print_tstamp(struct perf_session *session, +static void perf_evlist__print_tstamp(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(evlist); if (event->header.type != PERF_RECORD_SAMPLE && - !perf_evlist__sample_id_all(session->evlist)) { + !perf_evlist__sample_id_all(evlist)) { fputs("-1 -1 ", stdout); return; } @@ -737,7 +728,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.one.id, sample->read.one.value); } -static void dump_event(struct perf_session *session, union perf_event *event, +static void dump_event(struct perf_evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -749,7 +740,7 @@ static void dump_event(struct perf_session *session, union perf_event *event, trace_event(event); if (sample) - perf_session__print_tstamp(session, event, sample); + perf_evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); @@ -797,8 +788,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->attr.read_format); } -static struct machine * - perf_session__find_machine_for_cpumode(struct perf_session *session, +static struct machine *machines__find_for_cpumode(struct machines *machines, union perf_event *event, struct perf_sample *sample) { @@ -816,26 +806,24 @@ static struct machine * else pid = sample->pid; - machine = perf_session__find_machine(session, pid); + machine = machines__find(machines, pid); if (!machine) - machine = perf_session__findnew_machine(session, - DEFAULT_GUEST_KERNEL_ID); + machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } - return &session->machines.host; + return &machines->host; } -static int deliver_sample_value(struct perf_session *session, +static int deliver_sample_value(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, struct machine *machine) { - struct perf_sample_id *sid; + struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); - sid = perf_evlist__id2sid(session->evlist, v->id); if (sid) { sample->id = v->id; sample->period = v->value - sid->period; @@ -843,14 +831,14 @@ static int deliver_sample_value(struct perf_session *session, } if (!sid || sid->evsel == NULL) { - ++session->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } return tool->sample(tool, event, sample, sid->evsel, machine); } -static int deliver_sample_group(struct perf_session *session, +static int deliver_sample_group(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -860,7 +848,7 @@ static int deliver_sample_group(struct perf_session *session, u64 i; for (i = 0; i < sample->read.group.nr; i++) { - ret = deliver_sample_value(session, tool, event, sample, + ret = deliver_sample_value(evlist, tool, event, sample, &sample->read.group.values[i], machine); if (ret) @@ -871,7 +859,7 @@ static int deliver_sample_group(struct perf_session *session, } static int -perf_session__deliver_sample(struct perf_session *session, + perf_evlist__deliver_sample(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -888,41 +876,40 @@ perf_session__deliver_sample(struct perf_session *session, /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) - return deliver_sample_group(session, tool, event, sample, + return deliver_sample_group(evlist, tool, event, sample, machine); else - return deliver_sample_value(session, tool, event, sample, + return deliver_sample_value(evlist, tool, event, sample, &sample->read.one, machine); } -int perf_session__deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, u64 file_offset) +static int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; struct machine *machine; - dump_event(session, event, file_offset, sample); + dump_event(evlist, event, file_offset, sample); - evsel = perf_evlist__id2evsel(session->evlist, sample->id); + evsel = perf_evlist__id2evsel(evlist, sample->id); - machine = perf_session__find_machine_for_cpumode(session, event, - sample); + machine = machines__find_for_cpumode(machines, event, sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->stats.nr_unprocessable_samples; + ++evlist->stats.nr_unprocessable_samples; return 0; } - return perf_session__deliver_sample(session, tool, event, - sample, evsel, machine); + return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: @@ -935,7 +922,7 @@ int perf_session__deliver_event(struct perf_session *session, return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->stats.total_lost += event->lost.lost; + evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); @@ -944,20 +931,21 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->stats.nr_unknown_events; + ++evlist->stats.nr_unknown_events; return -1; } } static s64 perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) { + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); int err; - dump_event(session, event, file_offset, NULL); + dump_event(session->evlist, event, file_offset, NULL); /* These events are processed right away */ switch (event->header.type) { @@ -981,7 +969,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, session); + return tool->finished_round(tool, event, oe); case PERF_RECORD_ID_INDEX: return tool->id_index(tool, event, session); default: @@ -991,15 +979,17 @@ static s64 perf_session__process_user_event(struct perf_session *session, int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool) + struct perf_sample *sample) { - events_stats__inc(&session->stats, event->header.type); + struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->ordered_events.tool; + + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, tool, 0); + return perf_session__process_user_event(session, event, 0); - return perf_session__deliver_event(session, event, sample, tool, 0); + return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0); } static void event_swap(union perf_event *event, bool sample_id_all) @@ -1067,40 +1057,39 @@ out_parse_sample: } static s64 perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - u64 file_offset) + union perf_event *event, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->ordered_events.tool; struct perf_sample sample; int ret; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(session->evlist)); + event_swap(event, perf_evlist__sample_id_all(evlist)); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, tool, file_offset); + return perf_session__process_user_event(session, event, file_offset); /* * For all kernel events we get the sample data */ - ret = perf_evlist__parse_sample(session->evlist, event, &sample); + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) return ret; if (tool->ordered_events) { - ret = perf_session_queue_event(session, event, tool, &sample, - file_offset); + ret = perf_session__queue_event(session, event, &sample, file_offset); if (ret != -ETIME) return ret; } - return perf_session__deliver_event(session, event, &sample, tool, - file_offset); + return machines__deliver_event(&session->machines, evlist, event, + &sample, tool, file_offset); } void perf_event_header__bswap(struct perf_event_header *hdr) @@ -1128,54 +1117,55 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } -static void perf_session__warn_about_errors(const struct perf_session *session, - const struct perf_tool *tool) +static void perf_tool__warn_about_errors(const struct perf_tool *tool, + const struct events_stats *stats) { if (tool->lost == perf_event__process_lost && - session->stats.nr_events[PERF_RECORD_LOST] != 0) { + stats->nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->stats.nr_events[0], - session->stats.nr_events[PERF_RECORD_LOST]); + stats->nr_events[0], + stats->nr_events[PERF_RECORD_LOST]); } - if (session->stats.nr_unknown_events != 0) { + if (stats->nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_unknown_events); + stats->nr_unknown_events); } - if (session->stats.nr_unknown_id != 0) { + if (stats->nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->stats.nr_unknown_id); + stats->nr_unknown_id); } - if (session->stats.nr_invalid_chains != 0) { - ui__warning("Found invalid callchains!\n\n" - "%u out of %u events were discarded for this reason.\n\n" - "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_invalid_chains, - session->stats.nr_events[PERF_RECORD_SAMPLE]); - } + if (stats->nr_invalid_chains != 0) { + ui__warning("Found invalid callchains!\n\n" + "%u out of %u events were discarded for this reason.\n\n" + "Consider reporting to linux-kernel@vger.kernel.org.\n\n", + stats->nr_invalid_chains, + stats->nr_events[PERF_RECORD_SAMPLE]); + } - if (session->stats.nr_unprocessable_samples != 0) { + if (stats->nr_unprocessable_samples != 0) { ui__warning("%u unprocessable samples recorded.\n" "Do you have a KVM guest running and not using 'perf kvm'?\n", - session->stats.nr_unprocessable_samples); + stats->nr_unprocessable_samples); } - if (session->stats.nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); + if (stats->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", stats->nr_unordered_events); } volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *session, - struct perf_tool *tool) +static int __perf_session__process_pipe_events(struct perf_session *session) { + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; @@ -1239,7 +1229,7 @@ more: } } - if ((skip = perf_session__process_event(session, event, tool, head)) < 0) { + if ((skip = perf_session__process_event(session, event, head)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", head, event->header.size, event->header.type); err = -EINVAL; @@ -1255,10 +1245,10 @@ more: goto more; done: /* do the final flush for ordered samples */ - err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: free(buf); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); return err; } @@ -1305,8 +1295,10 @@ fetch_mmaped_event(struct perf_session *session, static int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, - u64 file_size, struct perf_tool *tool) + u64 file_size) { + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; @@ -1375,8 +1367,7 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, tool, file_pos)) - < 0) { + (skip = perf_session__process_event(session, event, file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1400,17 +1391,16 @@ more: out: /* do the final flush for ordered samples */ - err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: ui_progress__finish(); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); session->one_mmap = false; return err; } -int perf_session__process_events(struct perf_session *session, - struct perf_tool *tool) +int perf_session__process_events(struct perf_session *session) { u64 size = perf_data_file__size(session->file); int err; @@ -1421,10 +1411,9 @@ int perf_session__process_events(struct perf_session *session, if (!perf_data_file__is_pipe(session->file)) err = __perf_session__process_events(session, session->header.data_offset, - session->header.data_size, - size, tool); + session->header.data_size, size); else - err = __perf_session__process_pipe_events(session, tool); + err = __perf_session__process_pipe_events(session); return err; } @@ -1488,7 +1477,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { size_t ret = fprintf(fp, "Aggregated stats:\n"); - ret += events_stats__fprintf(&session->stats, fp); + ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 6d663dc76404..1310998f8318 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -20,7 +20,6 @@ struct perf_session { struct machines machines; struct perf_evlist *evlist; struct trace_event tevent; - struct events_stats stats; bool repipe; bool one_mmap; void *one_mmap_addr; @@ -49,20 +48,13 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, union perf_event **event_ptr, struct perf_sample *sample); -int perf_session__process_events(struct perf_session *session, - struct perf_tool *tool); +int perf_session__process_events(struct perf_session *session); -int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_tool *tool, struct perf_sample *sample, - u64 file_offset); +int perf_session__queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset); void perf_tool__fill_defaults(struct perf_tool *tool); -int perf_session__deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, u64 file_offset); - int perf_session__resolve_callchain(struct perf_session *session, struct perf_evsel *evsel, struct thread *thread, @@ -126,8 +118,7 @@ extern volatile int session_done; int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool); + struct perf_sample *sample); int perf_event__process_id_index(struct perf_tool *tool, union perf_event *event, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 7a39c1ed8d37..4593f36ecc4c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1463,6 +1463,15 @@ int sort_dimension__add(const char *tok) sort__has_parent = 1; } else if (sd->entry == &sort_sym) { sort__has_sym = 1; + /* + * perf diff displays the performance difference amongst + * two or more perf.data files. Those files could come + * from different binaries. So we should not compare + * their ips, but the name of symbol. + */ + if (sort__mode == SORT_MODE__DIFF) + sd->entry->se_collapse = sort__sym_sort; + } else if (sd->entry == &sort_dso) { sort__has_dso = 1; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index c03e4ff8beff..846036a921dc 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -44,6 +44,7 @@ extern struct sort_entry sort_dso_to; extern struct sort_entry sort_sym_from; extern struct sort_entry sort_sym_to; extern enum sort_type sort__first_dimension; +extern const char default_mem_sort_order[]; struct he_stat { u64 period; @@ -102,7 +103,6 @@ struct hist_entry { bool init_have_children; char level; - bool used; u8 filtered; char *srcline; struct symbol *parent; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b02731a19d1f..476268c99431 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -11,6 +11,11 @@ #include <symbol/kallsyms.h> #include "debug.h" +#ifndef EM_AARCH64 +#define EM_AARCH64 183 /* ARM 64 bit */ +#endif + + #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); @@ -574,32 +579,37 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) static int decompress_kmodule(struct dso *dso, const char *name, enum dso_binary_type type) { - int fd; - const char *ext = strrchr(name, '.'); + int fd = -1; char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; + struct kmod_path m; if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && type != DSO_BINARY_TYPE__BUILD_ID_CACHE) return -1; - if (!ext || !is_supported_compression(ext + 1)) { - ext = strrchr(dso->name, '.'); - if (!ext || !is_supported_compression(ext + 1)) - return -1; - } + if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE) + name = dso->long_name; - fd = mkstemp(tmpbuf); - if (fd < 0) + if (kmod_path__parse_ext(&m, name) || !m.comp) return -1; - if (!decompress_to_file(ext + 1, name, fd)) { + fd = mkstemp(tmpbuf); + if (fd < 0) { + dso->load_errno = errno; + goto out; + } + + if (!decompress_to_file(m.ext, name, fd)) { + dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } unlink(tmpbuf); +out: + free(m.ext); return fd; } @@ -628,37 +638,49 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, Elf *elf; int fd; - if (dso__needs_decompress(dso)) + if (dso__needs_decompress(dso)) { fd = decompress_kmodule(dso, name, type); - else + if (fd < 0) + return -1; + } else { fd = open(name, O_RDONLY); - - if (fd < 0) - return -1; + if (fd < 0) { + dso->load_errno = errno; + return -1; + } + } elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); if (elf == NULL) { pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF; goto out_close; } if (gelf_getehdr(elf, &ehdr) == NULL) { + dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF; pr_debug("%s: cannot get elf header.\n", __func__); goto out_elf_end; } - if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) + if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) { + dso->load_errno = DSO_LOAD_ERRNO__INTERNAL_ERROR; goto out_elf_end; + } /* Always reject images with a mismatched build-id: */ if (dso->has_build_id) { u8 build_id[BUILD_ID_SIZE]; - if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) { + dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID; goto out_elf_end; + } - if (!dso__build_id_equal(dso, build_id)) + if (!dso__build_id_equal(dso, build_id)) { + dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID; goto out_elf_end; + } } ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); @@ -694,8 +716,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, } ss->name = strdup(name); - if (!ss->name) + if (!ss->name) { + dso->load_errno = errno; goto out_elf_end; + } ss->elf = elf; ss->fd = fd; @@ -1043,7 +1067,8 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_duplicate(&dso->symbols[map->type]); + if (!symbol_conf.allow_aliases) + symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); if (kmap) { /* diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index d7efb03b3f9a..fd8477cacf88 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -246,13 +246,12 @@ out: return ret; } -int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, - const char *name, +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type) { int fd = open(name, O_RDONLY); if (fd < 0) - return -1; + goto out_errno; ss->name = strdup(name); if (!ss->name) @@ -264,6 +263,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, return 0; out_close: close(fd); +out_errno: + dso->load_errno = errno; return -1; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a69066865a55..fddeb9073039 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -15,6 +15,7 @@ #include "machine.h" #include "symbol.h" #include "strlist.h" +#include "intlist.h" #include "header.h" #include <elf.h> @@ -1859,6 +1860,20 @@ int setup_list(struct strlist **list, const char *list_str, return 0; } +int setup_intlist(struct intlist **list, const char *list_str, + const char *list_name) +{ + if (list_str == NULL) + return 0; + + *list = intlist__new(list_str); + if (!*list) { + pr_err("problems parsing %s list\n", list_name); + return -1; + } + return 0; +} + static bool symbol__read_kptr_restrict(void) { bool value = false; @@ -1909,9 +1924,17 @@ int symbol__init(struct perf_session_env *env) symbol_conf.comm_list_str, "comm") < 0) goto out_free_dso_list; + if (setup_intlist(&symbol_conf.pid_list, + symbol_conf.pid_list_str, "pid") < 0) + goto out_free_comm_list; + + if (setup_intlist(&symbol_conf.tid_list, + symbol_conf.tid_list_str, "tid") < 0) + goto out_free_pid_list; + if (setup_list(&symbol_conf.sym_list, symbol_conf.sym_list_str, "symbol") < 0) - goto out_free_comm_list; + goto out_free_tid_list; /* * A path to symbols of "/" is identical to "" @@ -1930,6 +1953,10 @@ int symbol__init(struct perf_session_env *env) symbol_conf.initialized = true; return 0; +out_free_tid_list: + intlist__delete(symbol_conf.tid_list); +out_free_pid_list: + intlist__delete(symbol_conf.pid_list); out_free_comm_list: strlist__delete(symbol_conf.comm_list); out_free_dso_list: @@ -1944,6 +1971,8 @@ void symbol__exit(void) strlist__delete(symbol_conf.sym_list); strlist__delete(symbol_conf.dso_list); strlist__delete(symbol_conf.comm_list); + intlist__delete(symbol_conf.tid_list); + intlist__delete(symbol_conf.pid_list); vmlinux_path__exit(); symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 1650dcb3a67b..09561500164a 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -78,6 +78,7 @@ static inline size_t symbol__size(const struct symbol *sym) } struct strlist; +struct intlist; struct symbol_conf { unsigned short priv_size; @@ -87,6 +88,7 @@ struct symbol_conf { ignore_vmlinux_buildid, show_kernel_path, use_modules, + allow_aliases, sort_by_name, show_nr_samples, show_total_period, @@ -114,6 +116,8 @@ struct symbol_conf { const char *guestmount; const char *dso_list_str, *comm_list_str, + *pid_list_str, + *tid_list_str, *sym_list_str, *col_width_list_str; struct strlist *dso_list, @@ -123,6 +127,8 @@ struct symbol_conf { *dso_to_list, *sym_from_list, *sym_to_list; + struct intlist *pid_list, + *tid_list; const char *symfs; }; @@ -294,5 +300,7 @@ int compare_proc_modules(const char *from, const char *to); int setup_list(struct strlist **list, const char *list_str, const char *list_name); +int setup_intlist(struct intlist **list, const char *list_str, + const char *list_name); #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index e74c5963dc7a..a53603b27e52 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -123,11 +123,8 @@ int target__strerror(struct target *target, int errnum, if (errnum >= 0) { const char *err = strerror_r(errnum, buf, buflen); - if (err != buf) { - size_t len = strlen(err); - memcpy(buf, err, min(buflen - 1, len)); - *(buf + min(buflen - 1, len)) = '\0'; - } + if (err != buf) + scnprintf(buf, buflen, "%s", err); return 0; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 9ebc8b1f9be5..1c8fbc9588c5 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -82,6 +82,20 @@ void thread__delete(struct thread *thread) free(thread); } +struct thread *thread__get(struct thread *thread) +{ + ++thread->refcnt; + return thread; +} + +void thread__put(struct thread *thread) +{ + if (thread && --thread->refcnt == 0) { + list_del_init(&thread->node); + thread__delete(thread); + } +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) @@ -192,7 +206,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) err = thread__set_comm(thread, comm, timestamp); if (err) return err; - thread->comm_set = true; } thread->ppid = parent->tid; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 160fd066a7d1..9b8a54dc34a8 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -7,6 +7,7 @@ #include <sys/types.h> #include "symbol.h" #include <strlist.h> +#include <intlist.h> struct thread_stack; @@ -20,6 +21,7 @@ struct thread { pid_t tid; pid_t ppid; int cpu; + int refcnt; char shortname[3]; bool comm_set; bool dead; /* if set thread has exited */ @@ -37,6 +39,18 @@ struct comm; struct thread *thread__new(pid_t pid, pid_t tid); int thread__init_map_groups(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); + +struct thread *thread__get(struct thread *thread); +void thread__put(struct thread *thread); + +static inline void __thread__zput(struct thread **thread) +{ + thread__put(*thread); + *thread = NULL; +} + +#define thread__zput(thread) __thread__zput(&thread) + static inline void thread__exited(struct thread *thread) { thread->dead = true; @@ -87,6 +101,16 @@ static inline bool thread__is_filtered(struct thread *thread) return true; } + if (symbol_conf.pid_list && + !intlist__has_entry(symbol_conf.pid_list, thread->pid_)) { + return true; + } + + if (symbol_conf.tid_list && + !intlist__has_entry(symbol_conf.tid_list, thread->tid)) { + return true; + } + return false; } diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index bb2708bbfaca..51d9e56c0f84 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -10,6 +10,7 @@ struct perf_evsel; struct perf_sample; struct perf_tool; struct machine; +struct ordered_events; typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -25,6 +26,9 @@ typedef int (*event_attr_op)(struct perf_tool *tool, typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, + struct ordered_events *oe); + struct perf_tool { event_sample sample, read; @@ -38,8 +42,8 @@ struct perf_tool { unthrottle; event_attr_op attr; event_op2 tracing_data; - event_op2 finished_round, - build_id, + event_oe finished_round; + event_op2 build_id, id_index; bool ordered_events; bool ordering_requires_timestamps; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e3c40a520a25..7b09a443a280 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -266,7 +266,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, u64 *fde_count) { int ret = -EINVAL, fd; - u64 offset = dso->data.frame_offset; + u64 offset = dso->data.eh_frame_hdr_offset; if (offset == 0) { fd = dso__data_fd(dso, machine); @@ -275,7 +275,7 @@ 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"); - dso->data.frame_offset = offset; + dso->data.eh_frame_hdr_offset = offset; } if (offset) @@ -291,7 +291,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, struct machine *machine, u64 *offset) { int fd; - u64 ofs = dso->data.frame_offset; + u64 ofs = dso->data.debug_frame_offset; if (ofs == 0) { fd = dso__data_fd(dso, machine); @@ -300,7 +300,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, /* Check the .debug_frame section for unwinding info */ ofs = elf_section_offset(fd, ".debug_frame"); - dso->data.frame_offset = ofs; + dso->data.debug_frame_offset = ofs; } *offset = ofs; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 92db3f156b63..4ee6d0d4c993 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -269,6 +269,13 @@ void dump_stack(void) void dump_stack(void) {} #endif +void sighandler_dump_stack(int sig) +{ + psignal(sig, "perf"); + dump_stack(); + exit(sig); +} + void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 73c2f8e557ab..1ff23e04ad27 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -277,6 +277,7 @@ char *ltrim(char *s); char *rtrim(char *s); void dump_stack(void); +void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; @@ -328,4 +329,8 @@ bool find_process(const char *name); int gzip_decompress_to_file(const char *input, int output_fd); #endif +#ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_to_file(const char *input, int output_fd); +#endif + #endif /* GIT_COMPAT_UTIL_H */ |