diff options
Diffstat (limited to 'tools/perf')
29 files changed, 821 insertions, 98 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 5a626ef666c2..3eea6de35a38 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -430,6 +430,9 @@ Configure all used events to run in user space. --timestamp-filename Append timestamp to output file name. +--timestamp-boundary:: +Record timestamp boundary (time of first/last samples). + --switch-output[=mode]:: Generate multiple perf.data files, timestamp prefixed, switching to a new one based on 'mode' value: diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index ddde2b54af57..63d0db3184c9 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -402,6 +402,26 @@ OPTIONS stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. + Also support time percent with multiple time range. Time string is + 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10. + + For example: + Select the second 10% time slice: + + perf report --time 10%/2 + + Select from 0% to 10% time slice: + + perf report --time 0%-10% + + Select the first and second 10% time slices: + + perf report --time 10%/1,10%/2 + + Select from 0% to 10% and 30% to 40% slices: + + perf report --time 0%-10%,30%-40% + --itrace:: Options for decoding instruction tracing data. The options are: @@ -437,8 +457,23 @@ include::itrace.txt[] will be printed. Each entry is function name or file/line. Enabled by default, disable with --no-inline. +--mmaps:: + Show --tasks output plus mmap information in a format similar to + /proc/<PID>/maps. + + Please note that not all mmaps are stored, options affecting which ones + are include 'perf record --data', for instance. + +--stats:: + Display overall events statistics without any further processing. + (like the one at the end of the perf report -D command) + +--tasks:: + Display monitored tasks stored in perf data. Displaying pid/tid/ppid + plus the command string aligned to distinguish parent and child tasks. + include::callchain-overhead-calculation.txt[] SEE ALSO -------- -linkperf:perf-stat[1], linkperf:perf-annotate[1] +linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 974ceb12c7f3..806ec6391fd6 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -117,7 +117,7 @@ OPTIONS Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - brstackoff, callindent, insn, insnlen, synth, phys_addr, metric. + brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -225,6 +225,24 @@ OPTIONS that the metric computed is averaged over the whole sampling period, not just for the sample point. + For sample events it's possible to display misc field with -F +misc option, + following letters are displayed for each bit: + + PERF_RECORD_MISC_KERNEL K + PERF_RECORD_MISC_USER U + PERF_RECORD_MISC_HYPERVISOR H + PERF_RECORD_MISC_GUEST_KERNEL G + PERF_RECORD_MISC_GUEST_USER g + PERF_RECORD_MISC_MMAP_DATA* M + PERF_RECORD_MISC_COMM_EXEC E + PERF_RECORD_MISC_SWITCH_OUT S + + $ perf script -F +misc ... + sched-messaging 1414 K 28690.636582: 4590 cycles ... + sched-messaging 1407 U 28690.636600: 325620 cycles ... + sched-messaging 1414 K 28690.636608: 19473 cycles ... + misc field ___________/ + -k:: --vmlinux=<file>:: vmlinux pathname @@ -282,6 +300,9 @@ OPTIONS Display context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. +--show-lost-events + Display lost events i.e. events of type PERF_RECORD_LOST. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. @@ -329,6 +350,22 @@ include::itrace.txt[] stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. + Also support time percent with multipe time range. Time string is + 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10. + + For example: + Select the second 10% time slice + perf script --time 10%/2 + + Select from 0% to 10% time slice + perf script --time 0%-10% + + Select the first and second 10% time slices + perf script --time 10%/1,10%/2 + + Select from 0% to 10% and 30% to 40% slices + perf script --time 0%-10%,30%-40% + --max-blocks:: Set the maximum number of program blocks to print with brstackasm for each sample. diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 15e8b48077ba..f7d85e89a98a 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -261,6 +261,10 @@ struct { struct perf_header_string map; }[number_of_cache_levels]; + HEADER_SAMPLE_TIME = 21, + +Two uint64_t for the time of first sample and the time of last sample. + other bits are reserved and should ignored for now HEADER_FEAT_BITS = 256, diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f050f38d8fa3..12dec6ea5ed2 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -780,7 +780,7 @@ else NO_PERF_READ_VDSOX32 := 1 endif -ifdef LIBBABELTRACE +ifndef NO_LIBBABELTRACE $(call feature_check,libbabeltrace) ifeq ($(feature-libbabeltrace), 1) CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 68cf1360a3f3..9fdefd748e2e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -77,7 +77,7 @@ include ../scripts/utilities.mak # # Define NO_ZLIB if you do not want to support compressed kernel modules # -# Define LIBBABELTRACE if you DO want libbabeltrace support +# 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 diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 9c917f80c906..05920e3edf7a 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#ifndef REMOTE_UNWIND_LIBUNWIND #include <errno.h> +#ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 50385d89c497..65681a1a292a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -78,6 +78,7 @@ struct record { bool no_buildid_cache_set; bool buildid_all; bool timestamp_filename; + bool timestamp_boundary; struct switch_output switch_output; unsigned long long samples; }; @@ -409,8 +410,15 @@ static int process_sample_event(struct perf_tool *tool, { struct record *rec = container_of(tool, struct record, tool); - rec->samples++; + if (rec->evlist->first_sample_time == 0) + rec->evlist->first_sample_time = sample->time; + + rec->evlist->last_sample_time = sample->time; + if (rec->buildid_all) + return 0; + + rec->samples++; return build_id__mark_dso_hit(tool, event, sample, evsel, machine); } @@ -435,9 +443,11 @@ static int process_buildids(struct record *rec) /* * If --buildid-all is given, it marks all DSO regardless of hits, - * so no need to process samples. + * so no need to process samples. But if timestamp_boundary is enabled, + * it still needs to walk on all samples to get the timestamps of + * first/last samples. */ - if (rec->buildid_all) + if (rec->buildid_all && !rec->timestamp_boundary) rec->tool.sample = NULL; return perf_session__process_events(session); @@ -1621,6 +1631,8 @@ static struct option __record_options[] = { "Record build-id of all DSOs regardless of hits"), OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, "append timestamp to output filename"), + OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary, + "Record timestamp boundary (time of first/last samples)"), OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str, &record.switch_output.set, "signal,size,time", "Switch output when receive SIGUSR2 or cross size,time threshold", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index eb9ce6327e71..dd4df9a5cd06 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -15,6 +15,7 @@ #include "util/color.h" #include <linux/list.h> #include <linux/rbtree.h> +#include <linux/err.h> #include "util/symbol.h" #include "util/callchain.h" #include "util/values.h" @@ -51,6 +52,9 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include <linux/mman.h> + +#define PTIME_RANGE_MAX 10 struct report { struct perf_tool tool; @@ -60,6 +64,9 @@ struct report { bool show_threads; bool inverted_callchain; bool mem_mode; + bool stats_mode; + bool tasks_mode; + bool mmaps_mode; bool header; bool header_only; bool nonany_branch_mode; @@ -69,7 +76,8 @@ struct report { const char *cpu_list; const char *symbol_filter_str; const char *time_str; - struct perf_time_interval ptime; + struct perf_time_interval ptime_range[PTIME_RANGE_MAX]; + int range_num; float min_percent; u64 nr_entries; u64 queue_size; @@ -162,12 +170,28 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, struct hist_entry *he = iter->he; struct report *rep = arg; struct branch_info *bi; + struct perf_sample *sample = iter->sample; + struct perf_evsel *evsel = iter->evsel; + int err; + + if (!ui__has_annotation()) + return 0; + + hist__account_cycles(sample->branch_stack, al, sample, + rep->nonany_branch_mode); bi = he->branch_info; + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + branch_type_count(&rep->brtype_stat, &bi->flags, bi->from.addr, bi->to.addr); - return 0; +out: + return err; } static int process_sample_event(struct perf_tool *tool, @@ -186,8 +210,10 @@ static int process_sample_event(struct perf_tool *tool, }; int ret = 0; - if (perf_time__skip_sample(&rep->ptime, sample->time)) + if (perf_time__ranges_skip_sample(rep->ptime_range, rep->range_num, + sample->time)) { return 0; + } if (machine__resolve(machine, &al, sample) < 0) { pr_debug("problem processing %d event, skipping it.\n", @@ -567,6 +593,174 @@ static void report__output_resort(struct report *rep) ui_progress__finish(); } +static void stats_setup(struct report *rep) +{ + memset(&rep->tool, 0, sizeof(rep->tool)); + rep->tool.no_warn = true; +} + +static int stats_print(struct report *rep) +{ + struct perf_session *session = rep->session; + + perf_session__fprintf_nr_events(session, stdout); + return 0; +} + +static void tasks_setup(struct report *rep) +{ + memset(&rep->tool, 0, sizeof(rep->tool)); + if (rep->mmaps_mode) { + rep->tool.mmap = perf_event__process_mmap; + rep->tool.mmap2 = perf_event__process_mmap2; + } + rep->tool.comm = perf_event__process_comm; + rep->tool.exit = perf_event__process_exit; + rep->tool.fork = perf_event__process_fork; + rep->tool.no_warn = true; +} + +struct task { + struct thread *thread; + struct list_head list; + struct list_head children; +}; + +static struct task *tasks_list(struct task *task, struct machine *machine) +{ + struct thread *parent_thread, *thread = task->thread; + struct task *parent_task; + + /* Already listed. */ + if (!list_empty(&task->list)) + return NULL; + + /* Last one in the chain. */ + if (thread->ppid == -1) + return task; + + parent_thread = machine__find_thread(machine, -1, thread->ppid); + if (!parent_thread) + return ERR_PTR(-ENOENT); + + parent_task = thread__priv(parent_thread); + list_add_tail(&task->list, &parent_task->children); + return tasks_list(parent_task, machine); +} + +static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) +{ + size_t printed = 0; + struct rb_node *nd; + + for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { + struct map *map = rb_entry(nd, struct map, rb_node); + + printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", + indent, "", map->start, map->end, + map->prot & PROT_READ ? 'r' : '-', + map->prot & PROT_WRITE ? 'w' : '-', + map->prot & PROT_EXEC ? 'x' : '-', + map->flags & MAP_SHARED ? 's' : 'p', + map->pgoff, + map->ino, map->dso->name); + } + + return printed; +} + +static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp) +{ + int printed = 0, i; + for (i = 0; i < MAP__NR_TYPES; ++i) + printed += maps__fprintf_task(&mg->maps[i], indent, fp); + return printed; +} + +static void task__print_level(struct task *task, FILE *fp, int level) +{ + struct thread *thread = task->thread; + struct task *child; + int comm_indent = fprintf(fp, " %8d %8d %8d |%*s", + thread->pid_, thread->tid, thread->ppid, + level, ""); + + fprintf(fp, "%s\n", thread__comm_str(thread)); + + map_groups__fprintf_task(thread->mg, comm_indent, fp); + + if (!list_empty(&task->children)) { + list_for_each_entry(child, &task->children, list) + task__print_level(child, fp, level + 1); + } +} + +static int tasks_print(struct report *rep, FILE *fp) +{ + struct perf_session *session = rep->session; + struct machine *machine = &session->machines.host; + struct task *tasks, *task; + unsigned int nr = 0, itask = 0, i; + struct rb_node *nd; + LIST_HEAD(list); + + /* + * No locking needed while accessing machine->threads, + * because --tasks is single threaded command. + */ + + /* Count all the threads. */ + for (i = 0; i < THREADS__TABLE_SIZE; i++) + nr += machine->threads[i].nr; + + tasks = malloc(sizeof(*tasks) * nr); + if (!tasks) + return -ENOMEM; + + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + struct threads *threads = &machine->threads[i]; + + for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + task = tasks + itask++; + + task->thread = rb_entry(nd, struct thread, rb_node); + INIT_LIST_HEAD(&task->children); + INIT_LIST_HEAD(&task->list); + thread__set_priv(task->thread, task); + } + } + + /* + * Iterate every task down to the unprocessed parent + * and link all in task children list. Task with no + * parent is added into 'list'. + */ + for (itask = 0; itask < nr; itask++) { + task = tasks + itask; + + if (!list_empty(&task->list)) + continue; + + task = tasks_list(task, machine); + if (IS_ERR(task)) { + pr_err("Error: failed to process tasks\n"); + free(tasks); + return PTR_ERR(task); + } + + if (task) + list_add_tail(&task->list, &list); + } + + fprintf(fp, "# %8s %8s %8s %s\n", "pid", "tid", "ppid", "comm"); + + list_for_each_entry(task, &list, list) + task__print_level(task, fp, 0); + + free(tasks); + return 0; +} + static int __cmd_report(struct report *rep) { int ret; @@ -598,12 +792,24 @@ static int __cmd_report(struct report *rep) return ret; } + if (rep->stats_mode) + stats_setup(rep); + + if (rep->tasks_mode) + tasks_setup(rep); + ret = perf_session__process_events(session); if (ret) { ui__error("failed to process sample\n"); return ret; } + if (rep->stats_mode) + return stats_print(rep); + + if (rep->tasks_mode) + return tasks_print(rep, stdout); + report__warn_kptr_restrict(rep); evlist__for_each_entry(session->evlist, pos) @@ -760,6 +966,9 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN(0, "stats", &report.stats_mode, "Display event stats"), + OPT_BOOLEAN(0, "tasks", &report.tasks_mode, "Display recorded tasks"), + OPT_BOOLEAN(0, "mmaps", &report.mmaps_mode, "Display recorded tasks memory maps"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, @@ -907,6 +1116,9 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } + if (report.mmaps_mode) + report.tasks_mode = true; + if (quiet) perf_quiet_option(); @@ -1021,6 +1233,12 @@ repeat: report.tool.show_feat_hdr = SHOW_FEAT_HEADER; if (report.show_full_info) report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; + if (report.stats_mode || report.tasks_mode) + use_browser = 0; + if (report.stats_mode && report.tasks_mode) { + pr_err("Error: --tasks and --mmaps can't be used together with --stats\n"); + goto error; + } if (strcmp(input_name, "-") != 0) setup_browser(true); @@ -1043,7 +1261,8 @@ repeat: ret = 0; goto error; } - } else if (use_browser == 0 && !quiet) { + } else if (use_browser == 0 && !quiet && + !report.stats_mode && !report.tasks_mode) { fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n", stdout); } @@ -1077,9 +1296,25 @@ repeat: if (symbol__init(&session->header.env) < 0) goto error; - if (perf_time__parse_str(&report.ptime, report.time_str) != 0) { - pr_err("Invalid time string\n"); - return -EINVAL; + if (perf_time__parse_str(report.ptime_range, report.time_str) != 0) { + if (session->evlist->first_sample_time == 0 && + session->evlist->last_sample_time == 0) { + pr_err("No first/last sample time in perf data\n"); + return -EINVAL; + } + + report.range_num = perf_time__percent_parse_str( + report.ptime_range, PTIME_RANGE_MAX, + report.time_str, + session->evlist->first_sample_time, + session->evlist->last_sample_time); + + if (report.range_num < 0) { + pr_err("Invalid time string\n"); + return -EINVAL; + } + } else { + report.range_num = 1; } sort__setup_elide(stdout); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 77e47cf39f2c..c1cce474c0f1 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -93,6 +93,7 @@ enum perf_output_field { PERF_OUTPUT_PHYS_ADDR = 1U << 26, PERF_OUTPUT_UREGS = 1U << 27, PERF_OUTPUT_METRIC = 1U << 28, + PERF_OUTPUT_MISC = 1U << 29, }; struct output_option { @@ -128,6 +129,7 @@ struct output_option { {.str = "synth", .field = PERF_OUTPUT_SYNTH}, {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR}, {.str = "metric", .field = PERF_OUTPUT_METRIC}, + {.str = "misc", .field = PERF_OUTPUT_MISC}, }; enum { @@ -594,7 +596,8 @@ static int perf_sample__fprintf_uregs(struct perf_sample *sample, static int perf_sample__fprintf_start(struct perf_sample *sample, struct thread *thread, - struct perf_evsel *evsel, FILE *fp) + struct perf_evsel *evsel, + u32 type, FILE *fp) { struct perf_event_attr *attr = &evsel->attr; unsigned long secs; @@ -624,6 +627,47 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, printed += fprintf(fp, "[%03d] ", sample->cpu); } + if (PRINT_FIELD(MISC)) { + int ret = 0; + + #define has(m) \ + (sample->misc & PERF_RECORD_MISC_##m) == PERF_RECORD_MISC_##m + + if (has(KERNEL)) + ret += fprintf(fp, "K"); + if (has(USER)) + ret += fprintf(fp, "U"); + if (has(HYPERVISOR)) + ret += fprintf(fp, "H"); + if (has(GUEST_KERNEL)) + ret += fprintf(fp, "G"); + if (has(GUEST_USER)) + ret += fprintf(fp, "g"); + + switch (type) { + case PERF_RECORD_MMAP: + case PERF_RECORD_MMAP2: + if (has(MMAP_DATA)) + ret += fprintf(fp, "M"); + break; + case PERF_RECORD_COMM: + if (has(COMM_EXEC)) + ret += fprintf(fp, "E"); + break; + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + if (has(SWITCH_OUT)) + ret += fprintf(fp, "S"); + default: + break; + } + + #undef has + + ret += fprintf(fp, "%*s", 6 - ret, " "); + printed += ret; + } + if (PRINT_FIELD(TIME)) { nsecs = sample->time; secs = nsecs / NSEC_PER_SEC; @@ -1436,6 +1480,8 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, return 0; } +#define PTIME_RANGE_MAX 10 + struct perf_script { struct perf_tool tool; struct perf_session *session; @@ -1443,13 +1489,15 @@ struct perf_script { bool show_mmap_events; bool show_switch_events; bool show_namespace_events; + bool show_lost_events; bool allocated; bool per_event_dump; struct cpu_map *cpus; struct thread_map *threads; int name_width; const char *time_str; - struct perf_time_interval ptime; + struct perf_time_interval ptime_range[PTIME_RANGE_MAX]; + int range_num; }; static int perf_evlist__max_name_len(struct perf_evlist *evlist) @@ -1499,7 +1547,7 @@ static void script_print_metric(void *ctx, const char *color, if (!fmt) return; perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel, - mctx->fp); + PERF_RECORD_SAMPLE, mctx->fp); fputs("\tmetric: ", mctx->fp); if (color) color_fprintf(mctx->fp, color, fmt, val); @@ -1513,7 +1561,7 @@ static void script_new_line(void *ctx) struct metric_ctx *mctx = ctx; perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel, - mctx->fp); + PERF_RECORD_SAMPLE, mctx->fp); fputs("\tmetric: ", mctx->fp); } @@ -1581,7 +1629,8 @@ static void process_event(struct perf_script *script, ++es->samples; - perf_sample__fprintf_start(sample, thread, evsel, fp); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_SAMPLE, fp); if (PRINT_FIELD(PERIOD)) fprintf(fp, "%10" PRIu64 " ", sample->period); @@ -1734,8 +1783,10 @@ static int process_sample_event(struct perf_tool *tool, struct perf_script *scr = container_of(tool, struct perf_script, tool); struct addr_location al; - if (perf_time__skip_sample(&scr->ptime, sample->time)) + if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num, + sample->time)) { return 0; + } if (debug_mode) { if (sample->time < last_timestamp) { @@ -1828,7 +1879,8 @@ static int process_comm_event(struct perf_tool *tool, sample->tid = event->comm.tid; sample->pid = event->comm.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_COMM, stdout); perf_event__fprintf(event, stdout); ret = 0; out: @@ -1863,7 +1915,8 @@ static int process_namespaces_event(struct perf_tool *tool, sample->tid = event->namespaces.tid; sample->pid = event->namespaces.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_NAMESPACES, stdout); perf_event__fprintf(event, stdout); ret = 0; out: @@ -1896,7 +1949,8 @@ static int process_fork_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_FORK, stdout); perf_event__fprintf(event, stdout); thread__put(thread); @@ -1925,7 +1979,8 @@ static int process_exit_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_EXIT, stdout); perf_event__fprintf(event, stdout); if (perf_event__process_exit(tool, event, sample, machine) < 0) @@ -1960,7 +2015,8 @@ static int process_mmap_event(struct perf_tool *tool, sample->tid = event->mmap.tid; sample->pid = event->mmap.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP, stdout); perf_event__fprintf(event, stdout); thread__put(thread); return 0; @@ -1991,7 +2047,8 @@ static int process_mmap2_event(struct perf_tool *tool, sample->tid = event->mmap2.tid; sample->pid = event->mmap2.pid; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP2, stdout); perf_event__fprintf(event, stdout); thread__put(thread); return 0; @@ -2017,7 +2074,31 @@ static int process_switch_event(struct perf_tool *tool, return -1; } - perf_sample__fprintf_start(sample, thread, evsel, stdout); + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_SWITCH, stdout); + perf_event__fprintf(event, stdout); + thread__put(thread); + return 0; +} + +static int +process_lost_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct thread *thread; + + thread = machine__findnew_thread(machine, sample->pid, + sample->tid); + if (thread == NULL) + return -1; + + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_LOST, stdout); perf_event__fprintf(event, stdout); thread__put(thread); return 0; @@ -2117,6 +2198,8 @@ static int __cmd_script(struct perf_script *script) script->tool.context_switch = process_switch_event; if (script->show_namespace_events) script->tool.namespaces = process_namespaces_event; + if (script->show_lost_events) + script->tool.lost = process_lost_event; if (perf_script__setup_per_event_dump(script)) { pr_err("Couldn't create the per event dump files\n"); @@ -3053,6 +3136,8 @@ int cmd_script(int argc, const char **argv) "Show context switch events (if recorded)"), OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, "Show namespace events (if recorded)"), + OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events, + "Show lost events (if recorded)"), OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump, "Dump trace output to files named by the monitored events"), OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), @@ -3360,10 +3445,27 @@ int cmd_script(int argc, const char **argv) goto out_delete; /* needs to be parsed after looking up reference time */ - if (perf_time__parse_str(&script.ptime, script.time_str) != 0) { - pr_err("Invalid time string\n"); - err = -EINVAL; - goto out_delete; + if (perf_time__parse_str(script.ptime_range, script.time_str) != 0) { + if (session->evlist->first_sample_time == 0 && + session->evlist->last_sample_time == 0) { + pr_err("No first/last sample time in perf data\n"); + err = -EINVAL; + goto out_delete; + } + + script.range_num = perf_time__percent_parse_str( + script.ptime_range, PTIME_RANGE_MAX, + script.time_str, + session->evlist->first_sample_time, + session->evlist->last_sample_time); + + if (script.range_num < 0) { + pr_err("Invalid time string\n"); + err = -EINVAL; + goto out_delete; + } + } else { + script.range_num = 1; } err = __cmd_script(&script); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7c57898095ea..71e64bdca86f 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -622,6 +622,7 @@ static struct syscall_fmt { .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, }, { .name = "getrlimit", .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "gettid", .errpid = true, }, { .name = "ioctl", .arg = { #if defined(__i386__) || defined(__x86_64__) diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c index 268e5f8e4aa2..e4123c1b0e88 100644 --- a/tools/perf/tests/bpf-script-example.c +++ b/tools/perf/tests/bpf-script-example.c @@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = { .max_entries = 1, }; -SEC("func=SyS_epoll_wait") -int bpf_func__SyS_epoll_wait(void *ctx) +SEC("func=SyS_epoll_pwait") +int bpf_func__SyS_epoll_pwait(void *ctx) { int ind =0; int *flag = bpf_map_lookup_elem(&flip_table, &ind); diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index c433dd30975a..8e709c9d512c 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -19,13 +19,13 @@ #ifdef HAVE_LIBBPF_SUPPORT -static int epoll_wait_loop(void) +static int epoll_pwait_loop(void) { int i; /* Should fail NR_ITERS times */ for (i = 0; i < NR_ITERS; i++) - epoll_wait(-(i + 1), NULL, 0, 0); + epoll_pwait(-(i + 1), NULL, 0, 0, NULL); return 0; } @@ -63,46 +63,41 @@ static struct { bool pin; } bpf_testcase_table[] = { { - LLVM_TESTCASE_BASE, - "Basic BPF filtering", - "[basic_bpf_test]", - "fix 'perf test LLVM' first", - "load bpf object failed", - &epoll_wait_loop, - (NR_ITERS + 1) / 2, - false, + .prog_id = LLVM_TESTCASE_BASE, + .desc = "Basic BPF filtering", + .name = "[basic_bpf_test]", + .msg_compile_fail = "fix 'perf test LLVM' first", + .msg_load_fail = "load bpf object failed", + .target_func = &epoll_pwait_loop, + .expect_result = (NR_ITERS + 1) / 2, }, { - LLVM_TESTCASE_BASE, - "BPF pinning", - "[bpf_pinning]", - "fix kbuild first", - "check your vmlinux setting?", - &epoll_wait_loop, - (NR_ITERS + 1) / 2, - true, + .prog_id = LLVM_TESTCASE_BASE, + .desc = "BPF pinning", + .name = "[bpf_pinning]", + .msg_compile_fail = "fix kbuild first", + .msg_load_fail = "check your vmlinux setting?", + .target_func = &epoll_pwait_loop, + .expect_result = (NR_ITERS + 1) / 2, + .pin = true, }, #ifdef HAVE_BPF_PROLOGUE { - LLVM_TESTCASE_BPF_PROLOGUE, - "BPF prologue generation", - "[bpf_prologue_test]", - "fix kbuild first", - "check your vmlinux setting?", - &llseek_loop, - (NR_ITERS + 1) / 4, - false, + .prog_id = LLVM_TESTCASE_BPF_PROLOGUE, + .desc = "BPF prologue generation", + .name = "[bpf_prologue_test]", + .msg_compile_fail = "fix kbuild first", + .msg_load_fail = "check your vmlinux setting?", + .target_func = &llseek_loop, + .expect_result = (NR_ITERS + 1) / 4, }, #endif { - LLVM_TESTCASE_BPF_RELOCATION, - "BPF relocation checker", - "[bpf_relocation_test]", - "fix 'perf test LLVM' first", - "libbpf error when dealing with relocation", - NULL, - 0, - false, + .prog_id = LLVM_TESTCASE_BPF_RELOCATION, + .desc = "BPF relocation checker", + .name = "[bpf_relocation_test]", + .msg_compile_fail = "fix 'perf test LLVM' first", + .msg_load_fail = "libbpf error when dealing with relocation", }, }; @@ -190,7 +185,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), } if (count != expect) { - pr_debug("BPF filter result incorrect\n"); + pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count); goto out_delete_evlist; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 68e687d1bf99..28b233c3dcbe 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1960,7 +1960,8 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, if (percent_max <= 0.5) continue; - al->path = get_srcline(map->dso, start + al->offset, NULL, false, true); + al->path = get_srcline(map->dso, start + al->offset, NULL, + false, true, start + al->offset); insert_source_line(&tmp_root, al); } diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 97a8ef9980db..44e603c27944 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1435,6 +1435,11 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) event->context_switch.next_prev_tid); } +static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost); +} + size_t perf_event__fprintf(union perf_event *event, FILE *fp) { size_t ret = fprintf(fp, "PERF_RECORD_%s", @@ -1467,6 +1472,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_SWITCH_CPU_WIDE: ret += perf_event__fprintf_switch(event, fp); break; + case PERF_RECORD_LOST: + ret += perf_event__fprintf_lost(event, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1ae95efbfb95..e5fbd6dd1b01 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -205,6 +205,7 @@ struct perf_sample { u32 flags; u16 insn_len; u8 cpumode; + u16 misc; char insn[MAX_INSN]; void *raw_data; struct ip_callchain *callchain; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 75160666d305..e7fbca69cbac 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -50,6 +50,8 @@ struct perf_evlist { struct perf_evsel *selected; struct events_stats stats; struct perf_env *env; + u64 first_sample_time; + u64 last_sample_time; }; struct perf_evsel_str_handler { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a4d256ea0dc4..d934f04e3110 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1577,6 +1577,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(use_clockid, p_unsigned); PRINT_ATTRf(context_switch, p_unsigned); PRINT_ATTRf(write_backward, p_unsigned); + PRINT_ATTRf(namespaces, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); @@ -2041,6 +2042,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, data->stream_id = data->id = data->time = -1ULL; data->period = evsel->attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + data->misc = event->header.misc; data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index ca73aa7be708..a326e0d8b5b6 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -16,6 +16,7 @@ #include <linux/stringify.h> #include <sys/stat.h> #include <sys/utsname.h> +#include <linux/time64.h> #include "evlist.h" #include "evsel.h" @@ -35,6 +36,7 @@ #include <api/fs/fs.h> #include "asm/bug.h" #include "tool.h" +#include "time-utils.h" #include "sane_ctype.h" @@ -1180,6 +1182,20 @@ static int write_stat(struct feat_fd *ff __maybe_unused, return 0; } +static int write_sample_time(struct feat_fd *ff, + struct perf_evlist *evlist) +{ + int ret; + + ret = do_write(ff, &evlist->first_sample_time, + sizeof(evlist->first_sample_time)); + if (ret < 0) + return ret; + + return do_write(ff, &evlist->last_sample_time, + sizeof(evlist->last_sample_time)); +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1505,6 +1521,28 @@ static void print_group_desc(struct feat_fd *ff, FILE *fp) } } +static void print_sample_time(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + char time_buf[32]; + double d; + + session = container_of(ff->ph, struct perf_session, header); + + timestamp__scnprintf_usec(session->evlist->first_sample_time, + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of first sample : %s\n", time_buf); + + timestamp__scnprintf_usec(session->evlist->last_sample_time, + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of last sample : %s\n", time_buf); + + d = (double)(session->evlist->last_sample_time - + session->evlist->first_sample_time) / NSEC_PER_MSEC; + + fprintf(fp, "# sample duration : %10.3f ms\n", d); +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -2146,6 +2184,27 @@ out_free_caches: return -1; } +static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_session *session; + u64 first_sample_time, last_sample_time; + int ret; + + session = container_of(ff->ph, struct perf_session, header); + + ret = do_read_u64(ff, &first_sample_time); + if (ret) + return -1; + + ret = do_read_u64(ff, &last_sample_time); + if (ret) + return -1; + + session->evlist->first_sample_time = first_sample_time; + session->evlist->last_sample_time = last_sample_time; + return 0; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2203,6 +2262,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(AUXTRACE, auxtrace, false), FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), + FEAT_OPR(SAMPLE_TIME, sample_time, false), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 317fb901e47f..f28aaaa3a440 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -35,6 +35,7 @@ enum { HEADER_AUXTRACE, HEADER_STAT, HEADER_CACHE, + HEADER_SAMPLE_TIME, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 64d255f6a537..b05a67464c03 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1726,7 +1726,7 @@ static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip) bool show_addr = callchain_param.key == CCKEY_ADDRESS; srcline = get_srcline(map->dso, map__rip_2objdump(map, ip), - sym, show_sym, show_addr); + sym, show_sym, show_addr, ip); srcline__tree_insert(&map->dso->srclines, ip, srcline); } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 6d40efd74402..8fe57031e1a8 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -419,7 +419,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { srcline = get_srcline(map->dso, map__rip_2objdump(map, addr), NULL, - true, true); + true, true, addr); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 54e30f1bcbd7..8d0fa2f8da16 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1773,7 +1773,8 @@ done: err = perf_session__flush_thread_stacks(session); out_err: free(buf); - perf_session__warn_about_errors(session); + if (!tool->no_warn) + perf_session__warn_about_errors(session); ordered_events__free(&session->ordered_events); auxtrace__free_events(session); return err; @@ -1929,7 +1930,8 @@ out: err = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); - perf_session__warn_about_errors(session); + if (!tool->no_warn) + perf_session__warn_about_errors(session); /* * We may switching perf.data output, make ordered_events * reusable. diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index a00eacdf02ed..211e7f326b9f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -336,7 +336,7 @@ char *hist_entry__get_srcline(struct hist_entry *he) return SRCLINE_UNKNOWN; return get_srcline(map->dso, map__rip_2objdump(map, he->ip), - he->ms.sym, true, true); + he->ms.sym, true, true, he->ip); } static int64_t @@ -380,7 +380,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, left->branch_info->from.al_addr), left->branch_info->from.sym, - true, true); + true, true, + left->branch_info->from.al_addr); } if (!right->branch_info->srcline_from) { struct map *map = right->branch_info->from.map; @@ -391,7 +392,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, right->branch_info->from.al_addr), right->branch_info->from.sym, - true, true); + true, true, + right->branch_info->from.al_addr); } return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); } @@ -423,7 +425,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, left->branch_info->to.al_addr), left->branch_info->from.sym, - true, true); + true, true, + left->branch_info->to.al_addr); } if (!right->branch_info->srcline_to) { struct map *map = right->branch_info->to.map; @@ -434,7 +437,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, right->branch_info->to.al_addr), right->branch_info->to.sym, - true, true); + true, true, + right->branch_info->to.al_addr); } return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); } @@ -465,7 +469,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e) return no_srcfile; sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip), - e->ms.sym, false, true, true); + e->ms.sym, false, true, true, e->ip); if (!strcmp(sf, SRCLINE_UNKNOWN)) return no_srcfile; p = strchr(sf, ':'); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index d19f05c56de6..3c21fd059b64 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -496,7 +496,8 @@ out: #define A2L_FAIL_LIMIT 123 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool show_addr, bool unwind_inlines) + bool show_sym, bool show_addr, bool unwind_inlines, + u64 ip) { char *file = NULL; unsigned line = 0; @@ -536,7 +537,7 @@ out: if (sym) { if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "", - addr - sym->start) < 0) + ip - sym->start) < 0) return SRCLINE_UNKNOWN; } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0) return SRCLINE_UNKNOWN; @@ -550,9 +551,9 @@ void free_srcline(char *srcline) } char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool show_addr) + bool show_sym, bool show_addr, u64 ip) { - return __get_srcline(dso, addr, sym, show_sym, show_addr, false); + return __get_srcline(dso, addr, sym, show_sym, show_addr, false, ip); } struct srcline_node { diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h index 847b7086182c..b2bb5502fd62 100644 --- a/tools/perf/util/srcline.h +++ b/tools/perf/util/srcline.h @@ -11,9 +11,10 @@ struct symbol; extern bool srcline_full_filename; char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool show_addr); + bool show_sym, bool show_addr, u64 ip); char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool show_addr, bool unwind_inlines); + bool show_sym, bool show_addr, bool unwind_inlines, + u64 ip); void free_srcline(char *srcline); /* insert the srcline into the DSO, which will take ownership */ diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 81927d027417..3f7f18f06982 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -6,6 +6,7 @@ #include <time.h> #include <errno.h> #include <inttypes.h> +#include <math.h> #include "perf.h" #include "debug.h" @@ -60,11 +61,10 @@ static int parse_timestr_sec_nsec(struct perf_time_interval *ptime, return 0; } -int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) +static int split_start_end(char **start, char **end, const char *ostr, char ch) { char *start_str, *end_str; char *d, *str; - int rc = 0; if (ostr == NULL || *ostr == '\0') return 0; @@ -74,25 +74,35 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) if (str == NULL) return -ENOMEM; - ptime->start = 0; - ptime->end = 0; - - /* str has the format: <start>,<stop> - * variations: <start>, - * ,<stop> - * , - */ start_str = str; - d = strchr(start_str, ','); + d = strchr(start_str, ch); if (d) { *d = '\0'; ++d; } end_str = d; + *start = start_str; + *end = end_str; + + return 0; +} + +int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) +{ + char *start_str = NULL, *end_str; + int rc; + + rc = split_start_end(&start_str, &end_str, ostr, ','); + if (rc || !start_str) + return rc; + + ptime->start = 0; + ptime->end = 0; + rc = parse_timestr_sec_nsec(ptime, start_str, end_str); - free(str); + free(start_str); /* make sure end time is after start time if it was given */ if (rc == 0 && ptime->end && ptime->end < ptime->start) @@ -104,6 +114,177 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) return rc; } +static int parse_percent(double *pcnt, char *str) +{ + char *c; + + c = strchr(str, '%'); + if (c) + *c = '\0'; + else + return -1; + + *pcnt = atof(str) / 100.0; + + return 0; +} + +static int percent_slash_split(char *str, struct perf_time_interval *ptime, + u64 start, u64 end) +{ + char *p, *end_str; + double pcnt, start_pcnt, end_pcnt; + u64 total = end - start; + int i; + + /* + * Example: + * 10%/2: select the second 10% slice and the third 10% slice + */ + + /* We can modify this string since the original one is copied */ + p = strchr(str, '/'); + if (!p) + return -1; + + *p = '\0'; + if (parse_percent(&pcnt, str) < 0) + return -1; + + p++; + i = (int)strtol(p, &end_str, 10); + if (*end_str) + return -1; + + if (pcnt <= 0.0) + return -1; + + start_pcnt = pcnt * (i - 1); + end_pcnt = pcnt * i; + + if (start_pcnt < 0.0 || start_pcnt > 1.0 || + end_pcnt < 0.0 || end_pcnt > 1.0) { + return -1; + } + + ptime->start = start + round(start_pcnt * total); + ptime->end = start + round(end_pcnt * total); + + return 0; +} + +static int percent_dash_split(char *str, struct perf_time_interval *ptime, + u64 start, u64 end) +{ + char *start_str = NULL, *end_str; + double start_pcnt, end_pcnt; + u64 total = end - start; + int ret; + + /* + * Example: 0%-10% + */ + + ret = split_start_end(&start_str, &end_str, str, '-'); + if (ret || !start_str) + return ret; + + if ((parse_percent(&start_pcnt, start_str) != 0) || + (parse_percent(&end_pcnt, end_str) != 0)) { + free(start_str); + return -1; + } + + free(start_str); + + if (start_pcnt < 0.0 || start_pcnt > 1.0 || + end_pcnt < 0.0 || end_pcnt > 1.0 || + start_pcnt > end_pcnt) { + return -1; + } + + ptime->start = start + round(start_pcnt * total); + ptime->end = start + round(end_pcnt * total); + + return 0; +} + +typedef int (*time_pecent_split)(char *, struct perf_time_interval *, + u64 start, u64 end); + +static int percent_comma_split(struct perf_time_interval *ptime_buf, int num, + const char *ostr, u64 start, u64 end, + time_pecent_split func) +{ + char *str, *p1, *p2; + int len, ret, i = 0; + + str = strdup(ostr); + if (str == NULL) + return -ENOMEM; + + len = strlen(str); + p1 = str; + + while (p1 < str + len) { + if (i >= num) { + free(str); + return -1; + } + + p2 = strchr(p1, ','); + if (p2) + *p2 = '\0'; + + ret = (func)(p1, &ptime_buf[i], start, end); + if (ret < 0) { + free(str); + return -1; + } + + pr_debug("start time %d: %" PRIu64 ", ", i, ptime_buf[i].start); + pr_debug("end time %d: %" PRIu64 "\n", i, ptime_buf[i].end); + + i++; + + if (p2) + p1 = p2 + 1; + else + break; + } + + free(str); + return i; +} + +int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num, + const char *ostr, u64 start, u64 end) +{ + char *c; + + /* + * ostr example: + * 10%/2,10%/3: select the second 10% slice and the third 10% slice + * 0%-10%,30%-40%: multiple time range + */ + + memset(ptime_buf, 0, sizeof(*ptime_buf) * num); + + c = strchr(ostr, '/'); + if (c) { + return percent_comma_split(ptime_buf, num, ostr, start, + end, percent_slash_split); + } + + c = strchr(ostr, '-'); + if (c) { + return percent_comma_split(ptime_buf, num, ostr, start, + end, percent_dash_split); + } + + return -1; +} + bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp) { /* if time is not set don't drop sample */ @@ -119,6 +300,34 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp) return false; } +bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, + int num, u64 timestamp) +{ + struct perf_time_interval *ptime; + int i; + + if ((timestamp == 0) || (num == 0)) + return false; + + if (num == 1) + return perf_time__skip_sample(&ptime_buf[0], timestamp); + + /* + * start/end of multiple time ranges must be valid. + */ + for (i = 0; i < num; i++) { + ptime = &ptime_buf[i]; + + if (timestamp >= ptime->start && + ((timestamp < ptime->end && i < num - 1) || + (timestamp <= ptime->end && i == num - 1))) { + break; + } + } + + return (i == num) ? true : false; +} + int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) { u64 sec = timestamp / NSEC_PER_SEC; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index 15b475c50ccf..34d5eba26bf5 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -13,8 +13,14 @@ int parse_nsec_time(const char *str, u64 *ptime); int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr); +int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num, + const char *ostr, u64 start, u64 end); + bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp); +bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, + int num, u64 timestamp); + int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); int fetch_current_timestamp(char *buf, size_t sz); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 2532b558099b..183c91453522 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -76,6 +76,7 @@ struct perf_tool { bool ordered_events; bool ordering_requires_timestamps; bool namespace_events; + bool no_warn; enum show_feature_header show_feat_hdr; }; |
