diff options
Diffstat (limited to 'tools/perf/util')
96 files changed, 3546 insertions, 1566 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8dcfca1a882f..b8e05a147b2b 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,4 +1,5 @@ perf-y += annotate.o +perf-y += block-info.o perf-y += block-range.o perf-y += build-id.o perf-y += cacheline.o @@ -95,6 +96,7 @@ perf-y += cloexec.o perf-y += call-path.o perf-y += rwsem.o perf-y += thread-stack.o +perf-y += spark.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ perf-$(CONFIG_AUXTRACE) += intel-pt.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e830eadfca2a..5ea9a4534848 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -43,6 +43,7 @@ #include <linux/string.h> #include <bpf/libbpf.h> #include <subcmd/parse-options.h> +#include <subcmd/run-command.h> /* FIXME: For the HE_COLORSET */ #include "ui/browser.h" @@ -242,7 +243,7 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s char *endptr, *tok, *name; struct map *map = ms->map; struct addr_map_symbol target = { - .map = map, + .ms = { .map = map, }, }; ops->target.addr = strtoull(ops->raw, &endptr, 16); @@ -270,9 +271,9 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s find_target: target.addr = map__objdump_2mem(map, ops->target.addr); - if (map_groups__find_ams(&target) == 0 && - map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) - ops->target.sym = target.sym; + if (map_groups__find_ams(ms->mg, &target) == 0 && + map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; return 0; @@ -331,7 +332,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s struct map *map = ms->map; struct symbol *sym = ms->sym; struct addr_map_symbol target = { - .map = map, + .ms = { .map = map, }, }; const char *c = strchr(ops->raw, ','); u64 start, end; @@ -390,9 +391,9 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * Actual navigation will come next, with further understanding of how * the symbol searching and disassembly should be done. */ - if (map_groups__find_ams(&target) == 0 && - map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) - ops->target.sym = target.sym; + if (map_groups__find_ams(ms->mg, &target) == 0 && + map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; if (!ops->target.outside) { ops->target.offset = target.addr - start; @@ -853,6 +854,10 @@ static int __symbol__account_cycles(struct cyc_hist *ch, ch[offset].start < start) return 0; } + + if (ch[offset].num < NUM_SPARKS) + ch[offset].cycles_spark[ch[offset].num] = cycles; + ch[offset].have_start = have_start; ch[offset].start = start; ch[offset].cycles += cycles; @@ -860,14 +865,15 @@ static int __symbol__account_cycles(struct cyc_hist *ch, return 0; } -static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, +static int __symbol__inc_addr_samples(struct map_symbol *ms, struct annotated_source *src, int evidx, u64 addr, struct perf_sample *sample) { + struct symbol *sym = ms->sym; unsigned offset; struct sym_hist *h; - pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); + pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, ms->map->unmap_ip(ms->map, addr)); if ((addr < sym->start || addr >= sym->end) && (addr != sym->end || sym->start != sym->end)) { @@ -934,17 +940,17 @@ alloc_histograms: return notes->src; } -static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, +static int symbol__inc_addr_samples(struct map_symbol *ms, struct evsel *evsel, u64 addr, struct perf_sample *sample) { + struct symbol *sym = ms->sym; struct annotated_source *src; if (sym == NULL) return 0; src = symbol__hists(sym, evsel->evlist->core.nr_entries); - return (src) ? __symbol__inc_addr_samples(sym, map, src, evsel->idx, - addr, sample) : 0; + return src ? __symbol__inc_addr_samples(ms, src, evsel->idx, addr, sample) : 0; } static int symbol__account_cycles(u64 addr, u64 start, @@ -992,17 +998,17 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, * it starts on the function start. */ if (start && - (start->sym == ams->sym || - (ams->sym && - start->addr == ams->sym->start + ams->map->start))) + (start->ms.sym == ams->ms.sym || + (ams->ms.sym && + start->addr == ams->ms.sym->start + ams->ms.map->start))) saddr = start->al_addr; if (saddr == 0) pr_debug2("BB with bad start: addr %"PRIx64" start %"PRIx64" sym %"PRIx64" saddr %"PRIx64"\n", ams->addr, start ? start->addr : 0, - ams->sym ? ams->sym->start + ams->map->start : 0, + ams->ms.sym ? ams->ms.sym->start + ams->ms.map->start : 0, saddr); - err = symbol__account_cycles(ams->al_addr, saddr, ams->sym, cycles); + err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles); if (err) pr_debug2("account_cycles failed %d\n", err); return err; @@ -1088,13 +1094,13 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, struct evsel *evsel) { - return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample); + return symbol__inc_addr_samples(&ams->ms, evsel, ams->al_addr, sample); } int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, struct evsel *evsel, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample); + return symbol__inc_addr_samples(&he->ms, evsel, ip, sample); } static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) @@ -1485,44 +1491,26 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start * means that it's not a disassembly line so should be treated differently. * The ops.raw part will be parsed further according to type of the instruction. */ -static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, +static int symbol__parse_objdump_line(struct symbol *sym, struct annotate_args *args, - int *line_nr) + char *parsed_line, int *line_nr) { struct map *map = args->ms.map; struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; - char *line = NULL, *parsed_line, *tmp, *tmp2; - size_t line_len; + char *tmp; s64 line_ip, offset = -1; regmatch_t match[2]; - if (getline(&line, &line_len, file) < 0) - return -1; - - if (!line) - return -1; - - line_ip = -1; - parsed_line = strim(line); - /* /filename:linenr ? Save line number and ignore. */ if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) { *line_nr = atoi(parsed_line + match[1].rm_so); return 0; } - tmp = skip_spaces(parsed_line); - if (*tmp) { - /* - * Parse hexa addresses followed by ':' - */ - line_ip = strtoull(tmp, &tmp2, 16); - if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') - line_ip = -1; - } - - if (line_ip != -1) { + /* Process hex address followed by ':'. */ + line_ip = strtoull(parsed_line, &tmp, 16); + if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') { u64 start = map__rip_2objdump(map, sym->start), end = map__rip_2objdump(map, sym->end); @@ -1530,7 +1518,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, if ((u64)line_ip < start || (u64)line_ip >= end) offset = -1; else - parsed_line = tmp2 + 1; + parsed_line = tmp + 1; } args->offset = offset; @@ -1539,7 +1527,6 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, args->ms.sym = sym; dl = disasm_line__new(args); - free(line); (*line_nr)++; if (dl == NULL) @@ -1554,13 +1541,13 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, /* kcore has no symbols, so add the call target symbol */ if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) { struct addr_map_symbol target = { - .map = map, .addr = dl->ops.target.addr, + .ms = { .map = map, }, }; - if (!map_groups__find_ams(&target) && - target.sym->start == target.al_addr) - dl->ops.target.sym = target.sym; + if (!map_groups__find_ams(args->ms.mg, &target) && + target.ms.sym->start == target.al_addr) + dl->ops.target.sym = target.ms.sym; } annotation_line__add(&dl->al, ¬es->src->source); @@ -1597,10 +1584,9 @@ static void delete_last_nop(struct symbol *sym) } } -int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *map, - int errnum, char *buf, size_t buflen) +int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; BUG_ON(buflen == 0); @@ -1631,6 +1617,19 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map * case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF: scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation"); break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP: + scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions."); + break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING: + scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization."); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE: + scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF: + scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.", + dso->long_name); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -1662,7 +1661,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil build_id_path = strdup(filename); if (!build_id_path) - return -1; + return ENOMEM; /* * old style build-id cache has name of XX/XXXXXXX.. while @@ -1713,13 +1712,13 @@ static int symbol__disassemble_bpf(struct symbol *sym, char tpath[PATH_MAX]; size_t buf_size; int nr_skip = 0; - int ret = -1; char *buf; bfd *bfdf; + int ret; FILE *s; if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) - return -1; + return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, sym->name, sym->start, sym->end - sym->start); @@ -1732,8 +1731,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, assert(bfd_check_format(bfdf, bfd_object)); s = open_memstream(&buf, &buf_size); - if (!s) + if (!s) { + ret = errno; goto out; + } init_disassemble_info(&info, s, (fprintf_ftype) fprintf); @@ -1742,8 +1743,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id); - if (!info_node) + if (!info_node) { + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; goto out; + } info_linear = info_node->info_linear; sub_id = dso->bpf_prog.sub_id; @@ -1840,6 +1843,67 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, } #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +/* + * Possibly create a new version of line with tabs expanded. Returns the + * existing or new line, storage is updated if a new line is allocated. If + * allocation fails then NULL is returned. + */ +static char *expand_tabs(char *line, char **storage, size_t *storage_len) +{ + size_t i, src, dst, len, new_storage_len, num_tabs; + char *new_line; + size_t line_len = strlen(line); + + for (num_tabs = 0, i = 0; i < line_len; i++) + if (line[i] == '\t') + num_tabs++; + + if (num_tabs == 0) + return line; + + /* + * Space for the line and '\0', less the leading and trailing + * spaces. Each tab may introduce 7 additional spaces. + */ + new_storage_len = line_len + 1 + (num_tabs * 7); + + new_line = malloc(new_storage_len); + if (new_line == NULL) { + pr_err("Failure allocating memory for tab expansion\n"); + return NULL; + } + + /* + * Copy regions starting at src and expand tabs. If there are two + * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces + * are inserted. + */ + for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) { + if (line[i] == '\t') { + len = i - src; + memcpy(&new_line[dst], &line[src], len); + dst += len; + new_line[dst++] = ' '; + while (dst % 8 != 0) + new_line[dst++] = ' '; + src = i + 1; + num_tabs--; + } + } + + /* Expand the last region. */ + len = line_len - src; + memcpy(&new_line[dst], &line[src], len); + dst += len; + new_line[dst] = '\0'; + + free(*storage); + *storage = new_line; + *storage_len = new_storage_len; + return new_line; + +} + static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *opts = args->options; @@ -1851,10 +1915,19 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) struct kcore_extract kce; bool delete_extract = false; bool decomp = false; - int stdout_fd[2]; int lineno = 0; int nline; - pid_t pid; + char *line; + size_t line_len; + const char *objdump_argv[] = { + "/bin/sh", + "-c", + NULL, /* Will be the objdump command to run. */ + "--", + NULL, /* Will be the symfs path. */ + NULL, + }; + struct child_process objdump_process; int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); if (err) @@ -1884,7 +1957,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) if (dso__decompress_kmodule_path(dso, symfs_filename, tmp, sizeof(tmp)) < 0) - goto out; + return -1; decomp = true; strcpy(symfs_filename, tmp); @@ -1893,13 +1966,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand", + " -l -d %s %s -C \"$1\"", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), - opts->show_asm_raw ? "" : "--no-show-raw", + opts->show_asm_raw ? "" : "--no-show-raw-insn", opts->annotate_src ? "-S" : ""); if (err < 0) { @@ -1909,55 +1982,73 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) pr_debug("Executing: %s\n", command); - err = -1; - if (pipe(stdout_fd) < 0) { - pr_err("Failure creating the pipe to run %s\n", command); - goto out_free_command; - } - - pid = fork(); - if (pid < 0) { - pr_err("Failure forking to run %s\n", command); - goto out_close_stdout; - } + objdump_argv[2] = command; + objdump_argv[4] = symfs_filename; - if (pid == 0) { - close(stdout_fd[0]); - dup2(stdout_fd[1], 1); - close(stdout_fd[1]); - execl("/bin/sh", "sh", "-c", command, "--", symfs_filename, - NULL); - perror(command); - exit(-1); + /* Create a pipe to read from for stdout */ + memset(&objdump_process, 0, sizeof(objdump_process)); + objdump_process.argv = objdump_argv; + objdump_process.out = -1; + if (start_command(&objdump_process)) { + pr_err("Failure starting to run %s\n", command); + err = -1; + goto out_free_command; } - close(stdout_fd[1]); - - file = fdopen(stdout_fd[0], "r"); + file = fdopen(objdump_process.out, "r"); if (!file) { pr_err("Failure creating FILE stream for %s\n", command); /* * If we were using debug info should retry with * original binary. */ - goto out_free_command; + err = -1; + goto out_close_stdout; } + /* Storage for getline. */ + line = NULL; + line_len = 0; + nline = 0; while (!feof(file)) { + const char *match; + char *expanded_line; + + if (getline(&line, &line_len, file) < 0 || !line) + break; + + /* Skip lines containing "filename:" */ + match = strstr(line, symfs_filename); + if (match && match[strlen(symfs_filename)] == ':') + continue; + + expanded_line = strim(line); + expanded_line = expand_tabs(expanded_line, &line, &line_len); + if (!expanded_line) + break; + /* * The source code line number (lineno) needs to be kept in * across calls to symbol__parse_objdump_line(), so that it * can associate it with the instructions till the next one. * See disasm_line__new() and struct disasm_line::line_nr. */ - if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0) + if (symbol__parse_objdump_line(sym, args, expanded_line, + &lineno) < 0) break; nline++; } + free(line); - if (nline == 0) + err = finish_command(&objdump_process); + if (err) + pr_err("Error running %s\n", command); + + if (nline == 0) { + err = -1; pr_err("No output from %s\n", command); + } /* * kallsyms does not have symbol sizes so there may a nop at the end. @@ -1967,23 +2058,21 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) delete_last_nop(sym); fclose(file); - err = 0; + +out_close_stdout: + close(objdump_process.out); + out_free_command: free(command); -out_remove_tmp: - close(stdout_fd[0]); +out_remove_tmp: if (decomp) unlink(symfs_filename); if (delete_extract) kcore_extract__delete(&kce); -out: - return err; -out_close_stdout: - close(stdout_fd[1]); - goto out_free_command; + return err; } static void calc_percent(struct sym_hist *sym_hist, @@ -2054,11 +2143,10 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) annotation__calc_percent(notes, evsel, symbol__size(sym)); } -int symbol__annotate(struct symbol *sym, struct map *map, - struct evsel *evsel, size_t privsize, - struct annotation_options *options, - struct arch **parch) +int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch) { + struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { .privsize = privsize, @@ -2071,11 +2159,11 @@ int symbol__annotate(struct symbol *sym, struct map *map, int err; if (!arch_name) - return -1; + return errno; args.arch = arch = arch__find(arch_name); if (arch == NULL) - return -ENOTSUP; + return ENOTSUP; if (parch) *parch = arch; @@ -2088,9 +2176,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, } } - args.ms.map = map; - args.ms.sym = sym; - notes->start = map__rip_2objdump(map, sym->start); + args.ms = *ms; + notes->start = map__rip_2objdump(ms->map, sym->start); return symbol__disassemble(sym, &args); } @@ -2246,10 +2333,11 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) return 0; } -int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct evsel *evsel, +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { + struct map *map = ms->map; + struct symbol *sym = ms->sym; struct dso *dso = map->dso; char *filename; const char *d_filename; @@ -2653,30 +2741,29 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, resort_source_line(root, &tmp_root); } -static void symbol__calc_lines(struct symbol *sym, struct map *map, - struct rb_root *root, +static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root, struct annotation_options *opts) { - struct annotation *notes = symbol__annotation(sym); + struct annotation *notes = symbol__annotation(ms->sym); - annotation__calc_lines(notes, map, root, opts); + annotation__calc_lines(notes, ms->map, root, opts); } -int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct evsel *evsel, +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; + struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; struct hists *hists = evsel__hists(evsel); char buf[1024]; - if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0) + if (symbol__annotate2(ms, evsel, opts, NULL) < 0) return -1; if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line, opts); + symbol__calc_lines(ms, &source_line, opts); print_summary(&source_line, dso->long_name); } @@ -2690,25 +2777,25 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, return 0; } -int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct evsel *evsel, +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; + struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(sym, map, evsel, 0, opts, NULL) < 0) + if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line, opts); + symbol__calc_lines(ms, &source_line, opts); print_summary(&source_line, dso->long_name); } - symbol__annotate_printf(sym, map, evsel, opts); + symbol__annotate_printf(ms, evsel, opts); annotated_source__purge(symbol__annotation(sym)->src); @@ -2962,21 +3049,22 @@ void annotation_line__write(struct annotation_line *al, struct annotation *notes wops->write_graph); } -int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel, +int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct arch **parch) { + struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); size_t size = symbol__size(sym); int nr_pcnt = 1, err; notes->offsets = zalloc(size * sizeof(struct annotation_line *)); if (notes->offsets == NULL) - return -1; + return ENOMEM; if (perf_evsel__is_group_event(evsel)) nr_pcnt = evsel->core.nr_members; - err = symbol__annotate(sym, map, evsel, 0, options, parch); + err = symbol__annotate(ms, evsel, 0, options, parch); if (err) goto out_free_offsets; @@ -2997,7 +3085,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel, out_free_offsets: zfree(¬es->offsets); - return -1; + return err; } #define ANNOTATION__CFG(n) \ diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index d94be9140e31..7075d98f69d9 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -11,6 +11,7 @@ #include <pthread.h> #include <asm/bug.h> #include "symbol_conf.h" +#include "spark.h" struct hist_browser_timer; struct hist_entry; @@ -235,6 +236,7 @@ struct cyc_hist { u64 cycles_aggr; u64 cycles_max; u64 cycles_min; + s64 cycles_spark[NUM_SPARKS]; u32 num; u32 num_aggr; u8 have_start; @@ -347,11 +349,11 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__annotate(struct symbol *sym, struct map *map, +int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize, struct annotation_options *options, struct arch **parch); -int symbol__annotate2(struct symbol *sym, struct map *map, +int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct arch **parch); @@ -370,15 +372,17 @@ enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START, SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP, + SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE, + SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF, __SYMBOL_ANNOTATE_ERRNO__END, }; -int symbol__strerror_disassemble(struct symbol *sym, struct map *map, - int errnum, char *buf, size_t buflen); +int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); -int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct evsel *evsel, +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); @@ -389,20 +393,16 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, bool ui__has_annotation(void); -int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); -int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); #ifdef HAVE_SLANG_SUPPORT -int symbol__tui_annotate(struct symbol *sym, struct map *map, - struct evsel *evsel, +int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts); #else -static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, - struct map *map __maybe_unused, +static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *opts __maybe_unused) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 8470dfe9fe97..eb087e7df6f4 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -31,6 +31,7 @@ #include "map.h" #include "pmu.h" #include "evsel.h" +#include "evsel_config.h" #include "symbol.h" #include "util/synthetic-events.h" #include "thread_map.h" @@ -57,6 +58,72 @@ #include "symbol/kallsyms.h" #include <internal/lib.h> +static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel) +{ + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (pmu->type == evsel->core.attr.type) + break; + } + + return pmu; +} + +static bool perf_evsel__is_aux_event(struct evsel *evsel) +{ + struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); + + return pmu && pmu->auxtrace; +} + +/* + * Make a group from 'leader' to 'last', requiring that the events were not + * already grouped to a different leader. + */ +static int perf_evlist__regroup(struct evlist *evlist, + struct evsel *leader, + struct evsel *last) +{ + struct evsel *evsel; + bool grp; + + if (!perf_evsel__is_group_leader(leader)) + return -EINVAL; + + grp = false; + evlist__for_each_entry(evlist, evsel) { + if (grp) { + if (!(evsel->leader == leader || + (evsel->leader == evsel && + evsel->core.nr_members <= 1))) + return -EINVAL; + } else if (evsel == leader) { + grp = true; + } + if (evsel == last) + break; + } + + grp = false; + evlist__for_each_entry(evlist, evsel) { + if (grp) { + if (evsel->leader != leader) { + evsel->leader = leader; + if (leader->core.nr_members < 1) + leader->core.nr_members = 1; + leader->core.nr_members += 1; + } + } else if (evsel == leader) { + grp = true; + } + if (evsel == last) + break; + } + + return 0; +} + static bool auxtrace__dont_decode(struct perf_session *session) { return !session->itrace_synth_opts || @@ -597,6 +664,132 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, return -EINVAL; } +/* + * Event record size is 16-bit which results in a maximum size of about 64KiB. + * Allow about 4KiB for the rest of the sample record, to give a maximum + * AUX area sample size of 60KiB. + */ +#define MAX_AUX_SAMPLE_SIZE (60 * 1024) + +/* Arbitrary default size if no other default provided */ +#define DEFAULT_AUX_SAMPLE_SIZE (4 * 1024) + +static int auxtrace_validate_aux_sample_size(struct evlist *evlist, + struct record_opts *opts) +{ + struct evsel *evsel; + bool has_aux_leader = false; + u32 sz; + + evlist__for_each_entry(evlist, evsel) { + sz = evsel->core.attr.aux_sample_size; + if (perf_evsel__is_group_leader(evsel)) { + has_aux_leader = perf_evsel__is_aux_event(evsel); + if (sz) { + if (has_aux_leader) + pr_err("Cannot add AUX area sampling to an AUX area event\n"); + else + pr_err("Cannot add AUX area sampling to a group leader\n"); + return -EINVAL; + } + } + if (sz > MAX_AUX_SAMPLE_SIZE) { + pr_err("AUX area sample size %u too big, max. %d\n", + sz, MAX_AUX_SAMPLE_SIZE); + return -EINVAL; + } + if (sz) { + if (!has_aux_leader) { + pr_err("Cannot add AUX area sampling because group leader is not an AUX area event\n"); + return -EINVAL; + } + perf_evsel__set_sample_bit(evsel, AUX); + opts->auxtrace_sample_mode = true; + } else { + perf_evsel__reset_sample_bit(evsel, AUX); + } + } + + if (!opts->auxtrace_sample_mode) { + pr_err("AUX area sampling requires an AUX area event group leader plus other events to which to add samples\n"); + return -EINVAL; + } + + if (!perf_can_aux_sample()) { + pr_err("AUX area sampling is not supported by kernel\n"); + return -EINVAL; + } + + return 0; +} + +int auxtrace_parse_sample_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts, const char *str) +{ + struct perf_evsel_config_term *term; + struct evsel *aux_evsel; + bool has_aux_sample_size = false; + bool has_aux_leader = false; + struct evsel *evsel; + char *endptr; + unsigned long sz; + + if (!str) + goto no_opt; + + if (!itr) { + pr_err("No AUX area event to sample\n"); + return -EINVAL; + } + + sz = strtoul(str, &endptr, 0); + if (*endptr || sz > UINT_MAX) { + pr_err("Bad AUX area sampling option: '%s'\n", str); + return -EINVAL; + } + + if (!sz) + sz = itr->default_aux_sample_size; + + if (!sz) + sz = DEFAULT_AUX_SAMPLE_SIZE; + + /* Set aux_sample_size based on --aux-sample option */ + evlist__for_each_entry(evlist, evsel) { + if (perf_evsel__is_group_leader(evsel)) { + has_aux_leader = perf_evsel__is_aux_event(evsel); + } else if (has_aux_leader) { + evsel->core.attr.aux_sample_size = sz; + } + } +no_opt: + aux_evsel = NULL; + /* Override with aux_sample_size from config term */ + evlist__for_each_entry(evlist, evsel) { + if (perf_evsel__is_aux_event(evsel)) + aux_evsel = evsel; + term = perf_evsel__get_config_term(evsel, AUX_SAMPLE_SIZE); + if (term) { + has_aux_sample_size = true; + evsel->core.attr.aux_sample_size = term->val.aux_sample_size; + /* If possible, group with the AUX event */ + if (aux_evsel && evsel->core.attr.aux_sample_size) + perf_evlist__regroup(evlist, aux_evsel, evsel); + } + } + + if (!str && !has_aux_sample_size) + return 0; + + if (!itr) { + pr_err("No AUX area event to sample\n"); + return -EINVAL; + } + + return auxtrace_validate_aux_sample_size(evlist, opts); +} + struct auxtrace_record *__weak auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err) { @@ -811,6 +1004,113 @@ struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue, } } +struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *queues, + struct perf_sample *sample, + struct perf_session *session) +{ + struct perf_sample_id *sid; + unsigned int idx; + u64 id; + + id = sample->id; + if (!id) + return NULL; + + sid = perf_evlist__id2sid(session->evlist, id); + if (!sid) + return NULL; + + idx = sid->idx; + + if (idx >= queues->nr_queues) + return NULL; + + return &queues->queue_array[idx]; +} + +int auxtrace_queues__add_sample(struct auxtrace_queues *queues, + struct perf_session *session, + struct perf_sample *sample, u64 data_offset, + u64 reference) +{ + struct auxtrace_buffer buffer = { + .pid = -1, + .data_offset = data_offset, + .reference = reference, + .size = sample->aux_sample.size, + }; + struct perf_sample_id *sid; + u64 id = sample->id; + unsigned int idx; + + if (!id) + return -EINVAL; + + sid = perf_evlist__id2sid(session->evlist, id); + if (!sid) + return -ENOENT; + + idx = sid->idx; + buffer.tid = sid->tid; + buffer.cpu = sid->cpu; + + return auxtrace_queues__add_buffer(queues, session, idx, &buffer, NULL); +} + +struct queue_data { + bool samples; + bool events; +}; + +static int auxtrace_queue_data_cb(struct perf_session *session, + union perf_event *event, u64 offset, + void *data) +{ + struct queue_data *qd = data; + struct perf_sample sample; + int err; + + if (qd->events && event->header.type == PERF_RECORD_AUXTRACE) { + if (event->header.size < sizeof(struct perf_record_auxtrace)) + return -EINVAL; + offset += event->header.size; + return session->auxtrace->queue_data(session, NULL, event, + offset); + } + + if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) + return 0; + + err = perf_evlist__parse_sample(session->evlist, event, &sample); + if (err) + return err; + + if (!sample.aux_sample.size) + return 0; + + offset += sample.aux_sample.data - (void *)event; + + return session->auxtrace->queue_data(session, &sample, NULL, offset); +} + +int auxtrace_queue_data(struct perf_session *session, bool samples, bool events) +{ + struct queue_data qd = { + .samples = samples, + .events = events, + }; + + if (auxtrace__dont_decode(session)) + return 0; + + if (!session->auxtrace || !session->auxtrace->queue_data) + return -EINVAL; + + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + auxtrace_queue_data_cb, &qd); +} + void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd) { size_t adj = buffer->data_offset & (page_size - 1); @@ -1457,6 +1757,34 @@ int auxtrace_cache__add(struct auxtrace_cache *c, u32 key, return 0; } +static struct auxtrace_cache_entry *auxtrace_cache__rm(struct auxtrace_cache *c, + u32 key) +{ + struct auxtrace_cache_entry *entry; + struct hlist_head *hlist; + struct hlist_node *n; + + if (!c) + return NULL; + + hlist = &c->hashtable[hash_32(key, c->bits)]; + hlist_for_each_entry_safe(entry, n, hlist, hash) { + if (entry->key == key) { + hlist_del(&entry->hash); + return entry; + } + } + + return NULL; +} + +void auxtrace_cache__remove(struct auxtrace_cache *c, u32 key) +{ + struct auxtrace_cache_entry *entry = auxtrace_cache__rm(c, key); + + auxtrace_cache__free_entry(c, entry); +} + void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key) { struct auxtrace_cache_entry *entry; @@ -2152,18 +2480,6 @@ out_exit: return err; } -static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel) -{ - struct perf_pmu *pmu = NULL; - - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - if (pmu->type == evsel->core.attr.type) - break; - } - - return pmu; -} - static int perf_evsel__nr_addr_filter(struct evsel *evsel) { struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); @@ -2208,6 +2524,16 @@ int auxtrace__process_event(struct perf_session *session, union perf_event *even return session->auxtrace->process_event(session, event, sample, tool); } +void auxtrace__dump_auxtrace_sample(struct perf_session *session, + struct perf_sample *sample) +{ + if (!session->auxtrace || !session->auxtrace->dump_auxtrace_sample || + auxtrace__dont_decode(session)) + return; + + session->auxtrace->dump_auxtrace_sample(session, sample); +} + int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool) { if (!session->auxtrace) diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index f201f36bc35f..749d72cd9c7b 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -141,6 +141,9 @@ struct auxtrace_index { * struct auxtrace - session callbacks to allow AUX area data decoding. * @process_event: lets the decoder see all session events * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event + * @queue_data: queue an AUX sample or PERF_RECORD_AUXTRACE event for later + * processing + * @dump_auxtrace_sample: dump AUX area sample data * @flush_events: process any remaining data * @free_events: free resources associated with event processing * @free: free resources associated with the session @@ -153,6 +156,11 @@ struct auxtrace { int (*process_auxtrace_event)(struct perf_session *session, union perf_event *event, struct perf_tool *tool); + int (*queue_data)(struct perf_session *session, + struct perf_sample *sample, union perf_event *event, + u64 data_offset); + void (*dump_auxtrace_sample)(struct perf_session *session, + struct perf_sample *sample); int (*flush_events)(struct perf_session *session, struct perf_tool *tool); void (*free_events)(struct perf_session *session); @@ -313,6 +321,7 @@ struct auxtrace_mmap_params { * @reference: provide a 64-bit reference number for auxtrace_event * @read_finish: called after reading from an auxtrace mmap * @alignment: alignment (if any) for AUX area data + * @default_aux_sample_size: default sample size for --aux sample option */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, @@ -336,6 +345,7 @@ struct auxtrace_record { u64 (*reference)(struct auxtrace_record *itr); int (*read_finish)(struct auxtrace_record *itr, int idx); unsigned int alignment; + unsigned int default_aux_sample_size; }; /** @@ -462,9 +472,19 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct perf_session *session, union perf_event *event, off_t data_offset, struct auxtrace_buffer **buffer_ptr); +struct auxtrace_queue * +auxtrace_queues__sample_queue(struct auxtrace_queues *queues, + struct perf_sample *sample, + struct perf_session *session); +int auxtrace_queues__add_sample(struct auxtrace_queues *queues, + struct perf_session *session, + struct perf_sample *sample, u64 data_offset, + u64 reference); void auxtrace_queues__free(struct auxtrace_queues *queues); int auxtrace_queues__process_index(struct auxtrace_queues *queues, struct perf_session *session); +int auxtrace_queue_data(struct perf_session *session, bool samples, + bool events); struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue, struct auxtrace_buffer *buffer); void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd); @@ -489,6 +509,7 @@ void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c); void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry); int auxtrace_cache__add(struct auxtrace_cache *c, u32 key, struct auxtrace_cache_entry *entry); +void auxtrace_cache__remove(struct auxtrace_cache *c, u32 key); void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key); struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, @@ -497,6 +518,9 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, struct record_opts *opts, const char *str); +int auxtrace_parse_sample_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts, const char *str); int auxtrace_record__options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts); @@ -549,6 +573,8 @@ int auxtrace_parse_filters(struct evlist *evlist); int auxtrace__process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool); +void auxtrace__dump_auxtrace_sample(struct perf_session *session, + struct perf_sample *sample); int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool); void auxtrace__free_events(struct perf_session *session); void auxtrace__free(struct perf_session *session); @@ -648,6 +674,18 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, } static inline +int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused, + struct evlist *evlist __maybe_unused, + struct record_opts *opts __maybe_unused, + const char *str) +{ + if (!str) + return 0; + pr_err("AUX area tracing not supported\n"); + return -EINVAL; +} + +static inline int auxtrace__process_event(struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, @@ -657,6 +695,12 @@ int auxtrace__process_event(struct perf_session *session __maybe_unused, } static inline +void auxtrace__dump_auxtrace_sample(struct perf_session *session __maybe_unused, + struct perf_sample *sample __maybe_unused) +{ +} + +static inline int auxtrace__flush_events(struct perf_session *session __maybe_unused, struct perf_tool *tool __maybe_unused) { diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c new file mode 100644 index 000000000000..c4b030bf6ec2 --- /dev/null +++ b/tools/perf/util/block-info.c @@ -0,0 +1,477 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdlib.h> +#include <string.h> +#include <linux/zalloc.h> +#include "block-info.h" +#include "sort.h" +#include "annotate.h" +#include "symbol.h" +#include "dso.h" +#include "map.h" +#include "srcline.h" +#include "evlist.h" +#include "hist.h" +#include "ui/browsers/hists.h" + +static struct block_header_column { + const char *name; + int width; +} block_columns[PERF_HPP_REPORT__BLOCK_MAX_INDEX] = { + [PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT] = { + .name = "Sampled Cycles%", + .width = 15, + }, + [PERF_HPP_REPORT__BLOCK_LBR_CYCLES] = { + .name = "Sampled Cycles", + .width = 14, + }, + [PERF_HPP_REPORT__BLOCK_CYCLES_PCT] = { + .name = "Avg Cycles%", + .width = 11, + }, + [PERF_HPP_REPORT__BLOCK_AVG_CYCLES] = { + .name = "Avg Cycles", + .width = 10, + }, + [PERF_HPP_REPORT__BLOCK_RANGE] = { + .name = "[Program Block Range]", + .width = 70, + }, + [PERF_HPP_REPORT__BLOCK_DSO] = { + .name = "Shared Object", + .width = 20, + } +}; + +struct block_info *block_info__get(struct block_info *bi) +{ + if (bi) + refcount_inc(&bi->refcnt); + return bi; +} + +void block_info__put(struct block_info *bi) +{ + if (bi && refcount_dec_and_test(&bi->refcnt)) + free(bi); +} + +struct block_info *block_info__new(void) +{ + struct block_info *bi = zalloc(sizeof(*bi)); + + if (bi) + refcount_set(&bi->refcnt, 1); + return bi; +} + +int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + struct block_info *bi_l = left->block_info; + struct block_info *bi_r = right->block_info; + int cmp; + + if (!bi_l->sym || !bi_r->sym) { + if (!bi_l->sym && !bi_r->sym) + return 0; + else if (!bi_l->sym) + return -1; + else + return 1; + } + + if (bi_l->sym == bi_r->sym) { + if (bi_l->start == bi_r->start) { + if (bi_l->end == bi_r->end) + return 0; + else + return (int64_t)(bi_r->end - bi_l->end); + } else + return (int64_t)(bi_r->start - bi_l->start); + } else { + cmp = strcmp(bi_l->sym->name, bi_r->sym->name); + return cmp; + } + + if (bi_l->sym->start != bi_r->sym->start) + return (int64_t)(bi_r->sym->start - bi_l->sym->start); + + return (int64_t)(bi_r->sym->end - bi_l->sym->end); +} + +static void init_block_info(struct block_info *bi, struct symbol *sym, + struct cyc_hist *ch, int offset, + u64 total_cycles) +{ + bi->sym = sym; + bi->start = ch->start; + bi->end = offset; + bi->cycles = ch->cycles; + bi->cycles_aggr = ch->cycles_aggr; + bi->num = ch->num; + bi->num_aggr = ch->num_aggr; + bi->total_cycles = total_cycles; + + memcpy(bi->cycles_spark, ch->cycles_spark, + NUM_SPARKS * sizeof(u64)); +} + +int block_info__process_sym(struct hist_entry *he, struct block_hist *bh, + u64 *block_cycles_aggr, u64 total_cycles) +{ + struct annotation *notes; + struct cyc_hist *ch; + static struct addr_location al; + u64 cycles = 0; + + if (!he->ms.map || !he->ms.sym) + return 0; + + memset(&al, 0, sizeof(al)); + al.map = he->ms.map; + al.sym = he->ms.sym; + + notes = symbol__annotation(he->ms.sym); + if (!notes || !notes->src || !notes->src->cycles_hist) + return 0; + ch = notes->src->cycles_hist; + for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) { + if (ch[i].num_aggr) { + struct block_info *bi; + struct hist_entry *he_block; + + bi = block_info__new(); + if (!bi) + return -1; + + init_block_info(bi, he->ms.sym, &ch[i], i, + total_cycles); + cycles += bi->cycles_aggr / bi->num_aggr; + + he_block = hists__add_entry_block(&bh->block_hists, + &al, bi); + if (!he_block) { + block_info__put(bi); + return -1; + } + } + } + + if (block_cycles_aggr) + *block_cycles_aggr += cycles; + + return 0; +} + +static int block_column_header(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hists *hists __maybe_unused, + int line __maybe_unused, + int *span __maybe_unused) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + block_fmt->header); +} + +static int block_column_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct hists *hists __maybe_unused) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + + return block_fmt->width; +} + +static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + double ratio = 0.0; + char buf[16]; + + if (block_fmt->total_cycles) + ratio = (double)bi->cycles / (double)block_fmt->total_cycles; + + sprintf(buf, "%.2f%%", 100.0 * ratio); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt, + struct hist_entry *left, + struct hist_entry *right) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi_l = left->block_info; + struct block_info *bi_r = right->block_info; + double l, r; + + if (block_fmt->total_cycles) { + l = ((double)bi_l->cycles / + (double)block_fmt->total_cycles) * 100000.0; + r = ((double)bi_r->cycles / + (double)block_fmt->total_cycles) * 100000.0; + return (int64_t)l - (int64_t)r; + } + + return 0; +} + +static void cycles_string(u64 cycles, char *buf, int size) +{ + if (cycles >= 1000000) + scnprintf(buf, size, "%.1fM", (double)cycles / 1000000.0); + else if (cycles >= 1000) + scnprintf(buf, size, "%.1fK", (double)cycles / 1000.0); + else + scnprintf(buf, size, "%1d", cycles); +} + +static int block_cycles_lbr_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char cycles_buf[16]; + + cycles_string(bi->cycles_aggr, cycles_buf, sizeof(cycles_buf)); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + cycles_buf); +} + +static int block_cycles_pct_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + double ratio = 0.0; + u64 avg; + char buf[16]; + + if (block_fmt->block_cycles && bi->num_aggr) { + avg = bi->cycles_aggr / bi->num_aggr; + ratio = (double)avg / (double)block_fmt->block_cycles; + } + + sprintf(buf, "%.2f%%", 100.0 * ratio); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int block_avg_cycles_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char cycles_buf[16]; + + cycles_string(bi->cycles_aggr / bi->num_aggr, cycles_buf, + sizeof(cycles_buf)); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + cycles_buf); +} + +static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char buf[128]; + char *start_line, *end_line; + + symbol_conf.disable_add2line_warn = true; + + start_line = map__srcline(he->ms.map, bi->sym->start + bi->start, + he->ms.sym); + + end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, + he->ms.sym); + + if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + scnprintf(buf, sizeof(buf), "[%s -> %s]", + start_line, end_line); + } else { + scnprintf(buf, sizeof(buf), "[%7lx -> %7lx]", + bi->start, bi->end); + } + + free_srcline(start_line); + free_srcline(end_line); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int block_dso_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct map *map = he->ms.map; + + if (map && map->dso) { + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + map->dso->short_name); + } + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + "[unknown]"); +} + +static void init_block_header(struct block_fmt *block_fmt) +{ + struct perf_hpp_fmt *fmt = &block_fmt->fmt; + + BUG_ON(block_fmt->idx >= PERF_HPP_REPORT__BLOCK_MAX_INDEX); + + block_fmt->header = block_columns[block_fmt->idx].name; + block_fmt->width = block_columns[block_fmt->idx].width; + + fmt->header = block_column_header; + fmt->width = block_column_width; +} + +static void hpp_register(struct block_fmt *block_fmt, int idx, + struct perf_hpp_list *hpp_list) +{ + struct perf_hpp_fmt *fmt = &block_fmt->fmt; + + block_fmt->idx = idx; + INIT_LIST_HEAD(&fmt->list); + INIT_LIST_HEAD(&fmt->sort_list); + + switch (idx) { + case PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT: + fmt->entry = block_total_cycles_pct_entry; + fmt->cmp = block_info__cmp; + fmt->sort = block_total_cycles_pct_sort; + break; + case PERF_HPP_REPORT__BLOCK_LBR_CYCLES: + fmt->entry = block_cycles_lbr_entry; + break; + case PERF_HPP_REPORT__BLOCK_CYCLES_PCT: + fmt->entry = block_cycles_pct_entry; + break; + case PERF_HPP_REPORT__BLOCK_AVG_CYCLES: + fmt->entry = block_avg_cycles_entry; + break; + case PERF_HPP_REPORT__BLOCK_RANGE: + fmt->entry = block_range_entry; + break; + case PERF_HPP_REPORT__BLOCK_DSO: + fmt->entry = block_dso_entry; + break; + default: + return; + } + + init_block_header(block_fmt); + perf_hpp_list__column_register(hpp_list, fmt); +} + +static void register_block_columns(struct perf_hpp_list *hpp_list, + struct block_fmt *block_fmts) +{ + for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) + hpp_register(&block_fmts[i], i, hpp_list); +} + +static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts) +{ + __hists__init(&bh->block_hists, &bh->block_list); + perf_hpp_list__init(&bh->block_list); + bh->block_list.nr_header_lines = 1; + + register_block_columns(&bh->block_list, block_fmts); + + perf_hpp_list__register_sort_field(&bh->block_list, + &block_fmts[PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT].fmt); +} + +static void process_block_report(struct hists *hists, + struct block_report *block_report, + u64 total_cycles) +{ + struct rb_node *next = rb_first_cached(&hists->entries); + struct block_hist *bh = &block_report->hist; + struct hist_entry *he; + + init_block_hist(bh, block_report->fmts); + + while (next) { + he = rb_entry(next, struct hist_entry, rb_node); + block_info__process_sym(he, bh, &block_report->cycles, + total_cycles); + next = rb_next(&he->rb_node); + } + + for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) { + block_report->fmts[i].total_cycles = total_cycles; + block_report->fmts[i].block_cycles = block_report->cycles; + } + + hists__output_resort(&bh->block_hists, NULL); +} + +struct block_report *block_info__create_report(struct evlist *evlist, + u64 total_cycles) +{ + struct block_report *block_reports; + int nr_hists = evlist->core.nr_entries, i = 0; + struct evsel *pos; + + block_reports = calloc(nr_hists, sizeof(struct block_report)); + if (!block_reports) + return NULL; + + evlist__for_each_entry(evlist, pos) { + struct hists *hists = evsel__hists(pos); + + process_block_report(hists, &block_reports[i], total_cycles); + i++; + } + + return block_reports; +} + +int report__browse_block_hists(struct block_hist *bh, float min_percent, + struct evsel *evsel, struct perf_env *env, + struct annotation_options *annotation_opts) +{ + int ret; + + switch (use_browser) { + case 0: + symbol_conf.report_individual_block = true; + hists__fprintf(&bh->block_hists, true, 0, 0, min_percent, + stdout, true); + hists__delete_entries(&bh->block_hists); + return 0; + case 1: + symbol_conf.report_individual_block = true; + ret = block_hists_tui_browse(bh, evsel, min_percent, + env, annotation_opts); + hists__delete_entries(&bh->block_hists); + return ret; + default: + return -1; + } + + return 0; +} + +float block_info__total_cycles_percent(struct hist_entry *he) +{ + struct block_info *bi = he->block_info; + + if (bi->total_cycles) + return bi->cycles * 100.0 / bi->total_cycles; + + return 0.0; +} diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h new file mode 100644 index 000000000000..bef0d75e9819 --- /dev/null +++ b/tools/perf/util/block-info.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_BLOCK_H +#define __PERF_BLOCK_H + +#include <linux/types.h> +#include <linux/refcount.h> +#include "hist.h" +#include "symbol.h" +#include "sort.h" +#include "ui/ui.h" + +struct block_info { + struct symbol *sym; + u64 start; + u64 end; + u64 cycles; + u64 cycles_aggr; + s64 cycles_spark[NUM_SPARKS]; + u64 total_cycles; + int num; + int num_aggr; + refcount_t refcnt; +}; + +struct block_fmt { + struct perf_hpp_fmt fmt; + int idx; + int width; + const char *header; + u64 total_cycles; + u64 block_cycles; +}; + +enum { + PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT, + PERF_HPP_REPORT__BLOCK_LBR_CYCLES, + PERF_HPP_REPORT__BLOCK_CYCLES_PCT, + PERF_HPP_REPORT__BLOCK_AVG_CYCLES, + PERF_HPP_REPORT__BLOCK_RANGE, + PERF_HPP_REPORT__BLOCK_DSO, + PERF_HPP_REPORT__BLOCK_MAX_INDEX +}; + +struct block_report { + struct block_hist hist; + u64 cycles; + struct block_fmt fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX]; +}; + +struct block_hist; + +struct block_info *block_info__new(void); +struct block_info *block_info__get(struct block_info *bi); +void block_info__put(struct block_info *bi); + +static inline void __block_info__zput(struct block_info **bi) +{ + block_info__put(*bi); + *bi = NULL; +} + +#define block_info__zput(bi) __block_info__zput(&bi) + +int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right); + +int block_info__process_sym(struct hist_entry *he, struct block_hist *bh, + u64 *block_cycles_aggr, u64 total_cycles); + +struct block_report *block_info__create_report(struct evlist *evlist, + u64 total_cycles); + +int report__browse_block_hists(struct block_hist *bh, float min_percent, + struct evsel *evsel, struct perf_env *env, + struct annotation_options *annotation_opts); + +float block_info__total_cycles_percent(struct hist_entry *he); + +#endif /* __PERF_BLOCK_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 9a9b56ed3f0a..5cefce33b66b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -582,8 +582,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) return -1; } call->ip = cursor_node->ip; - call->ms.sym = cursor_node->sym; - call->ms.map = map__get(cursor_node->map); + call->ms = cursor_node->ms; + map__get(call->ms.map); call->srcline = cursor_node->srcline; if (cursor_node->branch) { @@ -720,21 +720,21 @@ static enum match_result match_chain(struct callchain_cursor_node *node, /* otherwise fall-back to symbol-based comparison below */ __fallthrough; case CCKEY_FUNCTION: - if (node->sym && cnode->ms.sym) { + if (node->ms.sym && cnode->ms.sym) { /* * Compare inlined frames based on their symbol name * because different inlined frames will have the same * symbol start. Otherwise do a faster comparison based * on the symbol start address. */ - if (cnode->ms.sym->inlined || node->sym->inlined) { + if (cnode->ms.sym->inlined || node->ms.sym->inlined) { match = match_chain_strings(cnode->ms.sym->name, - node->sym->name); + node->ms.sym->name); if (match != MATCH_ERROR) break; } else { match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start, - node->map, node->sym->start); + node->ms.map, node->ms.sym->start); break; } } @@ -742,7 +742,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, __fallthrough; case CCKEY_ADDRESS: default: - match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip); + match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->ms.map, node->ip); break; } @@ -1004,8 +1004,7 @@ merge_chain_branch(struct callchain_cursor *cursor, int err = 0; list_for_each_entry_safe(list, next_list, &src->val, list) { - callchain_cursor_append(cursor, list->ip, - list->ms.map, list->ms.sym, + callchain_cursor_append(cursor, list->ip, &list->ms, false, NULL, 0, 0, 0, list->srcline); list_del_init(&list->list); map__zput(list->ms.map); @@ -1044,7 +1043,7 @@ int callchain_merge(struct callchain_cursor *cursor, } int callchain_cursor_append(struct callchain_cursor *cursor, - u64 ip, struct map *map, struct symbol *sym, + u64 ip, struct map_symbol *ms, bool branch, struct branch_flags *flags, int nr_loop_iter, u64 iter_cycles, u64 branch_from, const char *srcline) @@ -1060,9 +1059,9 @@ int callchain_cursor_append(struct callchain_cursor *cursor, } node->ip = ip; - map__zput(node->map); - node->map = map__get(map); - node->sym = sym; + map__zput(node->ms.map); + node->ms = *ms; + map__get(node->ms.map); node->branch = branch; node->nr_loop_iter = nr_loop_iter; node->iter_cycles = iter_cycles; @@ -1107,8 +1106,9 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - al->map = node->map; - al->sym = node->sym; + al->mg = node->ms.mg; + al->map = node->ms.map; + al->sym = node->ms.sym; al->srcline = node->srcline; al->addr = node->ip; @@ -1119,8 +1119,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * goto out; } - if (al->map->groups == &al->machine->kmaps) { - if (machine__is_host(al->machine)) { + if (al->mg == &al->mg->machine->kmaps) { + if (machine__is_host(al->mg->machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; } else { @@ -1128,7 +1128,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * al->level = 'g'; } } else { - if (machine__is_host(al->machine)) { + if (machine__is_host(al->mg->machine)) { al->cpumode = PERF_RECORD_MISC_USER; al->level = '.'; } else if (perf_guest) { @@ -1571,7 +1571,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst, if (node == NULL) break; - rc = callchain_cursor_append(dst, node->ip, node->map, node->sym, + rc = callchain_cursor_append(dst, node->ip, &node->ms, node->branch, &node->branch_flags, node->nr_loop_iter, node->iter_cycles, @@ -1597,5 +1597,5 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) cursor->last = &cursor->first; for (node = cursor->first; node != NULL; node = node->next) - map__zput(node->map); + map__zput(node->ms.map); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 83398e5bbe4b..706bb7bbe1e1 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -141,8 +141,7 @@ struct callchain_list { */ struct callchain_cursor_node { u64 ip; - struct map *map; - struct symbol *sym; + struct map_symbol ms; const char *srcline; bool branch; struct branch_flags branch_flags; @@ -195,7 +194,7 @@ int callchain_merge(struct callchain_cursor *cursor, void callchain_cursor_reset(struct callchain_cursor *cursor); int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, - struct map *map, struct symbol *sym, + struct map_symbol *ms, bool branch, struct branch_flags *flags, int nr_loop_iter, u64 iter_cycles, u64 branch_from, const char *srcline); diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c index 3fa0db136667..47e03de7c235 100644 --- a/tools/perf/util/copyfile.c +++ b/tools/perf/util/copyfile.c @@ -101,14 +101,16 @@ static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, if (tofd < 0) goto out; - if (fchmod(tofd, mode)) - goto out_close_to; - if (st.st_size == 0) { /* /proc? do it slowly... */ err = slow_copyfile(from, tmp, nsi); + if (!err && fchmod(tofd, mode)) + err = -1; goto out_close_to; } + if (fchmod(tofd, mode)) + goto out_close_to; + nsinfo__mountns_enter(nsi, &nsc); fromfd = open(from, O_RDONLY); nsinfo__mountns_exit(&nsc); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index a22c1114e880..983b7388f22b 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -206,6 +206,11 @@ int cpu_map__get_core_id(int cpu) return ret ?: value; } +int cpu_map__get_node_id(int cpu) +{ + return cpu__get_node(cpu); +} + int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) { int cpu, s_die; @@ -235,6 +240,14 @@ int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) return (s_die << 16) | (cpu & 0xffff); } +int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +{ + if (idx < 0 || idx >= map->nr) + return -1; + + return cpu_map__get_node_id(map->map[idx]); +} + int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp) { return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); @@ -250,6 +263,11 @@ int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **cor return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); } +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap) +{ + return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); +} + /* setup simple routines to easily access node numbers given a cpu number */ static int get_max_num(char *path, int *max) { diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 2553bef1279d..57943f3685f8 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -20,9 +20,12 @@ int cpu_map__get_die_id(int cpu); int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_core_id(int cpu); int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__get_node_id(int cpu); +int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp); int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep); int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep); +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep); const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 4ba0f871f086..f5f855fff412 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -110,7 +110,7 @@ static int cs_etm__decode_data_block(struct cs_etm_queue *etmq); * encode the etm queue number as the upper 16 bit and the channel as * the lower 16 bit. */ -#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan) \ +#define TO_CS_QUEUE_NR(queue_nr, trace_chan_id) \ (queue_nr << 16 | trace_chan_id) #define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16) #define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff) @@ -819,7 +819,7 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, * Note that packets decoded above are still in the traceID's packet * queue and will be processed in cs_etm__process_queues(). */ - cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan); + cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id); ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp); out: return ret; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 88fba2ba549f..c47aa34fdc0a 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + /* + * Directory containing a single regular perf data file which is already + * open, means there is nothing more to do here. + */ + if (perf_data__is_single_file(data)) + return 0; + if (WARN_ON(!data->is_dir)) return -EINVAL; @@ -96,7 +103,7 @@ int perf_data__open_dir(struct perf_data *data) if (stat(path, &st)) continue; - if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4)) + if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data.", 5)) continue; ret = -ENOMEM; @@ -306,7 +313,7 @@ static int open_dir(struct perf_data *data) * So far we open only the header, so we can read the data version and * layout. */ - if (asprintf(&data->file.path, "%s/header", data->path) < 0) + if (asprintf(&data->file.path, "%s/data", data->path) < 0) return -1; if (perf_data__is_write(data) && @@ -406,7 +413,7 @@ unsigned long perf_data__size(struct perf_data *data) u64 size = data->file.size; int i; - if (!data->is_dir) + if (perf_data__is_single_file(data)) return size; for (i = 0; i < data->dir.nr; i++) { @@ -417,3 +424,36 @@ unsigned long perf_data__size(struct perf_data *data) return size; } + +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz) +{ + int ret; + + if (!data->is_dir) + return -1; + + ret = snprintf(buf, buf_sz, "%s/kcore_dir", data->path); + if (ret < 0 || (size_t)ret >= buf_sz) + return -1; + + return mkdir(buf, S_IRWXU); +} + +char *perf_data__kallsyms_name(struct perf_data *data) +{ + char *kallsyms_name; + struct stat st; + + if (!data->is_dir) + return NULL; + + if (asprintf(&kallsyms_name, "%s/kcore_dir/kallsyms", data->path) < 0) + return NULL; + + if (stat(kallsyms_name, &st)) { + free(kallsyms_name); + return NULL; + } + + return kallsyms_name; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 259868a39019..75947ef6bc17 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -9,6 +9,11 @@ enum perf_data_mode { PERF_DATA_MODE_READ, }; +enum perf_dir_version { + PERF_DIR_SINGLE_FILE = 0, + PERF_DIR_VERSION = 1, +}; + struct perf_data_file { char *path; int fd; @@ -50,6 +55,11 @@ static inline bool perf_data__is_dir(struct perf_data *data) return data->is_dir; } +static inline bool perf_data__is_single_file(struct perf_data *data) +{ + return data->dir.version == PERF_DIR_SINGLE_FILE; +} + static inline int perf_data__fd(struct perf_data *data) { return data->file.fd; @@ -77,4 +87,6 @@ int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); +char *perf_data__kallsyms_name(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 752227b265e7..d029faf9fc9f 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -181,7 +181,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (al->map) { struct dso *dso = al->map->dso; - err = db_export__dso(dbe, dso, al->machine); + err = db_export__dso(dbe, dso, al->mg->machine); if (err) return err; *dso_db_id = dso->db_id; @@ -249,9 +249,9 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, * constructing an addr_location struct and then passing it to * db_ids_from_al() to perform the export. */ - al.sym = node->sym; - al.map = node->map; - al.machine = machine; + al.sym = node->ms.sym; + al.map = node->ms.map; + al.mg = thread->mg; al.addr = node->ip; if (al.map && !al.sym) @@ -360,13 +360,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, if (err) return err; - err = db_export__machine(dbe, al->machine); + err = db_export__machine(dbe, al->mg->machine); if (err) return err; - main_thread = thread__main_thread(al->machine, thread); + main_thread = thread__main_thread(al->mg->machine, thread); - err = db_export__threads(dbe, thread, main_thread, al->machine, &comm); + err = db_export__threads(dbe, thread, main_thread, al->mg->machine, &comm); if (err) goto out_put; @@ -380,7 +380,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, goto out_put; if (dbe->cpr) { - struct call_path *cp = call_path_from_sample(dbe, al->machine, + struct call_path *cp = call_path_from_sample(dbe, al->mg->machine, thread, sample, evsel); if (cp) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index e55114f0336f..adb656745ecc 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -24,6 +24,7 @@ #include <linux/ctype.h> int verbose; +int debug_peo_args; bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; @@ -180,6 +181,7 @@ static struct debug_variable { { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = "stderr", .ptr = &redirect_to_stderr}, { .name = "data-convert", .ptr = &debug_data_convert }, + { .name = "perf-event-open", .ptr = &debug_peo_args }, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index d25ae1c4cee9..f1734abd98dd 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -8,6 +8,7 @@ #include <linux/compiler.h> extern int verbose; +extern int debug_peo_args; extern bool quiet, dump_trace; extern int debug_ordered_events; extern int debug_data_convert; @@ -30,6 +31,14 @@ extern int debug_data_convert; #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +/* Special macro to print perf_event_open arguments/return value. */ +#define pr_debug2_peo(fmt, ...) { \ + if (debug_peo_args) \ + pr_debugN(0, pr_fmt(fmt), ##__VA_ARGS__); \ + else \ + pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__); \ +} + #define pr_time_N(n, var, t, fmt, ...) \ eprintf_time(n, var, t, fmt, ##__VA_ARGS__) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e11ddf86f2b3..91f21239608b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -768,7 +768,7 @@ dso_cache__free(struct dso *dso) pthread_mutex_unlock(&dso->lock); } -static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset) +static struct dso_cache *__dso_cache__find(struct dso *dso, u64 offset) { const struct rb_root *root = &dso->data.cache; struct rb_node * const *p = &root->rb_node; @@ -827,14 +827,16 @@ out: return cache; } -static ssize_t -dso_cache__memcpy(struct dso_cache *cache, u64 offset, - u8 *data, u64 size) +static ssize_t dso_cache__memcpy(struct dso_cache *cache, u64 offset, u8 *data, + u64 size, bool out) { u64 cache_offset = offset - cache->offset; u64 cache_size = min(cache->size - cache_offset, size); - memcpy(data, cache->data + cache_offset, cache_size); + if (out) + memcpy(data, cache->data + cache_offset, cache_size); + else + memcpy(cache->data + cache_offset, data, cache_size); return cache_size; } @@ -863,63 +865,73 @@ out: return ret; } -static ssize_t -dso_cache__read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static struct dso_cache *dso_cache__populate(struct dso *dso, + struct machine *machine, + u64 offset, ssize_t *ret) { u64 cache_offset = offset & DSO__DATA_CACHE_MASK; struct dso_cache *cache; struct dso_cache *old; - ssize_t ret; cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); - if (!cache) - return -ENOMEM; + if (!cache) { + *ret = -ENOMEM; + return NULL; + } if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) - ret = bpf_read(dso, cache_offset, cache->data); + *ret = bpf_read(dso, cache_offset, cache->data); else - ret = file_read(dso, machine, cache_offset, cache->data); + *ret = file_read(dso, machine, cache_offset, cache->data); - if (ret > 0) { - cache->offset = cache_offset; - cache->size = ret; + if (*ret <= 0) { + free(cache); + return NULL; + } - old = dso_cache__insert(dso, cache); - if (old) { - /* we lose the race */ - free(cache); - cache = old; - } + cache->offset = cache_offset; + cache->size = *ret; - ret = dso_cache__memcpy(cache, offset, data, size); + old = dso_cache__insert(dso, cache); + if (old) { + /* we lose the race */ + free(cache); + cache = old; } - if (ret <= 0) - free(cache); + return cache; +} - return ret; +static struct dso_cache *dso_cache__find(struct dso *dso, + struct machine *machine, + u64 offset, + ssize_t *ret) +{ + struct dso_cache *cache = __dso_cache__find(dso, offset); + + return cache ? cache : dso_cache__populate(dso, machine, offset, ret); } -static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t dso_cache_io(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, bool out) { struct dso_cache *cache; + ssize_t ret = 0; - cache = dso_cache__find(dso, offset); - if (cache) - return dso_cache__memcpy(cache, offset, data, size); - else - return dso_cache__read(dso, machine, offset, data, size); + cache = dso_cache__find(dso, machine, offset, &ret); + if (!cache) + return ret; + + return dso_cache__memcpy(cache, offset, data, size, out); } /* * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks * in the rb_tree. Any read to already cached data is served - * by cached data. + * by cached data. Writes update the cache only, not the backing file. */ -static ssize_t cached_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t cached_io(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, bool out) { ssize_t r = 0; u8 *p = data; @@ -927,7 +939,7 @@ static ssize_t cached_read(struct dso *dso, struct machine *machine, do { ssize_t ret; - ret = dso_cache_read(dso, machine, offset, p, size); + ret = dso_cache_io(dso, machine, offset, p, size, out); if (ret < 0) return ret; @@ -1011,8 +1023,9 @@ off_t dso__data_size(struct dso *dso, struct machine *machine) return dso->data.file_size; } -static ssize_t data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t data_read_write_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, + bool out) { if (dso__data_file_size(dso, machine)) return -1; @@ -1024,7 +1037,7 @@ static ssize_t data_read_offset(struct dso *dso, struct machine *machine, if (offset + size < offset) return -1; - return cached_read(dso, machine, offset, data, size); + return cached_io(dso, machine, offset, data, size, out); } /** @@ -1044,7 +1057,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, if (dso->data.status == DSO_DATA_STATUS_ERROR) return -1; - return data_read_offset(dso, machine, offset, data, size); + return data_read_write_offset(dso, machine, offset, data, size, true); } /** @@ -1065,6 +1078,46 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, return dso__data_read_offset(dso, machine, offset, data, size); } +/** + * dso__data_write_cache_offs - Write data to dso data cache at file offset + * @dso: dso object + * @machine: machine object + * @offset: file offset + * @data: buffer to write + * @size: size of the @data buffer + * + * Write into the dso file data cache, but do not change the file itself. + */ +ssize_t dso__data_write_cache_offs(struct dso *dso, struct machine *machine, + u64 offset, const u8 *data_in, ssize_t size) +{ + u8 *data = (u8 *)data_in; /* cast away const to use same fns for r/w */ + + if (dso->data.status == DSO_DATA_STATUS_ERROR) + return -1; + + return data_read_write_offset(dso, machine, offset, data, size, false); +} + +/** + * dso__data_write_cache_addr - Write data to dso data cache at dso address + * @dso: dso object + * @machine: machine object + * @add: virtual memory address + * @data: buffer to write + * @size: size of the @data buffer + * + * External interface to write into the dso file data cache, but do not change + * the file itself. + */ +ssize_t dso__data_write_cache_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + const u8 *data, ssize_t size) +{ + u64 offset = map->map_ip(map, addr); + return dso__data_write_cache_offs(dso, machine, offset, data, size); +} + struct map *dso__new_map(const char *name) { struct map *map = NULL; @@ -1096,7 +1149,7 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name, return dso; } -void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) +static void dso__set_long_name_id(struct dso *dso, const char *name, struct dso_id *id, bool name_allocated) { struct rb_root *root = dso->root; @@ -1109,8 +1162,8 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) if (root) { rb_erase(&dso->rb_node, root); /* - * __dsos__findnew_link_by_longname() isn't guaranteed to add it - * back, so a clean removal is required here. + * __dsos__findnew_link_by_longname_id() isn't guaranteed to + * add it back, so a clean removal is required here. */ RB_CLEAR_NODE(&dso->rb_node); dso->root = NULL; @@ -1121,7 +1174,12 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) dso->long_name_allocated = name_allocated; if (root) - __dsos__findnew_link_by_longname(root, dso, NULL); + __dsos__findnew_link_by_longname_id(root, dso, NULL, id); +} + +void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) +{ + dso__set_long_name_id(dso, name, NULL, name_allocated); } void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) @@ -1162,13 +1220,15 @@ void dso__set_sorted_by_name(struct dso *dso) dso->sorted_by_name = true; } -struct dso *dso__new(const char *name) +struct dso *dso__new_id(const char *name, struct dso_id *id) { struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); if (dso != NULL) { strcpy(dso->name, name); - dso__set_long_name(dso, dso->name, false); + if (id) + dso->id = *id; + dso__set_long_name_id(dso, dso->name, id, false); dso__set_short_name(dso, dso->name, false); dso->symbols = dso->symbol_names = RB_ROOT_CACHED; dso->data.cache = RB_ROOT; @@ -1199,6 +1259,11 @@ struct dso *dso__new(const char *name) return dso; } +struct dso *dso__new(const char *name) +{ + return dso__new_id(name, NULL); +} + void dso__delete(struct dso *dso) { if (!RB_EMPTY_NODE(&dso->rb_node)) diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index e4dddb76770d..2db64b79617a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -122,6 +122,16 @@ enum dso_load_errno { #define DSO__DATA_CACHE_SIZE 4096 #define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) +/* + * Data about backing storage DSO, comes from PERF_RECORD_MMAP2 meta events + */ +struct dso_id { + u32 maj; + u32 min; + u64 ino; + u64 ino_generation; +}; + struct dso_cache { struct rb_node rb_node; u64 offset; @@ -196,6 +206,7 @@ struct dso { u64 db_id; }; struct nsinfo *nsinfo; + struct dso_id id; refcount_t refcnt; char name[0]; }; @@ -214,9 +225,11 @@ static inline void dso__set_loaded(struct dso *dso) dso->loaded = true; } +struct dso *dso__new_id(const char *name, struct dso_id *id); struct dso *dso__new(const char *name); void dso__delete(struct dso *dso); +int dso__cmp_id(struct dso *a, struct dso *b); void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated); void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated); @@ -285,6 +298,8 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * dso__data_size * dso__data_read_offset * dso__data_read_addr + * dso__data_write_cache_offs + * dso__data_write_cache_addr * * Please refer to the dso.c object code for each function and * arguments documentation. Following text tries to explain the @@ -332,6 +347,11 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by); +ssize_t dso__data_write_cache_offs(struct dso *dso, struct machine *machine, + u64 offset, const u8 *data, ssize_t size); +ssize_t dso__data_write_cache_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + const u8 *data, ssize_t size); struct map *dso__new_map(const char *name); struct dso *machine__findnew_kernel(struct machine *machine, const char *name, diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index 3ea80d203587..591707c69c39 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -9,6 +9,40 @@ #include <string.h> #include <symbol.h> // filename__read_build_id +static int __dso_id__cmp(struct dso_id *a, struct dso_id *b) +{ + if (a->maj > b->maj) return -1; + if (a->maj < b->maj) return 1; + + if (a->min > b->min) return -1; + if (a->min < b->min) return 1; + + if (a->ino > b->ino) return -1; + if (a->ino < b->ino) return 1; + + if (a->ino_generation > b->ino_generation) return -1; + if (a->ino_generation < b->ino_generation) return 1; + + return 0; +} + +static int dso_id__cmp(struct dso_id *a, struct dso_id *b) +{ + /* + * The second is always dso->id, so zeroes if not set, assume passing + * NULL for a means a zeroed id + */ + if (a == NULL) + return 0; + + return __dso_id__cmp(a, b); +} + +int dso__cmp_id(struct dso *a, struct dso *b) +{ + return __dso_id__cmp(&a->id, &b->id); +} + bool __dsos__read_build_ids(struct list_head *head, bool with_hits) { bool have_build_id = false; @@ -34,12 +68,30 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } +static int __dso__cmp_long_name(const char *long_name, struct dso_id *id, struct dso *b) +{ + int rc = strcmp(long_name, b->long_name); + return rc ?: dso_id__cmp(id, &b->id); +} + +static int __dso__cmp_short_name(const char *short_name, struct dso_id *id, struct dso *b) +{ + int rc = strcmp(short_name, b->short_name); + return rc ?: dso_id__cmp(id, &b->id); +} + +static int dso__cmp_short_name(struct dso *a, struct dso *b) +{ + return __dso__cmp_short_name(a->short_name, &a->id, b); +} + /* * Find a matching entry and/or link current entry to RB tree. * Either one of the dso or name parameter must be non-NULL or the * function will not work. */ -struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name) +struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso, + const char *name, struct dso_id *id) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -51,7 +103,7 @@ struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *d */ while (*p) { struct dso *this = rb_entry(*p, struct dso, rb_node); - int rc = strcmp(name, this->long_name); + int rc = __dso__cmp_long_name(name, id, this); parent = *p; if (rc == 0) { @@ -67,7 +119,7 @@ struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *d * In this case, the short name should be different. * Comparing the short names to differentiate the DSOs. */ - rc = strcmp(dso->short_name, this->short_name); + rc = dso__cmp_short_name(dso, this); if (rc == 0) { pr_err("Duplicated dso name: %s\n", name); return NULL; @@ -90,7 +142,7 @@ struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *d void __dsos__add(struct dsos *dsos, struct dso *dso) { list_add_tail(&dso->node, &dsos->head); - __dsos__findnew_link_by_longname(&dsos->root, dso, NULL); + __dsos__findnew_link_by_longname_id(&dsos->root, dso, NULL, &dso->id); /* * It is now in the linked list, grab a reference, then garbage collect * this when needing memory, by looking at LRU dso instances in the @@ -121,26 +173,27 @@ void dsos__add(struct dsos *dsos, struct dso *dso) up_write(&dsos->lock); } -struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) +static struct dso *__dsos__findnew_by_longname_id(struct rb_root *root, const char *name, struct dso_id *id) +{ + return __dsos__findnew_link_by_longname_id(root, NULL, name, id); +} + +static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id, bool cmp_short) { struct dso *pos; if (cmp_short) { list_for_each_entry(pos, &dsos->head, node) - if (strcmp(pos->short_name, name) == 0) + if (__dso__cmp_short_name(name, id, pos) == 0) return pos; return NULL; } - return __dsos__findnew_by_longname(&dsos->root, name); + return __dsos__findnew_by_longname_id(&dsos->root, name, id); } -struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short) +struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) { - struct dso *dso; - down_read(&dsos->lock); - dso = __dsos__find(dsos, name, cmp_short); - up_read(&dsos->lock); - return dso; + return __dsos__find_id(dsos, name, NULL, cmp_short); } static void dso__set_basename(struct dso *dso) @@ -175,9 +228,9 @@ static void dso__set_basename(struct dso *dso) dso__set_short_name(dso, base, true); } -struct dso *__dsos__addnew(struct dsos *dsos, const char *name) +static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, struct dso_id *id) { - struct dso *dso = dso__new(name); + struct dso *dso = dso__new_id(name, id); if (dso != NULL) { __dsos__add(dsos, dso); @@ -188,18 +241,22 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name) return dso; } -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); + return __dsos__addnew_id(dsos, name, NULL); +} - return dso ? dso : __dsos__addnew(dsos, name); +static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id) +{ + struct dso *dso = __dsos__find_id(dsos, name, id, false); + return dso ? dso : __dsos__addnew_id(dsos, name, id); } -struct dso *dsos__findnew(struct dsos *dsos, const char *name) +struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id) { struct dso *dso; down_write(&dsos->lock); - dso = dso__get(__dsos__findnew(dsos, name)); + dso = dso__get(__dsos__findnew_id(dsos, name, id)); up_write(&dsos->lock); return dso; } diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h index 32f1fbee0feb..5dbec2bc6966 100644 --- a/tools/perf/util/dsos.h +++ b/tools/perf/util/dsos.h @@ -9,6 +9,7 @@ #include "rwsem.h" struct dso; +struct dso_id; /* * DSOs are put into both a list for fast iteration and rbtree for fast @@ -24,16 +25,11 @@ void __dsos__add(struct dsos *dsos, struct dso *dso); void dsos__add(struct dsos *dsos, struct dso *dso); struct dso *__dsos__addnew(struct dsos *dsos, const char *name); struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short); -struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short); -struct dso *__dsos__findnew(struct dsos *dsos, const char *name); -struct dso *dsos__findnew(struct dsos *dsos, const char *name); -struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name); - -static inline struct dso *__dsos__findnew_by_longname(struct rb_root *root, const char *name) -{ - return __dsos__findnew_link_by_longname(root, NULL, name); -} +struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id); + +struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso, + const char *name, struct dso_id *id); bool __dsos__read_build_ids(struct list_head *head, bool with_hits); diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index df6cee5c071f..aa898014ad12 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -59,6 +59,51 @@ const char *cu_get_comp_dir(Dwarf_Die *cu_die) return dwarf_formstring(&attr); } +/* Unlike dwarf_getsrc_die(), cu_getsrc_die() only returns statement line */ +static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) +{ + Dwarf_Addr laddr; + Dwarf_Lines *lines; + Dwarf_Line *line; + size_t nlines, l, u, n; + bool flag; + + if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0 || + nlines == 0) + return NULL; + + /* Lines are sorted by address, use binary search */ + l = 0; u = nlines - 1; + while (l < u) { + n = u - (u - l) / 2; + line = dwarf_onesrcline(lines, n); + if (!line || dwarf_lineaddr(line, &laddr) != 0) + return NULL; + if (addr < laddr) + u = n - 1; + else + l = n; + } + /* Going backward to find the lowest line */ + do { + line = dwarf_onesrcline(lines, --l); + if (!line || dwarf_lineaddr(line, &laddr) != 0) + return NULL; + } while (laddr == addr); + l++; + /* Going foward to find the statement line */ + do { + line = dwarf_onesrcline(lines, l++); + if (!line || dwarf_lineaddr(line, &laddr) != 0 || + dwarf_linebeginstatement(line, &flag) != 0) + return NULL; + if (laddr > addr) + return NULL; + } while (!flag); + + return line; +} + /** * cu_find_lineinfo - Get a line number and file name for given address * @cu_die: a CU DIE @@ -72,17 +117,26 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, const char **fname, int *lineno) { Dwarf_Line *line; - Dwarf_Addr laddr; + Dwarf_Die die_mem; + Dwarf_Addr faddr; + + if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem) + && die_entrypc(&die_mem, &faddr) == 0 && + faddr == addr) { + *fname = dwarf_decl_file(&die_mem); + dwarf_decl_line(&die_mem, lineno); + goto out; + } - line = dwarf_getsrc_die(cu_die, (Dwarf_Addr)addr); - if (line && dwarf_lineaddr(line, &laddr) == 0 && - addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) { + line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr); + if (line && dwarf_lineno(line, lineno) == 0) { *fname = dwarf_linesrc(line, NULL, NULL); if (!*fname) /* line number is useless without filename */ *lineno = 0; } +out: return *lineno ?: -ENOENT; } @@ -308,20 +362,50 @@ bool die_is_func_def(Dwarf_Die *dw_die) } /** + * die_entrypc - Returns entry PC (the lowest address) of a DIE + * @dw_die: a DIE + * @addr: where to store entry PC + * + * Since dwarf_entrypc() does not return entry PC if the DIE has only address + * range, we have to use this to retrieve the lowest address from the address + * range attribute. + */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) +{ + Dwarf_Addr base, end; + + if (!addr) + return -EINVAL; + + if (dwarf_entrypc(dw_die, addr) == 0) + return 0; + + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; +} + +/** * die_is_func_instance - Ensure that this DIE is an instance of a subprogram * @dw_die: a DIE * * Ensure that this DIE is an instance (which has an entry address). - * This returns true if @dw_die is a function instance. If not, you need to - * call die_walk_instances() to find actual instances. + * This returns true if @dw_die is a function instance. If not, the @dw_die + * must be a prototype. You can use die_walk_instances() to find actual + * instances. **/ bool die_is_func_instance(Dwarf_Die *dw_die) { Dwarf_Addr tmp; + Dwarf_Attribute attr_mem; + int tag = dwarf_tag(dw_die); + + if (tag != DW_TAG_subprogram && + tag != DW_TAG_inlined_subroutine) + return false; - /* Actually gcc optimizes non-inline as like as inlined */ - return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; + return dwarf_entrypc(dw_die, &tmp) == 0 || + dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL; } + /** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure @@ -598,6 +682,9 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) Dwarf_Die *origin; int tmp; + if (!die_is_func_instance(inst)) + return DIE_FIND_CB_CONTINUE; + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); if (attr == NULL) return DIE_FIND_CB_CONTINUE; @@ -669,15 +756,14 @@ static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { fname = die_get_call_file(in_die); lineno = die_get_call_lineno(in_die); - if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + if (fname && lineno > 0 && die_entrypc(in_die, &addr) == 0) { lw->retval = lw->callback(fname, lineno, addr, lw->data); if (lw->retval != 0) return DIE_FIND_CB_END; } + if (!lw->recursive) + return DIE_FIND_CB_SIBLING; } - if (!lw->recursive) - /* Don't need to search recursively */ - return DIE_FIND_CB_SIBLING; if (addr) { fname = dwarf_decl_file(in_die); @@ -710,7 +796,7 @@ static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, /* Handle function declaration line */ fname = dwarf_decl_file(sp_die); if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && - dwarf_entrypc(sp_die, &addr) == 0) { + die_entrypc(sp_die, &addr) == 0) { lw.retval = callback(fname, lineno, addr, data); if (lw.retval != 0) goto done; @@ -724,6 +810,10 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) { struct __line_walk_param *lw = data; + /* + * Since inlined function can include another inlined function in + * the same file, we need to walk in it recursively. + */ lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); if (lw->retval != 0) return DWARF_CB_ABORT; @@ -748,11 +838,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) Dwarf_Lines *lines; Dwarf_Line *line; Dwarf_Addr addr; - const char *fname, *decf = NULL; + const char *fname, *decf = NULL, *inf = NULL; int lineno, ret = 0; int decl = 0, inl; Dwarf_Die die_mem, *cu_die; size_t nlines, i; + bool flag; /* Get the CU die */ if (dwarf_tag(rt_die) != DW_TAG_compile_unit) { @@ -783,6 +874,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) "Possible error in debuginfo.\n"); continue; } + /* Skip end-of-sequence */ + if (dwarf_lineendsequence(line, &flag) != 0 || flag) + continue; + /* Skip Non statement line-info */ + if (dwarf_linebeginstatement(line, &flag) != 0 || !flag) + continue; /* Filter lines based on address */ if (rt_die != cu_die) { /* @@ -792,13 +889,21 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (!dwarf_haspc(rt_die, addr)) continue; + if (die_find_inlinefunc(rt_die, addr, &die_mem)) { + /* Call-site check */ + inf = die_get_call_file(&die_mem); + if ((inf && !strcmp(inf, decf)) && + die_get_call_lineno(&die_mem) == lineno) + goto found; + dwarf_decl_line(&die_mem, &inl); if (inl != decl || decf != dwarf_decl_file(&die_mem)) continue; } } +found: /* Get source line */ fname = dwarf_linesrc(line, NULL, NULL); @@ -813,8 +918,9 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (rt_die != cu_die) /* - * Don't need walk functions recursively, because nested - * inlined functions don't have lines of the specified DIE. + * Don't need walk inlined functions recursively, because + * inner inlined functions don't have the lines of the + * specified function. */ ret = __die_walk_funclines(rt_die, false, callback, data); else { @@ -989,7 +1095,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die, bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; @@ -1052,7 +1158,7 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index f204e5892403..506006e0cf66 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -29,6 +29,9 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Get DW_AT_linkage_name (should be NULL for C binary) */ const char *die_get_linkage_name(Dwarf_Die *dw_die); +/* Get the lowest PC in DIE (including range list) */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr); + /* Ensure that this DIE is a subprogram and definition (not declaration) */ bool die_is_func_def(Dwarf_Die *dw_die); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 3baca06786fb..6242a9215df7 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -2,6 +2,7 @@ #include "cpumap.h" #include "debug.h" #include "env.h" +#include "util/header.h" #include <linux/ctype.h> #include <linux/zalloc.h> #include "bpf-event.h" @@ -179,6 +180,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) perf_cpu_map__put(env->numa_nodes[i].map); @@ -256,6 +258,21 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; } +int perf_env__read_cpuid(struct perf_env *env) +{ + char cpuid[128]; + int err = get_cpuid(cpuid, sizeof(cpuid)); + + if (err) + return err; + + free(env->cpuid); + env->cpuid = strdup(cpuid); + if (env->cpuid == NULL) + return ENOMEM; + return 0; +} + static int perf_env__read_arch(struct perf_env *env) { struct utsname uts; @@ -338,3 +355,42 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } + + +int perf_env__numa_node(struct perf_env *env, int cpu) +{ + if (!env->nr_numa_map) { + struct numa_node *nn; + int i, nr = 0; + + for (i = 0; i < env->nr_numa_nodes; i++) { + nn = &env->numa_nodes[i]; + nr = max(nr, perf_cpu_map__max(nn->map)); + } + + nr++; + + /* + * We initialize the numa_map array to prepare + * it for missing cpus, which return node -1 + */ + env->numa_map = malloc(nr * sizeof(int)); + if (!env->numa_map) + return -1; + + for (i = 0; i < nr; i++) + env->numa_map[i] = -1; + + env->nr_numa_map = nr; + + for (i = 0; i < env->nr_numa_nodes; i++) { + int tmp, j; + + nn = &env->numa_nodes[i]; + perf_cpu_map__for_each_cpu(j, tmp, nn->map) + env->numa_map[j] = i; + } + } + + return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; +} diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index db40906e2937..11d05ae3606a 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -87,6 +87,10 @@ struct perf_env { struct rb_root btfs; u32 btfs_cnt; } bpf_progs; + + /* For fast cpu to numa node lookup via perf_env__numa_node */ + int *numa_map; + int nr_numa_map; }; enum perf_compress_type { @@ -104,6 +108,7 @@ void perf_env__exit(struct perf_env *env); int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]); +int perf_env__read_cpuid(struct perf_env *env); int perf_env__read_cpu_topology_map(struct perf_env *env); void cpu_cache_level__free(struct cpu_cache_level *cache); @@ -119,4 +124,6 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); + +int perf_env__numa_node(struct perf_env *env, int cpu); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index fc1e5a991008..0141b26bae47 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -461,7 +461,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct machine *machine = mg->machine; bool load_map = false; - al->machine = machine; + al->mg = mg; al->thread = thread; al->addr = addr; al->cpumode = cpumode; @@ -474,13 +474,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - mg = &machine->kmaps; + al->mg = mg = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - mg = &machine->kmaps; + al->mg = mg = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { al->level = 'u'; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index a0a0c91cde4a..85223159737c 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -114,6 +114,11 @@ enum { #define MAX_INSN 16 +struct aux_sample { + u64 size; + void *data; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -142,6 +147,7 @@ struct perf_sample { struct regs_dump intr_regs; struct stack_dump user_stack; struct sample_read read; + struct aux_sample aux_sample; }; #define PERF_MEM_DATA_SRC_NONE \ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d277a98e62df..fdce590d2278 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -21,6 +21,7 @@ #include "../perf.h" #include "asm/bug.h" #include "bpf-event.h" +#include "util/string2.h" #include <signal.h> #include <unistd.h> #include <sched.h> @@ -42,6 +43,7 @@ #include <perf/evlist.h> #include <perf/evsel.h> #include <perf/cpumap.h> +#include <perf/mmap.h> #include <internal/xyarray.h> @@ -57,7 +59,6 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, { perf_evlist__init(&evlist->core); perf_evlist__set_maps(&evlist->core, cpus, threads); - fdarray__init(&evlist->core.pollfd, 64); evlist->workload.pid = -1; evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; } @@ -138,7 +139,7 @@ void evlist__exit(struct evlist *evlist) { zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); - fdarray__exit(&evlist->core.pollfd); + perf_evlist__exit(&evlist->core); } void evlist__delete(struct evlist *evlist) @@ -148,10 +149,6 @@ void evlist__delete(struct evlist *evlist) evlist__munmap(evlist); evlist__close(evlist); - perf_cpu_map__put(evlist->core.cpus); - perf_thread_map__put(evlist->core.threads); - evlist->core.cpus = NULL; - evlist->core.threads = NULL; evlist__purge(evlist); evlist__exit(evlist); free(evlist); @@ -186,6 +183,30 @@ void perf_evlist__splice_list_tail(struct evlist *evlist, } } +int __evlist__set_tracepoints_handlers(struct evlist *evlist, + const struct evsel_str_handler *assocs, size_t nr_assocs) +{ + struct evsel *evsel; + size_t i; + int err; + + for (i = 0; i < nr_assocs; i++) { + // Adding a handler for an event not in this evlist, just ignore it. + evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name); + if (evsel == NULL) + continue; + + err = -EEXIST; + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; + } + + err = 0; +out: + return err; +} + void __perf_evlist__set_leader(struct list_head *list) { struct evsel *evsel, *leader; @@ -403,19 +424,9 @@ int evlist__add_pollfd(struct evlist *evlist, int fd) return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN); } -static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, - void *arg __maybe_unused) -{ - struct mmap *map = fda->priv[fd].ptr; - - if (map) - perf_mmap__put(map); -} - int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) { - return fdarray__filter(&evlist->core.pollfd, revents_and_mask, - perf_evlist__munmap_filtered, NULL); + return perf_evlist__filter_pollfd(&evlist->core, revents_and_mask); } int evlist__poll(struct evlist *evlist, int timeout) @@ -423,22 +434,6 @@ int evlist__poll(struct evlist *evlist, int timeout) return perf_evlist__poll(&evlist->core, timeout); } -static void perf_evlist__set_sid_idx(struct evlist *evlist, - struct evsel *evsel, int idx, int cpu, - int thread) -{ - struct perf_sample_id *sid = SID(evsel, cpu, thread); - sid->idx = idx; - if (evlist->core.cpus && cpu >= 0) - sid->cpu = evlist->core.cpus->map[cpu]; - else - sid->cpu = -1; - if (!evsel->core.system_wide && evlist->core.threads && thread >= 0) - sid->tid = perf_thread_map__pid(evlist->core.threads, thread); - else - sid->tid = -1; -} - struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) { struct hlist_head *head; @@ -577,11 +572,11 @@ static void evlist__munmap_nofree(struct evlist *evlist) if (evlist->mmap) for (i = 0; i < evlist->core.nr_mmaps; i++) - perf_mmap__munmap(&evlist->mmap[i]); + perf_mmap__munmap(&evlist->mmap[i].core); if (evlist->overwrite_mmap) for (i = 0; i < evlist->core.nr_mmaps; i++) - perf_mmap__munmap(&evlist->overwrite_mmap[i]); + perf_mmap__munmap(&evlist->overwrite_mmap[i].core); } void evlist__munmap(struct evlist *evlist) @@ -591,22 +586,26 @@ void evlist__munmap(struct evlist *evlist) zfree(&evlist->overwrite_mmap); } +static void perf_mmap__unmap_cb(struct perf_mmap *map) +{ + struct mmap *m = container_of(map, struct mmap, core); + + mmap__munmap(m); +} + static struct mmap *evlist__alloc_mmap(struct evlist *evlist, bool overwrite) { int i; struct mmap *map; - evlist->core.nr_mmaps = perf_cpu_map__nr(evlist->core.cpus); - if (perf_cpu_map__empty(evlist->core.cpus)) - evlist->core.nr_mmaps = perf_thread_map__nr(evlist->core.threads); map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap)); if (!map) return NULL; for (i = 0; i < evlist->core.nr_mmaps; i++) { - map[i].core.fd = -1; - map[i].core.overwrite = overwrite; + struct perf_mmap *prev = i ? &map[i - 1].core : NULL; + /* * When the perf_mmap() call is made we grab one refcount, plus * one extra to let perf_mmap__consume() get the last @@ -616,151 +615,56 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist, * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and * thus does perf_mmap__get() on it. */ - refcount_set(&map[i].core.refcnt, 0); + perf_mmap__init(&map[i].core, prev, overwrite, perf_mmap__unmap_cb); } + return map; } -static bool -perf_evlist__should_poll(struct evlist *evlist __maybe_unused, - struct evsel *evsel) +static void +perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist, + struct perf_mmap_param *_mp, + int idx, bool per_cpu) { - if (evsel->core.attr.write_backward) - return false; - return true; + struct evlist *evlist = container_of(_evlist, struct evlist, core); + struct mmap_params *mp = container_of(_mp, struct mmap_params, core); + + auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, idx, per_cpu); } -static int evlist__mmap_per_evsel(struct evlist *evlist, int idx, - struct mmap_params *mp, int cpu_idx, - int thread, int *_output, int *_output_overwrite) +static struct perf_mmap* +perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) { - struct evsel *evsel; - int revent; - int evlist_cpu = cpu_map__cpu(evlist->core.cpus, cpu_idx); - - evlist__for_each_entry(evlist, evsel) { - struct mmap *maps = evlist->mmap; - int *output = _output; - int fd; - int cpu; - - mp->prot = PROT_READ | PROT_WRITE; - if (evsel->core.attr.write_backward) { - output = _output_overwrite; - maps = evlist->overwrite_mmap; - - if (!maps) { - maps = evlist__alloc_mmap(evlist, true); - if (!maps) - return -1; - evlist->overwrite_mmap = maps; - if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); - } - mp->prot &= ~PROT_WRITE; - } - - if (evsel->core.system_wide && thread) - continue; + struct evlist *evlist = container_of(_evlist, struct evlist, core); + struct mmap *maps; - cpu = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu); - if (cpu == -1) - continue; - - fd = FD(evsel, cpu, thread); + maps = overwrite ? evlist->overwrite_mmap : evlist->mmap; - if (*output == -1) { - *output = fd; + if (!maps) { + maps = evlist__alloc_mmap(evlist, overwrite); + if (!maps) + return NULL; - if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0) - return -1; + if (overwrite) { + evlist->overwrite_mmap = maps; + if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) - return -1; - - perf_mmap__get(&maps[idx]); - } - - revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0; - - /* - * The system_wide flag causes a selected event to be opened - * always without a pid. Consequently it will never get a - * POLLHUP, but it is used for tracking in combination with - * other events, so it should not need to be polled anyway. - * Therefore don't add it for polling. - */ - if (!evsel->core.system_wide && - perf_evlist__add_pollfd(&evlist->core, fd, &maps[idx], revent) < 0) { - perf_mmap__put(&maps[idx]); - return -1; - } - - if (evsel->core.attr.read_format & PERF_FORMAT_ID) { - if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread, - fd) < 0) - return -1; - perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, - thread); + evlist->mmap = maps; } } - return 0; + return &maps[idx].core; } -static int evlist__mmap_per_cpu(struct evlist *evlist, - struct mmap_params *mp) +static int +perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp, + int output, int cpu) { - int cpu, thread; - int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); - int nr_threads = perf_thread_map__nr(evlist->core.threads); - - pr_debug2("perf event ring buffer mmapped per cpu\n"); - for (cpu = 0; cpu < nr_cpus; cpu++) { - int output = -1; - int output_overwrite = -1; - - auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu, - true); + struct mmap *map = container_of(_map, struct mmap, core); + struct mmap_params *mp = container_of(_mp, struct mmap_params, core); - for (thread = 0; thread < nr_threads; thread++) { - if (evlist__mmap_per_evsel(evlist, cpu, mp, cpu, - thread, &output, &output_overwrite)) - goto out_unmap; - } - } - - return 0; - -out_unmap: - evlist__munmap_nofree(evlist); - return -1; -} - -static int evlist__mmap_per_thread(struct evlist *evlist, - struct mmap_params *mp) -{ - int thread; - int nr_threads = perf_thread_map__nr(evlist->core.threads); - - pr_debug2("perf event ring buffer mmapped per thread\n"); - for (thread = 0; thread < nr_threads; thread++) { - int output = -1; - int output_overwrite = -1; - - auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread, - false); - - if (evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, - &output, &output_overwrite)) - goto out_unmap; - } - - return 0; - -out_unmap: - evlist__munmap_nofree(evlist); - return -1; + return mmap__mmap(map, mp, output, cpu); } unsigned long perf_event_mlock_kb_in_pages(void) @@ -890,43 +794,30 @@ int evlist__mmap_ex(struct evlist *evlist, unsigned int pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level) { - struct evsel *evsel; - const struct perf_cpu_map *cpus = evlist->core.cpus; - const struct perf_thread_map *threads = evlist->core.threads; /* * Delay setting mp.prot: set it before calling perf_mmap__mmap. * Its value is decided by evsel's write_backward. * So &mp should not be passed through const pointer. */ - struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush, - .comp_level = comp_level }; - - if (!evlist->mmap) - evlist->mmap = evlist__alloc_mmap(evlist, false); - if (!evlist->mmap) - return -ENOMEM; - - if (evlist->core.pollfd.entries == NULL && perf_evlist__alloc_pollfd(&evlist->core) < 0) - return -ENOMEM; + struct mmap_params mp = { + .nr_cblocks = nr_cblocks, + .affinity = affinity, + .flush = flush, + .comp_level = comp_level + }; + struct perf_evlist_mmap_ops ops = { + .idx = perf_evlist__mmap_cb_idx, + .get = perf_evlist__mmap_cb_get, + .mmap = perf_evlist__mmap_cb_mmap, + }; evlist->core.mmap_len = evlist__mmap_size(pages); pr_debug("mmap size %zuB\n", evlist->core.mmap_len); - mp.mask = evlist->core.mmap_len - page_size - 1; auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len, auxtrace_pages, auxtrace_overwrite); - evlist__for_each_entry(evlist, evsel) { - if ((evsel->core.attr.read_format & PERF_FORMAT_ID) && - evsel->core.sample_id == NULL && - perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr) < 0) - return -ENOMEM; - } - - if (perf_cpu_map__empty(cpus)) - return evlist__mmap_per_thread(evlist, &mp); - - return evlist__mmap_per_cpu(evlist, &mp); + return perf_evlist__mmap_ops(&evlist->core, &ops, &mp.core); } int evlist__mmap(struct evlist *evlist, unsigned int pages) @@ -1029,6 +920,9 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) struct evsel *evsel; int err = 0; + if (filter == NULL) + return -1; + evlist__for_each_entry(evlist, evsel) { if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; @@ -1041,16 +935,35 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) return err; } -int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter) +{ + struct evsel *evsel; + int err = 0; + + if (filter == NULL) + return -1; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) + continue; + + err = perf_evsel__append_tp_filter(evsel, filter); + if (err) + break; + } + + return err; +} + +char *asprintf__tp_filter_pids(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; + return NULL; } else { char *tmp; @@ -1062,9 +975,18 @@ int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t * } } - ret = perf_evlist__set_tp_filter(evlist, filter); + return filter; out_free: free(filter); + return NULL; +} + +int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +{ + char *filter = asprintf__tp_filter_pids(npids, pids); + int ret = perf_evlist__set_tp_filter(evlist, filter); + + free(filter); return ret; } @@ -1073,6 +995,20 @@ int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) return perf_evlist__set_tp_filter_pids(evlist, 1, &pid); } +int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +{ + char *filter = asprintf__tp_filter_pids(npids, pids); + int ret = perf_evlist__append_tp_filter(evlist, filter); + + free(filter); + return ret; +} + +int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) +{ + return perf_evlist__append_tp_filter_pids(evlist, 1, &pid); +} + bool perf_evlist__valid_sample_type(struct evlist *evlist) { struct evsel *pos; @@ -1659,7 +1595,7 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, is_open = false; if (c2->leader == leader) { if (is_open) - perf_evsel__close(&evsel->core); + perf_evsel__close(&c2->core); c2->leader = c2; c2->core.nr_members = 0; } @@ -1729,9 +1665,9 @@ static void *perf_evlist__poll_thread(void *arg) struct mmap *map = &evlist->mmap[i]; union perf_event *event; - if (perf_mmap__read_init(map)) + if (perf_mmap__read_init(&map->core)) continue; - while ((event = perf_mmap__read_event(map)) != NULL) { + while ((event = perf_mmap__read_event(&map->core)) != NULL) { struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (evsel && evsel->side_band.cb) @@ -1739,10 +1675,10 @@ static void *perf_evlist__poll_thread(void *arg) else pr_warning("cannot locate proper evsel for the side band event\n"); - perf_mmap__consume(map); + perf_mmap__consume(&map->core); got_data = true; } - perf_mmap__read_done(map); + perf_mmap__read_done(&map->core); } if (draining && !got_data) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 7cfe75522ba5..3655b9ebb147 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -118,6 +118,13 @@ void perf_evlist__stop_sb_thread(struct evlist *evlist); int perf_evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); +int __evlist__set_tracepoints_handlers(struct evlist *evlist, + const struct evsel_str_handler *assocs, + size_t nr_assocs); + +#define evlist__set_tracepoints_handlers(evlist, array) \ + __evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) + void __perf_evlist__set_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit); void __perf_evlist__reset_sample_bit(struct evlist *evlist, @@ -133,6 +140,11 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter); int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); +int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter); + +int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); +int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); + struct evsel * perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id); @@ -164,6 +176,7 @@ void perf_evlist__set_id_pos(struct evlist *evlist); bool perf_can_sample_identifier(void); bool perf_can_record_switch_events(void); bool perf_can_record_cpu_wide(void); +bool perf_can_aux_sample(void); void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5591af81a070..f4dea055b080 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -30,6 +30,7 @@ #include "counts.h" #include "event.h" #include "evsel.h" +#include "util/env.h" #include "util/evsel_config.h" #include "util/evsel_fprintf.h" #include "evlist.h" @@ -845,6 +846,11 @@ static void apply_config_terms(struct evsel *evsel, case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT: attr->aux_output = term->val.aux_output ? 1 : 0; break; + case PERF_EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: + /* Already applied by auxtrace */ + break; + case PERF_EVSEL__CONFIG_TERM_CFG_CHG: + break; default: break; } @@ -904,6 +910,19 @@ static bool is_dummy_event(struct evsel *evsel) (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); } +struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel, + enum evsel_term_type type) +{ + struct perf_evsel_config_term *term, *found_term = NULL; + + list_for_each_entry(term, &evsel->config_terms, list) { + if (term->type == type) + found_term = term; + } + + return found_term; +} + /* * The enable_on_exec/disabled value strategy: * @@ -1523,7 +1542,7 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, static void display_attr(struct perf_event_attr *attr) { - if (verbose >= 2) { + if (verbose >= 2 || debug_peo_args) { fprintf(stderr, "%.60s\n", graph_dotted_line); fprintf(stderr, "perf_event_attr:\n"); perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); @@ -1539,7 +1558,7 @@ static int perf_event_open(struct evsel *evsel, int fd; while (1) { - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", + pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpu, group_fd, flags); fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, group_fd, flags); @@ -1559,9 +1578,9 @@ static int perf_event_open(struct evsel *evsel, break; } - pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); + pr_debug2_peo("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); evsel->core.attr.precise_ip--; - pr_debug2("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip); + pr_debug2_peo("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip); display_attr(&evsel->core.attr); } @@ -1573,7 +1592,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; - int pid = -1, err; + int pid = -1, err, old_errno; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) || @@ -1680,12 +1699,12 @@ retry_open: continue; } - pr_debug2("\nsys_perf_event_open failed, error %d\n", + pr_debug2_peo("\nsys_perf_event_open failed, error %d\n", err); goto try_fallback; } - pr_debug2(" = %d\n", fd); + pr_debug2_peo(" = %d\n", fd); if (evsel->bpf_fd >= 0) { int evt_fd = fd; @@ -1726,8 +1745,8 @@ try_fallback: */ if (err == -EMFILE && set_rlimit < INCREASED_MAX) { struct rlimit l; - int old_errno = errno; + old_errno = errno; if (getrlimit(RLIMIT_NOFILE, &l) == 0) { if (set_rlimit == NO_CHANGE) l.rlim_cur = l.rlim_max; @@ -1753,71 +1772,74 @@ try_fallback: */ if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { perf_missing_features.aux_output = true; - pr_debug2("Kernel has no attr.aux_output support, bailing out\n"); + pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n"); goto out_close; } else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) { perf_missing_features.bpf = true; - pr_debug2("switching off bpf_event\n"); + pr_debug2_peo("switching off bpf_event\n"); goto fallback_missing_features; } else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { perf_missing_features.ksymbol = true; - pr_debug2("switching off ksymbol\n"); + pr_debug2_peo("switching off ksymbol\n"); goto fallback_missing_features; } else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { perf_missing_features.write_backward = true; - pr_debug2("switching off write_backward\n"); + pr_debug2_peo("switching off write_backward\n"); goto out_close; } else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { perf_missing_features.clockid_wrong = true; - pr_debug2("switching off clockid\n"); + pr_debug2_peo("switching off clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { perf_missing_features.clockid = true; - pr_debug2("switching off use_clockid\n"); + pr_debug2_peo("switching off use_clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { perf_missing_features.cloexec = true; - pr_debug2("switching off cloexec flag\n"); + pr_debug2_peo("switching off cloexec flag\n"); goto fallback_missing_features; } else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { perf_missing_features.mmap2 = true; - pr_debug2("switching off mmap2\n"); + pr_debug2_peo("switching off mmap2\n"); goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) { perf_missing_features.exclude_guest = true; - pr_debug2("switching off exclude_guest, exclude_host\n"); + pr_debug2_peo("switching off exclude_guest, exclude_host\n"); goto fallback_missing_features; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; - pr_debug2("switching off sample_id_all\n"); + pr_debug2_peo("switching off sample_id_all\n"); goto retry_sample_id; } else if (!perf_missing_features.lbr_flags && (evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; - pr_debug2("switching off branch sample type no (cycles/flags)\n"); + pr_debug2_peo("switching off branch sample type no (cycles/flags)\n"); goto fallback_missing_features; } else if (!perf_missing_features.group_read && evsel->core.attr.inherit && (evsel->core.attr.read_format & PERF_FORMAT_GROUP) && perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; - pr_debug2("switching off group read\n"); + pr_debug2_peo("switching off group read\n"); goto fallback_missing_features; } out_close: if (err) threads->err_thread = thread; + old_errno = errno; do { while (--thread >= 0) { - close(FD(evsel, cpu, thread)); + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } thread = nthreads; } while (--cpu >= 0); + errno = old_errno; return err; } @@ -2205,6 +2227,19 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + if (type & PERF_SAMPLE_AUX) { + OVERFLOW_CHECK_u64(array); + sz = *array++; + + OVERFLOW_CHECK(array, sz, max_size); + /* Undo swap of data */ + if (swapped) + mem_bswap_64((char *)array, sz); + data->aux_sample.size = sz; + data->aux_sample.data = (char *)array; + array = (void *)array + sz; + } + return 0; } @@ -2512,7 +2547,7 @@ struct perf_env *perf_evsel__env(struct evsel *evsel) { if (evsel && evsel->evlist) return evsel->evlist->env; - return NULL; + return &perf_env; } static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index 8a7648037c18..1f8d2fe0b66e 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -25,6 +25,8 @@ enum evsel_term_type { PERF_EVSEL__CONFIG_TERM_BRANCH, PERF_EVSEL__CONFIG_TERM_PERCORE, PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT, + PERF_EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, + PERF_EVSEL__CONFIG_TERM_CFG_CHG, }; struct perf_evsel_config_term { @@ -44,7 +46,18 @@ struct perf_evsel_config_term { unsigned long max_events; bool percore; bool aux_output; + u32 aux_sample_size; + u64 cfg_chg; } val; bool weak; }; + +struct evsel; + +struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel, + enum evsel_term_type type); + +#define perf_evsel__get_config_term(evsel, type) \ + __perf_evsel__get_config_term(evsel, PERF_EVSEL__CONFIG_TERM_ ## type) + #endif // __PERF_EVSEL_CONFIG_H diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 028df7afb0dc..3b4842840db0 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -125,13 +125,18 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, callchain_cursor_commit(cursor); while (1) { + struct symbol *sym; + struct map *map; u64 addr = 0; node = callchain_cursor_current(cursor); if (!node) break; - if (node->sym && node->sym->ignore && print_skip_ignored) + sym = node->ms.sym; + map = node->ms.map; + + if (sym && sym->ignore && print_skip_ignored) goto next; printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); @@ -142,42 +147,42 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_ip) printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); - if (node->map) - addr = node->map->map_ip(node->map, node->ip); + if (map) + addr = map->map_ip(map, node->ip); if (print_sym) { printed += fprintf(fp, " "); node_al.addr = addr; - node_al.map = node->map; + node_al.map = map; if (print_symoffset) { - printed += __symbol__fprintf_symname_offs(node->sym, &node_al, + printed += __symbol__fprintf_symname_offs(sym, &node_al, print_unknown_as_addr, true, fp); } else { - printed += __symbol__fprintf_symname(node->sym, &node_al, + printed += __symbol__fprintf_symname(sym, &node_al, print_unknown_as_addr, fp); } } - if (print_dso && (!node->sym || !node->sym->inlined)) { + if (print_dso && (!sym || !sym->inlined)) { printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(node->map, fp); + printed += map__fprintf_dsoname(map, fp); printed += fprintf(fp, ")"); } if (print_srcline) - printed += map__fprintf_srcline(node->map, addr, "\n ", fp); + printed += map__fprintf_srcline(map, addr, "\n ", fp); - if (node->sym && node->sym->inlined) + if (sym && sym->inlined) printed += fprintf(fp, " (inlined)"); if (!print_oneline) printed += fprintf(fp, "\n"); /* Add srccode here too? */ - if (bt_stop_list && node->sym && - strlist__has_entry(bt_stop_list, node->sym->name)) { + if (bt_stop_list && sym && + strlist__has_entry(bt_stop_list, sym->name)) { break; } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 86d9396cb131..becc2d109423 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1296,8 +1296,10 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) continue; if (WARN_ONCE(cnt >= size, - "failed to write MEM_TOPOLOGY, way too many nodes\n")) + "failed to write MEM_TOPOLOGY, way too many nodes\n")) { + closedir(dir); return -1; + } ret = memory_node__read(&nodes[cnt++], idx); } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index ca53a929e9fd..840f95cee349 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -52,10 +52,6 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; -enum perf_dir_version { - PERF_DIR_VERSION = 1, -}; - struct perf_file_section { u64 offset; u64 size; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 679a1d75090c..0a8d72ae93ca 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -18,6 +18,7 @@ #include "srcline.h" #include "symbol.h" #include "thread.h" +#include "block-info.h" #include "ui/progress.h" #include <errno.h> #include <math.h> @@ -80,6 +81,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) int symlen; u16 len; + if (h->block_info) + return; /* * +4 accounts for '[x] ' priv level info * +2 accounts for 0x prefix on raw addresses @@ -109,13 +112,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); if (h->branch_info) { - if (h->branch_info->from.sym) { - symlen = (int)h->branch_info->from.sym->namelen + 4; + if (h->branch_info->from.ms.sym) { + symlen = (int)h->branch_info->from.ms.sym->namelen + 4; if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); - symlen = dso__name_len(h->branch_info->from.map->dso); + symlen = dso__name_len(h->branch_info->from.ms.map->dso); hists__new_col_len(hists, HISTC_DSO_FROM, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -123,13 +126,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM); } - if (h->branch_info->to.sym) { - symlen = (int)h->branch_info->to.sym->namelen + 4; + if (h->branch_info->to.ms.sym) { + symlen = (int)h->branch_info->to.ms.sym->namelen + 4; if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); - symlen = dso__name_len(h->branch_info->to.map->dso); + symlen = dso__name_len(h->branch_info->to.ms.map->dso); hists__new_col_len(hists, HISTC_DSO_TO, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -146,8 +149,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) } if (h->mem_info) { - if (h->mem_info->daddr.sym) { - symlen = (int)h->mem_info->daddr.sym->namelen + 4 + if (h->mem_info->daddr.ms.sym) { + symlen = (int)h->mem_info->daddr.ms.sym->namelen + 4 + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -161,8 +164,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen); } - if (h->mem_info->iaddr.sym) { - symlen = (int)h->mem_info->iaddr.sym->namelen + 4 + if (h->mem_info->iaddr.ms.sym) { + symlen = (int)h->mem_info->iaddr.ms.sym->namelen + 4 + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL, symlen); @@ -172,8 +175,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen); } - if (h->mem_info->daddr.map) { - symlen = dso__name_len(h->mem_info->daddr.map->dso); + if (h->mem_info->daddr.ms.map) { + symlen = dso__name_len(h->mem_info->daddr.ms.map->dso); hists__new_col_len(hists, HISTC_MEM_DADDR_DSO, symlen); } else { @@ -440,13 +443,13 @@ static int hist_entry__init(struct hist_entry *he, memcpy(he->branch_info, template->branch_info, sizeof(*he->branch_info)); - map__get(he->branch_info->from.map); - map__get(he->branch_info->to.map); + map__get(he->branch_info->from.ms.map); + map__get(he->branch_info->to.ms.map); } if (he->mem_info) { - map__get(he->mem_info->iaddr.map); - map__get(he->mem_info->daddr.map); + map__get(he->mem_info->iaddr.ms.map); + map__get(he->mem_info->daddr.ms.map); } if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) @@ -489,13 +492,13 @@ err_rawdata: err_infos: if (he->branch_info) { - map__put(he->branch_info->from.map); - map__put(he->branch_info->to.map); + map__put(he->branch_info->from.ms.map); + map__put(he->branch_info->to.ms.map); zfree(&he->branch_info); } if (he->mem_info) { - map__put(he->mem_info->iaddr.map); - map__put(he->mem_info->daddr.map); + map__put(he->mem_info->iaddr.ms.map); + map__put(he->mem_info->daddr.ms.map); } err: map__zput(he->ms.map); @@ -689,6 +692,7 @@ __hists__add_entry(struct hists *hists, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, .ms = { + .mg = al->mg, .map = al->map, .sym = al->sym, }, @@ -755,6 +759,11 @@ struct hist_entry *hists__add_entry_block(struct hists *hists, struct hist_entry entry = { .block_info = block_info, .hists = hists, + .ms = { + .mg = al->mg, + .map = al->map, + .sym = al->sym, + }, }, *he = hists__findnew_entry(hists, &entry, al, false); return he; @@ -886,8 +895,9 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) if (iter->curr >= iter->total) return 0; - al->map = bi[i].to.map; - al->sym = bi[i].to.sym; + al->mg = bi[i].to.ms.mg; + al->map = bi[i].to.ms.map; + al->sym = bi[i].to.ms.sym; al->addr = bi[i].to.addr; return 1; } @@ -905,7 +915,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a bi = iter->priv; - if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + if (iter->hide_unresolved && !(bi[i].from.ms.sym && bi[i].to.ms.sym)) goto out; /* @@ -1062,6 +1072,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .comm = thread__comm(al->thread), .ip = al->addr, .ms = { + .mg = al->mg, .map = al->map, .sym = al->sym, }, @@ -1244,16 +1255,16 @@ void hist_entry__delete(struct hist_entry *he) map__zput(he->ms.map); if (he->branch_info) { - map__zput(he->branch_info->from.map); - map__zput(he->branch_info->to.map); + map__zput(he->branch_info->from.ms.map); + map__zput(he->branch_info->to.ms.map); free_srcline(he->branch_info->srcline_from); free_srcline(he->branch_info->srcline_to); zfree(&he->branch_info); } if (he->mem_info) { - map__zput(he->mem_info->iaddr.map); - map__zput(he->mem_info->daddr.map); + map__zput(he->mem_info->iaddr.ms.map); + map__zput(he->mem_info->daddr.ms.map); mem_info__zput(he->mem_info); } @@ -1625,7 +1636,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; @@ -2569,7 +2580,8 @@ int hists__unlink(struct hists *hists) } void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, - struct perf_sample *sample, bool nonany_branch_mode) + struct perf_sample *sample, bool nonany_branch_mode, + u64 *total_cycles) { struct branch_info *bi; @@ -2596,6 +2608,9 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, nonany_branch_mode ? NULL : prev, bi[i].flags.cycles); prev = &bi[i].to; + + if (total_cycles) + *total_cycles += bi[i].flags.cycles; } free(bi); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 6a186b668303..45286900aacb 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -449,6 +449,8 @@ enum rstype { A_SOURCE }; +struct block_hist; + #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" void attr_to_script(char *buf, struct perf_event_attr *attr); @@ -474,6 +476,10 @@ void run_script(char *cmd); int res_sample_browse(struct res_sample *res_samples, int num_res, struct evsel *evsel, enum rstype rstype); void res_sample_init(void); + +int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, + float min_percent, struct perf_env *env, + struct annotation_options *annotation_opts); #else static inline int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, @@ -518,6 +524,15 @@ static inline int res_sample_browse(struct res_sample *res_samples __maybe_unuse static inline void res_sample_init(void) {} +static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused, + struct evsel *evsel __maybe_unused, + float min_percent __maybe_unused, + struct perf_env *env __maybe_unused, + struct annotation_options *annotation_opts __maybe_unused) +{ + return 0; +} + #define K_LEFT -1000 #define K_RIGHT -2000 #define K_SWITCH_INPUT_DATA -3000 @@ -527,7 +542,8 @@ unsigned int hists__sort_list_width(struct hists *hists); unsigned int hists__overhead_width(struct hists *hists); void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, - struct perf_sample *sample, bool nonany_branch_mode); + struct perf_sample *sample, bool nonany_branch_mode, + u64 *total_cycles); struct option; int parse_filter_percentage(const struct option *opt, const char *arg, int unset); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index a1c9eb6d4f40..409afc611be9 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -233,6 +233,16 @@ static void intel_pt_log_event(union perf_event *event) perf_event__fprintf(event, f); } +static void intel_pt_dump_sample(struct perf_session *session, + struct perf_sample *sample) +{ + struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, + auxtrace); + + printf("\n"); + intel_pt_dump(pt, sample->aux_sample.data, sample->aux_sample.size); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -836,6 +846,18 @@ static bool intel_pt_have_tsc(struct intel_pt *pt) return have_tsc; } +static bool intel_pt_sampling_mode(struct intel_pt *pt) +{ + struct evsel *evsel; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if ((evsel->core.attr.sample_type & PERF_SAMPLE_AUX) && + evsel->core.attr.aux_sample_size) + return true; + } + return false; +} + static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns) { u64 quot, rem; @@ -2320,6 +2342,56 @@ static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid, return 0; } +static void intel_pt_sample_set_pid_tid_cpu(struct intel_pt_queue *ptq, + struct auxtrace_queue *queue, + struct perf_sample *sample) +{ + struct machine *m = ptq->pt->machine; + + ptq->pid = sample->pid; + ptq->tid = sample->tid; + ptq->cpu = queue->cpu; + + intel_pt_log("queue %u cpu %d pid %d tid %d\n", + ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid); + + thread__zput(ptq->thread); + + if (ptq->tid == -1) + return; + + if (ptq->pid == -1) { + ptq->thread = machine__find_thread(m, -1, ptq->tid); + if (ptq->thread) + ptq->pid = ptq->thread->pid_; + return; + } + + ptq->thread = machine__findnew_thread(m, ptq->pid, ptq->tid); +} + +static int intel_pt_process_timeless_sample(struct intel_pt *pt, + struct perf_sample *sample) +{ + struct auxtrace_queue *queue; + struct intel_pt_queue *ptq; + u64 ts = 0; + + queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session); + if (!queue) + return -EINVAL; + + ptq = queue->priv; + if (!ptq) + return 0; + + ptq->stop = false; + ptq->time = sample->time; + intel_pt_sample_set_pid_tid_cpu(ptq, queue, sample); + intel_pt_run_decoder(ptq, &ts); + return 0; +} + static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample) { return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu, @@ -2550,7 +2622,11 @@ static int intel_pt_process_event(struct perf_session *session, } if (pt->timeless_decoding) { - if (event->header.type == PERF_RECORD_EXIT) { + if (pt->sampling_mode) { + if (sample->aux_sample.size) + err = intel_pt_process_timeless_sample(pt, + sample); + } else if (event->header.type == PERF_RECORD_EXIT) { err = intel_pt_process_timeless_queues(pt, event->fork.tid, sample->time); @@ -2676,6 +2752,28 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session, return 0; } +static int intel_pt_queue_data(struct perf_session *session, + struct perf_sample *sample, + union perf_event *event, u64 data_offset) +{ + struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, + auxtrace); + u64 timestamp; + + if (event) { + return auxtrace_queues__add_event(&pt->queues, session, event, + data_offset, NULL); + } + + if (sample->time && sample->time != (u64)-1) + timestamp = perf_time_to_tsc(sample->time, &pt->tc); + else + timestamp = 0; + + return auxtrace_queues__add_sample(&pt->queues, session, sample, + data_offset, timestamp); +} + struct intel_pt_synth { struct perf_tool dummy_tool; struct perf_session *session; @@ -3178,7 +3276,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (pt->timeless_decoding && !pt->tc.time_mult) pt->tc.time_mult = 1; pt->have_tsc = intel_pt_have_tsc(pt); - pt->sampling_mode = false; + pt->sampling_mode = intel_pt_sampling_mode(pt); pt->est_tsc = !pt->timeless_decoding; pt->unknown_thread = thread__new(999999999, 999999999); @@ -3205,6 +3303,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event, pt->auxtrace.process_event = intel_pt_process_event; pt->auxtrace.process_auxtrace_event = intel_pt_process_auxtrace_event; + pt->auxtrace.queue_data = intel_pt_queue_data; + pt->auxtrace.dump_auxtrace_sample = intel_pt_dump_sample; pt->auxtrace.flush_events = intel_pt_flush; pt->auxtrace.free_events = intel_pt_free_events; pt->auxtrace.free = intel_pt_free; @@ -3282,7 +3382,10 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_setup_pebs_events(pt); - err = auxtrace_queues__process_index(&pt->queues, session); + if (pt->sampling_mode || list_empty(&session->auxtrace_index)) + err = auxtrace_queue_data(session, true, true); + else + err = auxtrace_queues__process_index(&pt->queues, session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 1bdf4c6ea3e5..e3ccb0ce1938 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -395,7 +395,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) size_t size; u16 idr_size; const char *sym; - uint32_t count; + uint64_t count; int ret, csize, usize; pid_t pid, tid; struct { @@ -418,7 +418,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) return -1; filename = event->mmap2.filename; - size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so", + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, pid, count); @@ -529,7 +529,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) return -1; filename = event->mmap2.filename; - size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64, + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, pid, jr->move.code_index); diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 8d04e3d070b1..eae47c2509eb 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -233,14 +233,14 @@ static int detect_kbuild_dir(char **kbuild_dir) const char *prefix_dir = ""; const char *suffix_dir = ""; + /* _UTSNAME_LENGTH is 65 */ + char release[128]; + char *autoconf_path; int err; if (!test_dir) { - /* _UTSNAME_LENGTH is 65 */ - char release[128]; - err = fetch_kernel_version(NULL, release, sizeof(release)); if (err) @@ -418,10 +418,9 @@ void llvm__dump_obj(const char *path, void *obj_buf, size_t size) goto out; } - pr_info("LLVM: dumping %s\n", obj_path); + pr_debug("LLVM: dumping %s\n", obj_path); if (fwrite(obj_buf, size, 1, fp) != 1) - pr_warning("WARNING: failed to write to file '%s': %s, skip object dumping\n", - obj_path, strerror(errno)); + pr_debug("WARNING: failed to write to file '%s': %s, skip object dumping\n", obj_path, strerror(errno)); fclose(fp); out: free(obj_path); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 70a9f8716a4b..e2a312c649f0 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -42,6 +42,11 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); +static struct dso *machine__kernel_dso(struct machine *machine) +{ + return machine->vmlinux_map->dso; +} + static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -767,45 +772,16 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, return machine__process_ksymbol_register(machine, event, sample); } -static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename) -{ - const char *dup_filename; - - if (!filename || !dso || !dso->long_name) - return; - if (dso->long_name[0] != '[') - return; - if (!strchr(filename, '/')) - return; - - dup_filename = strdup(filename); - if (!dup_filename) - return; - - dso__set_long_name(dso, dup_filename, true); -} - -struct map *machine__findnew_module_map(struct machine *machine, u64 start, - const char *filename) +static struct map *machine__addnew_module_map(struct machine *machine, u64 start, + const char *filename) { struct map *map = NULL; - struct dso *dso = NULL; struct kmod_path m; + struct dso *dso; if (kmod_path__parse_name(&m, filename)) return NULL; - map = map_groups__find_by_name(&machine->kmaps, m.name); - if (map) { - /* - * If the map's dso is an offline module, give dso__load() - * a chance to find the file path of that module by fixing - * long_name. - */ - dso__adjust_kmod_long_name(map->dso, filename); - goto out; - } - dso = machine__findnew_module_dso(machine, &m, filename); if (dso == NULL) goto out; @@ -861,7 +837,7 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) { int i; size_t printed = 0; - struct dso *kdso = machine__kernel_map(machine)->dso; + struct dso *kdso = machine__kernel_dso(machine); if (kdso->has_build_id) { char filename[PATH_MAX]; @@ -1057,7 +1033,7 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, * In the vmlinux case, pgoff is a virtual address which must now be * mapped to a vmlinux offset. */ - for (map = maps__first(maps); map; map = map__next(map)) { + maps__for_each_entry(maps, map) { struct kmap *kmap = __map__kmap(map); struct map *dest_map; @@ -1404,7 +1380,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, if (arch__fix_module_text_start(&start, &size, name) < 0) return -1; - map = machine__findnew_module_map(machine, start, name); + map = machine__addnew_module_map(machine, start, name); if (map == NULL) return -1; map->end = start + size; @@ -1543,8 +1519,7 @@ static bool perf_event__is_extra_kernel_mmap(struct machine *machine, static int machine__process_extra_kernel_map(struct machine *machine, union perf_event *event) { - struct map *kernel_map = machine__kernel_map(machine); - struct dso *kernel = kernel_map ? kernel_map->dso : NULL; + struct dso *kernel = machine__kernel_dso(machine); struct extra_kernel_map xm = { .start = event->mmap.start, .end = event->mmap.start + event->mmap.len, @@ -1580,8 +1555,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, strlen(machine->mmap_name) - 1) == 0; if (event->mmap.filename[0] == '/' || (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - map = machine__findnew_module_map(machine, event->mmap.start, - event->mmap.filename); + map = machine__addnew_module_map(machine, event->mmap.start, + event->mmap.filename); if (map == NULL) goto out_problem; @@ -1676,6 +1651,12 @@ int machine__process_mmap2_event(struct machine *machine, { struct thread *thread; struct map *map; + struct dso_id dso_id = { + .maj = event->mmap2.maj, + .min = event->mmap2.min, + .ino = event->mmap2.ino, + .ino_generation = event->mmap2.ino_generation, + }; int ret = 0; if (dump_trace) @@ -1696,10 +1677,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, - event->mmap2.maj, - event->mmap2.min, event->mmap2.ino, - event->mmap2.ino_generation, - event->mmap2.prot, + &dso_id, event->mmap2.prot, event->mmap2.flags, event->mmap2.filename, thread); @@ -1752,9 +1730,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - 0, 0, 0, 0, prot, 0, - event->mmap.filename, - thread); + NULL, prot, 0, event->mmap.filename, thread); if (map == NULL) goto out_problem_map; @@ -1964,8 +1940,9 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; + ams->ms.mg = al.mg; + ams->ms.sym = al.sym; + ams->ms.map = al.map; ams->phys_addr = 0; } @@ -1981,8 +1958,9 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; + ams->ms.mg = al.mg; + ams->ms.sym = al.sym; + ams->ms.map = al.map; ams->phys_addr = phys_addr; } @@ -2002,8 +1980,9 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return mi; } -static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip) +static char *callchain_srcline(struct map_symbol *ms, u64 ip) { + struct map *map = ms->map; char *srcline = NULL; if (!map || callchain_param.key == CCKEY_FUNCTION) @@ -2015,7 +1994,7 @@ 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, ip); + ms->sym, show_sym, show_addr, ip); srcline__tree_insert(&map->dso->srclines, ip, srcline); } @@ -2038,6 +2017,7 @@ static int add_callchain_ip(struct thread *thread, struct iterations *iter, u64 branch_from) { + struct map_symbol ms; struct addr_location al; int nr_loop_iter = 0; u64 iter_cycles = 0; @@ -2095,8 +2075,11 @@ static int add_callchain_ip(struct thread *thread, iter_cycles = iter->cycles; } - srcline = callchain_srcline(al.map, al.sym, al.addr); - return callchain_cursor_append(cursor, ip, al.map, al.sym, + ms.mg = al.mg; + ms.map = al.map; + ms.sym = al.sym; + srcline = callchain_srcline(&ms, al.addr); + return callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, iter_cycles, branch_from, srcline); } @@ -2403,7 +2386,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (callchain_param.order != ORDER_CALLEE) { + if (chain && callchain_param.order != ORDER_CALLEE) { err = find_prev_cpumode(chain, thread, cursor, parent, root_al, &cpumode, chain->nr - first_call); if (err) @@ -2444,9 +2427,10 @@ check_calls: return 0; } -static int append_inlines(struct callchain_cursor *cursor, - struct map *map, struct symbol *sym, u64 ip) +static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip) { + struct symbol *sym = ms->sym; + struct map *map = ms->map; struct inline_node *inline_node; struct inline_list *ilist; u64 addr; @@ -2467,8 +2451,11 @@ static int append_inlines(struct callchain_cursor *cursor, } list_for_each_entry(ilist, &inline_node->val, list) { - ret = callchain_cursor_append(cursor, ip, map, - ilist->symbol, false, + struct map_symbol ilist_ms = { + .map = map, + .sym = ilist->symbol, + }; + ret = callchain_cursor_append(cursor, ip, &ilist_ms, false, NULL, 0, 0, 0, ilist->srcline); if (ret != 0) @@ -2484,22 +2471,21 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) const char *srcline = NULL; u64 addr = entry->ip; - if (symbol_conf.hide_unresolved && entry->sym == NULL) + if (symbol_conf.hide_unresolved && entry->ms.sym == NULL) return 0; - if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) + if (append_inlines(cursor, &entry->ms, entry->ip) == 0) return 0; /* * Convert entry->ip from a virtual address to an offset in * its corresponding binary. */ - if (entry->map) - addr = map__map_ip(entry->map, entry->ip); + if (entry->ms.map) + addr = map__map_ip(entry->ms.map, entry->ip); - srcline = callchain_srcline(entry->map, entry->sym, addr); - return callchain_cursor_append(cursor, entry->ip, - entry->map, entry->sym, + srcline = callchain_srcline(&entry->ms, addr); + return callchain_cursor_append(cursor, entry->ip, &entry->ms, false, NULL, 0, 0, 0, srcline); } @@ -2725,9 +2711,14 @@ out: return addr_cpumode; } +struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id) +{ + return dsos__findnew_id(&machine->dsos, filename, id); +} + struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { - return dsos__findnew(&machine->dsos, filename); + return machine__findnew_dso_id(machine, filename, NULL); } char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 18e13c0ccd6a..499be204830d 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -11,6 +11,7 @@ struct addr_location; struct branch_stack; struct dso; +struct dso_id; struct evsel; struct perf_sample; struct symbol; @@ -202,6 +203,7 @@ int machine__nr_cpus_avail(struct machine *machine); struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); +struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id); struct dso *machine__findnew_dso(struct machine *machine, const char *filename); size_t machine__fprintf(struct machine *machine, FILE *fp); @@ -221,8 +223,6 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp); } -struct map *machine__findnew_module_map(struct machine *machine, u64 start, - const char *filename); int arch__fix_module_text_start(u64 *start, u64 *size, const char *name); int machine__load_kallsyms(struct machine *machine, const char *filename); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 5b83ed1ebbd6..744bfbaf35cf 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "symbol.h" +#include <assert.h> #include <errno.h> #include <inttypes.h> #include <limits.h> @@ -25,7 +26,6 @@ #include "ui/ui.h" static void __maps__insert(struct maps *maps, struct map *map); -static void __maps__insert_name(struct maps *maps, struct map *map); static inline int is_anon_memory(const char *filename, u32 flags) { @@ -139,14 +139,13 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; RB_CLEAR_NODE(&map->rb_node); - map->groups = NULL; map->erange_warned = false; refcount_set(&map->refcnt, 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, u32 prot, u32 flags, char *filename, + u64 pgoff, struct dso_id *id, + u32 prot, u32 flags, char *filename, struct thread *thread) { struct map *map = malloc(sizeof(*map)); @@ -162,11 +161,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, anon = is_anon_memory(filename, flags); vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); - - map->maj = d_maj; - map->min = d_min; - map->ino = ino; - map->ino_generation = ino_gen; map->prot = prot; map->flags = flags; nsi = nsinfo__get(thread->nsinfo); @@ -196,7 +190,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, pgoff = 0; dso = machine__findnew_vdso(machine, thread); } else - dso = machine__findnew_dso(machine, filename); + dso = machine__findnew_dso_id(machine, filename, id); if (dso == NULL) goto out_delete; @@ -243,18 +237,11 @@ struct map *map__new2(u64 start, struct dso *dso) return map; } -/* - * Use this and __map__is_kmodule() for map instances that are in - * machine->kmaps, and thus have map->groups->machine all properly set, to - * disambiguate between the kernel and modules. - * - * When the need arises, introduce map__is_{kernel,kmodule)() that - * checks (map->groups != NULL && map->groups->machine != NULL && - * map->dso->kernel) before calling __map__is_{kernel,kmodule}()) - */ bool __map__is_kernel(const struct map *map) { - return machine__kernel_map(map->groups->machine) == map; + if (!map->dso->kernel) + return false; + return machine__kernel_map(map__kmaps((struct map *)map)->machine) == map; } bool __map__is_extra_kernel_map(const struct map *map) @@ -287,7 +274,7 @@ bool map__has_symbols(const struct map *map) static void map__exit(struct map *map) { - BUG_ON(!RB_EMPTY_NODE(&map->rb_node)); + BUG_ON(refcount_read(&map->refcnt) != 0); dso__zput(map->dso); } @@ -394,7 +381,6 @@ struct map *map__clone(struct map *from) refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); - map->groups = NULL; } return map; @@ -574,7 +560,6 @@ u64 map__objdump_2mem(struct map *map, u64 ip) static void maps__init(struct maps *maps) { maps->entries = RB_ROOT; - maps->names = RB_ROOT; init_rwsem(&maps->lock); } @@ -582,39 +567,72 @@ void map_groups__init(struct map_groups *mg, struct machine *machine) { maps__init(&mg->maps); mg->machine = machine; + mg->last_search_by_name = NULL; + mg->nr_maps = 0; + mg->maps_by_name = NULL; refcount_set(&mg->refcnt, 1); } -void map_groups__insert(struct map_groups *mg, struct map *map) +static void __map_groups__free_maps_by_name(struct map_groups *mg) { - maps__insert(&mg->maps, map); - map->groups = mg; + /* + * Free everything to try to do it from the rbtree in the next search + */ + zfree(&mg->maps_by_name); + mg->nr_maps_allocated = 0; } -static void __maps__purge(struct maps *maps) +void map_groups__insert(struct map_groups *mg, struct map *map) { - struct rb_root *root = &maps->entries; - struct rb_node *next = rb_first(root); + struct maps *maps = &mg->maps; - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); + down_write(&maps->lock); + __maps__insert(maps, map); + ++mg->nr_maps; - next = rb_next(&pos->rb_node); - rb_erase_init(&pos->rb_node, root); - map__put(pos); + /* + * If we already performed some search by name, then we need to add the just + * inserted map and resort. + */ + if (mg->maps_by_name) { + if (mg->nr_maps > mg->nr_maps_allocated) { + int nr_allocate = mg->nr_maps * 2; + struct map **maps_by_name = realloc(mg->maps_by_name, nr_allocate * sizeof(map)); + + if (maps_by_name == NULL) { + __map_groups__free_maps_by_name(mg); + return; + } + + mg->maps_by_name = maps_by_name; + mg->nr_maps_allocated = nr_allocate; + } + mg->maps_by_name[mg->nr_maps - 1] = map; + __map_groups__sort_by_name(mg); } + up_write(&maps->lock); } -static void __maps__purge_names(struct maps *maps) +void map_groups__remove(struct map_groups *mg, struct map *map) { - struct rb_root *root = &maps->names; - struct rb_node *next = rb_first(root); + struct maps *maps = &mg->maps; + down_write(&maps->lock); + if (mg->last_search_by_name == map) + mg->last_search_by_name = NULL; - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node_name); + __maps__remove(maps, map); + --mg->nr_maps; + if (mg->maps_by_name) + __map_groups__free_maps_by_name(mg); + up_write(&maps->lock); +} - next = rb_next(&pos->rb_node_name); - rb_erase_init(&pos->rb_node_name, root); +static void __maps__purge(struct maps *maps) +{ + struct map *pos, *next; + + maps__for_each_entry_safe(maps, pos, next) { + rb_erase_init(&pos->rb_node, &maps->entries); map__put(pos); } } @@ -623,7 +641,6 @@ static void maps__exit(struct maps *maps) { down_write(&maps->lock); __maps__purge(maps); - __maps__purge_names(maps); up_write(&maps->lock); } @@ -686,13 +703,11 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { struct symbol *sym; - struct rb_node *nd; + struct map *pos; down_read(&maps->lock); - for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); - + maps__for_each_entry(maps, pos) { sym = map__find_symbol_by_name(pos, name); if (sym == NULL) @@ -719,31 +734,30 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, return maps__find_symbol_by_name(&mg->maps, name, mapp); } -int map_groups__find_ams(struct addr_map_symbol *ams) +int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams) { - if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { - if (ams->map->groups == NULL) + if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) { + if (mg == NULL) return -1; - ams->map = map_groups__find(ams->map->groups, ams->addr); - if (ams->map == NULL) + ams->ms.map = map_groups__find(mg, ams->addr); + if (ams->ms.map == NULL) return -1; } - ams->al_addr = ams->map->map_ip(ams->map, ams->addr); - ams->sym = map__find_symbol(ams->map, ams->al_addr); + ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr); + ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr); - return ams->sym ? 0 : -1; + return ams->ms.sym ? 0 : -1; } static size_t maps__fprintf(struct maps *maps, FILE *fp) { size_t printed = 0; - struct rb_node *nd; + struct map *pos; down_read(&maps->lock); - for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); + maps__for_each_entry(maps, pos) { printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 2) { @@ -765,12 +779,11 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) static void __map_groups__insert(struct map_groups *mg, struct map *map) { __maps__insert(&mg->maps, map); - __maps__insert_name(&mg->maps, map); - map->groups = mg; } -static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) +int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp) { + struct maps *maps = &mg->maps; struct rb_root *root; struct rb_node *next, *first; int err = 0; @@ -835,7 +848,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp } before->end = map->start; - __map_groups__insert(pos->groups, before); + __map_groups__insert(mg, before); if (verbose >= 2 && !use_browser) map__fprintf(before, fp); map__put(before); @@ -850,7 +863,9 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp } after->start = map->end; - __map_groups__insert(pos->groups, after); + after->pgoff += map->end - pos->start; + assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end)); + __map_groups__insert(mg, after); if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); @@ -868,12 +883,6 @@ out: return err; } -int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - FILE *fp) -{ - return maps__fixup_overlappings(&mg->maps, map, fp); -} - /* * XXX This should not really _copy_ te maps, but refcount them. */ @@ -886,7 +895,7 @@ int map_groups__clone(struct thread *thread, struct map_groups *parent) down_read(&maps->lock); - for (map = maps__first(maps); map; map = map__next(map)) { + maps__for_each_entry(maps, map) { struct map *new = map__clone(map); if (new == NULL) goto out_unlock; @@ -926,42 +935,17 @@ static void __maps__insert(struct maps *maps, struct map *map) map__get(map); } -static void __maps__insert_name(struct maps *maps, struct map *map) -{ - struct rb_node **p = &maps->names.rb_node; - struct rb_node *parent = NULL; - struct map *m; - int rc; - - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct map, rb_node_name); - rc = strcmp(m->dso->short_name, map->dso->short_name); - if (rc < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&map->rb_node_name, parent, p); - rb_insert_color(&map->rb_node_name, &maps->names); - map__get(map); -} - void maps__insert(struct maps *maps, struct map *map) { down_write(&maps->lock); __maps__insert(maps, map); - __maps__insert_name(maps, map); up_write(&maps->lock); } -static void __maps__remove(struct maps *maps, struct map *map) +void __maps__remove(struct maps *maps, struct map *map) { rb_erase_init(&map->rb_node, &maps->entries); map__put(map); - - rb_erase_init(&map->rb_node_name, &maps->names); - map__put(map); } void maps__remove(struct maps *maps, struct map *map) @@ -1004,7 +988,7 @@ struct map *maps__first(struct maps *maps) return NULL; } -struct map *map__next(struct map *map) +static struct map *__map__next(struct map *map) { struct rb_node *next = rb_next(&map->rb_node); @@ -1013,6 +997,11 @@ struct map *map__next(struct map *map) return NULL; } +struct map *map__next(struct map *map) +{ + return map ? __map__next(map) : NULL; +} + struct kmap *__map__kmap(struct map *map) { if (!map->dso || !map->dso->kernel) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index c3614195ddc7..5e8899883231 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -23,18 +23,13 @@ struct map { struct rb_node rb_node; struct list_head node; }; - struct rb_node rb_node_name; u64 start; u64 end; - bool erange_warned; - u32 priv; + bool erange_warned:1; + bool priv:1; u32 prot; - u32 flags; u64 pgoff; u64 reloc; - u32 maj, min; /* only valid for MMAP2 record */ - u64 ino; /* only valid for MMAP2 record */ - u64 ino_generation;/* only valid for MMAP2 record */ /* ip -> dso rip */ u64 (*map_ip)(struct map *, u64); @@ -42,8 +37,8 @@ struct map { u64 (*unmap_ip)(struct map *, u64); struct dso *dso; - struct map_groups *groups; refcount_t refcnt; + u32 flags; }; struct kmap; @@ -110,9 +105,11 @@ struct thread; void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso); + +struct dso_id; + struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, u32 prot, u32 flags, + u64 pgoff, struct dso_id *id, u32 prot, u32 flags, char *filename, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h index 77252e14008f..63ed211fe241 100644 --- a/tools/perf/util/map_groups.h +++ b/tools/perf/util/map_groups.h @@ -16,21 +16,32 @@ struct thread; struct maps { struct rb_root entries; - struct rb_root names; struct rw_semaphore lock; }; void maps__insert(struct maps *maps, struct map *map); void maps__remove(struct maps *maps, struct map *map); +void __maps__remove(struct maps *maps, struct map *map); struct map *maps__find(struct maps *maps, u64 addr); struct map *maps__first(struct maps *maps); struct map *map__next(struct map *map); + +#define maps__for_each_entry(maps, map) \ + for (map = maps__first(maps); map; map = map__next(map)) + +#define maps__for_each_entry_safe(maps, map, next) \ + for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map)) + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp); struct map_groups { struct maps maps; struct machine *machine; + struct map *last_search_by_name; + struct map **maps_by_name; refcount_t refcnt; + unsigned int nr_maps; + unsigned int nr_maps_allocated; #ifdef HAVE_LIBUNWIND_SUPPORT void *addr_space; struct unwind_libunwind_ops *unwind_libunwind_ops; @@ -64,29 +75,25 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); void map_groups__insert(struct map_groups *mg, struct map *map); -static inline void map_groups__remove(struct map_groups *mg, struct map *map) -{ - maps__remove(&mg->maps, map); -} +void map_groups__remove(struct map_groups *mg, struct map *map); static inline struct map *map_groups__find(struct map_groups *mg, u64 addr) { return maps__find(&mg->maps, addr); } -struct map *map_groups__first(struct map_groups *mg); +#define map_groups__for_each_entry(mg, map) \ + for (map = maps__first(&mg->maps); map; map = map__next(map)) -static inline struct map *map_groups__next(struct map *map) -{ - return map__next(map); -} +#define map_groups__for_each_entry_safe(mg, map, next) \ + for (map = maps__first(&mg->maps), next = map__next(map); map; map = next, next = map__next(map)) struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp); struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp); struct addr_map_symbol; -int map_groups__find_ams(struct addr_map_symbol *ams); +int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams); int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp); @@ -94,4 +101,6 @@ struct map *map_groups__find_by_name(struct map_groups *mg, const char *name); int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map); +void __map_groups__sort_by_name(struct map_groups *mg); + #endif // __PERF_MAP_GROUPS_H diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 5a1aed9f6bb4..2964d971aeab 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -4,17 +4,18 @@ #include <linux/types.h> +struct map_groups; struct map; struct symbol; struct map_symbol { + struct map_groups *mg; struct map *map; struct symbol *sym; }; struct addr_map_symbol { - struct map *map; - struct symbol *sym; + struct map_symbol ms; u64 addr; u64 al_addr; u64 phys_addr; diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 3d391583f2ae..aa29589f6904 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -410,7 +410,7 @@ do { \ return -1; } - if (!mi->daddr.map || !mi->iaddr.map) { + if (!mi->daddr.ms.map || !mi->iaddr.ms.map) { stats->nomap++; return -1; } diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index a7c0424dbda3..6a4d350d5cdb 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -523,7 +523,7 @@ int metricgroup__parse_groups(const struct option *opt, if (ret) return ret; pr_debug("adding %s\n", extra_events.buf); - memset(&parse_error, 0, sizeof(struct parse_events_error)); + bzero(&parse_error, sizeof(parse_error)); ret = parse_events(perf_evlist, extra_events.buf, &parse_error); if (ret) { parse_events_print_error(&parse_error, extra_events.buf); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index a35dc57d5995..063d1b93c53d 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -13,6 +13,7 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> // sysconf() +#include <perf/mmap.h> #ifdef HAVE_LIBNUMA_SUPPORT #include <numaif.h> #endif @@ -23,116 +24,9 @@ #include "../perf.h" #include <internal/lib.h> /* page_size */ -size_t perf_mmap__mmap_len(struct mmap *map) +size_t mmap__mmap_len(struct mmap *map) { - return map->core.mask + 1 + page_size; -} - -/* When check_messup is true, 'end' must points to a good entry */ -static union perf_event *perf_mmap__read(struct mmap *map, - u64 *startp, u64 end) -{ - unsigned char *data = map->core.base + page_size; - union perf_event *event = NULL; - int diff = end - *startp; - - if (diff >= (int)sizeof(event->header)) { - size_t size; - - event = (union perf_event *)&data[*startp & map->core.mask]; - size = event->header.size; - - if (size < sizeof(event->header) || diff < (int)size) - return NULL; - - /* - * Event straddles the mmap boundary -- header should always - * be inside due to u64 alignment of output. - */ - if ((*startp & map->core.mask) + size != ((*startp + size) & map->core.mask)) { - unsigned int offset = *startp; - unsigned int len = min(sizeof(*event), size), cpy; - void *dst = map->core.event_copy; - - do { - cpy = min(map->core.mask + 1 - (offset & map->core.mask), len); - memcpy(dst, &data[offset & map->core.mask], cpy); - offset += cpy; - dst += cpy; - len -= cpy; - } while (len); - - event = (union perf_event *)map->core.event_copy; - } - - *startp += size; - } - - return event; -} - -/* - * Read event from ring buffer one by one. - * Return one event for each call. - * - * Usage: - * perf_mmap__read_init() - * while(event = perf_mmap__read_event()) { - * //process the event - * perf_mmap__consume() - * } - * perf_mmap__read_done() - */ -union perf_event *perf_mmap__read_event(struct mmap *map) -{ - union perf_event *event; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->core.refcnt)) - return NULL; - - /* non-overwirte doesn't pause the ringbuffer */ - if (!map->core.overwrite) - map->core.end = perf_mmap__read_head(map); - - event = perf_mmap__read(map, &map->core.start, map->core.end); - - if (!map->core.overwrite) - map->core.prev = map->core.start; - - return event; -} - -static bool perf_mmap__empty(struct mmap *map) -{ - return perf_mmap__read_head(map) == map->core.prev && !map->auxtrace_mmap.base; -} - -void perf_mmap__get(struct mmap *map) -{ - refcount_inc(&map->core.refcnt); -} - -void perf_mmap__put(struct mmap *map) -{ - BUG_ON(map->core.base && refcount_read(&map->core.refcnt) == 0); - - if (refcount_dec_and_test(&map->core.refcnt)) - perf_mmap__munmap(map); -} - -void perf_mmap__consume(struct mmap *map) -{ - if (!map->core.overwrite) { - u64 old = map->core.prev; - - perf_mmap__write_tail(map, old); - } - - if (refcount_read(&map->core.refcnt) == 1 && perf_mmap__empty(map)) - perf_mmap__put(map); + return perf_mmap__mmap_len(&map->core); } int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, @@ -170,7 +64,7 @@ static int perf_mmap__aio_enabled(struct mmap *map) #ifdef HAVE_LIBNUMA_SUPPORT static int perf_mmap__aio_alloc(struct mmap *map, int idx) { - map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, + map->aio.data[idx] = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); if (map->aio.data[idx] == MAP_FAILED) { map->aio.data[idx] = NULL; @@ -183,7 +77,7 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx) static void perf_mmap__aio_free(struct mmap *map, int idx) { if (map->aio.data[idx]) { - munmap(map->aio.data[idx], perf_mmap__mmap_len(map)); + munmap(map->aio.data[idx], mmap__mmap_len(map)); map->aio.data[idx] = NULL; } } @@ -196,7 +90,7 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) { data = map->aio.data[idx]; - mmap_len = perf_mmap__mmap_len(map); + mmap_len = mmap__mmap_len(map); node_mask = 1UL << cpu__get_node(cpu); if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) { pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n", @@ -210,7 +104,7 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) #else /* !HAVE_LIBNUMA_SUPPORT */ static int perf_mmap__aio_alloc(struct mmap *map, int idx) { - map->aio.data[idx] = malloc(perf_mmap__mmap_len(map)); + map->aio.data[idx] = malloc(mmap__mmap_len(map)); if (map->aio.data[idx] == NULL) return -1; @@ -311,19 +205,13 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) } #endif -void perf_mmap__munmap(struct mmap *map) +void mmap__munmap(struct mmap *map) { perf_mmap__aio_munmap(map); if (map->data != NULL) { - munmap(map->data, perf_mmap__mmap_len(map)); + munmap(map->data, mmap__mmap_len(map)); map->data = NULL; } - if (map->core.base != NULL) { - munmap(map->core.base, perf_mmap__mmap_len(map)); - map->core.base = NULL; - map->core.fd = -1; - refcount_set(&map->core.refcnt, 0); - } auxtrace_mmap__munmap(&map->auxtrace_mmap); } @@ -353,34 +241,13 @@ static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params CPU_SET(map->core.cpu, &map->affinity_mask); } -int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) { - /* - * The last one will be done at perf_mmap__consume(), so that we - * make sure we don't prevent tools from consuming every last event in - * the ring buffer. - * - * I.e. we can get the POLLHUP meaning that the fd doesn't exist - * anymore, but the last events for it are still in the ring buffer, - * waiting to be consumed. - * - * Tools can chose to ignore this at their own discretion, but the - * evlist layer can't just drop it when filtering events in - * perf_evlist__filter_pollfd(). - */ - refcount_set(&map->core.refcnt, 2); - map->core.prev = 0; - map->core.mask = mp->mask; - map->core.base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, - MAP_SHARED, fd, 0); - if (map->core.base == MAP_FAILED) { + if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", errno); - map->core.base = NULL; return -1; } - map->core.fd = fd; - map->core.cpu = cpu; perf_mmap__setup_affinity_mask(map, mp); @@ -389,7 +256,7 @@ int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) map->comp_level = mp->comp_level; if (map->comp_level && !perf_mmap__aio_enabled(map)) { - map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, + map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); if (map->data == MAP_FAILED) { pr_debug2("failed to mmap data buffer, error %d\n", @@ -406,96 +273,16 @@ int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) return perf_mmap__aio_mmap(map, mp); } -static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end) -{ - struct perf_event_header *pheader; - u64 evt_head = *start; - int size = mask + 1; - - pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start); - pheader = (struct perf_event_header *)(buf + (*start & mask)); - while (true) { - if (evt_head - *start >= (unsigned int)size) { - pr_debug("Finished reading overwrite ring buffer: rewind\n"); - if (evt_head - *start > (unsigned int)size) - evt_head -= pheader->size; - *end = evt_head; - return 0; - } - - pheader = (struct perf_event_header *)(buf + (evt_head & mask)); - - if (pheader->size == 0) { - pr_debug("Finished reading overwrite ring buffer: get start\n"); - *end = evt_head; - return 0; - } - - evt_head += pheader->size; - pr_debug3("move evt_head: %"PRIx64"\n", evt_head); - } - WARN_ONCE(1, "Shouldn't get here\n"); - return -1; -} - -/* - * Report the start and end of the available data in ringbuffer - */ -static int __perf_mmap__read_init(struct mmap *md) -{ - u64 head = perf_mmap__read_head(md); - u64 old = md->core.prev; - unsigned char *data = md->core.base + page_size; - unsigned long size; - - md->core.start = md->core.overwrite ? head : old; - md->core.end = md->core.overwrite ? old : head; - - if ((md->core.end - md->core.start) < md->core.flush) - return -EAGAIN; - - size = md->core.end - md->core.start; - if (size > (unsigned long)(md->core.mask) + 1) { - if (!md->core.overwrite) { - WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); - - md->core.prev = head; - perf_mmap__consume(md); - return -EAGAIN; - } - - /* - * Backward ring buffer is full. We still have a chance to read - * most of data from it. - */ - if (overwrite_rb_find_range(data, md->core.mask, &md->core.start, &md->core.end)) - return -EINVAL; - } - - return 0; -} - -int perf_mmap__read_init(struct mmap *map) -{ - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->core.refcnt)) - return -ENOENT; - - return __perf_mmap__read_init(map); -} - int perf_mmap__push(struct mmap *md, void *to, int push(struct mmap *map, void *to, void *buf, size_t size)) { - u64 head = perf_mmap__read_head(md); + u64 head = perf_mmap__read_head(&md->core); unsigned char *data = md->core.base + page_size; unsigned long size; void *buf; int rc = 0; - rc = perf_mmap__read_init(md); + rc = perf_mmap__read_init(&md->core); if (rc < 0) return (rc == -EAGAIN) ? 1 : -1; @@ -522,24 +309,7 @@ int perf_mmap__push(struct mmap *md, void *to, } md->core.prev = head; - perf_mmap__consume(md); + perf_mmap__consume(&md->core); out: return rc; } - -/* - * Mandatory for overwrite mode - * The direction of overwrite mode is backward. - * The last perf_mmap__read() will set tail to map->core.prev. - * Need to correct the map->core.prev to head which is the end of next read. - */ -void perf_mmap__read_done(struct mmap *map) -{ - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->core.refcnt)) - return; - - map->core.prev = perf_mmap__read_head(map); -} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e567c1c875bd..bee4e83f7109 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -37,37 +37,19 @@ struct mmap { }; struct mmap_params { - int prot, mask, nr_cblocks, affinity, flush, comp_level; + struct perf_mmap_param core; + int nr_cblocks, affinity, flush, comp_level; struct auxtrace_mmap_params auxtrace_mp; }; -int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); -void perf_mmap__munmap(struct mmap *map); - -void perf_mmap__get(struct mmap *map); -void perf_mmap__put(struct mmap *map); - -void perf_mmap__consume(struct mmap *map); - -static inline u64 perf_mmap__read_head(struct mmap *mm) -{ - return ring_buffer_read_head(mm->core.base); -} - -static inline void perf_mmap__write_tail(struct mmap *md, u64 tail) -{ - ring_buffer_write_tail(md->core.base, tail); -} +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); +void mmap__munmap(struct mmap *map); union perf_event *perf_mmap__read_forward(struct mmap *map); -union perf_event *perf_mmap__read_event(struct mmap *map); - int perf_mmap__push(struct mmap *md, void *to, int push(struct mmap *map, void *to, void *buf, size_t size)); -size_t perf_mmap__mmap_len(struct mmap *map); +size_t mmap__mmap_len(struct mmap *map); -int perf_mmap__read_init(struct mmap *md); -void perf_mmap__read_done(struct mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index b5e2adef49de..ed7c008b9c8b 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -182,6 +182,37 @@ static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir) #define MAX_EVENT_LENGTH 512 +void parse_events__handle_error(struct parse_events_error *err, int idx, + char *str, char *help) +{ + if (WARN(!str, "WARNING: failed to provide error string\n")) { + free(help); + return; + } + switch (err->num_errors) { + case 0: + err->idx = idx; + err->str = str; + err->help = help; + break; + case 1: + err->first_idx = err->idx; + err->idx = idx; + err->first_str = err->str; + err->str = str; + err->first_help = err->help; + err->help = help; + break; + default: + WARN_ONCE(1, "WARNING: multiple event parsing errors\n"); + free(err->str); + err->str = str; + free(err->help); + err->help = help; + break; + } + err->num_errors++; +} struct tracepoint_path *tracepoint_id_to_path(u64 config) { @@ -480,6 +511,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, static void tracepoint_error(struct parse_events_error *e, int err, const char *sys, const char *name) { + const char *str; char help[BUFSIZ]; if (!e) @@ -493,18 +525,18 @@ static void tracepoint_error(struct parse_events_error *e, int err, switch (err) { case EACCES: - e->str = strdup("can't access trace events"); + str = "can't access trace events"; break; case ENOENT: - e->str = strdup("unknown tracepoint"); + str = "unknown tracepoint"; break; default: - e->str = strdup("failed to add tracepoint"); + str = "failed to add tracepoint"; break; } tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name); - e->help = strdup(help); + parse_events__handle_error(e, 0, strdup(str), strdup(help)); } static int add_tracepoint(struct list_head *list, int *idx, @@ -932,11 +964,11 @@ static int check_type_val(struct parse_events_term *term, return 0; if (err) { - err->idx = term->err_val; - if (type == PARSE_EVENTS__TERM_TYPE_NUM) - err->str = strdup("expected numeric value"); - else - err->str = strdup("expected string value"); + parse_events__handle_error(err, term->err_val, + type == PARSE_EVENTS__TERM_TYPE_NUM + ? strdup("expected numeric value") + : strdup("expected string value"), + NULL); } return -EINVAL; } @@ -965,6 +997,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", }; static bool config_term_shrinked; @@ -972,8 +1005,11 @@ static bool config_term_shrinked; static bool config_term_avail(int term_type, struct parse_events_error *err) { + char *err_str; + if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) { - err->str = strdup("Invalid term_type"); + parse_events__handle_error(err, -1, + strdup("Invalid term_type"), NULL); return false; } if (!config_term_shrinked) @@ -992,9 +1028,9 @@ config_term_avail(int term_type, struct parse_events_error *err) return false; /* term_type is validated so indexing is safe */ - if (asprintf(&err->str, "'%s' is not usable in 'perf stat'", - config_term_names[term_type]) < 0) - err->str = NULL; + if (asprintf(&err_str, "'%s' is not usable in 'perf stat'", + config_term_names[term_type]) >= 0) + parse_events__handle_error(err, -1, err_str, NULL); return false; } } @@ -1036,17 +1072,20 @@ do { \ case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: CHECK_TYPE_VAL(STR); if (strcmp(term->val.str, "no") && - parse_branch_str(term->val.str, &attr->branch_sample_type)) { - err->str = strdup("invalid branch sample type"); - err->idx = term->err_val; + parse_branch_str(term->val.str, + &attr->branch_sample_type)) { + parse_events__handle_error(err, term->err_val, + strdup("invalid branch sample type"), + NULL); return -EINVAL; } break; case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); if (term->val.num > 1) { - err->str = strdup("expected 0 or 1"); - err->idx = term->err_val; + parse_events__handle_error(err, term->err_val, + strdup("expected 0 or 1"), + NULL); return -EINVAL; } break; @@ -1080,18 +1119,28 @@ do { \ case PARSE_EVENTS__TERM_TYPE_PERCORE: CHECK_TYPE_VAL(NUM); if ((unsigned int)term->val.num > 1) { - err->str = strdup("expected 0 or 1"); - err->idx = term->err_val; + parse_events__handle_error(err, term->err_val, + strdup("expected 0 or 1"), + NULL); return -EINVAL; } break; case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + CHECK_TYPE_VAL(NUM); + if (term->val.num > UINT_MAX) { + parse_events__handle_error(err, term->err_val, + strdup("too big"), + NULL); + return -EINVAL; + } + break; default: - err->str = strdup("unknown term"); - err->idx = term->err_term; - err->help = parse_events_formats_error_string(NULL); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + parse_events_formats_error_string(NULL)); return -EINVAL; } @@ -1139,12 +1188,13 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); default: if (err) { - err->idx = term->err_term; - err->str = strdup("unknown term"); - err->help = strdup("valid terms: call-graph,stack-size\n"); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + strdup("valid terms: call-graph,stack-size\n")); } return -EINVAL; } @@ -1234,11 +1284,47 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0); break; + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + ADD_CONFIG_TERM(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num); + break; + default: + break; + } + } + return 0; +} + +/* + * Add PERF_EVSEL__CONFIG_TERM_CFG_CHG where cfg_chg will have a bit set for + * each bit of attr->config that the user has changed. + */ +static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, + struct list_head *head_terms) +{ + struct parse_events_term *term; + u64 bits = 0; + int type; + + list_for_each_entry(term, head_config, list) { + switch (term->type_term) { + case PARSE_EVENTS__TERM_TYPE_USER: + type = perf_pmu__format_type(&pmu->format, term->config); + if (type != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + bits |= perf_pmu__format_bits(&pmu->format, term->config); + break; + case PARSE_EVENTS__TERM_TYPE_CONFIG: + bits = ~(u64)0; + break; default: break; } } -#undef ADD_EVSEL_CONFIG + + if (bits) + ADD_CONFIG_TERM(CFG_CHG, cfg_chg, bits); + +#undef ADD_CONFIG_TERM return 0; } @@ -1323,10 +1409,12 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, pmu = perf_pmu__find(name); if (!pmu) { - if (asprintf(&err->str, + char *err_str; + + if (asprintf(&err_str, "Cannot find PMU `%s'. Missing kernel support?", - name) < 0) - err->str = NULL; + name) >= 0) + parse_events__handle_error(err, 0, err_str, NULL); return -EINVAL; } @@ -1365,8 +1453,22 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) + /* + * When using default config, record which bits of attr->config were + * changed by the user. + */ + if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) + return -ENOMEM; + + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + struct perf_evsel_config_term *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &config_terms, list) { + list_del_init(&pos->list); + free(pos); + } return -EINVAL; + } evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, @@ -1389,7 +1491,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { - struct list_head *head; struct parse_events_term *term; struct list_head *list; struct perf_pmu *pmu = NULL; @@ -1406,19 +1507,30 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + struct list_head *head; + char *config; + head = malloc(sizeof(struct list_head)); if (!head) return -1; INIT_LIST_HEAD(head); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - str, 1, false, &str, NULL) < 0) + config = strdup(str); + if (!config) return -1; + if (parse_events_term__num(&term, + PARSE_EVENTS__TERM_TYPE_USER, + config, 1, false, &config, + NULL) < 0) { + free(list); + free(config); + return -1; + } list_add_tail(&term->list, head); if (!parse_events_add_pmu(parse_state, list, pmu->name, head, true, true)) { - pr_debug("%s -> %s/%s/\n", str, + pr_debug("%s -> %s/%s/\n", config, pmu->name, alias->str); ok++; } @@ -1427,8 +1539,10 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } } } - if (!ok) + if (!ok) { + free(list); return -1; + } *listp = list; return 0; } @@ -1927,15 +2041,20 @@ int parse_events(struct evlist *evlist, const char *str, ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); + + if (!ret && list_empty(&parse_state.list)) { + WARN_ONCE(true, "WARNING: event parser found nothing\n"); + return -1; + } + + /* + * Add list to the evlist even with errors to allow callers to clean up. + */ + perf_evlist__splice_list_tail(evlist, &parse_state.list); + if (!ret) { struct evsel *last; - if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing\n"); - return -1; - } - - perf_evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups += parse_state.nr_groups; last = evlist__last(evlist); last->cmdline_group_boundary = true; @@ -1960,15 +2079,14 @@ static int get_term_width(void) return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col; } -void parse_events_print_error(struct parse_events_error *err, - const char *event) +static void __parse_events_print_error(int err_idx, const char *err_str, + const char *err_help, const char *event) { const char *str = "invalid or unsupported event: "; char _buf[MAX_WIDTH]; char *buf = (char *) event; int idx = 0; - - if (err->str) { + if (err_str) { /* -2 for extra '' in the final fprintf */ int width = get_term_width() - 2; int len_event = strlen(event); @@ -1991,8 +2109,8 @@ void parse_events_print_error(struct parse_events_error *err, buf = _buf; /* We're cutting from the beginning. */ - if (err->idx > max_err_idx) - cut = err->idx - max_err_idx; + if (err_idx > max_err_idx) + cut = err_idx - max_err_idx; strncpy(buf, event + cut, max_len); @@ -2005,16 +2123,33 @@ void parse_events_print_error(struct parse_events_error *err, buf[max_len] = 0; } - idx = len_str + err->idx - cut; + idx = len_str + err_idx - cut; } fprintf(stderr, "%s'%s'\n", str, buf); if (idx) { - fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str); - if (err->help) - fprintf(stderr, "\n%s\n", err->help); - zfree(&err->str); - zfree(&err->help); + fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err_str); + if (err_help) + fprintf(stderr, "\n%s\n", err_help); + } +} + +void parse_events_print_error(struct parse_events_error *err, + const char *event) +{ + if (!err->num_errors) + return; + + __parse_events_print_error(err->idx, err->str, err->help, event); + zfree(&err->str); + zfree(&err->help); + + if (err->num_errors > 1) { + fputs("\nInitial error:\n", stderr); + __parse_events_print_error(err->first_idx, err->first_str, + err->first_help, event); + zfree(&err->first_str); + zfree(&err->first_help); } } @@ -2024,8 +2159,11 @@ int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { struct evlist *evlist = *(struct evlist **)opt->value; - struct parse_events_error err = { .idx = 0, }; - int ret = parse_events(evlist, str, &err); + struct parse_events_error err; + int ret; + + bzero(&err, sizeof(err)); + ret = parse_events(evlist, str, &err); if (ret) { parse_events_print_error(&err, str); @@ -2600,7 +2738,7 @@ out_enomem: * Print the help text for the event symbols: */ void print_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag) + bool long_desc, bool details_flag, bool deprecated) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2612,7 +2750,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_hwcache_events(event_glob, name_only); print_pmu_events(event_glob, name_only, quiet_flag, long_desc, - details_flag); + details_flag, deprecated); if (event_glob != NULL) return; @@ -2718,30 +2856,63 @@ int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx) { struct event_symbol *sym; + char *str; struct parse_events_term temp = { .type_val = PARSE_EVENTS__TERM_TYPE_STR, .type_term = PARSE_EVENTS__TERM_TYPE_USER, - .config = config ?: (char *) "event", + .config = config, }; + if (!temp.config) { + temp.config = strdup("event"); + if (!temp.config) + return -ENOMEM; + } BUG_ON(idx >= PERF_COUNT_HW_MAX); sym = &event_symbols_hw[idx]; - return new_term(term, &temp, (char *) sym->symbol, 0); + str = strdup(sym->symbol); + if (!str) + return -ENOMEM; + return new_term(term, &temp, str, 0); } int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term) { + char *str; struct parse_events_term temp = { .type_val = term->type_val, .type_term = term->type_term, - .config = term->config, + .config = NULL, .err_term = term->err_term, .err_val = term->err_val, }; - return new_term(new, &temp, term->val.str, term->val.num); + if (term->config) { + temp.config = strdup(term->config); + if (!temp.config) + return -ENOMEM; + } + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + return new_term(new, &temp, NULL, term->val.num); + + str = strdup(term->val.str); + if (!str) + return -ENOMEM; + return new_term(new, &temp, str, 0); +} + +void parse_events_term__delete(struct parse_events_term *term) +{ + if (term->array.nr_ranges) + zfree(&term->array.ranges); + + if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) + zfree(&term->val.str); + + zfree(&term->config); + free(term); } int parse_events_copy_term_list(struct list_head *old, @@ -2774,10 +2945,8 @@ void parse_events_terms__purge(struct list_head *terms) struct parse_events_term *term, *h; list_for_each_entry_safe(term, h, terms, list) { - if (term->array.nr_ranges) - zfree(&term->array.ranges); list_del_init(&term->list); - free(term); + parse_events_term__delete(term); } } @@ -2797,13 +2966,10 @@ void parse_events__clear_array(struct parse_events_array *a) void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str) { - struct parse_events_error *err = parse_state->error; - - if (!err) + if (!parse_state->error) return; - err->idx = idx; - err->str = strdup(str); - WARN_ONCE(!err->str, "WARNING: failed to allocate error string"); + + parse_events__handle_error(parse_state->error, idx, strdup(str), NULL); } static void config_terms_list(char *buf, size_t buf_sz) diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 616ca1eda0eb..27596cbd0ba0 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -77,6 +77,7 @@ enum { PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, + PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -110,9 +111,13 @@ struct parse_events_term { }; struct parse_events_error { + int num_errors; /* number of errors encountered */ int idx; /* index in the parsed string */ char *str; /* string to display at the index */ char *help; /* optional help string */ + int first_idx;/* as above, but for the first encountered error */ + char *first_str; + char *first_help; }; struct parse_events_state { @@ -124,6 +129,8 @@ struct parse_events_state { struct list_head *terms; }; +void parse_events__handle_error(struct parse_events_error *err, int idx, + char *str, char *help); void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, @@ -137,6 +144,7 @@ int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx); int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); +void parse_events_term__delete(struct parse_events_term *term); void parse_events_terms__delete(struct list_head *terms); void parse_events_terms__purge(struct list_head *terms); void parse_events__clear_array(struct parse_events_array *a); @@ -195,7 +203,7 @@ void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc, bool details_flag); + bool long_desc, bool details_flag, bool deprecated); struct event_symbol { const char *symbol; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 7469497cd28e..7b1c8ee537cf 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -285,6 +285,7 @@ overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } +aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 48126ae4cd13..e2eea4e601b4 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -12,6 +12,7 @@ #include <stdio.h> #include <linux/compiler.h> #include <linux/types.h> +#include <linux/zalloc.h> #include "pmu.h" #include "evsel.h" #include "parse-events.h" @@ -25,12 +26,28 @@ do { \ YYABORT; \ } while (0) -#define ALLOC_LIST(list) \ -do { \ - list = malloc(sizeof(*list)); \ - ABORT_ON(!list); \ - INIT_LIST_HEAD(list); \ -} while (0) +static struct list_head* alloc_list() +{ + struct list_head *list; + + list = malloc(sizeof(*list)); + if (!list) + return NULL; + + INIT_LIST_HEAD(list); + return list; +} + +static void free_list_evsel(struct list_head* list_evsel) +{ + struct evsel *evsel, *tmp; + + list_for_each_entry_safe(evsel, tmp, list_evsel, core.node) { + list_del_init(&evsel->core.node); + perf_evsel__delete(evsel); + } + free(list_evsel); +} static void inc_group_count(struct list_head *list, struct parse_events_state *parse_state) @@ -61,6 +78,7 @@ static void inc_group_count(struct list_head *list, %type <num> PE_VALUE_SYM_TOOL %type <num> PE_RAW %type <num> PE_TERM +%type <num> value_sym %type <str> PE_NAME %type <str> PE_BPF_OBJECT %type <str> PE_BPF_SOURCE @@ -71,37 +89,43 @@ static void inc_group_count(struct list_head *list, %type <str> PE_EVENT_NAME %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %type <str> PE_DRV_CFG_TERM -%type <num> value_sym -%type <head> event_config -%type <head> opt_event_config -%type <head> opt_pmu_config +%destructor { free ($$); } <str> %type <term> event_term -%type <head> event_pmu -%type <head> event_legacy_symbol -%type <head> event_legacy_cache -%type <head> event_legacy_mem -%type <head> event_legacy_tracepoint +%destructor { parse_events_term__delete ($$); } <term> +%type <list_terms> event_config +%type <list_terms> opt_event_config +%type <list_terms> opt_pmu_config +%destructor { parse_events_terms__delete ($$); } <list_terms> +%type <list_evsel> event_pmu +%type <list_evsel> event_legacy_symbol +%type <list_evsel> event_legacy_cache +%type <list_evsel> event_legacy_mem +%type <list_evsel> event_legacy_tracepoint +%type <list_evsel> event_legacy_numeric +%type <list_evsel> event_legacy_raw +%type <list_evsel> event_bpf_file +%type <list_evsel> event_def +%type <list_evsel> event_mod +%type <list_evsel> event_name +%type <list_evsel> event +%type <list_evsel> events +%type <list_evsel> group_def +%type <list_evsel> group +%type <list_evsel> groups +%destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name -%type <head> event_legacy_numeric -%type <head> event_legacy_raw -%type <head> event_bpf_file -%type <head> event_def -%type <head> event_mod -%type <head> event_name -%type <head> event -%type <head> events -%type <head> group_def -%type <head> group -%type <head> groups +%destructor { free ($$.sys); free ($$.event); } <tracepoint_name> %type <array> array %type <array> array_term %type <array> array_terms +%destructor { free ($$.ranges); } <array> %union { char *str; u64 num; - struct list_head *head; + struct list_head *list_evsel; + struct list_head *list_terms; struct parse_events_term *term; struct tracepoint_name { char *sys; @@ -120,6 +144,7 @@ start_events: groups { struct parse_events_state *parse_state = _parse_state; + /* frees $1 */ parse_events_update_lists($1, &parse_state->list); } @@ -129,6 +154,7 @@ groups ',' group struct list_head *list = $1; struct list_head *group = $3; + /* frees $3 */ parse_events_update_lists(group, list); $$ = list; } @@ -138,6 +164,7 @@ groups ',' event struct list_head *list = $1; struct list_head *event = $3; + /* frees $3 */ parse_events_update_lists(event, list); $$ = list; } @@ -150,8 +177,14 @@ group: group_def ':' PE_MODIFIER_EVENT { struct list_head *list = $1; + int err; - ABORT_ON(parse_events__modifier_group(list, $3)); + err = parse_events__modifier_group(list, $3); + free($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -164,6 +197,7 @@ PE_NAME '{' events '}' inc_group_count(list, _parse_state); parse_events__set_leader($1, list, _parse_state); + free($1); $$ = list; } | @@ -182,6 +216,7 @@ events ',' event struct list_head *event = $3; struct list_head *list = $1; + /* frees $3 */ parse_events_update_lists(event, list); $$ = list; } @@ -194,13 +229,19 @@ event_mod: event_name PE_MODIFIER_EVENT { struct list_head *list = $1; + int err; /* * Apply modifier on all events added by single event definition * (there could be more events added for multiple tracepoint * definitions via '*?'. */ - ABORT_ON(parse_events__modifier_event(list, $2, false)); + err = parse_events__modifier_event(list, $2, false); + free($2); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -209,8 +250,14 @@ event_name event_name: PE_EVENT_NAME event_def { - ABORT_ON(parse_events_name($2, $1)); + int err; + + err = parse_events_name($2, $1); free($1); + if (err) { + free_list_evsel($2); + YYABORT; + } $$ = $2; } | @@ -230,22 +277,34 @@ PE_NAME opt_pmu_config { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; - struct list_head *list, *orig_terms, *terms; + struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL; + char *pattern = NULL; + +#define CLEANUP_YYABORT \ + do { \ + parse_events_terms__delete($2); \ + parse_events_terms__delete(orig_terms); \ + free(list); \ + free($1); \ + free(pattern); \ + YYABORT; \ + } while(0) if (parse_events_copy_term_list($2, &orig_terms)) - YYABORT; + CLEANUP_YYABORT; if (error) error->idx = @1.first_column; - ALLOC_LIST(list); + list = alloc_list(); + if (!list) + CLEANUP_YYABORT; if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; int ok = 0; - char *pattern; if (asprintf(&pattern, "%s*", $1) < 0) - YYABORT; + CLEANUP_YYABORT; while ((pmu = perf_pmu__scan(pmu)) != NULL) { char *name = pmu->name; @@ -254,31 +313,32 @@ PE_NAME opt_pmu_config strncmp($1, "uncore_", 7)) name += 7; if (!fnmatch(pattern, name, 0)) { - if (parse_events_copy_term_list(orig_terms, &terms)) { - free(pattern); - YYABORT; - } + if (parse_events_copy_term_list(orig_terms, &terms)) + CLEANUP_YYABORT; if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) ok++; parse_events_terms__delete(terms); } } - free(pattern); - if (!ok) - YYABORT; + CLEANUP_YYABORT; } parse_events_terms__delete($2); parse_events_terms__delete(orig_terms); + free($1); $$ = list; +#undef CLEANUP_YYABORT } | PE_KERNEL_PMU_EVENT sep_dc { struct list_head *list; + int err; - if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0) + err = parse_events_multi_pmu_add(_parse_state, $1, &list); + free($1); + if (err < 0) YYABORT; $$ = list; } @@ -289,6 +349,8 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc char pmu_name[128]; snprintf(&pmu_name, 128, "%s-%s", $1, $3); + free($1); + free($3); if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) YYABORT; $$ = list; @@ -305,10 +367,16 @@ value_sym '/' event_config '/' struct list_head *list; int type = $1 >> 16; int config = $1 & 255; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, type, config, $3); parse_events_terms__delete($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -318,7 +386,8 @@ value_sym sep_slash_slash_dc int type = $1 >> 16; int config = $1 & 255; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } @@ -327,7 +396,8 @@ PE_VALUE_SYM_TOOL sep_slash_slash_dc { struct list_head *list; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); ABORT_ON(parse_events_add_tool(_parse_state, list, $1)); $$ = list; } @@ -338,10 +408,19 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_e struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6); parse_events_terms__delete($6); + free($1); + free($3); + free($5); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -350,10 +429,18 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4); parse_events_terms__delete($4); + free($1); + free($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -362,10 +449,17 @@ PE_NAME_CACHE_TYPE opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2); parse_events_terms__delete($2); + free($1); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } @@ -374,10 +468,17 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_state *parse_state = _parse_state; struct list_head *list; - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4)); + int err; + + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, $6, $4); + free($6); + if (err) { + free(list); + YYABORT; + } $$ = list; } | @@ -386,9 +487,13 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc struct parse_events_state *parse_state = _parse_state; struct list_head *list; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)); + list = alloc_list(); + ABORT_ON(!list); + if (parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, NULL, $4)) { + free(list); + YYABORT; + } $$ = list; } | @@ -396,10 +501,17 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_state *parse_state = _parse_state; struct list_head *list; - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0)); + int err; + + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, $4, 0); + free($4); + if (err) { + free(list); + YYABORT; + } $$ = list; } | @@ -408,9 +520,13 @@ PE_PREFIX_MEM PE_VALUE sep_dc struct parse_events_state *parse_state = _parse_state; struct list_head *list; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)); + list = alloc_list(); + ABORT_ON(!list); + if (parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, NULL, 0)) { + free(list); + YYABORT; + } $$ = list; } @@ -420,28 +536,35 @@ tracepoint_name opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); if (error) error->idx = @1.first_column; - if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, - error, $2)) - return -1; + err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, + error, $2); + parse_events_terms__delete($2); + free($1.sys); + free($1.event); + if (err) { + free(list); + YYABORT; + } $$ = list; } tracepoint_name: PE_NAME '-' PE_NAME ':' PE_NAME { - char sys_name[128]; struct tracepoint_name tracepoint; - snprintf(&sys_name, 128, "%s-%s", $1, $3); - tracepoint.sys = &sys_name; + ABORT_ON(asprintf(&tracepoint.sys, "%s-%s", $1, $3) < 0); tracepoint.event = $5; - + free($1); + free($3); $$ = tracepoint; } | @@ -456,10 +579,16 @@ event_legacy_numeric: PE_VALUE ':' PE_VALUE opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4); parse_events_terms__delete($4); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -467,10 +596,16 @@ event_legacy_raw: PE_RAW opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2); parse_events_terms__delete($2); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -479,20 +614,33 @@ PE_BPF_OBJECT opt_event_config { struct parse_events_state *parse_state = _parse_state; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_load_bpf(parse_state, list, $1, false, $2); parse_events_terms__delete($2); + free($1); + if (err) { + free(list); + YYABORT; + } $$ = list; } | PE_BPF_SOURCE opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_load_bpf(_parse_state, list, $1, true, $2); parse_events_terms__delete($2); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -525,6 +673,10 @@ opt_pmu_config: start_terms: event_config { struct parse_events_state *parse_state = _parse_state; + if (parse_state->terms) { + parse_events_terms__delete ($1); + YYABORT; + } parse_state->terms = $1; } @@ -534,7 +686,10 @@ event_config ',' event_term struct list_head *head = $1; struct parse_events_term *term = $3; - ABORT_ON(!head); + if (!head) { + parse_events_term__delete(term); + YYABORT; + } list_add_tail(&term->list, head); $$ = $1; } @@ -555,8 +710,12 @@ PE_NAME '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, &@1, &@3)); + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3, &@1, &@3)) { + free($1); + free($3); + YYABORT; + } $$ = term; } | @@ -564,8 +723,11 @@ PE_NAME '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, false, &@1, &@3)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3, false, &@1, &@3)) { + free($1); + YYABORT; + } $$ = term; } | @@ -574,7 +736,10 @@ PE_NAME '=' PE_VALUE_SYM_HW struct parse_events_term *term; int config = $3 & 255; - ABORT_ON(parse_events_term__sym_hw(&term, $1, config)); + if (parse_events_term__sym_hw(&term, $1, config)) { + free($1); + YYABORT; + } $$ = term; } | @@ -582,8 +747,11 @@ PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, true, &@1, NULL)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1, true, &@1, NULL)) { + free($1); + YYABORT; + } $$ = term; } | @@ -600,7 +768,10 @@ PE_TERM '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)); + if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) { + free($3); + YYABORT; + } $$ = term; } | @@ -624,9 +795,13 @@ PE_NAME array '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, &@1, &@4)); - + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, &@1, &@4)) { + free($1); + free($4); + free($2.ranges); + YYABORT; + } term->array = $2; $$ = term; } @@ -635,8 +810,12 @@ PE_NAME array '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, false, &@1, &@4)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, false, &@1, &@4)) { + free($1); + free($2.ranges); + YYABORT; + } term->array = $2; $$ = term; } @@ -644,9 +823,15 @@ PE_NAME array '=' PE_VALUE PE_DRV_CFG_TERM { struct parse_events_term *term; + char *config = strdup($1); - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, - $1, $1, &@1, NULL)); + ABORT_ON(!config); + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, + config, $1, &@1, NULL)) { + free($1); + free(config); + YYABORT; + } $$ = term; } @@ -668,14 +853,12 @@ array_terms ',' array_term struct parse_events_array new_array; new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges; - new_array.ranges = malloc(sizeof(new_array.ranges[0]) * - new_array.nr_ranges); + new_array.ranges = realloc($1.ranges, + sizeof(new_array.ranges[0]) * + new_array.nr_ranges); ABORT_ON(!new_array.ranges); - memcpy(&new_array.ranges[0], $1.ranges, - $1.nr_ranges * sizeof(new_array.ranges[0])); memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges, $3.nr_ranges * sizeof(new_array.ranges[0])); - free($1.ranges); free($3.ranges); $$ = new_array; } diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index ef46c2848808..e687497b3aac 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -13,7 +13,7 @@ static int __parse_regs(const struct option *opt, const char *str, int unset, bool intr) { uint64_t *mode = (uint64_t *)opt->value; - const struct sample_reg *r; + const struct sample_reg *r = NULL; char *s, *os = NULL, *p; int ret = -1; uint64_t mask; @@ -46,19 +46,23 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr) if (!strcmp(s, "?")) { fprintf(stderr, "available registers: "); +#ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { if (r->mask & mask) fprintf(stderr, "%s ", r->name); } +#endif fputc('\n', stderr); /* just printing available regs */ return -1; } +#ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { if ((r->mask & mask) && !strcasecmp(s, r->name)) break; } - if (!r->name) { +#endif + if (!r || !r->name) { ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n", s, intr ? "-I" : "--user-regs="); goto error; diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index d4ad3f04923a..651203126c71 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -34,7 +34,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), - bit_name(WEIGHT), bit_name(PHYS_ADDR), + bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), { .name = NULL, } }; #undef bit_name @@ -143,6 +143,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(sample_regs_intr, p_hex); PRINT_ATTRf(aux_watermark, p_unsigned); PRINT_ATTRf(sample_max_stack, p_unsigned); + PRINT_ATTRf(aux_sample_size, p_unsigned); return ret; } diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 2774cec1f15f..5ee47ae1509c 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -3,10 +3,6 @@ #include "perf_regs.h" #include "event.h" -const struct sample_reg __weak sample_reg_masks[] = { - SMPL_REG_END -}; - int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, char **new_op __maybe_unused) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 47fe34e5f7d5..e014c2c038f4 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -15,8 +15,6 @@ struct sample_reg { #define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) } #define SMPL_REG_END { .name = NULL } -extern const struct sample_reg sample_reg_masks[]; - enum { SDT_ARG_VALID = 0, SDT_ARG_SKIP, @@ -27,6 +25,8 @@ uint64_t arch__intr_reg_mask(void); uint64_t arch__user_reg_mask(void); #ifdef HAVE_PERF_REGS_SUPPORT +extern const struct sample_reg sample_reg_masks[]; + #include <perf_regs.h> #define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP)) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 5608da82ad23..e8d348988026 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -308,7 +308,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, char *long_desc, char *topic, char *unit, char *perpkg, char *metric_expr, - char *metric_name) + char *metric_name, + char *deprecated) { struct parse_events_term *term; struct perf_pmu_alias *alias; @@ -325,6 +326,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->unit[0] = '\0'; alias->per_pkg = false; alias->snapshot = false; + alias->deprecated = false; ret = parse_events_terms(&alias->terms, val); if (ret) { @@ -379,6 +381,9 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; alias->str = strdup(newval); + if (deprecated) + alias->deprecated = true; + if (!perf_pmu_merge_alias(alias, list)) list_add_tail(&alias->list, list); @@ -400,7 +405,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI strim(buf); return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, - NULL, NULL, NULL); + NULL, NULL, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -787,7 +792,8 @@ new_alias: (char *)pe->long_desc, (char *)pe->topic, (char *)pe->unit, (char *)pe->perpkg, (char *)pe->metric_expr, - (char *)pe->metric_name); + (char *)pe->metric_name, + (char *)pe->deprecated); } } @@ -925,6 +931,16 @@ __u64 perf_pmu__format_bits(struct list_head *formats, const char *name) return bits; } +int perf_pmu__format_type(struct list_head *formats, const char *name) +{ + struct perf_pmu_format *format = pmu_find_format(formats, name); + + if (!format) + return -1; + + return format->value; +} + /* * Sets value based on the format definition (format parameter) * and unformated value (value parameter). @@ -1044,9 +1060,9 @@ static int pmu_config_term(struct list_head *formats, if (err) { char *pmu_term = pmu_formats_string(formats); - err->idx = term->err_term; - err->str = strdup("unknown term"); - err->help = parse_events_formats_error_string(pmu_term); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + parse_events_formats_error_string(pmu_term)); free(pmu_term); } return -EINVAL; @@ -1074,8 +1090,9 @@ static int pmu_config_term(struct list_head *formats, if (term->no_value && bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { if (err) { - err->idx = term->err_val; - err->str = strdup("no value assigned for term"); + parse_events__handle_error(err, term->err_val, + strdup("no value assigned for term"), + NULL); } return -EINVAL; } @@ -1088,8 +1105,9 @@ static int pmu_config_term(struct list_head *formats, term->config, term->val.str); } if (err) { - err->idx = term->err_val; - err->str = strdup("expected numeric value"); + parse_events__handle_error(err, term->err_val, + strdup("expected numeric value"), + NULL); } return -EINVAL; } @@ -1102,11 +1120,15 @@ static int pmu_config_term(struct list_head *formats, max_val = pmu_format_max_value(format->bits); if (val > max_val) { if (err) { - err->idx = term->err_val; - if (asprintf(&err->str, - "value too big for format, maximum is %llu", - (unsigned long long)max_val) < 0) - err->str = strdup("value too big for format"); + char *err_str; + + parse_events__handle_error(err, term->err_val, + asprintf(&err_str, + "value too big for format, maximum is %llu", + (unsigned long long)max_val) < 0 + ? strdup("value too big for format") + : err_str, + NULL); return -EINVAL; } /* @@ -1248,7 +1270,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->metric_name = alias->metric_name; list_del_init(&term->list); - free(term); + parse_events_term__delete(term); } /* @@ -1383,7 +1405,7 @@ static void wordwrap(char *s, int start, int max, int corr) } void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag) + bool long_desc, bool details_flag, bool deprecated) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1414,6 +1436,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, format_alias(buf, sizeof(buf), pmu, alias); bool is_cpu = !strcmp(pmu->name, "cpu"); + if (alias->deprecated && !deprecated) + continue; + if (event_glob != NULL && !(strglobmatch_nocase(name, event_glob) || (!is_cpu && strglobmatch_nocase(alias->name, diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index f36ade6df76d..6737e3d5d568 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -26,6 +26,7 @@ struct perf_pmu { __u32 type; bool selectable; bool is_uncore; + bool auxtrace; int max_precise; struct perf_event_attr *default_config; struct perf_cpu_map *cpus; @@ -57,6 +58,7 @@ struct perf_pmu_alias { double scale; bool per_pkg; bool snapshot; + bool deprecated; char *metric_expr; char *metric_name; }; @@ -70,6 +72,7 @@ int perf_pmu__config_terms(struct list_head *formats, struct list_head *head_terms, bool zero, struct parse_events_error *error); __u64 perf_pmu__format_bits(struct list_head *formats, const char *name); +int perf_pmu__format_type(struct list_head *formats, const char *name); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, @@ -85,7 +88,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); void print_pmu_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc, bool details_flag); + bool long_desc, bool details_flag, + bool deprecated); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 91cab5f669d2..52b2d165453a 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -46,7 +46,7 @@ #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ -struct probe_conf probe_conf; +struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM }; #define semantic_error(msg ...) pr_err("Semantic error :" msg) @@ -153,7 +153,7 @@ static struct map *kernel_get_module_map(const char *module) return map__get(pos); } - for (pos = maps__first(maps); pos; pos = map__next(pos)) { + maps__for_each_entry(maps, pos) { /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && @@ -1679,6 +1679,14 @@ int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev) if (ret < 0) goto out; + /* Generate event name if needed */ + if (!pev->event && pev->point.function && pev->point.line + && !pev->point.lazy_line && !pev->point.offset) { + if (asprintf(&pev->event, "%s_L%d", pev->point.function, + pev->point.line) < 0) + return -ENOMEM; + } + /* Copy arguments and ensure return probe has no C argument */ pev->nargs = argc - 1; pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); @@ -2730,8 +2738,13 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, if (tev->event == NULL || tev->group == NULL) return -ENOMEM; - /* Add added event name to namelist */ - strlist__add(namelist, event); + /* + * Add new event name to namelist if multiprobe event is NOT + * supported, since we have to use new event name for following + * probes in that case. + */ + if (!multiprobe_event_is_supported()) + strlist__add(namelist, event); return 0; } diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 96a319cd2378..4f0eb3a20c36 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -16,10 +16,13 @@ struct probe_conf { bool no_inlines; bool cache; int max_probes; + unsigned long magic_num; }; extern struct probe_conf probe_conf; extern bool probe_event_dry_run; +#define DEFAULT_PROBE_MAGIC_NUM 0xdeade12d /* u32: 3735937325 */ + struct symbol; /* kprobe-tracer and uprobe-tracer tracing point */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index b659466ea498..5003ba403345 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -1007,6 +1007,8 @@ enum ftrace_readme { FTRACE_README_KRETPROBE_OFFSET, FTRACE_README_UPROBE_REF_CTR, FTRACE_README_USER_ACCESS, + FTRACE_README_MULTIPROBE_EVENT, + FTRACE_README_IMMEDIATE_VALUE, FTRACE_README_END, }; @@ -1020,6 +1022,8 @@ static struct { DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"), DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"), + DEFINE_TYPE(FTRACE_README_MULTIPROBE_EVENT, "*Create/append/*"), + DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), }; static bool scan_ftrace_readme(enum ftrace_readme type) @@ -1085,3 +1089,13 @@ bool user_access_is_supported(void) { return scan_ftrace_readme(FTRACE_README_USER_ACCESS); } + +bool multiprobe_event_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_MULTIPROBE_EVENT); +} + +bool immediate_value_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_IMMEDIATE_VALUE); +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 986c1c94f64f..0dba88c0f5f0 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -71,6 +71,8 @@ bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); bool uprobe_ref_ctr_is_supported(void); bool user_access_is_supported(void); +bool multiprobe_event_is_supported(void); +bool immediate_value_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index cd9f95e5044e..c470c49a804f 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -177,6 +177,17 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL) goto static_var; + /* Constant value */ + if (dwarf_attr(vr_die, DW_AT_const_value, &attr) && + immediate_value_is_supported()) { + Dwarf_Sword snum; + + dwarf_formsdata(&attr, &snum); + ret = asprintf(&tvar->value, "\\%ld", (long)snum); + + return ret < 0 ? -ENOMEM : 0; + } + /* TODO: handle more than 1 exprs */ if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) return -EINVAL; /* Broken DIE ? */ @@ -525,6 +536,14 @@ next: return 0; } +static void print_var_not_found(const char *varname) +{ + pr_err("Failed to find the location of the '%s' variable at this address.\n" + " Perhaps it has been optimized out.\n" + " Use -V with the --range option to show '%s' location range.\n", + varname, varname); +} + /* Show a variables in kprobe event format */ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) { @@ -536,11 +555,11 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, &pf->sp_die, pf->machine, pf->tvar); + if (ret == -ENOENT && pf->skip_empty_arg) + /* This can be found in other place. skip it */ + return 0; if (ret == -ENOENT || ret == -EINVAL) { - pr_err("Failed to find the location of the '%s' variable at this address.\n" - " Perhaps it has been optimized out.\n" - " Use -V with the --range option to show '%s' location range.\n", - pf->pvar->var, pf->pvar->var); + print_var_not_found(pf->pvar->var); } else if (ret == -ENOTSUP) pr_err("Sorry, we don't support this variable location yet.\n"); else if (ret == 0 && pf->pvar->field) { @@ -587,6 +606,8 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) /* Search again in global variables */ if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) { + if (pf->skip_empty_arg) + return 0; pr_warning("Failed to find '%s' in this function.\n", pf->pvar->var); ret = -ENOENT; @@ -604,38 +625,26 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, const char *function, struct probe_trace_point *tp) { - Dwarf_Addr eaddr, highaddr; + Dwarf_Addr eaddr; GElf_Sym sym; const char *symbol; /* Verify the address is correct */ - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", + if (!dwarf_haspc(sp_die, paddr)) { + pr_warning("Specified offset is out of %s\n", dwarf_diename(sp_die)); return -EINVAL; } - symbol = dwarf_diename(sp_die); + /* Try to get actual symbol name from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); if (!symbol) { - /* Try to get the symbol name from symtab */ - symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); - if (!symbol) { - pr_warning("Failed to find symbol at 0x%lx\n", - (unsigned long)paddr); - return -ENOENT; - } - eaddr = sym.st_value; + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; } + eaddr = sym.st_value; + tp->offset = (unsigned long)(paddr - eaddr); tp->address = (unsigned long)paddr; tp->symbol = strdup(symbol); @@ -756,6 +765,16 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) return 0; } +/* Return innermost DIE */ +static int find_inner_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; +} + /* Find an appropriate scope fits to given conditions */ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) { @@ -767,12 +786,50 @@ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) .die_mem = die_mem, .found = false, }; + int ret; - cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + ret = cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, + &fsp); + if (!ret && !fsp.found) + cu_walk_functions_at(&pf->cu_die, pf->addr, + find_inner_scope_cb, &fsp); return fsp.found ? die_mem : NULL; } +static int verify_representive_line(struct probe_finder *pf, const char *fname, + int lineno, Dwarf_Addr addr) +{ + const char *__fname, *__func = NULL; + Dwarf_Die die_mem; + int __lineno; + + /* Verify line number and address by reverse search */ + if (cu_find_lineinfo(&pf->cu_die, addr, &__fname, &__lineno) < 0) + return 0; + + pr_debug2("Reversed line: %s:%d\n", __fname, __lineno); + if (strcmp(fname, __fname) || lineno == __lineno) + return 0; + + pr_warning("This line is sharing the address with other lines.\n"); + + if (pf->pev->point.function) { + /* Find best match function name and lines */ + pf->addr = addr; + if (find_best_scope(pf, &die_mem) + && die_match_name(&die_mem, pf->pev->point.function) + && dwarf_decl_line(&die_mem, &lineno) == 0) { + __func = dwarf_diename(&die_mem); + __lineno -= lineno; + } + } + pr_warning("Please try to probe at %s:%d instead.\n", + __func ? : __fname, __lineno); + + return -ENOENT; +} + static int probe_point_line_walker(const char *fname, int lineno, Dwarf_Addr addr, void *data) { @@ -783,6 +840,9 @@ static int probe_point_line_walker(const char *fname, int lineno, if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0) return 0; + if (verify_representive_line(pf, fname, lineno, addr)) + return -ENOENT; + pf->addr = addr; sc_die = find_best_scope(pf, &die_mem); if (!sc_die) { @@ -942,7 +1002,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ - if (dwarf_entrypc(in_die, &addr) != 0) { + if (die_entrypc(in_die, &addr) != 0) { pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); return -ENOENT; @@ -994,7 +1054,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = find_probe_point_by_line(pf); } else if (die_is_func_instance(sp_die)) { /* Instances always have the entry address */ - dwarf_entrypc(sp_die, &pf->addr); + die_entrypc(sp_die, &pf->addr); /* But in some case the entry address is 0 */ if (pf->addr == 0) { pr_debug("%s has no entry PC. Skipped\n", @@ -1334,6 +1394,44 @@ end: return ret; } +static int fill_empty_trace_arg(struct perf_probe_event *pev, + struct probe_trace_event *tevs, int ntevs) +{ + char **valp; + char *type; + int i, j, ret; + + for (i = 0; i < pev->nargs; i++) { + type = NULL; + for (j = 0; j < ntevs; j++) { + if (tevs[j].args[i].value) { + type = tevs[j].args[i].type; + break; + } + } + if (j == ntevs) { + print_var_not_found(pev->args[i].var); + return -ENOENT; + } + for (j = 0; j < ntevs; j++) { + valp = &tevs[j].args[i].value; + if (*valp) + continue; + + ret = asprintf(valp, "\\%lx", probe_conf.magic_num); + if (ret < 0) + return -ENOMEM; + /* Note that type can be NULL */ + if (type) { + tevs[j].args[i].type = strdup(type); + if (!tevs[j].args[i].type) + return -ENOMEM; + } + } + } + return 0; +} + /* Find probe_trace_events specified by perf_probe_event from debuginfo */ int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, @@ -1352,7 +1450,13 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, tf.tevs = *tevs; tf.ntevs = 0; + if (pev->nargs != 0 && immediate_value_is_supported()) + tf.pf.skip_empty_arg = true; + ret = debuginfo__find_probes(dbg, &tf.pf); + if (ret >= 0 && tf.pf.skip_empty_arg) + ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs); + if (ret < 0) { for (i = 0; i < tf.ntevs; i++) clear_probe_trace_event(&tf.tevs[i]); @@ -1425,6 +1529,18 @@ error: return DIE_FIND_CB_END; } +static bool available_var_finder_overlap(struct available_var_finder *af) +{ + int i; + + for (i = 0; i < af->nvls; i++) { + if (af->pf.addr == af->vls[i].point.address) + return true; + } + return false; + +} + /* Add a found vars into available variables list */ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1435,6 +1551,14 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) Dwarf_Die die_mem; int ret; + /* + * For some reason (e.g. different column assigned to same address), + * this callback can be called with the address which already passed. + * Ignore it first. + */ + if (available_var_finder_overlap(af)) + return 0; + /* Check number of tevs */ if (af->nvls == af->max_vls) { pr_warning("Too many( > %d) probe point found.\n", af->max_vls); @@ -1578,7 +1702,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, /* Get function entry information */ func = basefunc = dwarf_diename(&spdie); if (!func || - dwarf_entrypc(&spdie, &baseaddr) != 0 || + die_entrypc(&spdie, &baseaddr) != 0 || dwarf_decl_line(&spdie, &baseline) != 0) { lineno = 0; goto post; @@ -1595,7 +1719,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { /* There is an inline function */ - if (dwarf_entrypc(&indie, &_addr) == 0 && + if (die_entrypc(&indie, &_addr) == 0 && _addr == addr) { /* * addr is at an inline function entry. @@ -1675,12 +1799,19 @@ static int line_range_walk_cb(const char *fname, int lineno, void *data) { struct line_finder *lf = data; + const char *__fname; + int __lineno; int err; if ((strtailcmp(fname, lf->fname) != 0) || (lf->lno_s > lineno || lf->lno_e < lineno)) return 0; + /* Make sure this line can be reversable */ + if (cu_find_lineinfo(&lf->cu_die, addr, &__fname, &__lineno) > 0 + && (lineno != __lineno || strcmp(fname, __fname))) + return 0; + err = line_range_add_line(fname, lineno, lf->lr); if (err < 0 && err != -EEXIST) return err; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 670c477bf8cf..11be10080613 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -87,6 +87,7 @@ struct probe_finder { unsigned int machine; /* Target machine arch */ struct perf_probe_arg *pvar; /* Current target variable */ struct probe_trace_arg *tvar; /* Current result variable */ + bool skip_empty_arg; /* Skip non-exist args */ }; struct trace_event_finder { diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 53f31053a27a..83212c65848b 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -6,6 +6,7 @@ #include <linux/err.h> #include <perf/cpumap.h> #include <traceevent/event-parse.h> +#include <perf/mmap.h> #include "evlist.h" #include "callchain.h" #include "evsel.h" @@ -14,6 +15,7 @@ #include "thread_map.h" #include "trace-event.h" #include "mmap.h" +#include "util/env.h" #include <internal/lib.h> #include "../perf-sys.h" @@ -54,10 +56,16 @@ int parse_callchain_record(const char *arg __maybe_unused, } /* + * Add this one here not to drag util/env.c + */ +struct perf_env perf_env; + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ int verbose; +int debug_peo_args; int eprintf(int level, int var, const char *fmt, ...); @@ -1016,10 +1024,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (!md) return NULL; - if (perf_mmap__read_init(md) < 0) + if (perf_mmap__read_init(&md->core) < 0) goto end; - event = perf_mmap__read_event(md); + event = perf_mmap__read_event(&md->core); if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; @@ -1039,7 +1047,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, err = perf_evsel__parse_sample(evsel, event, &pevent->sample); /* Consume the even only after we parsed it out. */ - perf_mmap__consume(md); + perf_mmap__consume(&md->core); if (err) return PyErr_Format(PyExc_OSError, diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 8579505c29a4..7def66168503 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -136,6 +136,37 @@ bool perf_can_record_cpu_wide(void) return true; } +/* + * Architectures are expected to know if AUX area sampling is supported by the + * hardware. Here we check for kernel support. + */ +bool perf_can_aux_sample(void) +{ + struct perf_event_attr attr = { + .size = sizeof(struct perf_event_attr), + .exclude_kernel = 1, + /* + * Non-zero value causes the kernel to calculate the effective + * attribute size up to that byte. + */ + .aux_sample_size = 1, + }; + int fd; + + fd = sys_perf_event_open(&attr, -1, 0, -1, 0); + /* + * If the kernel attribute is big enough to contain aux_sample_size + * then we assume that it is supported. We are relying on the kernel to + * validate the attribute size before anything else that could be wrong. + */ + if (fd < 0 && errno == E2BIG) + return false; + if (fd >= 0) + close(fd); + + return true; +} + void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain) { diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 00275afc524d..5421fd2ad383 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -32,6 +32,7 @@ struct record_opts { bool full_auxtrace; bool auxtrace_snapshot_mode; bool auxtrace_snapshot_on_exit; + bool auxtrace_sample_mode; bool record_namespaces; bool record_switch_events; bool all_kernel; @@ -44,6 +45,7 @@ struct record_opts { bool strict_freq; bool sample_id; bool no_bpf_event; + bool kcore; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; @@ -55,6 +57,7 @@ struct record_opts { u64 user_interval; size_t auxtrace_snapshot_size; const char *auxtrace_snapshot_opts; + const char *auxtrace_sample_opts; bool sample_transaction; unsigned initial_delay; bool use_clockid; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 15961854ba67..0e608a5ef599 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -294,17 +294,17 @@ static SV *perl_process_callchain(struct perf_sample *sample, goto exit; } - if (node->sym) { + if (node->ms.sym) { HV *sym = newHV(); if (!sym) { hv_undef(elem); goto exit; } - if (!hv_stores(sym, "start", newSVuv(node->sym->start)) || - !hv_stores(sym, "end", newSVuv(node->sym->end)) || - !hv_stores(sym, "binding", newSVuv(node->sym->binding)) || - !hv_stores(sym, "name", newSVpvn(node->sym->name, - node->sym->namelen)) || + if (!hv_stores(sym, "start", newSVuv(node->ms.sym->start)) || + !hv_stores(sym, "end", newSVuv(node->ms.sym->end)) || + !hv_stores(sym, "binding", newSVuv(node->ms.sym->binding)) || + !hv_stores(sym, "name", newSVpvn(node->ms.sym->name, + node->ms.sym->namelen)) || !hv_stores(elem, "sym", newRV_noinc((SV*)sym))) { hv_undef(sym); hv_undef(elem); @@ -312,8 +312,8 @@ static SV *perl_process_callchain(struct perf_sample *sample, } } - if (node->map) { - struct map *map = node->map; + if (node->ms.map) { + struct map *map = node->ms.map; const char *dsoname = "[unknown]"; if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) @@ -539,10 +539,11 @@ static int perl_stop_script(void) static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.pl", outfile); @@ -603,8 +604,11 @@ sub print_backtrace\n\ }\n\n\ "); + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); - while ((event = trace_find_next_event(pevent, event))) { + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 5d341efc3237..9581a904af29 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -428,24 +428,24 @@ static PyObject *python_process_callchain(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "ip", PyLong_FromUnsignedLongLong(node->ip)); - if (node->sym) { + if (node->ms.sym) { PyObject *pysym = PyDict_New(); if (!pysym) Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(pysym, "start", - PyLong_FromUnsignedLongLong(node->sym->start)); + PyLong_FromUnsignedLongLong(node->ms.sym->start)); pydict_set_item_string_decref(pysym, "end", - PyLong_FromUnsignedLongLong(node->sym->end)); + PyLong_FromUnsignedLongLong(node->ms.sym->end)); pydict_set_item_string_decref(pysym, "binding", - _PyLong_FromLong(node->sym->binding)); + _PyLong_FromLong(node->ms.sym->binding)); pydict_set_item_string_decref(pysym, "name", - _PyUnicode_FromStringAndSize(node->sym->name, - node->sym->namelen)); + _PyUnicode_FromStringAndSize(node->ms.sym->name, + node->ms.sym->namelen)); pydict_set_item_string_decref(pyelem, "sym", pysym); } - if (node->map) { - const char *dsoname = get_dsoname(node->map); + if (node->ms.map) { + const char *dsoname = get_dsoname(node->ms.map); pydict_set_item_string_decref(pyelem, "dso", _PyUnicode_FromString(dsoname)); @@ -1127,7 +1127,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_u64(t, 0, es->db_id); tuple_set_u64(t, 1, es->evsel->db_id); - tuple_set_u64(t, 2, es->al->machine->db_id); + tuple_set_u64(t, 2, es->al->mg->machine->db_id); tuple_set_u64(t, 3, es->al->thread->db_id); tuple_set_u64(t, 4, es->comm_db_id); tuple_set_u64(t, 5, es->dso_db_id); @@ -1687,10 +1687,11 @@ static int python_stop_script(void) static int python_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.py", outfile); @@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); - while ((event = trace_find_next_event(pevent, event))) { + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); + + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 061bb4d6a3f5..d0d7d25b23e3 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -227,9 +227,13 @@ struct perf_session *perf_session__new(struct perf_data *data, /* Open the directory data. */ if (data->is_dir) { ret = perf_data__open_dir(data); - if (ret) - goto out_delete; + if (ret) + goto out_delete; } + + if (!symbol_conf.kallsyms_name && + !symbol_conf.vmlinux_name) + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { session->machines.host.env = &perf_env; @@ -748,6 +752,7 @@ do { \ bswap_field_32(sample_stack_user); bswap_field_32(aux_watermark); bswap_field_16(sample_max_stack); + bswap_field_32(aux_sample_size); /* * After read_format are bitfields. Check read_format because @@ -1491,8 +1496,13 @@ static int perf_session__deliver_event(struct perf_session *session, if (ret > 0) return 0; - return machines__deliver_event(&session->machines, session->evlist, - event, &sample, tool, file_offset); + ret = machines__deliver_event(&session->machines, session->evlist, + event, &sample, tool, file_offset); + + if (dump_trace && sample.aux_sample.size) + auxtrace__dump_auxtrace_sample(session, &sample); + + return ret; } static s64 perf_session__process_user_event(struct perf_session *session, @@ -1649,6 +1659,34 @@ out_parse_sample: return 0; } +int perf_session__peek_events(struct perf_session *session, u64 offset, + u64 size, peek_events_cb_t cb, void *data) +{ + u64 max_offset = offset + size; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *event; + int err; + + do { + err = perf_session__peek_event(session, offset, buf, + PERF_SAMPLE_MAX_SIZE, &event, + NULL); + if (err) + return err; + + err = cb(session, event, offset, data); + if (err) + return err; + + offset += event->header.size; + if (event->header.type == PERF_RECORD_AUXTRACE) + offset += event->auxtrace.size; + + } while (offset < max_offset); + + return err; +} + static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, u64 file_offset) { @@ -1954,8 +1992,8 @@ out_err: } static union perf_event * -fetch_mmaped_event(struct perf_session *session, - u64 head, size_t mmap_size, char *buf) +prefetch_event(char *buf, u64 head, size_t mmap_size, + bool needs_swap, union perf_event *error) { union perf_event *event; @@ -1967,20 +2005,32 @@ fetch_mmaped_event(struct perf_session *session, return NULL; event = (union perf_event *)(buf + head); + if (needs_swap) + perf_event_header__bswap(&event->header); - if (session->header.needs_swap) + if (head + event->header.size <= mmap_size) + return event; + + /* We're not fetching the event so swap back again */ + if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) { - /* We're not fetching the event so swap back again */ - if (session->header.needs_swap) - perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx: fuzzed perf.data?\n", - __func__, head, event->header.size, mmap_size); - return ERR_PTR(-EINVAL); - } + pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + + return error; +} + +static union perf_event * +fetch_mmaped_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, ERR_PTR(-EINVAL)); +} - return event; +static union perf_event * +fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, NULL); } static int __perf_session__process_decomp_events(struct perf_session *session) @@ -1993,10 +2043,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session) return 0; while (decomp->head < decomp->size && !session_done()) { - union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data); - - if (IS_ERR(event)) - return PTR_ERR(event); + union perf_event *event = fetch_decomp_event(decomp->head, decomp->size, decomp->data, + session->header.needs_swap); if (!event) break; @@ -2096,7 +2144,7 @@ remap: } more: - event = fetch_mmaped_event(session, head, mmap_size, buf); + event = fetch_mmaped_event(head, mmap_size, buf, session->header.needs_swap); if (IS_ERR(event)) return PTR_ERR(event); @@ -2355,35 +2403,6 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp, fprintf(fp, "# ========\n#\n"); } - -int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct evsel_str_handler *assocs, - size_t nr_assocs) -{ - struct evsel *evsel; - size_t i; - int err; - - for (i = 0; i < nr_assocs; i++) { - /* - * Adding a handler for an event not in the session, - * just ignore it. - */ - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name); - if (evsel == NULL) - continue; - - err = -EEXIST; - if (evsel->handler != NULL) - goto out; - evsel->handler = assocs[i].handler; - } - - err = 0; -out: - return err; -} - int perf_event__process_id_index(struct perf_session *session, union perf_event *event) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index b4c9428c18f0..f76480166d38 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -64,6 +64,11 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, void *buf, size_t buf_sz, union perf_event **event_ptr, struct perf_sample *sample); +typedef int (*peek_events_cb_t)(struct perf_session *session, + union perf_event *event, u64 offset, + void *data); +int perf_session__peek_events(struct perf_session *session, u64 offset, + u64 size, peek_events_cb_t cb, void *data); int perf_session__process_events(struct perf_session *session); @@ -120,12 +125,8 @@ void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); struct evsel_str_handler; -int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct evsel_str_handler *assocs, - size_t nr_assocs); - #define perf_session__set_tracepoints_handlers(session, array) \ - __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + __evlist__set_tracepoints_handlers(session->evlist, array, ARRAY_SIZE(array)) extern volatile int session_done; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 43d1d410854a..345b5ccc90f6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -287,10 +287,12 @@ sort__sym_sort(struct hist_entry *left, struct hist_entry *right) return strcmp(right->ms.sym->name, left->ms.sym->name); } -static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, +static int _hist_entry__sym_snprintf(struct map_symbol *ms, u64 ip, char level, char *bf, size_t size, unsigned int width) { + struct symbol *sym = ms->sym; + struct map *map = ms->map; size_t ret = 0; if (verbose > 0) { @@ -325,7 +327,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip, + return _hist_entry__sym_snprintf(&he->ms, he->ip, he->level, bf, size, width); } @@ -386,7 +388,7 @@ struct sort_entry sort_srcline = { static char *addr_map_symbol__srcline(struct addr_map_symbol *ams) { - return map__srcline(ams->map, ams->al_addr, ams->sym); + return map__srcline(ams->ms.map, ams->al_addr, ams->ms.sym); } static int64_t @@ -769,15 +771,15 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); - return _sort__dso_cmp(left->branch_info->from.map, - right->branch_info->from.map); + return _sort__dso_cmp(left->branch_info->from.ms.map, + right->branch_info->from.ms.map); } static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (he->branch_info) - return _hist_entry__dso_snprintf(he->branch_info->from.map, + return _hist_entry__dso_snprintf(he->branch_info->from.ms.map, bf, size, width); else return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -791,8 +793,8 @@ static int hist_entry__dso_from_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__DSO) return -1; - return dso && (!he->branch_info || !he->branch_info->from.map || - he->branch_info->from.map->dso != dso); + return dso && (!he->branch_info || !he->branch_info->from.ms.map || + he->branch_info->from.ms.map->dso != dso); } static int64_t @@ -801,15 +803,15 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); - return _sort__dso_cmp(left->branch_info->to.map, - right->branch_info->to.map); + return _sort__dso_cmp(left->branch_info->to.ms.map, + right->branch_info->to.ms.map); } static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (he->branch_info) - return _hist_entry__dso_snprintf(he->branch_info->to.map, + return _hist_entry__dso_snprintf(he->branch_info->to.ms.map, bf, size, width); else return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -823,8 +825,8 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__DSO) return -1; - return dso && (!he->branch_info || !he->branch_info->to.map || - he->branch_info->to.map->dso != dso); + return dso && (!he->branch_info || !he->branch_info->to.ms.map || + he->branch_info->to.ms.map->dso != dso); } static int64_t @@ -839,10 +841,10 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) from_l = &left->branch_info->from; from_r = &right->branch_info->from; - if (!from_l->sym && !from_r->sym) + if (!from_l->ms.sym && !from_r->ms.sym) return _sort__addr_cmp(from_l->addr, from_r->addr); - return _sort__sym_cmp(from_l->sym, from_r->sym); + return _sort__sym_cmp(from_l->ms.sym, from_r->ms.sym); } static int64_t @@ -856,10 +858,10 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) to_l = &left->branch_info->to; to_r = &right->branch_info->to; - if (!to_l->sym && !to_r->sym) + if (!to_l->ms.sym && !to_r->ms.sym) return _sort__addr_cmp(to_l->addr, to_r->addr); - return _sort__sym_cmp(to_l->sym, to_r->sym); + return _sort__sym_cmp(to_l->ms.sym, to_r->ms.sym); } static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, @@ -868,8 +870,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *from = &he->branch_info->from; - return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - he->level, bf, size, width); + return _hist_entry__sym_snprintf(&from->ms, from->addr, he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -881,8 +882,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *to = &he->branch_info->to; - return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - he->level, bf, size, width); + return _hist_entry__sym_snprintf(&to->ms, to->addr, he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -896,8 +896,8 @@ static int hist_entry__sym_from_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__SYMBOL) return -1; - return sym && !(he->branch_info && he->branch_info->from.sym && - strstr(he->branch_info->from.sym->name, sym)); + return sym && !(he->branch_info && he->branch_info->from.ms.sym && + strstr(he->branch_info->from.ms.sym->name, sym)); } static int hist_entry__sym_to_filter(struct hist_entry *he, int type, @@ -908,8 +908,8 @@ static int hist_entry__sym_to_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__SYMBOL) return -1; - return sym && !(he->branch_info && he->branch_info->to.sym && - strstr(he->branch_info->to.sym->name, sym)); + return sym && !(he->branch_info && he->branch_info->to.ms.sym && + strstr(he->branch_info->to.ms.sym->name, sym)); } struct sort_entry sort_dso_from = { @@ -1017,16 +1017,13 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; if (he->mem_info) { addr = he->mem_info->daddr.addr; - map = he->mem_info->daddr.map; - sym = he->mem_info->daddr.sym; + ms = &he->mem_info->daddr.ms; } - return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width); } int64_t @@ -1046,16 +1043,13 @@ static int hist_entry__iaddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; if (he->mem_info) { addr = he->mem_info->iaddr.addr; - map = he->mem_info->iaddr.map; - sym = he->mem_info->iaddr.sym; + ms = &he->mem_info->iaddr.ms; } - return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width); } static int64_t @@ -1065,9 +1059,9 @@ sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) struct map *map_r = NULL; if (left->mem_info) - map_l = left->mem_info->daddr.map; + map_l = left->mem_info->daddr.ms.map; if (right->mem_info) - map_r = right->mem_info->daddr.map; + map_r = right->mem_info->daddr.ms.map; return _sort__dso_cmp(map_l, map_r); } @@ -1078,7 +1072,7 @@ static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf, struct map *map = NULL; if (he->mem_info) - map = he->mem_info->daddr.map; + map = he->mem_info->daddr.ms.map; return _hist_entry__dso_snprintf(map, bf, size, width); } @@ -1200,6 +1194,7 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) { u64 l, r; struct map *l_map, *r_map; + int rc; if (!left->mem_info) return -1; if (!right->mem_info) return 1; @@ -1208,8 +1203,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (left->cpumode > right->cpumode) return -1; if (left->cpumode < right->cpumode) return 1; - l_map = left->mem_info->daddr.map; - r_map = right->mem_info->daddr.map; + l_map = left->mem_info->daddr.ms.map; + r_map = right->mem_info->daddr.ms.map; /* if both are NULL, jump to sort on al_addr instead */ if (!l_map && !r_map) @@ -1218,18 +1213,9 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (!l_map) return -1; if (!r_map) return 1; - if (l_map->maj > r_map->maj) return -1; - if (l_map->maj < r_map->maj) return 1; - - if (l_map->min > r_map->min) return -1; - if (l_map->min < r_map->min) return 1; - - if (l_map->ino > r_map->ino) return -1; - if (l_map->ino < r_map->ino) return 1; - - if (l_map->ino_generation > r_map->ino_generation) return -1; - if (l_map->ino_generation < r_map->ino_generation) return 1; - + rc = dso__cmp_id(l_map->dso, r_map->dso); + if (rc) + return rc; /* * Addresses with no major/minor numbers are assumed to be * anonymous in userspace. Sort those on pid then address. @@ -1240,8 +1226,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && (!(l_map->flags & MAP_SHARED)) && - !l_map->maj && !l_map->min && !l_map->ino && - !l_map->ino_generation) { + !l_map->dso->id.maj && !l_map->dso->id.min && + !l_map->dso->id.ino && !l_map->dso->id.ino_generation) { /* userspace anonymous */ if (left->thread->pid_ > right->thread->pid_) return -1; @@ -1264,27 +1250,26 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; char level = he->level; if (he->mem_info) { + struct map *map = he->mem_info->daddr.ms.map; + addr = cl_address(he->mem_info->daddr.al_addr); - map = he->mem_info->daddr.map; - sym = he->mem_info->daddr.sym; + ms = &he->mem_info->daddr.ms; /* print [s] for shared data mmaps */ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && map && !(map->prot & PROT_EXEC) && (map->flags & MAP_SHARED) && - (map->maj || map->min || map->ino || - map->ino_generation)) + (map->dso->id.maj || map->dso->id.min || + map->dso->id.ino || map->dso->id.ino_generation)) level = 's'; else if (!map) level = 'X'; } - return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, level, bf, size, width); } struct sort_entry sort_mispredict = { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7b93f34ac1f4..5aff9542d9b7 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -10,6 +10,8 @@ #include "callchain.h" #include "values.h" #include "hist.h" +#include "stat.h" +#include "spark.h" struct option; struct thread; @@ -71,6 +73,8 @@ struct hist_entry_diff { /* PERF_HPP_DIFF__CYCLES */ s64 cycles; }; + struct stats stats; + unsigned long svals[NUM_SPARKS]; }; struct hist_entry_ops { diff --git a/tools/perf/util/spark.c b/tools/perf/util/spark.c new file mode 100644 index 000000000000..70272a8b81a6 --- /dev/null +++ b/tools/perf/util/spark.c @@ -0,0 +1,34 @@ +#include <stdio.h> +#include <limits.h> +#include <string.h> +#include <stdlib.h> +#include "spark.h" +#include "stat.h" + +#define SPARK_SHIFT 8 + +/* Print spark lines on outf for numval values in val. */ +int print_spark(char *bf, int size, unsigned long *val, int numval) +{ + static const char *ticks[NUM_SPARKS] = { + "▁", "▂", "▃", "▄", "▅", "▆", "▇", "█" + }; + int i, printed = 0; + unsigned long min = ULONG_MAX, max = 0, f; + + for (i = 0; i < numval; i++) { + if (val[i] < min) + min = val[i]; + if (val[i] > max) + max = val[i]; + } + f = ((max - min) << SPARK_SHIFT) / (NUM_SPARKS - 1); + if (f < 1) + f = 1; + for (i = 0; i < numval; i++) { + printed += scnprintf(bf + printed, size - printed, "%s", + ticks[((val[i] - min) << SPARK_SHIFT) / f]); + } + + return printed; +} diff --git a/tools/perf/util/spark.h b/tools/perf/util/spark.h new file mode 100644 index 000000000000..25402d7d7a64 --- /dev/null +++ b/tools/perf/util/spark.h @@ -0,0 +1,8 @@ +#ifndef SPARK_H +#define SPARK_H 1 + +#define NUM_SPARKS 8 + +int print_spark(char *bf, int size, unsigned long *val, int numval); + +#endif diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index ed3b0ac2f785..bc31fccc0057 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -100,6 +100,15 @@ static void aggr_printout(struct perf_stat_config *config, nr, config->csv_sep); break; + case AGGR_NODE: + fprintf(config->output, "N%*d%s%*d%s", + config->csv_output ? 0 : -5, + id, + config->csv_sep, + config->csv_output ? 0 : 4, + nr, + config->csv_sep); + break; case AGGR_NONE: if (evsel->percore) { fprintf(config->output, "S%d-D%d-C%*d%s", @@ -965,6 +974,11 @@ static void print_interval(struct perf_stat_config *config, if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { + case AGGR_NODE: + fprintf(output, "# time node cpus"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; case AGGR_SOCKET: fprintf(output, "# time socket cpus"); if (!metric_only) @@ -1188,6 +1202,7 @@ perf_evlist__print_counters(struct evlist *evlist, case AGGR_CORE: case AGGR_DIE: case AGGR_SOCKET: + case AGGR_NODE: print_aggr(config, evlist, prefix); break; case AGGR_THREAD: diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ebdd130557fb..332cb730785b 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -299,6 +299,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, case AGGR_CORE: case AGGR_DIE: case AGGR_SOCKET: + case AGGR_NODE: case AGGR_NONE: if (!evsel->snapshot) perf_evsel__compute_deltas(evsel, cpu, thread, count); @@ -490,6 +491,16 @@ int create_perf_stat_counter(struct evsel *evsel, if (config->identifier) attr->sample_type = PERF_SAMPLE_IDENTIFIER; + if (config->all_user) { + attr->exclude_kernel = 1; + attr->exclude_user = 0; + } + + if (config->all_kernel) { + attr->exclude_kernel = 0; + attr->exclude_user = 1; + } + /* * Disabling all counters initially, they will be enabled * either manually by us or by kernel via enable_on_exec diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index edbeb2f63e8d..bfa9aaf36ce6 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -47,6 +47,7 @@ enum aggr_mode { AGGR_CORE, AGGR_THREAD, AGGR_UNSET, + AGGR_NODE, }; enum { @@ -106,6 +107,8 @@ struct perf_stat_config { bool big_num; bool no_merge; bool walltime_run_table; + bool all_kernel; + bool all_user; FILE *output; unsigned int interval; unsigned int timeout; diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h index 708805f5573e..73df616ced43 100644 --- a/tools/perf/util/string2.h +++ b/tools/perf/util/string2.h @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/types.h> +#include <sys/types.h> // pid_t #include <stddef.h> #include <string.h> @@ -32,6 +33,8 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int return asprintf_expr_inout_ints(var, false, nints, ints); } +char *asprintf__tp_filter_pids(size_t npids, pid_t *pids); + char *strpbrk_esc(char *str, const char *stopset); char *strdup_esc(const char *str); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66f4be1df573..16776d5fbaea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -934,7 +934,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, * we still are sure to have a reference to this DSO via * *curr_map->dso. */ - dsos__add(&map->groups->machine->dsos, curr_dso); + dsos__add(&kmaps->machine->dsos, curr_dso); /* kmaps already got it */ map__put(curr_map); dso__set_loaded(curr_dso); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a8f80e427674..db9667aacb88 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -242,28 +242,24 @@ void symbols__fixup_end(struct rb_root_cached *symbols) void map_groups__fixup_end(struct map_groups *mg) { struct maps *maps = &mg->maps; - struct map *next, *curr; + struct map *prev = NULL, *curr; down_write(&maps->lock); - curr = maps__first(maps); - if (curr == NULL) - goto out_unlock; + maps__for_each_entry(maps, curr) { + if (prev != NULL && !prev->end) + prev->end = curr->start; - for (next = map__next(curr); next; next = map__next(curr)) { - if (!curr->end) - curr->end = next->start; - curr = next; + prev = curr; } /* * We still haven't the actual symbols, so guess the * last map final address. */ - if (!curr->end) + if (curr && !curr->end) curr->end = ~0ULL; -out_unlock: up_write(&maps->lock); } @@ -1053,11 +1049,6 @@ out_delete_from: return ret; } -struct map *map_groups__first(struct map_groups *mg) -{ - return maps__first(&mg->maps); -} - static int do_validate_kcore_modules(const char *filename, struct map_groups *kmaps) { @@ -1069,13 +1060,10 @@ static int do_validate_kcore_modules(const char *filename, if (err) return err; - old_map = map_groups__first(kmaps); - while (old_map) { - struct map *next = map_groups__next(old_map); + map_groups__for_each_entry(kmaps, old_map) { struct module_info *mi; if (!__map__is_kmodule(old_map)) { - old_map = next; continue; } @@ -1085,8 +1073,6 @@ static int do_validate_kcore_modules(const char *filename, err = -EINVAL; goto out; } - - old_map = next; } out: delete_modules(&modules); @@ -1189,9 +1175,7 @@ int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) struct map *old_map; LIST_HEAD(merged); - for (old_map = map_groups__first(kmaps); old_map; - old_map = map_groups__next(old_map)) { - + map_groups__for_each_entry(kmaps, old_map) { /* no overload with this one */ if (new_map->end < old_map->start || new_map->start >= old_map->end) @@ -1264,7 +1248,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, { struct map_groups *kmaps = map__kmaps(map); struct kcore_mapfn_data md; - struct map *old_map, *new_map, *replacement_map = NULL; + struct map *old_map, *new_map, *replacement_map = NULL, *next; struct machine *machine; bool is_64_bit; int err, fd; @@ -1311,10 +1295,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - old_map = map_groups__first(kmaps); - while (old_map) { - struct map *next = map_groups__next(old_map); - + map_groups__for_each_entry_safe(kmaps, old_map, next) { /* * We need to preserve eBPF maps even if they are * covered by kcore, because we need to access @@ -1322,7 +1303,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map, */ if (old_map != map && !__map__is_bpf_prog(old_map)) map_groups__remove(kmaps, old_map); - old_map = next; } machine->trampolines_mapped = false; @@ -1550,7 +1530,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: /* * kernel modules know their symtab type - it's set when - * creating a module dso in machine__findnew_module_map(). + * creating a module dso in machine__addnew_module_map(). */ return kmod && dso->symtab_type == type; @@ -1608,7 +1588,7 @@ int dso__load(struct dso *dso, struct map *map) char *name; int ret = -1; u_int i; - struct machine *machine; + struct machine *machine = NULL; char *root_dir = (char *) ""; int ss_pos = 0; struct symsrc ss_[2]; @@ -1637,17 +1617,13 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - if (map->groups && map->groups->machine) - machine = map->groups->machine; - else - machine = NULL; - if (dso->kernel) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) ret = dso__load_guest_kernel_sym(dso, map); + machine = map__kmaps(map)->machine; if (machine__is(machine, "x86_64")) machine__map_x86_64_entry_trampolines(machine, dso); goto out; @@ -1784,28 +1760,82 @@ out: return ret; } +static int map__strcmp(const void *a, const void *b) +{ + const struct map *ma = *(const struct map **)a, *mb = *(const struct map **)b; + return strcmp(ma->dso->short_name, mb->dso->short_name); +} + +static int map__strcmp_name(const void *name, const void *b) +{ + const struct map *map = *(const struct map **)b; + return strcmp(name, map->dso->short_name); +} + +void __map_groups__sort_by_name(struct map_groups *mg) +{ + qsort(mg->maps_by_name, mg->nr_maps, sizeof(struct map *), map__strcmp); +} + +static int map__groups__sort_by_name_from_rbtree(struct map_groups *mg) +{ + struct map *map; + struct map **maps_by_name = realloc(mg->maps_by_name, mg->nr_maps * sizeof(map)); + int i = 0; + + if (maps_by_name == NULL) + return -1; + + mg->maps_by_name = maps_by_name; + mg->nr_maps_allocated = mg->nr_maps; + + maps__for_each_entry(&mg->maps, map) + maps_by_name[i++] = map; + + __map_groups__sort_by_name(mg); + return 0; +} + +static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) +{ + struct map **mapp; + + if (mg->maps_by_name == NULL && + map__groups__sort_by_name_from_rbtree(mg)) + return NULL; + + mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); + if (mapp) + return *mapp; + return NULL; +} + struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { struct maps *maps = &mg->maps; struct map *map; - struct rb_node *node; down_read(&maps->lock); - for (node = maps->names.rb_node; node; ) { - int rc; - - map = rb_entry(node, struct map, rb_node_name); - - rc = strcmp(map->dso->short_name, name); - if (rc < 0) - node = node->rb_left; - else if (rc > 0) - node = node->rb_right; - else + if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { + map = mg->last_search_by_name; + goto out_unlock; + } + /* + * If we have mg->maps_by_name, then the name isn't in the rbtree, + * as mg->maps_by_name mirrors the rbtree when lookups by name are + * made. + */ + map = __map_groups__find_by_name(mg, name); + if (map || mg->maps_by_name != NULL) + goto out_unlock; + /* Fallback to traversing the rbtree... */ + maps__for_each_entry(maps, map) + if (strcmp(map->dso->short_name, name) == 0) { + mg->last_search_by_name = map; goto out_unlock; - } + } map = NULL; @@ -2047,15 +2077,9 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map) { int err; const char *kallsyms_filename = NULL; - struct machine *machine; + struct machine *machine = map__kmaps(map)->machine; char path[PATH_MAX]; - if (!map->groups) { - pr_debug("Guest kernel map hasn't the point to groups\n"); - return -1; - } - machine = map->groups->machine; - if (machine__is_default_guest(machine)) { /* * if the user specified a vmlinux filename, use it and only @@ -2371,25 +2395,3 @@ struct mem_info *mem_info__new(void) refcount_set(&mi->refcnt, 1); return mi; } - -struct block_info *block_info__get(struct block_info *bi) -{ - if (bi) - refcount_inc(&bi->refcnt); - return bi; -} - -void block_info__put(struct block_info *bi) -{ - if (bi && refcount_dec_and_test(&bi->refcnt)) - free(bi); -} - -struct block_info *block_info__new(void) -{ - struct block_info *bi = zalloc(sizeof(*bi)); - - if (bi) - refcount_set(&bi->refcnt, 1); - return bi; -} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 0b0c6b5b1899..0b718cc9fb28 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -11,6 +11,7 @@ #include <stdio.h> #include "path.h" #include "symbol_conf.h" +#include "spark.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -105,20 +106,9 @@ struct ref_reloc_sym { u64 unrelocated_addr; }; -struct block_info { - struct symbol *sym; - u64 start; - u64 end; - u64 cycles; - u64 cycles_aggr; - int num; - int num_aggr; - refcount_t refcnt; -}; - struct addr_location { - struct machine *machine; struct thread *thread; + struct map_groups *mg; struct map *map; struct symbol *sym; const char *srcline; @@ -289,16 +279,4 @@ static inline void __mem_info__zput(struct mem_info **mi) #define mem_info__zput(mi) __mem_info__zput(&mi) -struct block_info *block_info__new(void); -struct block_info *block_info__get(struct block_info *bi); -void block_info__put(struct block_info *bi); - -static inline void __block_info__zput(struct block_info **bi) -{ - block_info__put(*bi); - *bi = NULL; -} - -#define block_info__zput(bi) __block_info__zput(&bi) - #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index e6880789864c..10f1ec3e0349 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -40,6 +40,7 @@ struct symbol_conf { raw_trace, report_hierarchy, report_block, + report_individual_block, inline_name, disable_add2line_warn; const char *vmlinux_name, diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 807cbca403a7..48c3f8b9c852 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -438,7 +438,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t else event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - for (pos = maps__first(maps); pos; pos = map__next(pos)) { + maps__for_each_entry(maps, pos) { size_t size; if (!__map__is_kmodule(pos)) @@ -1228,6 +1228,11 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_PHYS_ADDR) result += sizeof(u64); + if (type & PERF_SAMPLE_AUX) { + result += sizeof(u64); + result += sample->aux_sample.size; + } + return result; } @@ -1396,6 +1401,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } + if (type & PERF_SAMPLE_AUX) { + sz = sample->aux_sample.size; + *array++ = sz; + memcpy(array, sample->aux_sample.data, sz); + array = (void *)array + sz; + } + return 0; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index b64e9e049636..0a277a920970 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -350,7 +350,7 @@ static int __thread__prepare_access(struct thread *thread) down_read(&maps->lock); - for (map = maps__first(maps); map; map = map__next(map)) { + maps__for_each_entry(maps, map) { err = unwind__prepare_access(thread->mg, map, &initialized); if (err || initialized) break; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 9796a2e43f67..302443921681 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -458,10 +458,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, return true; } -int perf_time__parse_for_ranges(const char *time_str, +int perf_time__parse_for_ranges_reltime(const char *time_str, struct perf_session *session, struct perf_time_interval **ranges, - int *range_size, int *range_num) + int *range_size, int *range_num, + bool reltime) { bool has_percent = strchr(time_str, '%'); struct perf_time_interval *ptime_range; @@ -471,7 +472,7 @@ int perf_time__parse_for_ranges(const char *time_str, if (!ptime_range) return -ENOMEM; - if (has_percent) { + if (has_percent || reltime) { if (session->evlist->first_sample_time == 0 && session->evlist->last_sample_time == 0) { pr_err("HINT: no first/last sample time found in perf data.\n" @@ -479,7 +480,9 @@ int perf_time__parse_for_ranges(const char *time_str, "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n"); goto error; } + } + if (has_percent) { num = perf_time__percent_parse_str( ptime_range, size, time_str, @@ -492,6 +495,15 @@ int perf_time__parse_for_ranges(const char *time_str, if (num < 0) goto error_invalid; + if (reltime) { + int i; + + for (i = 0; i < num; i++) { + ptime_range[i].start += session->evlist->first_sample_time; + ptime_range[i].end += session->evlist->first_sample_time; + } + } + *range_size = size; *range_num = num; *ranges = ptime_range; @@ -504,6 +516,15 @@ error: return ret; } +int perf_time__parse_for_ranges(const char *time_str, + struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num) +{ + return perf_time__parse_for_ranges_reltime(time_str, session, ranges, + range_size, range_num, false); +} + int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) { u64 sec = timestamp / NSEC_PER_SEC; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index 4f42988eb2f7..1142b0bddd5e 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -26,6 +26,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, struct perf_session; +int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num, + bool reltime); + int perf_time__parse_for_ranges(const char *str, struct perf_session *session, struct perf_time_interval **ranges, int *range_size, int *range_num); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 5d6bfc70b210..9634f0ae57be 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent, return tep_parse_event(pevent, buf, size, sys); } -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event) -{ - static int idx; - int events_count; - struct tep_event *all_events; - - all_events = tep_get_first_event(pevent); - events_count = tep_get_events_count(pevent); - if (!pevent || !all_events || events_count < 1) - return NULL; - - if (!event) { - idx = 0; - return all_events; - } - - if (idx < events_count && event == (all_events + idx)) { - idx++; - if (idx == events_count) - return NULL; - return (all_events + idx); - } - - for (idx = 1; idx < events_count; idx++) { - if (event == (all_events + (idx - 1))) - return (all_events + idx); - } - return NULL; -} - struct flag { const char *name; unsigned long long value; diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 2e158387b3d7..72fdf2a3577c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event); unsigned long long read_size(struct tep_event *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 15f6e46d7124..d2a8df01c4a7 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -80,9 +80,10 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; - e->map = al.map; - e->sym = al.sym; + e->ip = ip; + e->ms.mg = al.mg; + e->ms.map = al.map; + e->ms.sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 1800887b2255..6d53347d6744 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -575,9 +575,10 @@ static int entry(u64 ip, struct thread *thread, struct unwind_entry e; struct addr_location al; - e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); - e.ip = ip; - e.map = al.map; + e.ms.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); + e.ip = ip; + e.ms.map = al.map; + e.ms.mg = al.mg; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 3a7d00c20d86..50337c966979 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -4,17 +4,15 @@ #include <linux/compiler.h> #include <linux/types.h> +#include "util/map_symbol.h" -struct map; struct map_groups; struct perf_sample; -struct symbol; struct thread; struct unwind_entry { - struct map *map; - struct symbol *sym; - u64 ip; + struct map_symbol ms; + u64 ip; }; typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 5eda6e19c947..969ae560dad9 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -154,8 +154,10 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) continue; - if (!match_pat(d->d_name, pat)) - return -2; + if (!match_pat(d->d_name, pat)) { + ret = -2; + break; + } scnprintf(namebuf, sizeof(namebuf), "%s/%s", path, d->d_name); @@ -180,14 +182,31 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) return rmdir(path); } +static int rm_rf_kcore_dir(const char *path) +{ + char kcore_dir_path[PATH_MAX]; + const char *pat[] = { + "kcore", + "kallsyms", + "modules", + NULL, + }; + + snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path); + + return rm_rf_depth_pat(kcore_dir_path, 0, pat); +} + int rm_rf_perf_data(const char *path) { const char *pat[] = { - "header", + "data", "data.*", NULL, }; + rm_rf_kcore_dir(path); + return rm_rf_depth_pat(path, 0, pat); } diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index ba4b4395f35d..6e00793c10ee 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -142,9 +142,9 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { enum dso_type dso_type = DSO__TYPE_UNKNOWN; - struct map *map = map_groups__first(thread->mg); + struct map *map; - for (; map ; map = map_groups__next(map)) { + map_groups__for_each_entry(thread->mg, map) { struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; |