diff options
Diffstat (limited to 'tools/perf/util')
68 files changed, 2690 insertions, 1005 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 79dea95a7f68..94518c1bf8b6 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -22,6 +22,7 @@ libperf-y += rbtree.o libperf-y += libstring.o libperf-y += bitmap.o libperf-y += hweight.o +libperf-y += smt.o libperf-y += quote.o libperf-y += strbuf.o libperf-y += string.o @@ -93,6 +94,7 @@ libperf-y += drv_configs.o libperf-y += units.o libperf-y += time-utils.o libperf-y += expr-bison.o +libperf-y += branch.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -104,6 +106,10 @@ ifndef CONFIG_LIBELF libperf-y += symbol-minimal.o endif +ifndef CONFIG_SETNS +libperf-y += setns.o +endif + libperf-$(CONFIG_DWARF) += probe-finder.o libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index be1caabb9290..4397a8b6e6cd 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -47,7 +47,12 @@ struct arch { bool sorted_instructions; bool initialized; void *priv; + unsigned int model; + unsigned int family; int (*init)(struct arch *arch); + bool (*ins_is_fused)(struct arch *arch, const char *ins1, + const char *ins2); + int (*cpuid_parse)(struct arch *arch, char *cpuid); struct { char comment_char; char skip_functions_char; @@ -129,6 +134,8 @@ static struct arch architectures[] = { .name = "x86", .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), + .ins_is_fused = x86__ins_is_fused, + .cpuid_parse = x86__cpuid_parse, .objdump = { .comment_char = '#', }, @@ -171,6 +178,14 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size, return ins__raw_scnprintf(ins, bf, size, ops); } +bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) +{ + if (!arch || !arch->ins_is_fused) + return false; + + return arch->ins_is_fused(arch, ins1, ins2); +} + static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map) { char *endptr, *tok, *name; @@ -502,6 +517,11 @@ bool ins__is_ret(const struct ins *ins) return ins->ops == &ret_ops; } +bool ins__is_lock(const struct ins *ins) +{ + return ins->ops == &lock_ops; +} + static int ins__key_cmp(const void *name, const void *insp) { const struct ins *ins = insp; @@ -590,10 +610,10 @@ int symbol__alloc_hist(struct symbol *sym) size_t sizeof_sym_hist; /* Check for overflow when calculating sizeof_sym_hist */ - if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64)) + if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry)) return -1; - sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); + sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry)); /* Check for overflow in zalloc argument */ if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) @@ -677,7 +697,8 @@ static int __symbol__account_cycles(struct annotation *notes, } static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct annotation *notes, int evidx, u64 addr) + struct annotation *notes, int evidx, u64 addr, + struct perf_sample *sample) { unsigned offset; struct sym_hist *h; @@ -693,12 +714,15 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, offset = addr - sym->start; h = annotation__histogram(notes, evidx); - h->sum++; - h->addr[offset]++; + h->nr_samples++; + h->addr[offset].nr_samples++; + h->period += sample->period; + h->addr[offset].period += sample->period; pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 - ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name, - addr, addr - sym->start, evidx, h->addr[offset]); + ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n", + sym->start, sym->name, addr, addr - sym->start, evidx, + h->addr[offset].nr_samples, h->addr[offset].period); return 0; } @@ -718,7 +742,8 @@ static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles } static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - int evidx, u64 addr) + int evidx, u64 addr, + struct perf_sample *sample) { struct annotation *notes; @@ -727,7 +752,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, notes = symbol__get_annotation(sym, false); if (notes == NULL) return -ENOMEM; - return __symbol__inc_addr_samples(sym, map, notes, evidx, addr); + return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample); } static int symbol__account_cycles(u64 addr, u64 start, @@ -791,14 +816,16 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, return err; } -int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx) +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, + int evidx) { - return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr); + return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample); } -int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip) +int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, + int evidx, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip); + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample); } static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map) @@ -908,11 +935,12 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa } double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, - s64 end, const char **path, u64 *nr_samples) + s64 end, const char **path, struct sym_hist_entry *sample) { struct source_line *src_line = notes->src->lines; double percent = 0.0; - *nr_samples = 0; + + sample->nr_samples = sample->period = 0; if (src_line) { size_t sizeof_src_line = sizeof(*src_line) + @@ -926,19 +954,24 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, *path = src_line->path; percent += src_line->samples[evidx].percent; - *nr_samples += src_line->samples[evidx].nr; + sample->nr_samples += src_line->samples[evidx].nr; offset++; } } else { struct sym_hist *h = annotation__histogram(notes, evidx); unsigned int hits = 0; + u64 period = 0; - while (offset < end) - hits += h->addr[offset++]; + while (offset < end) { + hits += h->addr[offset].nr_samples; + period += h->addr[offset].period; + ++offset; + } - if (h->sum) { - *nr_samples = hits; - percent = 100.0 * hits / h->sum; + if (h->nr_samples) { + sample->period = period; + sample->nr_samples = hits; + percent = 100.0 * hits / h->nr_samples; } } @@ -1037,10 +1070,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (dl->offset != -1) { const char *path = NULL; - u64 nr_samples; double percent, max_percent = 0.0; double *ppercents = &percent; - u64 *psamples = &nr_samples; + struct sym_hist_entry sample; + struct sym_hist_entry *psamples = &sample; int i, nr_percent = 1; const char *color; struct annotation *notes = symbol__annotation(sym); @@ -1054,7 +1087,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (perf_evsel__is_group_event(evsel)) { nr_percent = evsel->nr_members; ppercents = calloc(nr_percent, sizeof(double)); - psamples = calloc(nr_percent, sizeof(u64)); + psamples = calloc(nr_percent, sizeof(struct sym_hist_entry)); if (ppercents == NULL || psamples == NULL) { return -1; } @@ -1065,10 +1098,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st notes->src->lines ? i : evsel->idx + i, offset, next ? next->offset : (s64) len, - &path, &nr_samples); + &path, &sample); ppercents[i] = percent; - psamples[i] = nr_samples; + psamples[i] = sample; if (percent > max_percent) max_percent = percent; } @@ -1106,12 +1139,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st for (i = 0; i < nr_percent; i++) { percent = ppercents[i]; - nr_samples = psamples[i]; + sample = psamples[i]; color = get_percent_color(percent); if (symbol_conf.show_total_period) + color_fprintf(stdout, color, " %11" PRIu64, + sample.period); + else if (symbol_conf.show_nr_samples) color_fprintf(stdout, color, " %7" PRIu64, - nr_samples); + sample.nr_samples); else color_fprintf(stdout, color, " %7.2f", percent); } @@ -1127,13 +1163,13 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (ppercents != &percent) free(ppercents); - if (psamples != &nr_samples) + if (psamples != &sample) free(psamples); } else if (max_lines && printed >= max_lines) return 1; else { - int width = 8; + int width = symbol_conf.show_total_period ? 12 : 8; if (queue) return -1; @@ -1327,7 +1363,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil !dso__is_kcore(dso)) return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX; - build_id_filename = dso__build_id_filename(dso, NULL, 0); + build_id_filename = dso__build_id_filename(dso, NULL, 0, false); if (build_id_filename) { __symbol__join_symfs(filename, filename_size, build_id_filename); free(build_id_filename); @@ -1381,7 +1417,7 @@ static const char *annotate__norm_arch(const char *arch_name) int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize, - struct arch **parch) + struct arch **parch, char *cpuid) { struct dso *dso = map->dso; char command[PATH_MAX * 2]; @@ -1418,6 +1454,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, } } + if (arch->cpuid_parse && cpuid) + arch->cpuid_parse(arch, cpuid); + pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, symfs_filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); @@ -1648,19 +1687,19 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, struct sym_hist *h = annotation__histogram(notes, evidx); struct rb_root tmp_root = RB_ROOT; int nr_pcnt = 1; - u64 h_sum = h->sum; + u64 nr_samples = h->nr_samples; size_t sizeof_src_line = sizeof(struct source_line); if (perf_evsel__is_group_event(evsel)) { for (i = 1; i < evsel->nr_members; i++) { h = annotation__histogram(notes, evidx + i); - h_sum += h->sum; + nr_samples += h->nr_samples; } nr_pcnt = evsel->nr_members; sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples); } - if (!h_sum) + if (!nr_samples) return 0; src_line = notes->src->lines = calloc(len, sizeof_src_line); @@ -1670,7 +1709,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, start = map__rip_2objdump(map, sym->start); for (i = 0; i < len; i++) { - u64 offset, nr_samples; + u64 offset; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; @@ -1679,9 +1718,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, double percent = 0.0; h = annotation__histogram(notes, evidx + k); - nr_samples = h->addr[i]; - if (h->sum) - percent = 100.0 * nr_samples / h->sum; + nr_samples = h->addr[i].nr_samples; + if (h->nr_samples) + percent = 100.0 * nr_samples / h->nr_samples; if (percent > percent_max) percent_max = percent; @@ -1750,10 +1789,10 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) - if (h->addr[offset] != 0) + if (h->addr[offset].nr_samples != 0) printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, - sym->start + offset, h->addr[offset]); - printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); + sym->start + offset, h->addr[offset].nr_samples); + printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples); } int symbol__annotate_printf(struct symbol *sym, struct map *map, @@ -1771,7 +1810,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int printed = 2, queue_len = 0; int more = 0; u64 len; - int width = 8; + int width = symbol_conf.show_total_period ? 12 : 8; int graph_dotted_len; filename = strdup(dso->long_name); @@ -1789,7 +1828,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, width *= evsel->nr_members; graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", - width, width, "Percent", d_filename, evsel_name, h->sum); + width, width, symbol_conf.show_total_period ? "Period" : + symbol_conf.show_nr_samples ? "Samples" : "Percent", + d_filename, evsel_name, h->nr_samples); printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); @@ -1853,10 +1894,10 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) struct sym_hist *h = annotation__histogram(notes, evidx); int len = symbol__size(sym), offset; - h->sum = 0; + h->nr_samples = 0; for (offset = 0; offset < len; ++offset) { - h->addr[offset] = h->addr[offset] * 7 / 8; - h->sum += h->addr[offset]; + h->addr[offset].nr_samples = h->addr[offset].nr_samples * 7 / 8; + h->nr_samples += h->addr[offset].nr_samples; } } @@ -1907,7 +1948,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, u64 len; if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), - 0, NULL) < 0) + 0, NULL, NULL) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 21055034aedd..9ce575c25fd9 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -52,7 +52,9 @@ struct ins_ops { bool ins__is_jump(const struct ins *ins); bool ins__is_call(const struct ins *ins); bool ins__is_ret(const struct ins *ins); +bool ins__is_lock(const struct ins *ins); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); +bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); struct annotation; @@ -72,16 +74,22 @@ static inline bool disasm_line__has_offset(const struct disasm_line *dl) return dl->ops.target.offset_avail; } +struct sym_hist_entry { + u64 nr_samples; + u64 period; +}; + void disasm_line__free(struct disasm_line *dl); struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, - s64 end, const char **path, u64 *nr_samples); + s64 end, const char **path, struct sym_hist_entry *sample); struct sym_hist { - u64 sum; - u64 addr[0]; + u64 nr_samples; + u64 period; + struct sym_hist_entry addr[0]; }; struct cyc_hist { @@ -147,20 +155,22 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) return (void *)sym - symbol_conf.priv_size; } -int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, + int evidx); int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); -int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); +int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, + int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize, - struct arch **parch); + struct arch **parch, char *cpuid); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 4bd2d1d882af..4a1264c66101 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1246,7 +1246,7 @@ int bpf__config_obj(struct bpf_object *obj, if (!obj || !term || !term->config) return -EINVAL; - if (!prefixcmp(term->config, "map:")) { + if (strstarts(term->config, "map:")) { key_scan_pos = sizeof("map:") - 1; err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos); goto out; diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 1356220a9f1b..827f9140f3b8 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -58,6 +58,46 @@ check_pos(struct bpf_insn_pos *pos) return 0; } +/* + * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see + * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM + * instruction (BPF_{B,H,W,DW}). + */ +static int +argtype_to_ldx_size(const char *type) +{ + int arg_size = type ? atoi(&type[1]) : 64; + + switch (arg_size) { + case 8: + return BPF_B; + case 16: + return BPF_H; + case 32: + return BPF_W; + case 64: + default: + return BPF_DW; + } +} + +static const char * +insn_sz_to_str(int insn_sz) +{ + switch (insn_sz) { + case BPF_B: + return "BPF_B"; + case BPF_H: + return "BPF_H"; + case BPF_W: + return "BPF_W"; + case BPF_DW: + return "BPF_DW"; + default: + return "UNKNOWN"; + } +} + /* Give it a shorter name */ #define ins(i, p) append_insn((i), (p)) @@ -258,9 +298,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos, } /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) - ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i, + for (i = 0; i < nargs; i++) { + int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW; + + pr_debug("prologue: load arg %d, insn_sz is %s\n", + i, insn_sz_to_str(insn_sz)); + ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); + } ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c new file mode 100644 index 000000000000..a4fce2729e50 --- /dev/null +++ b/tools/perf/util/branch.c @@ -0,0 +1,147 @@ +#include "perf.h" +#include "util/util.h" +#include "util/debug.h" +#include "util/branch.h" + +static bool cross_area(u64 addr1, u64 addr2, int size) +{ + u64 align1, align2; + + align1 = addr1 & ~(size - 1); + align2 = addr2 & ~(size - 1); + + return (align1 != align2) ? true : false; +} + +#define AREA_4K 4096 +#define AREA_2M (2 * 1024 * 1024) + +void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, + u64 from, u64 to) +{ + if (flags->type == PERF_BR_UNKNOWN || from == 0) + return; + + st->counts[flags->type]++; + + if (flags->type == PERF_BR_COND) { + if (to > from) + st->cond_fwd++; + else + st->cond_bwd++; + } + + if (cross_area(from, to, AREA_2M)) + st->cross_2m++; + else if (cross_area(from, to, AREA_4K)) + st->cross_4k++; +} + +const char *branch_type_name(int type) +{ + const char *branch_names[PERF_BR_MAX] = { + "N/A", + "COND", + "UNCOND", + "IND", + "CALL", + "IND_CALL", + "RET", + "SYSCALL", + "SYSRET", + "COND_CALL", + "COND_RET" + }; + + if (type >= 0 && type < PERF_BR_MAX) + return branch_names[type]; + + return NULL; +} + +void branch_type_stat_display(FILE *fp, struct branch_type_stat *st) +{ + u64 total = 0; + int i; + + for (i = 0; i < PERF_BR_MAX; i++) + total += st->counts[i]; + + if (total == 0) + return; + + fprintf(fp, "\n#"); + fprintf(fp, "\n# Branch Statistics:"); + fprintf(fp, "\n#"); + + if (st->cond_fwd > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "COND_FWD", + 100.0 * (double)st->cond_fwd / (double)total); + } + + if (st->cond_bwd > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "COND_BWD", + 100.0 * (double)st->cond_bwd / (double)total); + } + + if (st->cross_4k > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "CROSS_4K", + 100.0 * (double)st->cross_4k / (double)total); + } + + if (st->cross_2m > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "CROSS_2M", + 100.0 * (double)st->cross_2m / (double)total); + } + + for (i = 0; i < PERF_BR_MAX; i++) { + if (st->counts[i] > 0) + fprintf(fp, "\n%8s: %5.1f%%", + branch_type_name(i), + 100.0 * + (double)st->counts[i] / (double)total); + } +} + +static int count_str_scnprintf(int idx, const char *str, char *bf, int size) +{ + return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str); +} + +int branch_type_str(struct branch_type_stat *st, char *bf, int size) +{ + int i, j = 0, printed = 0; + u64 total = 0; + + for (i = 0; i < PERF_BR_MAX; i++) + total += st->counts[i]; + + if (total == 0) + return 0; + + if (st->cond_fwd > 0) + printed += count_str_scnprintf(j++, "COND_FWD", bf + printed, size - printed); + + if (st->cond_bwd > 0) + printed += count_str_scnprintf(j++, "COND_BWD", bf + printed, size - printed); + + for (i = 0; i < PERF_BR_MAX; i++) { + if (i == PERF_BR_COND) + continue; + + if (st->counts[i] > 0) + printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed); + } + + if (st->cross_4k > 0) + printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed); + + if (st->cross_2m > 0) + printed += count_str_scnprintf(j++, "CROSS_2M", bf + printed, size - printed); + + return printed; +} diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h new file mode 100644 index 000000000000..1e3c7c5cdc63 --- /dev/null +++ b/tools/perf/util/branch.h @@ -0,0 +1,25 @@ +#ifndef _PERF_BRANCH_H +#define _PERF_BRANCH_H 1 + +#include <stdint.h> +#include "../perf.h" + +struct branch_type_stat { + bool branch_to; + u64 counts[PERF_BR_MAX]; + u64 cond_fwd; + u64 cond_bwd; + u64 cross_4k; + u64 cross_2m; +}; + +struct branch_flags; + +void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, + u64 from, u64 to); + +const char *branch_type_name(int type); +void branch_type_stat_display(FILE *fp, struct branch_type_stat *st); +int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize); + +#endif /* _PERF_BRANCH_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e0148b081bdf..c1a06fcd7e70 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -243,12 +243,15 @@ static bool build_id_cache__valid_id(char *sbuild_id) return result; } -static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso) +static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso, + bool is_debug) { - return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf"); + return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : (is_debug ? + "debug" : "elf")); } -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug) { bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); bool is_vdso = dso__is_vdso((struct dso *)dso); @@ -270,7 +273,8 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) ret = asnprintf(&bf, size, "%s", linkname); else ret = asnprintf(&bf, size, "%s/%s", linkname, - build_id_cache__basename(is_kallsyms, is_vdso)); + build_id_cache__basename(is_kallsyms, is_vdso, + is_debug)); if (ret < 0 || (!alloc && size < (unsigned int)ret)) bf = NULL; free(linkname); @@ -285,7 +289,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) else static int write_buildid(const char *name, size_t name_len, u8 *build_id, - pid_t pid, u16 misc, int fd) + pid_t pid, u16 misc, struct feat_fd *fd) { int err; struct build_id_event b; @@ -300,14 +304,15 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, b.header.misc = misc; b.header.size = sizeof(b) + len; - err = writen(fd, &b, sizeof(b)); + err = do_write(fd, &b, sizeof(b)); if (err < 0) return err; return write_padded(fd, name, name_len + 1, len); } -static int machine__write_buildid_table(struct machine *machine, int fd) +static int machine__write_buildid_table(struct machine *machine, + struct feat_fd *fd) { int err = 0; char nm[PATH_MAX]; @@ -352,7 +357,8 @@ static int machine__write_buildid_table(struct machine *machine, int fd) return err; } -int perf_session__write_buildid_table(struct perf_session *session, int fd) +int perf_session__write_buildid_table(struct perf_session *session, + struct feat_fd *fd) { struct rb_node *nd; int err = machine__write_buildid_table(&session->machines.host, fd); @@ -534,13 +540,14 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id) } char *build_id_cache__cachedir(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso) + struct nsinfo *nsi, bool is_kallsyms, + bool is_vdso) { char *realname = (char *)name, *filename; bool slash = is_kallsyms || is_vdso; if (!slash) { - realname = realpath(name, NULL); + realname = nsinfo__realpath(name, nsi); if (!realname) return NULL; } @@ -556,13 +563,13 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name, return filename; } -int build_id_cache__list_build_ids(const char *pathname, +int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result) { char *dir_name; int ret = 0; - dir_name = build_id_cache__cachedir(NULL, pathname, false, false); + dir_name = build_id_cache__cachedir(NULL, pathname, nsi, false, false); if (!dir_name) return -ENOMEM; @@ -576,16 +583,20 @@ int build_id_cache__list_build_ids(const char *pathname, #if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT) static int build_id_cache__add_sdt_cache(const char *sbuild_id, - const char *realname) + const char *realname, + struct nsinfo *nsi) { struct probe_cache *cache; int ret; + struct nscookie nsc; - cache = probe_cache__new(sbuild_id); + cache = probe_cache__new(sbuild_id, nsi); if (!cache) return -1; + nsinfo__mountns_enter(nsi, &nsc); ret = probe_cache__scan_sdt(cache, realname); + nsinfo__mountns_exit(&nsc); if (ret >= 0) { pr_debug4("Found %d SDTs in %s\n", ret, realname); if (probe_cache__commit(cache) < 0) @@ -595,25 +606,56 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id, return ret; } #else -#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0) +#define build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) (0) #endif +static char *build_id_cache__find_debug(const char *sbuild_id, + struct nsinfo *nsi) +{ + char *realname = NULL; + char *debugfile; + struct nscookie nsc; + size_t len = 0; + + debugfile = calloc(1, PATH_MAX); + if (!debugfile) + goto out; + + len = __symbol__join_symfs(debugfile, PATH_MAX, + "/usr/lib/debug/.build-id/"); + snprintf(debugfile + len, PATH_MAX - len, "%.2s/%s.debug", sbuild_id, + sbuild_id + 2); + + nsinfo__mountns_enter(nsi, &nsc); + realname = realpath(debugfile, NULL); + if (realname && access(realname, R_OK)) + zfree(&realname); + nsinfo__mountns_exit(&nsc); +out: + free(debugfile); + return realname; +} + int build_id_cache__add_s(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso) + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; char *realname = NULL, *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp; + char *debugfile = NULL; int err = -1; if (!is_kallsyms) { - realname = realpath(name, NULL); + if (!is_vdso) + realname = nsinfo__realpath(name, nsi); + else + realname = realpath(name, NULL); if (!realname) goto out_free; } - dir_name = build_id_cache__cachedir(sbuild_id, name, - is_kallsyms, is_vdso); + dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms, + is_vdso); if (!dir_name) goto out_free; @@ -627,20 +669,52 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, /* Save the allocated buildid dirname */ if (asprintf(&filename, "%s/%s", dir_name, - build_id_cache__basename(is_kallsyms, is_vdso)) < 0) { + build_id_cache__basename(is_kallsyms, is_vdso, + false)) < 0) { filename = NULL; goto out_free; } if (access(filename, F_OK)) { if (is_kallsyms) { - if (copyfile("/proc/kallsyms", filename)) + if (copyfile("/proc/kallsyms", filename)) + goto out_free; + } else if (nsi && nsi->need_setns) { + if (copyfile_ns(name, filename, nsi)) goto out_free; } else if (link(realname, filename) && errno != EEXIST && copyfile(name, filename)) goto out_free; } + /* Some binaries are stripped, but have .debug files with their symbol + * table. Check to see if we can locate one of those, since the elf + * file itself may not be very useful to users of our tools without a + * symtab. + */ + if (!is_kallsyms && !is_vdso && + strncmp(".ko", name + strlen(name) - 3, 3)) { + debugfile = build_id_cache__find_debug(sbuild_id, nsi); + if (debugfile) { + zfree(&filename); + if (asprintf(&filename, "%s/%s", dir_name, + build_id_cache__basename(false, false, true)) < 0) { + filename = NULL; + goto out_free; + } + if (access(filename, F_OK)) { + if (nsi && nsi->need_setns) { + if (copyfile_ns(debugfile, filename, + nsi)) + goto out_free; + } else if (link(debugfile, filename) && + errno != EEXIST && + copyfile(debugfile, filename)) + goto out_free; + } + } + } + if (!build_id_cache__linkname(sbuild_id, linkname, size)) goto out_free; tmp = strrchr(linkname, '/'); @@ -657,27 +731,30 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, err = 0; /* Update SDT cache : error is just warned */ - if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + if (realname && + build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) < 0) pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: if (!is_kallsyms) free(realname); free(filename); + free(debugfile); free(dir_name); free(linkname); return err; } static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, - const char *name, bool is_kallsyms, - bool is_vdso) + const char *name, struct nsinfo *nsi, + bool is_kallsyms, bool is_vdso) { char sbuild_id[SBUILD_ID_SIZE]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); + return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms, + is_vdso); } bool build_id_cache__cached(const char *sbuild_id) @@ -743,7 +820,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine) name = nm; } return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - is_kallsyms, is_vdso); + dso->nsinfo, is_kallsyms, is_vdso); } static int __dsos__cache_build_ids(struct list_head *head, diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 96690a55c62c..c94b0dcbfd74 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,10 +5,12 @@ #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" +#include "namespaces.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; +struct feat_fd; int build_id__sprintf(const u8 *build_id, int len, char *bf); int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); @@ -16,7 +18,8 @@ int filename__sprintf_build_id(const char *pathname, char *sbuild_id); char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, size_t size); -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, @@ -25,23 +28,26 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, int dsos__hit_all(struct perf_session *session); bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); -int perf_session__write_buildid_table(struct perf_session *session, int fd); +int perf_session__write_buildid_table(struct perf_session *session, + struct feat_fd *fd); int perf_session__cache_build_ids(struct perf_session *session); char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); char *build_id_cache__cachedir(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso); + struct nsinfo *nsi, bool is_kallsyms, + bool is_vdso); struct strlist; struct strlist *build_id_cache__list_all(bool validonly); char *build_id_cache__complement(const char *incomplete_sbuild_id); -int build_id_cache__list_build_ids(const char *pathname, +int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, - const char *name, bool is_kallsyms, bool is_vdso); + const char *name, struct nsinfo *nsi, + bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); extern char buildid_dir[]; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index b4204b43ed58..f320b0777e0d 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -23,6 +23,7 @@ #include "sort.h" #include "machine.h" #include "callchain.h" +#include "branch.h" #define CALLCHAIN_PARAM_DEFAULT \ .mode = CHAIN_GRAPH_ABS, \ @@ -303,7 +304,7 @@ int perf_callchain_config(const char *var, const char *value) { char *endptr; - if (prefixcmp(var, "call-graph.")) + if (!strstarts(var, "call-graph.")) return 0; var += sizeof("call-graph.") - 1; @@ -562,15 +563,33 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) if (cursor_node->branch) { call->branch_count = 1; - if (cursor_node->branch_flags.predicted) - call->predicted_count = 1; - - if (cursor_node->branch_flags.abort) - call->abort_count = 1; - - call->cycles_count = cursor_node->branch_flags.cycles; - call->iter_count = cursor_node->nr_loop_iter; - call->samples_count = cursor_node->samples; + if (cursor_node->branch_from) { + /* + * branch_from is set with value somewhere else + * to imply it's "to" of a branch. + */ + call->brtype_stat.branch_to = true; + + if (cursor_node->branch_flags.predicted) + call->predicted_count = 1; + + if (cursor_node->branch_flags.abort) + call->abort_count = 1; + + branch_type_count(&call->brtype_stat, + &cursor_node->branch_flags, + cursor_node->branch_from, + cursor_node->ip); + } else { + /* + * It's "from" of a branch + */ + call->brtype_stat.branch_to = false; + call->cycles_count = + cursor_node->branch_flags.cycles; + call->iter_count = cursor_node->nr_loop_iter; + call->samples_count = cursor_node->samples; + } } list_add_tail(&call->list, &node->val); @@ -679,15 +698,32 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (node->branch) { cnode->branch_count++; - if (node->branch_flags.predicted) - cnode->predicted_count++; - - if (node->branch_flags.abort) - cnode->abort_count++; - - cnode->cycles_count += node->branch_flags.cycles; - cnode->iter_count += node->nr_loop_iter; - cnode->samples_count += node->samples; + if (node->branch_from) { + /* + * It's "to" of a branch + */ + cnode->brtype_stat.branch_to = true; + + if (node->branch_flags.predicted) + cnode->predicted_count++; + + if (node->branch_flags.abort) + cnode->abort_count++; + + branch_type_count(&cnode->brtype_stat, + &node->branch_flags, + node->branch_from, + node->ip); + } else { + /* + * It's "from" of a branch + */ + cnode->brtype_stat.branch_to = false; + cnode->cycles_count += + node->branch_flags.cycles; + cnode->iter_count += node->nr_loop_iter; + cnode->samples_count += node->samples; + } } return MATCH_EQ; @@ -922,7 +958,7 @@ merge_chain_branch(struct callchain_cursor *cursor, list_for_each_entry_safe(list, next_list, &src->val, list) { callchain_cursor_append(cursor, list->ip, list->ms.map, list->ms.sym, - false, NULL, 0, 0); + false, NULL, 0, 0, 0); list_del(&list->list); map__zput(list->ms.map); free(list); @@ -962,7 +998,7 @@ int callchain_merge(struct callchain_cursor *cursor, int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, struct map *map, struct symbol *sym, bool branch, struct branch_flags *flags, - int nr_loop_iter, int samples) + int nr_loop_iter, int samples, u64 branch_from) { struct callchain_cursor_node *node = *cursor->last; @@ -986,6 +1022,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, memcpy(&node->branch_flags, flags, sizeof(struct branch_flags)); + node->branch_from = branch_from; cursor->nr++; cursor->last = &node->next; @@ -998,11 +1035,11 @@ int sample__resolve_callchain(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al, int max_stack) { - if (sample->callchain == NULL) + if (sample->callchain == NULL && !symbol_conf.show_branchflag_count) return 0; if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || - perf_hpp_list.parent) { + perf_hpp_list.parent || symbol_conf.show_branchflag_count) { return thread__resolve_callchain(al->thread, cursor, evsel, sample, parent, al, max_stack); } @@ -1011,7 +1048,8 @@ int sample__resolve_callchain(struct perf_sample *sample, int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) { - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if ((!symbol_conf.use_callchain || sample->callchain == NULL) && + !symbol_conf.show_branchflag_count) return 0; return callchain_append(he->callchain, &callchain_cursor, sample->period); } @@ -1214,95 +1252,120 @@ int callchain_branch_counts(struct callchain_root *root, cycles_count); } -static int counts_str_build(char *bf, int bfsize, - u64 branch_count, u64 predicted_count, - u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) +static int count_pri64_printf(int idx, const char *str, u64 value, char *bf, int bfsize) { - double predicted_percent = 0.0; - const char *null_str = ""; - char iter_str[32]; - char cycle_str[32]; - char *istr, *cstr; - u64 cycles; + int printed; - if (branch_count == 0) - return scnprintf(bf, bfsize, " (calltrace)"); + printed = scnprintf(bf, bfsize, "%s%s:%" PRId64 "", (idx) ? " " : " (", str, value); - cycles = cycles_count / branch_count; + return printed; +} - if (iter_count && samples_count) { - if (cycles > 0) - scnprintf(iter_str, sizeof(iter_str), - " iterations:%" PRId64 "", - iter_count / samples_count); - else - scnprintf(iter_str, sizeof(iter_str), - "iterations:%" PRId64 "", - iter_count / samples_count); - istr = iter_str; - } else - istr = (char *)null_str; +static int count_float_printf(int idx, const char *str, float value, + char *bf, int bfsize, float threshold) +{ + int printed; - if (cycles > 0) { - scnprintf(cycle_str, sizeof(cycle_str), - "cycles:%" PRId64 "", cycles); - cstr = cycle_str; - } else - cstr = (char *)null_str; + if (threshold != 0.0 && value < threshold) + return 0; - predicted_percent = predicted_count * 100.0 / branch_count; + printed = scnprintf(bf, bfsize, "%s%s:%.1f%%", (idx) ? " " : " (", str, value); - if ((predicted_count == branch_count) && (abort_count == 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, " (%s%s)", cstr, istr); - else - return scnprintf(bf, bfsize, "%s", (char *)null_str); + return printed; +} + +static int branch_to_str(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, + struct branch_type_stat *brtype_stat) +{ + int printed, i = 0; + + printed = branch_type_str(brtype_stat, bf, bfsize); + if (printed) + i++; + + if (predicted_count < branch_count) { + printed += count_float_printf(i++, "predicted", + predicted_count * 100.0 / branch_count, + bf + printed, bfsize - printed, 0.0); } - if ((predicted_count < branch_count) && (abort_count == 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (predicted:%.1f%% %s%s)", - predicted_percent, cstr, istr); - else { - return scnprintf(bf, bfsize, - " (predicted:%.1f%%)", - predicted_percent); - } + if (abort_count) { + printed += count_float_printf(i++, "abort", + abort_count * 100.0 / branch_count, + bf + printed, bfsize - printed, 0.1); } - if ((predicted_count == branch_count) && (abort_count > 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (abort:%" PRId64 " %s%s)", - abort_count, cstr, istr); - else - return scnprintf(bf, bfsize, - " (abort:%" PRId64 ")", - abort_count); + if (i) + printed += scnprintf(bf + printed, bfsize - printed, ")"); + + return printed; +} + +static int branch_from_str(char *bf, int bfsize, + u64 branch_count, + u64 cycles_count, u64 iter_count, + u64 samples_count) +{ + int printed = 0, i = 0; + u64 cycles; + + cycles = cycles_count / branch_count; + if (cycles) { + printed += count_pri64_printf(i++, "cycles", + cycles, + bf + printed, bfsize - printed); + } + + if (iter_count && samples_count) { + printed += count_pri64_printf(i++, "iterations", + iter_count / samples_count, + bf + printed, bfsize - printed); + } + + if (i) + printed += scnprintf(bf + printed, bfsize - printed, ")"); + + return printed; +} + +static int counts_str_build(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count, + struct branch_type_stat *brtype_stat) +{ + int printed; + + if (branch_count == 0) + return scnprintf(bf, bfsize, " (calltrace)"); + + if (brtype_stat->branch_to) { + printed = branch_to_str(bf, bfsize, branch_count, + predicted_count, abort_count, brtype_stat); + } else { + printed = branch_from_str(bf, bfsize, branch_count, + cycles_count, iter_count, samples_count); } - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 " %s%s)", - predicted_percent, abort_count, cstr, istr); + if (!printed) + bf[0] = 0; - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 ")", - predicted_percent, abort_count); + return printed; } static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, u64 branch_count, u64 predicted_count, u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) + u64 iter_count, u64 samples_count, + struct branch_type_stat *brtype_stat) { - char str[128]; + char str[256]; counts_str_build(str, sizeof(str), branch_count, predicted_count, abort_count, cycles_count, - iter_count, samples_count); + iter_count, samples_count, brtype_stat); if (fp) return fprintf(fp, "%s", str); @@ -1334,7 +1397,8 @@ int callchain_list_counts__printf_value(struct callchain_node *node, return callchain_counts_printf(fp, bf, bfsize, branch_count, predicted_count, abort_count, - cycles_count, iter_count, samples_count); + cycles_count, iter_count, samples_count, + &clist->brtype_stat); } static void free_callchain_node(struct callchain_node *node) @@ -1459,7 +1523,8 @@ int callchain_cursor__copy(struct callchain_cursor *dst, rc = callchain_cursor_append(dst, node->ip, node->map, node->sym, node->branch, &node->branch_flags, - node->nr_loop_iter, node->samples); + node->nr_loop_iter, node->samples, + node->branch_from); if (rc) break; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c56c23dbbf72..97738201464a 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,7 @@ #include "event.h" #include "map.h" #include "symbol.h" +#include "branch.h" #define HELP_PAD "\t\t\t\t" @@ -119,6 +120,7 @@ struct callchain_list { u64 cycles_count; u64 iter_count; u64 samples_count; + struct branch_type_stat brtype_stat; char *srcline; struct list_head list; }; @@ -135,6 +137,7 @@ struct callchain_cursor_node { struct symbol *sym; bool branch; struct branch_flags branch_flags; + u64 branch_from; int nr_loop_iter; int samples; struct callchain_cursor_node *next; @@ -198,7 +201,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor) int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, struct map *map, struct symbol *sym, bool branch, struct branch_flags *flags, - int nr_loop_iter, int samples); + int nr_loop_iter, int samples, u64 branch_from); /* Close a cursor writing session. Initialize for the reader */ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 03347748f3fa..0e77bc9e5f3c 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -98,8 +98,10 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) cgrp = counter->cgrp; if (!cgrp) continue; - if (!strcmp(cgrp->name, str)) + if (!strcmp(cgrp->name, str)) { + refcount_inc(&cgrp->refcnt); break; + } cgrp = NULL; } @@ -110,6 +112,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) return -1; cgrp->name = str; + refcount_set(&cgrp->refcnt, 1); cgrp->fd = open_cgroup(str); if (cgrp->fd == -1) { @@ -128,12 +131,11 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (refcount_read(&cgrp->refcnt) == 0) + if (refcount_dec_and_test(&cgrp->refcnt)) free(cgrp); return -1; found: - refcount_inc(&cgrp->refcnt); counter->cgrp = cgrp; return 0; } diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 31a7dea248d0..bc75596f9e79 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -19,6 +19,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include <linux/string.h> #include "sane_ctype.h" @@ -433,22 +434,22 @@ static int perf_ui_config(const char *var, const char *value) int perf_default_config(const char *var, const char *value, void *dummy __maybe_unused) { - if (!prefixcmp(var, "core.")) + if (strstarts(var, "core.")) return perf_default_core_config(var, value); - if (!prefixcmp(var, "hist.")) + if (strstarts(var, "hist.")) return perf_hist_config(var, value); - if (!prefixcmp(var, "ui.")) + if (strstarts(var, "ui.")) return perf_ui_config(var, value); - if (!prefixcmp(var, "call-graph.")) + if (strstarts(var, "call-graph.")) return perf_callchain_config(var, value); - if (!prefixcmp(var, "llvm.")) + if (strstarts(var, "llvm.")) return perf_llvm_config(var, value); - if (!prefixcmp(var, "buildid.")) + if (strstarts(var, "buildid.")) return perf_buildid_config(var, value); /* Add other config variables here. */ diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 34d8baaf558a..cb45a6aecf9d 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -12,6 +12,7 @@ struct perf_counts_values { }; u64 values[3]; }; + bool loaded; }; struct perf_counts { diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 3149b70799fd..2346cecb8ea2 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -76,6 +76,8 @@ struct ctf_writer { struct bt_ctf_event_class *comm_class; struct bt_ctf_event_class *exit_class; struct bt_ctf_event_class *fork_class; + struct bt_ctf_event_class *mmap_class; + struct bt_ctf_event_class *mmap2_class; }; struct convert { @@ -506,6 +508,81 @@ put_len_type: return ret; } +static int +add_callchain_output_values(struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct ip_callchain *callchain) +{ + struct bt_ctf_field_type *len_type, *seq_type; + struct bt_ctf_field *len_field, *seq_field; + unsigned int nr_elements = callchain->nr; + unsigned int i; + int ret; + + len_type = bt_ctf_event_class_get_field_by_name( + event_class, "perf_callchain_size"); + len_field = bt_ctf_field_create(len_type); + if (!len_field) { + pr_err("failed to create 'perf_callchain_size' for callchain output event\n"); + ret = -1; + goto put_len_type; + } + + ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements); + if (ret) { + pr_err("failed to set field value for perf_callchain_size\n"); + goto put_len_field; + } + ret = bt_ctf_event_set_payload(event, "perf_callchain_size", len_field); + if (ret) { + pr_err("failed to set payload to perf_callchain_size\n"); + goto put_len_field; + } + + seq_type = bt_ctf_event_class_get_field_by_name( + event_class, "perf_callchain"); + seq_field = bt_ctf_field_create(seq_type); + if (!seq_field) { + pr_err("failed to create 'perf_callchain' for callchain output event\n"); + ret = -1; + goto put_seq_type; + } + + ret = bt_ctf_field_sequence_set_length(seq_field, len_field); + if (ret) { + pr_err("failed to set length of 'perf_callchain'\n"); + goto put_seq_field; + } + + for (i = 0; i < nr_elements; i++) { + struct bt_ctf_field *elem_field = + bt_ctf_field_sequence_get_field(seq_field, i); + + ret = bt_ctf_field_unsigned_integer_set_value(elem_field, + ((u64 *)(callchain->ips))[i]); + + bt_ctf_field_put(elem_field); + if (ret) { + pr_err("failed to set callchain[%d]\n", i); + goto put_seq_field; + } + } + + ret = bt_ctf_event_set_payload(event, "perf_callchain", seq_field); + if (ret) + pr_err("failed to set payload for raw_data\n"); + +put_seq_field: + bt_ctf_field_put(seq_field); +put_seq_type: + bt_ctf_field_type_put(seq_type); +put_len_field: + bt_ctf_field_put(len_field); +put_len_type: + bt_ctf_field_type_put(len_type); + return ret; +} + static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, struct perf_evsel *evsel, @@ -519,7 +596,6 @@ static int add_generic_values(struct ctf_writer *cw, * PERF_SAMPLE_TIME - not needed as we have it in * ctf event header * PERF_SAMPLE_READ - TODO - * PERF_SAMPLE_CALLCHAIN - TODO * PERF_SAMPLE_RAW - tracepoint fields are handled separately * PERF_SAMPLE_BRANCH_STACK - TODO * PERF_SAMPLE_REGS_USER - TODO @@ -720,6 +796,7 @@ static int process_sample_event(struct perf_tool *tool, struct bt_ctf_event_class *event_class; struct bt_ctf_event *event; int ret; + unsigned long type = evsel->attr.sample_type; if (WARN_ONCE(!priv, "Failed to setup all events.\n")) return 0; @@ -751,6 +828,13 @@ static int process_sample_event(struct perf_tool *tool, return -1; } + if (type & PERF_SAMPLE_CALLCHAIN) { + ret = add_callchain_output_values(event_class, + event, sample->callchain); + if (ret) + return -1; + } + if (perf_evsel__is_bpf_output(evsel)) { ret = add_bpf_output_values(event_class, event, sample); if (ret) @@ -833,6 +917,18 @@ __FUNC_PROCESS_NON_SAMPLE(exit, __NON_SAMPLE_SET_FIELD(fork, u32, ptid); __NON_SAMPLE_SET_FIELD(fork, u64, time); ) +__FUNC_PROCESS_NON_SAMPLE(mmap, + __NON_SAMPLE_SET_FIELD(mmap, u32, pid); + __NON_SAMPLE_SET_FIELD(mmap, u32, tid); + __NON_SAMPLE_SET_FIELD(mmap, u64_hex, start); + __NON_SAMPLE_SET_FIELD(mmap, string, filename); +) +__FUNC_PROCESS_NON_SAMPLE(mmap2, + __NON_SAMPLE_SET_FIELD(mmap2, u32, pid); + __NON_SAMPLE_SET_FIELD(mmap2, u32, tid); + __NON_SAMPLE_SET_FIELD(mmap2, u64_hex, start); + __NON_SAMPLE_SET_FIELD(mmap2, string, filename); +) #undef __NON_SAMPLE_SET_FIELD #undef __FUNC_PROCESS_NON_SAMPLE @@ -1043,6 +1139,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, if (type & PERF_SAMPLE_TRANSACTION) ADD_FIELD(event_class, cw->data.u64, "perf_transaction"); + if (type & PERF_SAMPLE_CALLCHAIN) { + ADD_FIELD(event_class, cw->data.u32, "perf_callchain_size"); + ADD_FIELD(event_class, + bt_ctf_field_type_sequence_create( + cw->data.u64_hex, "perf_callchain_size"), + "perf_callchain"); + } + #undef ADD_FIELD return 0; } @@ -1164,6 +1268,19 @@ __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit, __NON_SAMPLE_ADD_FIELD(u64, time); ) +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u64_hex, start); + __NON_SAMPLE_ADD_FIELD(string, filename); +) + +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap2, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u64_hex, start); + __NON_SAMPLE_ADD_FIELD(string, filename); +) #undef __NON_SAMPLE_ADD_FIELD #undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS @@ -1181,6 +1298,12 @@ static int setup_non_sample_events(struct ctf_writer *cw, ret = add_fork_event(cw); if (ret) return ret; + ret = add_mmap_event(cw); + if (ret) + return ret; + ret = add_mmap2_event(cw); + if (ret) + return ret; return 0; } @@ -1482,6 +1605,8 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.comm = process_comm_event; c.tool.exit = process_exit_event; c.tool.fork = process_fork_event; + c.tool.mmap = process_mmap_event; + c.tool.mmap2 = process_mmap2_event; } err = perf_config(convert__config, &c); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 4e7ab611377a..b9e087fb8247 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -32,6 +32,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__JAVA_JIT] = 'j', [DSO_BINARY_TYPE__DEBUGLINK] = 'l', [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO] = 'D', [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o', @@ -97,7 +98,12 @@ int dso__read_binary_type_filename(const struct dso *dso, break; } case DSO_BINARY_TYPE__BUILD_ID_CACHE: - if (dso__build_id_filename(dso, filename, size) == NULL) + if (dso__build_id_filename(dso, filename, size, false) == NULL) + ret = -1; + break; + + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: + if (dso__build_id_filename(dso, filename, size, true) == NULL) ret = -1; break; @@ -504,7 +510,14 @@ static void check_data_close(void); */ static int open_dso(struct dso *dso, struct machine *machine) { - int fd = __open_dso(dso, machine); + int fd; + struct nscookie nsc; + + if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE) + nsinfo__mountns_enter(dso->nsinfo, &nsc); + fd = __open_dso(dso, machine); + if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE) + nsinfo__mountns_exit(&nsc); if (fd >= 0) { dso__list_add(dso); @@ -1236,6 +1249,7 @@ void dso__delete(struct dso *dso) dso_cache__free(dso); dso__free_a2l(dso); zfree(&dso->symsrc_filename); + nsinfo__zput(dso->nsinfo); pthread_mutex_destroy(&dso->lock); free(dso); } @@ -1301,6 +1315,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) { bool have_build_id = false; struct dso *pos; + struct nscookie nsc; list_for_each_entry(pos, head, node) { if (with_hits && !pos->hit && !dso__is_vdso(pos)) @@ -1309,11 +1324,13 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) have_build_id = true; continue; } + nsinfo__mountns_enter(pos->nsinfo, &nsc); if (filename__read_build_id(pos->long_name, pos->build_id, sizeof(pos->build_id)) > 0) { have_build_id = true; pos->has_build_id = true; } + nsinfo__mountns_exit(&nsc); } return have_build_id; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bd061ba7b47c..f886141678eb 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include "map.h" +#include "namespaces.h" #include "build-id.h" enum dso_binary_type { @@ -20,6 +21,7 @@ enum dso_binary_type { DSO_BINARY_TYPE__JAVA_JIT, DSO_BINARY_TYPE__DEBUGLINK, DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, @@ -187,6 +189,7 @@ struct dso { void *priv; u64 db_id; }; + struct nsinfo *nsinfo; refcount_t refcnt; char name[0]; }; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dc5c3bb69d73..1c905ba3641b 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -57,6 +57,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_STAT_ROUND] = "STAT_ROUND", [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", [PERF_RECORD_TIME_CONV] = "TIME_CONV", + [PERF_RECORD_HEADER_FEATURE] = "FEATURE", }; static const char *perf_ns__names[] = { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 9967c87af7a6..423ac82605f3 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -142,7 +142,8 @@ struct branch_flags { u64 in_tx:1; u64 abort:1; u64 cycles:16; - u64 reserved:44; + u64 type:4; + u64 reserved:40; }; struct branch_entry { @@ -244,6 +245,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_STAT_ROUND = 77, PERF_RECORD_EVENT_UPDATE = 78, PERF_RECORD_TIME_CONV = 79, + PERF_RECORD_HEADER_FEATURE = 80, PERF_RECORD_HEADER_MAX }; @@ -609,6 +611,12 @@ struct time_conv_event { u64 time_zero; }; +struct feature_event { + struct perf_event_header header; + u64 feat_id; + char data[]; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -639,6 +647,7 @@ union perf_event { struct stat_event stat; struct stat_round_event stat_round; struct time_conv_event time_conv; + struct feature_event feat; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 46c0faf6c502..6a0d7ffbeba0 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -242,9 +242,9 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr) } } -int perf_evlist__add_default(struct perf_evlist *evlist) +int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) { - struct perf_evsel *evsel = perf_evsel__new_cycles(); + struct perf_evsel *evsel = perf_evsel__new_cycles(precise); if (evsel == NULL) return -ENOMEM; @@ -1419,8 +1419,6 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e { struct perf_evsel *evsel; int err = 0; - const int ncpus = cpu_map__nr(evlist->cpus), - nthreads = thread_map__nr(evlist->threads); evlist__for_each_entry(evlist, evsel) { if (evsel->filter == NULL) @@ -1430,7 +1428,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e * filters only work for tracepoint event, which doesn't have cpu limit. * So evlist and evsel should always be same. */ - err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter); + err = perf_evsel__apply_filter(evsel, evsel->filter); if (err) { *err_evsel = evsel; break; @@ -1623,13 +1621,9 @@ void perf_evlist__set_selected(struct perf_evlist *evlist, void perf_evlist__close(struct perf_evlist *evlist) { struct perf_evsel *evsel; - int ncpus = cpu_map__nr(evlist->cpus); - int nthreads = thread_map__nr(evlist->threads); - evlist__for_each_entry_reverse(evlist, evsel) { - int n = evsel->cpus ? evsel->cpus->nr : ncpus; - perf_evsel__close(evsel, n, nthreads); - } + evlist__for_each_entry_reverse(evlist, evsel) + perf_evsel__close(evsel); } static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 8d601fbdd8d6..bf2c4936e35f 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -115,7 +115,14 @@ void perf_evlist__delete(struct perf_evlist *evlist); void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel); -int perf_evlist__add_default(struct perf_evlist *evlist); + +int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise); + +static inline int perf_evlist__add_default(struct perf_evlist *evlist) +{ + return __perf_evlist__add_default(evlist, true); +} + int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); @@ -258,6 +265,11 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list); +static inline bool perf_evlist__empty(struct perf_evlist *evlist) +{ + return list_empty(&evlist->entries); +} + static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) { return list_entry(evlist->entries.next, struct perf_evsel, node); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 413f74df08de..d9bd632ed7db 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -49,6 +49,7 @@ static struct { bool clockid_wrong; bool lbr_flags; bool write_backward; + bool group_read; } perf_missing_features; static clockid_t clockid; @@ -58,6 +59,8 @@ static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) return 0; } +void __weak test_attr__ready(void) { } + static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) { } @@ -268,7 +271,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } -struct perf_evsel *perf_evsel__new_cycles(void) +struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, @@ -278,6 +281,9 @@ struct perf_evsel *perf_evsel__new_cycles(void) struct perf_evsel *evsel; event_attr_init(&attr); + + if (!precise) + goto new_event; /* * Unnamed union member, not supported as struct member named * initializer in older compilers such as gcc 4.4.7 @@ -292,7 +298,7 @@ struct perf_evsel *perf_evsel__new_cycles(void) * to kick in when we return and before perf_evsel__open() is called. */ attr.sample_period = 0; - +new_event: evsel = perf_evsel__new(&attr); if (evsel == NULL) goto out; @@ -896,8 +902,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (opts->no_samples) attr->sample_freq = 0; - if (opts->inherit_stat) + if (opts->inherit_stat) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING | + PERF_FORMAT_ID; attr->inherit_stat = 1; + } if (opts->sample_address) { perf_evsel__set_sample_bit(evsel, ADDR); @@ -1045,16 +1056,13 @@ static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthread return evsel->fd != NULL ? 0 : -ENOMEM; } -static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads, +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg) { int cpu, thread; - if (evsel->system_wide) - nthreads = 1; - - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { int fd = FD(evsel, cpu, thread), err = ioctl(fd, ioc, arg); @@ -1066,10 +1074,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea return 0; } -int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter) +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) { - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_SET_FILTER, (void *)filter); } @@ -1116,20 +1123,14 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter) int perf_evsel__enable(struct perf_evsel *evsel) { - int nthreads = thread_map__nr(evsel->threads); - int ncpus = cpu_map__nr(evsel->cpus); - - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); } int perf_evsel__disable(struct perf_evsel *evsel) { - int nthreads = thread_map__nr(evsel->threads); - int ncpus = cpu_map__nr(evsel->cpus); - - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); } @@ -1179,15 +1180,12 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel) } } -void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +void perf_evsel__close_fd(struct perf_evsel *evsel) { int cpu, thread; - if (evsel->system_wide) - nthreads = 1; - - for (cpu = 0; cpu < ncpus; cpu++) - for (thread = 0; thread < nthreads; ++thread) { + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } @@ -1256,20 +1254,148 @@ void perf_counts_values__scale(struct perf_counts_values *count, *pscaled = scaled; } +static int perf_evsel__read_size(struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_GROUP) { + nr = evsel->nr_members; + size += sizeof(u64); + } + + size += entry * nr; + return size; +} + int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { + size_t size = perf_evsel__read_size(evsel); + memset(count, 0, sizeof(*count)); if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0) + if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) return -errno; return 0; } +static int +perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread) +{ + struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread); + + return perf_evsel__read(evsel, cpu, thread, count); +} + +static void +perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, + u64 val, u64 ena, u64 run) +{ + struct perf_counts_values *count; + + count = perf_counts(counter->counts, cpu, thread); + + count->val = val; + count->ena = ena; + count->run = run; + count->loaded = true; +} + +static int +perf_evsel__process_group_data(struct perf_evsel *leader, + int cpu, int thread, u64 *data) +{ + u64 read_format = leader->attr.read_format; + struct sample_read_value *v; + u64 nr, ena = 0, run = 0, i; + + nr = *data++; + + if (nr != (u64) leader->nr_members) + return -EINVAL; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ena = *data++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + run = *data++; + + v = (struct sample_read_value *) data; + + perf_evsel__set_count(leader, cpu, thread, + v[0].value, ena, run); + + for (i = 1; i < nr; i++) { + struct perf_evsel *counter; + + counter = perf_evlist__id2evsel(leader->evlist, v[i].id); + if (!counter) + return -EINVAL; + + perf_evsel__set_count(counter, cpu, thread, + v[i].value, ena, run); + } + + return 0; +} + +static int +perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) +{ + struct perf_stat_evsel *ps = leader->priv; + u64 read_format = leader->attr.read_format; + int size = perf_evsel__read_size(leader); + u64 *data = ps->group_data; + + if (!(read_format & PERF_FORMAT_ID)) + return -EINVAL; + + if (!perf_evsel__is_group_leader(leader)) + return -EINVAL; + + if (!data) { + data = zalloc(size); + if (!data) + return -ENOMEM; + + ps->group_data = data; + } + + if (FD(leader, cpu, thread) < 0) + return -EINVAL; + + if (readn(FD(leader, cpu, thread), data, size) <= 0) + return -errno; + + return perf_evsel__process_group_data(leader, cpu, thread, data); +} + +int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) +{ + u64 read_format = evsel->attr.read_format; + + if (read_format & PERF_FORMAT_GROUP) + return perf_evsel__read_group(evsel, cpu, thread); + else + return perf_evsel__read_one(evsel, cpu, thread); +} + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale) { @@ -1545,6 +1671,8 @@ fallback_missing_features: if (perf_missing_features.lbr_flags) evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); + if (perf_missing_features.group_read && evsel->attr.inherit) + evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1569,6 +1697,8 @@ retry_open: pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpus->map[cpu], group_fd, flags); + test_attr__ready(); + fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], group_fd, flags); @@ -1664,31 +1794,45 @@ try_fallback: */ if (!perf_missing_features.write_backward && evsel->attr.write_backward) { perf_missing_features.write_backward = true; + pr_debug2("switching off write_backward\n"); goto out_close; } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { perf_missing_features.clockid_wrong = true; + pr_debug2("switching off clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { perf_missing_features.clockid = true; + pr_debug2("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"); goto fallback_missing_features; } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; + pr_debug2("switching off mmap2\n"); goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { perf_missing_features.exclude_guest = true; + pr_debug2("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"); goto retry_sample_id; } else if (!perf_missing_features.lbr_flags && (evsel->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"); + goto fallback_missing_features; + } else if (!perf_missing_features.group_read && + evsel->attr.inherit && + (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + perf_missing_features.group_read = true; + pr_debug2("switching off group read\n"); goto fallback_missing_features; } out_close: @@ -1702,12 +1846,12 @@ out_close: return err; } -void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) +void perf_evsel__close(struct perf_evsel *evsel) { if (evsel->fd == NULL) return; - perf_evsel__close_fd(evsel, ncpus, nthreads); + perf_evsel__close_fd(evsel); perf_evsel__free_fd(evsel); } @@ -2535,7 +2679,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "unprivileged users (without CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" - ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" + " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" + ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" + " Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" @@ -2610,3 +2756,10 @@ char *perf_evsel__env_arch(struct perf_evsel *evsel) return evsel->evlist->env->arch; return NULL; } + +char *perf_evsel__env_cpuid(struct perf_evsel *evsel) +{ + if (evsel && evsel->evlist && evsel->evlist->env) + return evsel->evlist->env->cpuid; + return NULL; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d101695c482c..351d3b2d8887 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -185,7 +185,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char * return perf_evsel__newtp_idx(sys, name, 0); } -struct perf_evsel *perf_evsel__new_cycles(void); +struct perf_evsel *perf_evsel__new_cycles(bool precise); struct event_format *event_format__new(const char *sys, const char *name); @@ -226,7 +226,7 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel); int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close_fd(struct perf_evsel *evsel); void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, enum perf_event_sample_format bit); @@ -246,8 +246,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter); +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__enable(struct perf_evsel *evsel); int perf_evsel__disable(struct perf_evsel *evsel); @@ -257,7 +256,7 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads); int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads); -void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close(struct perf_evsel *evsel); struct perf_sample; @@ -299,6 +298,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); +int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread); + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); @@ -436,5 +437,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, attr__fprintf_f attr__fprintf, void *priv); char *perf_evsel__env_arch(struct perf_evsel *evsel); +char *perf_evsel__env_cpuid(struct perf_evsel *evsel); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 9c2760a1a96e..400ef9eab00a 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -1,7 +1,7 @@ #ifndef PARSE_CTX_H #define PARSE_CTX_H 1 -#define EXPR_MAX_OTHER 8 +#define EXPR_MAX_OTHER 15 #define MAX_PARSE_ID EXPR_MAX_OTHER struct parse_id { diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 954556bea36e..432b8560cf51 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -4,6 +4,7 @@ #include "util/debug.h" #define IN_EXPR_Y 1 #include "expr.h" +#include "smt.h" #include <string.h> #define MAXIDLEN 256 @@ -22,13 +23,15 @@ %token <num> NUMBER %token <id> ID +%token MIN MAX IF ELSE SMT_ON +%left MIN MAX IF %left '|' %left '^' %left '&' %left '-' '+' %left '*' '/' '%' %left NEG NOT -%type <num> expr +%type <num> expr if_expr %{ static int expr__lex(YYSTYPE *res, const char **pp); @@ -57,22 +60,33 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val) %} %% -all_expr: expr { *final_val = $1; } +all_expr: if_expr { *final_val = $1; } + ; + +if_expr: + expr IF expr ELSE expr { $$ = $3 ? $1 : $5; } + | expr ; expr: NUMBER | ID { if (lookup_id(ctx, $1, &$$) < 0) { - pr_debug("%s not found", $1); + pr_debug("%s not found\n", $1); YYABORT; } } + | expr '|' expr { $$ = (long)$1 | (long)$3; } + | expr '&' expr { $$ = (long)$1 & (long)$3; } + | expr '^' expr { $$ = (long)$1 ^ (long)$3; } | expr '+' expr { $$ = $1 + $3; } | expr '-' expr { $$ = $1 - $3; } | expr '*' expr { $$ = $1 * $3; } | expr '/' expr { if ($3 == 0) YYABORT; $$ = $1 / $3; } | expr '%' expr { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; } | '-' expr %prec NEG { $$ = -$2; } - | '(' expr ')' { $$ = $2; } + | '(' if_expr ')' { $$ = $2; } + | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } + | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } + | SMT_ON { $$ = smt_on() > 0; } ; %% @@ -82,13 +96,47 @@ static int expr__symbol(YYSTYPE *res, const char *p, const char **pp) char *dst = res->id; const char *s = p; - while (isalnum(*p) || *p == '_' || *p == '.') { + if (*p == '#') + *dst++ = *p++; + + while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') { if (p - s >= MAXIDLEN) return -1; - *dst++ = *p++; + /* + * Allow @ instead of / to be able to specify pmu/event/ without + * conflicts with normal division. + */ + if (*p == '@') + *dst++ = '/'; + else if (*p == '\\') + *dst++ = *++p; + else + *dst++ = *p; + p++; } *dst = 0; *pp = p; + dst = res->id; + switch (dst[0]) { + case 'm': + if (!strcmp(dst, "min")) + return MIN; + if (!strcmp(dst, "max")) + return MAX; + break; + case 'i': + if (!strcmp(dst, "if")) + return IF; + break; + case 'e': + if (!strcmp(dst, "else")) + return ELSE; + break; + case '#': + if (!strcasecmp(dst, "#smt_on")) + return SMT_ON; + break; + } return ID; } @@ -102,6 +150,7 @@ static int expr__lex(YYSTYPE *res, const char **pp) p++; s = p; switch (*p++) { + case '#': case 'a' ... 'z': case 'A' ... 'Z': return expr__symbol(res, p - 1, pp); @@ -132,6 +181,19 @@ void expr__ctx_init(struct parse_ctx *ctx) ctx->num_ids = 0; } +static bool already_seen(const char *val, const char *one, const char **other, + int num_other) +{ + int i; + + if (one && !strcasecmp(one, val)) + return true; + for (i = 0; i < num_other; i++) + if (!strcasecmp(other[i], val)) + return true; + return false; +} + int expr__find_other(const char *p, const char *one, const char ***other, int *num_otherp) { @@ -151,7 +213,7 @@ int expr__find_other(const char *p, const char *one, const char ***other, err = 0; break; } - if (tok == ID && strcasecmp(one, val.id)) { + if (tok == ID && !already_seen(val.id, one, *other, num_other)) { if (num_other >= EXPR_MAX_OTHER - 1) { pr_debug("Too many extra events in %s\n", orig); break; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 76ed7d03e500..605bbd5404fb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -12,6 +12,7 @@ #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> +#include <linux/stringify.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/utsname.h> @@ -34,6 +35,7 @@ #include "data.h" #include <api/fs/fs.h> #include "asm/bug.h" +#include "tool.h" #include "sane_ctype.h" @@ -59,6 +61,15 @@ struct perf_file_attr { struct perf_file_section ids; }; +struct feat_fd { + struct perf_header *ph; + int fd; + void *buf; /* Either buf != NULL or fd >= 0 */ + ssize_t offset; + size_t size; + struct perf_evsel *events; +}; + void perf_header__set_feat(struct perf_header *header, int feat) { set_bit(feat, header->adds_features); @@ -74,28 +85,60 @@ bool perf_header__has_feat(const struct perf_header *header, int feat) return test_bit(feat, header->adds_features); } -static int do_write(int fd, const void *buf, size_t size) +static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size) { - while (size) { - int ret = write(fd, buf, size); + ssize_t ret = writen(ff->fd, buf, size); - if (ret < 0) - return -errno; + if (ret != (ssize_t)size) + return ret < 0 ? (int)ret : -1; + return 0; +} + +static int __do_write_buf(struct feat_fd *ff, const void *buf, size_t size) +{ + /* struct perf_event_header::size is u16 */ + const size_t max_size = 0xffff - sizeof(struct perf_event_header); + size_t new_size = ff->size; + void *addr; - size -= ret; - buf += ret; + if (size + ff->offset > max_size) + return -E2BIG; + + while (size > (new_size - ff->offset)) + new_size <<= 1; + new_size = min(max_size, new_size); + + if (ff->size < new_size) { + addr = realloc(ff->buf, new_size); + if (!addr) + return -ENOMEM; + ff->buf = addr; + ff->size = new_size; } + memcpy(ff->buf + ff->offset, buf, size); + ff->offset += size; + return 0; } -int write_padded(int fd, const void *bf, size_t count, size_t count_aligned) +/* Return: 0 if succeded, -ERR if failed. */ +int do_write(struct feat_fd *ff, const void *buf, size_t size) +{ + if (!ff->buf) + return __do_write_fd(ff, buf, size); + return __do_write_buf(ff, buf, size); +} + +/* Return: 0 if succeded, -ERR if failed. */ +int write_padded(struct feat_fd *ff, const void *bf, + size_t count, size_t count_aligned) { static const char zero_buf[NAME_ALIGN]; - int err = do_write(fd, bf, count); + int err = do_write(ff, bf, count); if (!err) - err = do_write(fd, zero_buf, count_aligned - count); + err = do_write(ff, zero_buf, count_aligned - count); return err; } @@ -103,7 +146,8 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned) #define string_size(str) \ (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32)) -static int do_write_string(int fd, const char *str) +/* Return: 0 if succeded, -ERR if failed. */ +static int do_write_string(struct feat_fd *ff, const char *str) { u32 len, olen; int ret; @@ -112,32 +156,80 @@ static int do_write_string(int fd, const char *str) len = PERF_ALIGN(olen, NAME_ALIGN); /* write len, incl. \0 */ - ret = do_write(fd, &len, sizeof(len)); + ret = do_write(ff, &len, sizeof(len)); if (ret < 0) return ret; - return write_padded(fd, str, olen, len); + return write_padded(ff, str, olen, len); } -static char *do_read_string(int fd, struct perf_header *ph) +static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size) +{ + ssize_t ret = readn(ff->fd, addr, size); + + if (ret != size) + return ret < 0 ? (int)ret : -1; + return 0; +} + +static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size) +{ + if (size > (ssize_t)ff->size - ff->offset) + return -1; + + memcpy(addr, ff->buf + ff->offset, size); + ff->offset += size; + + return 0; + +} + +static int __do_read(struct feat_fd *ff, void *addr, ssize_t size) +{ + if (!ff->buf) + return __do_read_fd(ff, addr, size); + return __do_read_buf(ff, addr, size); +} + +static int do_read_u32(struct feat_fd *ff, u32 *addr) +{ + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_32(*addr); + return 0; +} + +static int do_read_u64(struct feat_fd *ff, u64 *addr) +{ + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_64(*addr); + return 0; +} + +static char *do_read_string(struct feat_fd *ff) { - ssize_t sz, ret; u32 len; char *buf; - sz = readn(fd, &len, sizeof(len)); - if (sz < (ssize_t)sizeof(len)) + if (do_read_u32(ff, &len)) return NULL; - if (ph->needs_swap) - len = bswap_32(len); - buf = malloc(len); if (!buf) return NULL; - ret = readn(fd, buf, len); - if (ret == (ssize_t)len) { + if (!__do_read(ff, buf, len)) { /* * strings are padded by zeroes * thus the actual strlen of buf @@ -150,25 +242,30 @@ static char *do_read_string(int fd, struct perf_header *ph) return NULL; } -static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist) +static int write_tracing_data(struct feat_fd *ff, + struct perf_evlist *evlist) { - return read_tracing_data(fd, &evlist->entries); -} + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + return read_tracing_data(ff->fd, &evlist->entries); +} -static int write_build_id(int fd, struct perf_header *h, +static int write_build_id(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_session *session; int err; - session = container_of(h, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); if (!perf_session__read_build_ids(session, true)) return -1; - err = perf_session__write_buildid_table(session, fd); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + err = perf_session__write_buildid_table(session, ff); if (err < 0) { pr_debug("failed to write buildid table\n"); return err; @@ -178,7 +275,7 @@ static int write_build_id(int fd, struct perf_header *h, return 0; } -static int write_hostname(int fd, struct perf_header *h __maybe_unused, +static int write_hostname(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -188,10 +285,10 @@ static int write_hostname(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.nodename); + return do_write_string(ff, uts.nodename); } -static int write_osrelease(int fd, struct perf_header *h __maybe_unused, +static int write_osrelease(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -201,10 +298,10 @@ static int write_osrelease(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.release); + return do_write_string(ff, uts.release); } -static int write_arch(int fd, struct perf_header *h __maybe_unused, +static int write_arch(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -214,16 +311,16 @@ static int write_arch(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.machine); + return do_write_string(ff, uts.machine); } -static int write_version(int fd, struct perf_header *h __maybe_unused, +static int write_version(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { - return do_write_string(fd, perf_version_string); + return do_write_string(ff, perf_version_string); } -static int __write_cpudesc(int fd, const char *cpuinfo_proc) +static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc) { FILE *file; char *buf = NULL; @@ -273,25 +370,22 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc) } p++; } - ret = do_write_string(fd, s); + ret = do_write_string(ff, s); done: free(buf); fclose(file); return ret; } -static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, +static int write_cpudesc(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { -#ifndef CPUINFO_PROC -#define CPUINFO_PROC {"model name", } -#endif const char *cpuinfo_procs[] = CPUINFO_PROC; unsigned int i; for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { int ret; - ret = __write_cpudesc(fd, cpuinfo_procs[i]); + ret = __write_cpudesc(ff, cpuinfo_procs[i]); if (ret >= 0) return ret; } @@ -299,7 +393,7 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, } -static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, +static int write_nrcpus(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { long nr; @@ -314,14 +408,14 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, nra = (u32)(nr & UINT_MAX); - ret = do_write(fd, &nrc, sizeof(nrc)); + ret = do_write(ff, &nrc, sizeof(nrc)); if (ret < 0) return ret; - return do_write(fd, &nra, sizeof(nra)); + return do_write(ff, &nra, sizeof(nra)); } -static int write_event_desc(int fd, struct perf_header *h __maybe_unused, +static int write_event_desc(struct feat_fd *ff, struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -333,7 +427,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, /* * write number of events */ - ret = do_write(fd, &nre, sizeof(nre)); + ret = do_write(ff, &nre, sizeof(nre)); if (ret < 0) return ret; @@ -341,12 +435,12 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, * size of perf_event_attr struct */ sz = (u32)sizeof(evsel->attr); - ret = do_write(fd, &sz, sizeof(sz)); + ret = do_write(ff, &sz, sizeof(sz)); if (ret < 0) return ret; evlist__for_each_entry(evlist, evsel) { - ret = do_write(fd, &evsel->attr, sz); + ret = do_write(ff, &evsel->attr, sz); if (ret < 0) return ret; /* @@ -357,27 +451,27 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, * type of ids, */ nri = evsel->ids; - ret = do_write(fd, &nri, sizeof(nri)); + ret = do_write(ff, &nri, sizeof(nri)); if (ret < 0) return ret; /* * write event string as passed on cmdline */ - ret = do_write_string(fd, perf_evsel__name(evsel)); + ret = do_write_string(ff, perf_evsel__name(evsel)); if (ret < 0) return ret; /* * write unique ids for this event */ - ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64)); if (ret < 0) return ret; } return 0; } -static int write_cmdline(int fd, struct perf_header *h __maybe_unused, +static int write_cmdline(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { char buf[MAXPATHLEN]; @@ -395,16 +489,16 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused, /* account for binary path */ n = perf_env.nr_cmdline + 1; - ret = do_write(fd, &n, sizeof(n)); + ret = do_write(ff, &n, sizeof(n)); if (ret < 0) return ret; - ret = do_write_string(fd, buf); + ret = do_write_string(ff, buf); if (ret < 0) return ret; for (i = 0 ; i < perf_env.nr_cmdline; i++) { - ret = do_write_string(fd, perf_env.cmdline_argv[i]); + ret = do_write_string(ff, perf_env.cmdline_argv[i]); if (ret < 0) return ret; } @@ -557,8 +651,8 @@ out_free: return tp; } -static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cpu_topology(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { struct cpu_topo *tp; u32 i; @@ -568,21 +662,21 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, if (!tp) return -1; - ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib)); if (ret < 0) goto done; for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(fd, tp->core_siblings[i]); + ret = do_write_string(ff, tp->core_siblings[i]); if (ret < 0) goto done; } - ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib)); + ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib)); if (ret < 0) goto done; for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(fd, tp->thread_siblings[i]); + ret = do_write_string(ff, tp->thread_siblings[i]); if (ret < 0) break; } @@ -592,11 +686,11 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, goto done; for (j = 0; j < perf_env.nr_cpus_avail; j++) { - ret = do_write(fd, &perf_env.cpu[j].core_id, + ret = do_write(ff, &perf_env.cpu[j].core_id, sizeof(perf_env.cpu[j].core_id)); if (ret < 0) return ret; - ret = do_write(fd, &perf_env.cpu[j].socket_id, + ret = do_write(ff, &perf_env.cpu[j].socket_id, sizeof(perf_env.cpu[j].socket_id)); if (ret < 0) return ret; @@ -608,8 +702,8 @@ done: -static int write_total_mem(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_total_mem(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -629,7 +723,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, if (!ret) { n = sscanf(buf, "%*s %"PRIu64, &mem); if (n == 1) - ret = do_write(fd, &mem, sizeof(mem)); + ret = do_write(ff, &mem, sizeof(mem)); } else ret = -1; free(buf); @@ -637,7 +731,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, return ret; } -static int write_topo_node(int fd, int node) +static int write_topo_node(struct feat_fd *ff, int node) { char str[MAXPATHLEN]; char field[32]; @@ -667,11 +761,11 @@ static int write_topo_node(int fd, int node) fclose(fp); fp = NULL; - ret = do_write(fd, &mem_total, sizeof(u64)); + ret = do_write(ff, &mem_total, sizeof(u64)); if (ret) goto done; - ret = do_write(fd, &mem_free, sizeof(u64)); + ret = do_write(ff, &mem_free, sizeof(u64)); if (ret) goto done; @@ -689,7 +783,7 @@ static int write_topo_node(int fd, int node) if (p) *p = '\0'; - ret = do_write_string(fd, buf); + ret = do_write_string(ff, buf); done: free(buf); if (fp) @@ -697,8 +791,8 @@ done: return ret; } -static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_numa_topology(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; size_t len = 0; @@ -725,17 +819,17 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, nr = (u32)node_map->nr; - ret = do_write(fd, &nr, sizeof(nr)); + ret = do_write(ff, &nr, sizeof(nr)); if (ret < 0) goto done; for (i = 0; i < nr; i++) { j = (u32)node_map->map[i]; - ret = do_write(fd, &j, sizeof(j)); + ret = do_write(ff, &j, sizeof(j)); if (ret < 0) break; - ret = write_topo_node(fd, i); + ret = write_topo_node(ff, i); if (ret < 0) break; } @@ -758,39 +852,40 @@ done: * }; */ -static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, +static int write_pmu_mappings(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_pmu *pmu = NULL; - off_t offset = lseek(fd, 0, SEEK_CUR); - __u32 pmu_num = 0; + u32 pmu_num = 0; int ret; - /* write real pmu_num later */ - ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + /* + * Do a first pass to count number of pmu to avoid lseek so this + * works in pipe mode as well. + */ + while ((pmu = perf_pmu__scan(pmu))) { + if (!pmu->name) + continue; + pmu_num++; + } + + ret = do_write(ff, &pmu_num, sizeof(pmu_num)); if (ret < 0) return ret; while ((pmu = perf_pmu__scan(pmu))) { if (!pmu->name) continue; - pmu_num++; - ret = do_write(fd, &pmu->type, sizeof(pmu->type)); + ret = do_write(ff, &pmu->type, sizeof(pmu->type)); if (ret < 0) return ret; - ret = do_write_string(fd, pmu->name); + ret = do_write_string(ff, pmu->name); if (ret < 0) return ret; } - if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { - /* discard all */ - lseek(fd, offset, SEEK_SET); - return -1; - } - return 0; } @@ -806,14 +901,14 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, * }[nr_groups]; * }; */ -static int write_group_desc(int fd, struct perf_header *h __maybe_unused, +static int write_group_desc(struct feat_fd *ff, struct perf_evlist *evlist) { u32 nr_groups = evlist->nr_groups; struct perf_evsel *evsel; int ret; - ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + ret = do_write(ff, &nr_groups, sizeof(nr_groups)); if (ret < 0) return ret; @@ -824,15 +919,15 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, u32 leader_idx = evsel->idx; u32 nr_members = evsel->nr_members; - ret = do_write_string(fd, name); + ret = do_write_string(ff, name); if (ret < 0) return ret; - ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + ret = do_write(ff, &leader_idx, sizeof(leader_idx)); if (ret < 0) return ret; - ret = do_write(fd, &nr_members, sizeof(nr_members)); + ret = do_write(ff, &nr_members, sizeof(nr_members)); if (ret < 0) return ret; } @@ -849,7 +944,7 @@ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) return -1; } -static int write_cpuid(int fd, struct perf_header *h __maybe_unused, +static int write_cpuid(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { char buffer[64]; @@ -861,25 +956,27 @@ static int write_cpuid(int fd, struct perf_header *h __maybe_unused, return -1; write_it: - return do_write_string(fd, buffer); + return do_write_string(ff, buffer); } -static int write_branch_stack(int fd __maybe_unused, - struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_branch_stack(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return 0; } -static int write_auxtrace(int fd, struct perf_header *h, +static int write_auxtrace(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_session *session; int err; - session = container_of(h, struct perf_session, header); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + session = container_of(ff->ph, struct perf_session, header); - err = auxtrace_index__write(fd, &session->auxtrace_index); + err = auxtrace_index__write(ff->fd, &session->auxtrace_index); if (err < 0) pr_err("Failed to write auxtrace index\n"); return err; @@ -1026,8 +1123,8 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) #define MAX_CACHES 2000 -static int write_cache(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cache(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { struct cpu_cache_level caches[MAX_CACHES]; u32 cnt = 0, i, version = 1; @@ -1039,11 +1136,11 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort); - ret = do_write(fd, &version, sizeof(u32)); + ret = do_write(ff, &version, sizeof(u32)); if (ret < 0) goto out; - ret = do_write(fd, &cnt, sizeof(u32)); + ret = do_write(ff, &cnt, sizeof(u32)); if (ret < 0) goto out; @@ -1051,7 +1148,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, struct cpu_cache_level *c = &caches[i]; #define _W(v) \ - ret = do_write(fd, &c->v, sizeof(u32)); \ + ret = do_write(ff, &c->v, sizeof(u32)); \ if (ret < 0) \ goto out; @@ -1062,7 +1159,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, #undef _W #define _W(v) \ - ret = do_write_string(fd, (const char *) c->v); \ + ret = do_write_string(ff, (const char *) c->v); \ if (ret < 0) \ goto out; @@ -1078,69 +1175,62 @@ out: return ret; } -static int write_stat(int fd __maybe_unused, - struct perf_header *h __maybe_unused, +static int write_stat(struct feat_fd *ff __maybe_unused, struct perf_evlist *evlist __maybe_unused) { return 0; } -static void print_hostname(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_hostname(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# hostname : %s\n", ph->env.hostname); + fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); } -static void print_osrelease(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_osrelease(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# os release : %s\n", ph->env.os_release); + fprintf(fp, "# os release : %s\n", ff->ph->env.os_release); } -static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static void print_arch(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# arch : %s\n", ph->env.arch); + fprintf(fp, "# arch : %s\n", ff->ph->env.arch); } -static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cpudesc(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc); + fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc); } -static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_nrcpus(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online); - fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail); + fprintf(fp, "# nrcpus online : %u\n", ff->ph->env.nr_cpus_online); + fprintf(fp, "# nrcpus avail : %u\n", ff->ph->env.nr_cpus_avail); } -static void print_version(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_version(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# perf version : %s\n", ph->env.version); + fprintf(fp, "# perf version : %s\n", ff->ph->env.version); } -static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cmdline(struct feat_fd *ff, FILE *fp) { int nr, i; - nr = ph->env.nr_cmdline; + nr = ff->ph->env.nr_cmdline; fprintf(fp, "# cmdline : "); for (i = 0; i < nr; i++) - fprintf(fp, "%s ", ph->env.cmdline_argv[i]); + fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); fputc('\n', fp); } -static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cpu_topology(struct feat_fd *ff, FILE *fp) { + struct perf_header *ph = ff->ph; + int cpu_nr = ph->env.nr_cpus_avail; int nr, i; char *str; - int cpu_nr = ph->env.nr_cpus_avail; nr = ph->env.nr_sibling_cores; str = ph->env.sibling_cores; @@ -1181,31 +1271,21 @@ static void free_event_desc(struct perf_evsel *events) free(events); } -static struct perf_evsel * -read_event_desc(struct perf_header *ph, int fd) +static struct perf_evsel *read_event_desc(struct feat_fd *ff) { struct perf_evsel *evsel, *events = NULL; u64 *id; void *buf = NULL; u32 nre, sz, nr, i, j; - ssize_t ret; size_t msz; /* number of events */ - ret = readn(fd, &nre, sizeof(nre)); - if (ret != (ssize_t)sizeof(nre)) + if (do_read_u32(ff, &nre)) goto error; - if (ph->needs_swap) - nre = bswap_32(nre); - - ret = readn(fd, &sz, sizeof(sz)); - if (ret != (ssize_t)sizeof(sz)) + if (do_read_u32(ff, &sz)) goto error; - if (ph->needs_swap) - sz = bswap_32(sz); - /* buffer to hold on file attr struct */ buf = malloc(sz); if (!buf) @@ -1227,25 +1307,23 @@ read_event_desc(struct perf_header *ph, int fd) * must read entire on-file attr struct to * sync up with layout. */ - ret = readn(fd, buf, sz); - if (ret != (ssize_t)sz) + if (__do_read(ff, buf, sz)) goto error; - if (ph->needs_swap) + if (ff->ph->needs_swap) perf_event__attr_swap(buf); memcpy(&evsel->attr, buf, msz); - ret = readn(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) + if (do_read_u32(ff, &nr)) goto error; - if (ph->needs_swap) { - nr = bswap_32(nr); + if (ff->ph->needs_swap) evsel->needs_swap = true; - } - evsel->name = do_read_string(fd, ph); + evsel->name = do_read_string(ff); + if (!evsel->name) + goto error; if (!nr) continue; @@ -1257,11 +1335,8 @@ read_event_desc(struct perf_header *ph, int fd) evsel->id = id; for (j = 0 ; j < nr; j++) { - ret = readn(fd, id, sizeof(*id)); - if (ret != (ssize_t)sizeof(*id)) + if (do_read_u64(ff, id)) goto error; - if (ph->needs_swap) - *id = bswap_64(*id); id++; } } @@ -1280,12 +1355,17 @@ static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, return fprintf(fp, ", %s = %s", name, val); } -static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +static void print_event_desc(struct feat_fd *ff, FILE *fp) { - struct perf_evsel *evsel, *events = read_event_desc(ph, fd); + struct perf_evsel *evsel, *events; u32 j; u64 *id; + if (ff->events) + events = ff->events; + else + events = read_event_desc(ff); + if (!events) { fprintf(fp, "# event desc: not available or unable to read\n"); return; @@ -1310,22 +1390,21 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) } free_event_desc(events); + ff->events = NULL; } -static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_total_mem(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem); + fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem); } -static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_numa_topology(struct feat_fd *ff, FILE *fp) { int i; struct numa_node *n; - for (i = 0; i < ph->env.nr_numa_nodes; i++) { - n = &ph->env.numa_nodes[i]; + for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) { + n = &ff->ph->env.numa_nodes[i]; fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," " free = %"PRIu64" kB\n", @@ -1336,56 +1415,51 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, } } -static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static void print_cpuid(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# cpuid : %s\n", ph->env.cpuid); + fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid); } -static void print_branch_stack(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains samples with branch stack\n"); } -static void print_auxtrace(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n"); } -static void print_stat(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_stat(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains stat data\n"); } -static void print_cache(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp __maybe_unused) +static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) { int i; fprintf(fp, "# CPU cache info:\n"); - for (i = 0; i < ph->env.caches_cnt; i++) { + for (i = 0; i < ff->ph->env.caches_cnt; i++) { fprintf(fp, "# "); - cpu_cache_level__fprintf(fp, &ph->env.caches[i]); + cpu_cache_level__fprintf(fp, &ff->ph->env.caches[i]); } } -static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { const char *delimiter = "# pmu mappings: "; char *str, *tmp; u32 pmu_num; u32 type; - pmu_num = ph->env.nr_pmu_mappings; + pmu_num = ff->ph->env.nr_pmu_mappings; if (!pmu_num) { fprintf(fp, "# pmu mappings: not available\n"); return; } - str = ph->env.pmu_mappings; + str = ff->ph->env.pmu_mappings; while (pmu_num) { type = strtoul(str, &tmp, 0); @@ -1408,14 +1482,13 @@ error: fprintf(fp, "# pmu mappings: unable to read\n"); } -static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_group_desc(struct feat_fd *ff, FILE *fp) { struct perf_session *session; struct perf_evsel *evsel; u32 nr = 0; - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); evlist__for_each_entry(session->evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && @@ -1588,113 +1661,61 @@ out: return err; } -static int process_tracing_data(struct perf_file_section *section __maybe_unused, - struct perf_header *ph __maybe_unused, - int fd, void *data) -{ - ssize_t ret = trace_report(fd, data, false); - return ret < 0 ? -1 : 0; -} - -static int process_build_id(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) - pr_debug("Failed to read buildids, continuing...\n"); - return 0; +/* Macro for features that simply need to read and store a string. */ +#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ +static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ +{\ + ff->ph->env.__feat_env = do_read_string(ff); \ + return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } -static int process_hostname(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.hostname = do_read_string(fd, ph); - return ph->env.hostname ? 0 : -ENOMEM; -} +FEAT_PROCESS_STR_FUN(hostname, hostname); +FEAT_PROCESS_STR_FUN(osrelease, os_release); +FEAT_PROCESS_STR_FUN(version, version); +FEAT_PROCESS_STR_FUN(arch, arch); +FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc); +FEAT_PROCESS_STR_FUN(cpuid, cpuid); -static int process_osrelease(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_tracing_data(struct feat_fd *ff, void *data) { - ph->env.os_release = do_read_string(fd, ph); - return ph->env.os_release ? 0 : -ENOMEM; -} + ssize_t ret = trace_report(ff->fd, data, false); -static int process_version(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.version = do_read_string(fd, ph); - return ph->env.version ? 0 : -ENOMEM; + return ret < 0 ? -1 : 0; } -static int process_arch(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) { - ph->env.arch = do_read_string(fd, ph); - return ph->env.arch ? 0 : -ENOMEM; + if (perf_header__read_build_ids(ff->ph, ff->fd, ff->offset, ff->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; } -static int process_nrcpus(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; - u32 nr; - - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) - return -1; - - if (ph->needs_swap) - nr = bswap_32(nr); - - ph->env.nr_cpus_avail = nr; - - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) - return -1; + int ret; + u32 nr_cpus_avail, nr_cpus_online; - if (ph->needs_swap) - nr = bswap_32(nr); + ret = do_read_u32(ff, &nr_cpus_avail); + if (ret) + return ret; - ph->env.nr_cpus_online = nr; + ret = do_read_u32(ff, &nr_cpus_online); + if (ret) + return ret; + ff->ph->env.nr_cpus_avail = (int)nr_cpus_avail; + ff->ph->env.nr_cpus_online = (int)nr_cpus_online; return 0; } -static int process_cpudesc(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.cpu_desc = do_read_string(fd, ph); - return ph->env.cpu_desc ? 0 : -ENOMEM; -} - -static int process_cpuid(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.cpuid = do_read_string(fd, ph); - return ph->env.cpuid ? 0 : -ENOMEM; -} - -static int process_total_mem(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) { - uint64_t mem; - ssize_t ret; + u64 total_mem; + int ret; - ret = readn(fd, &mem, sizeof(mem)); - if (ret != sizeof(mem)) + ret = do_read_u64(ff, &total_mem); + if (ret) return -1; - - if (ph->needs_swap) - mem = bswap_64(mem); - - ph->env.total_mem = mem; + ff->ph->env.total_mem = (unsigned long long)total_mem; return 0; } @@ -1731,43 +1752,42 @@ perf_evlist__set_event_name(struct perf_evlist *evlist, } static int -process_event_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *header, int fd, - void *data __maybe_unused) +process_event_desc(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; - struct perf_evsel *evsel, *events = read_event_desc(header, fd); + struct perf_evsel *evsel, *events = read_event_desc(ff); if (!events) return 0; - session = container_of(header, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); + + if (session->file->is_pipe) { + /* Save events for reading later by print_event_desc, + * since they can't be read again in pipe mode. */ + ff->events = events; + } + for (evsel = events; evsel->attr.size; evsel++) perf_evlist__set_event_name(session->evlist, evsel); - free_event_desc(events); + if (!session->file->is_pipe) + free_event_desc(events); return 0; } -static int process_cmdline(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; char *str, *cmdline = NULL, **argv = NULL; u32 nr, i, len = 0; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - - ph->env.nr_cmdline = nr; + ff->ph->env.nr_cmdline = nr; - cmdline = zalloc(section->size + nr + 1); + cmdline = zalloc(ff->size + nr + 1); if (!cmdline) return -1; @@ -1776,7 +1796,7 @@ static int process_cmdline(struct perf_file_section *section, goto error; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1785,8 +1805,8 @@ static int process_cmdline(struct perf_file_section *section, len += strlen(str) + 1; free(str); } - ph->env.cmdline = cmdline; - ph->env.cmdline_argv = (const char **) argv; + ff->ph->env.cmdline = cmdline; + ff->ph->env.cmdline_argv = (const char **) argv; return 0; error: @@ -1795,35 +1815,29 @@ error: return -1; } -static int process_cpu_topology(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; u32 nr, i; char *str; struct strbuf sb; - int cpu_nr = ph->env.nr_cpus_avail; + int cpu_nr = ff->ph->env.nr_cpus_avail; u64 size = 0; + struct perf_header *ph = ff->ph; ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); if (!ph->env.cpu) return -1; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.nr_sibling_cores = nr; size += sizeof(u32); if (strbuf_init(&sb, 128) < 0) goto free_cpu; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1835,18 +1849,14 @@ static int process_cpu_topology(struct perf_file_section *section, } ph->env.sibling_cores = strbuf_detach(&sb, NULL); - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.nr_sibling_threads = nr; size += sizeof(u32); for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1862,28 +1872,20 @@ static int process_cpu_topology(struct perf_file_section *section, * The header may be from old perf, * which doesn't include core id and socket id information. */ - if (section->size <= size) { + if (ff->size <= size) { zfree(&ph->env.cpu); return 0; } for (i = 0; i < (u32)cpu_nr; i++) { - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.cpu[i].core_id = nr; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - if (nr != (u32)-1 && nr > (u32)cpu_nr) { pr_debug("socket_id number is too big." "You may need to upgrade the perf tool.\n"); @@ -1902,23 +1904,16 @@ free_cpu: return -1; } -static int process_numa_topology(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) { struct numa_node *nodes, *n; - ssize_t ret; u32 nr, i; char *str; /* nr nodes */ - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - nodes = zalloc(sizeof(*nodes) * nr); if (!nodes) return -ENOMEM; @@ -1927,25 +1922,16 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse n = &nodes[i]; /* node number */ - ret = readn(fd, &n->node, sizeof(u32)); - if (ret != sizeof(n->node)) + if (do_read_u32(ff, &n->node)) goto error; - ret = readn(fd, &n->mem_total, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_total)) goto error; - ret = readn(fd, &n->mem_free, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_free)) goto error; - if (ph->needs_swap) { - n->node = bswap_32(n->node); - n->mem_total = bswap_64(n->mem_total); - n->mem_free = bswap_64(n->mem_free); - } - - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1955,8 +1941,8 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse free(str); } - ph->env.nr_numa_nodes = nr; - ph->env.numa_nodes = nodes; + ff->ph->env.nr_numa_nodes = nr; + ff->ph->env.numa_nodes = nodes; return 0; error: @@ -1964,39 +1950,30 @@ error: return -1; } -static int process_pmu_mappings(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; char *name; u32 pmu_num; u32 type; struct strbuf sb; - ret = readn(fd, &pmu_num, sizeof(pmu_num)); - if (ret != sizeof(pmu_num)) + if (do_read_u32(ff, &pmu_num)) return -1; - if (ph->needs_swap) - pmu_num = bswap_32(pmu_num); - if (!pmu_num) { pr_debug("pmu mappings not available\n"); return 0; } - ph->env.nr_pmu_mappings = pmu_num; + ff->ph->env.nr_pmu_mappings = pmu_num; if (strbuf_init(&sb, 128) < 0) return -1; while (pmu_num) { - if (readn(fd, &type, sizeof(type)) != sizeof(type)) + if (do_read_u32(ff, &type)) goto error; - if (ph->needs_swap) - type = bswap_32(type); - name = do_read_string(fd, ph); + name = do_read_string(ff); if (!name) goto error; @@ -2007,12 +1984,12 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused goto error; if (!strcmp(name, "msr")) - ph->env.msr_pmu_type = type; + ff->ph->env.msr_pmu_type = type; free(name); pmu_num--; } - ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL); return 0; error: @@ -2020,9 +1997,7 @@ error: return -1; } -static int process_group_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) { size_t ret = -1; u32 i, nr, nr_groups; @@ -2034,13 +2009,10 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, u32 nr_members; } *desc; - if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups)) + if (do_read_u32(ff, &nr_groups)) return -1; - if (ph->needs_swap) - nr_groups = bswap_32(nr_groups); - - ph->env.nr_groups = nr_groups; + ff->ph->env.nr_groups = nr_groups; if (!nr_groups) { pr_debug("group desc not available\n"); return 0; @@ -2051,26 +2023,21 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, return -1; for (i = 0; i < nr_groups; i++) { - desc[i].name = do_read_string(fd, ph); + desc[i].name = do_read_string(ff); if (!desc[i].name) goto out_free; - if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].leader_idx)) goto out_free; - if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].nr_members)) goto out_free; - - if (ph->needs_swap) { - desc[i].leader_idx = bswap_32(desc[i].leader_idx); - desc[i].nr_members = bswap_32(desc[i].nr_members); - } } /* * Rebuild group relationship based on the group_desc */ - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); session->evlist->nr_groups = nr_groups; i = nr = 0; @@ -2114,44 +2081,34 @@ out_free: return ret; } -static int process_auxtrace(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; int err; - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); - err = auxtrace_index__process(fd, section->size, session, - ph->needs_swap); + err = auxtrace_index__process(ff->fd, ff->size, session, + ff->ph->needs_swap); if (err < 0) pr_err("Failed to process auxtrace index\n"); return err; } -static int process_cache(struct perf_file_section *section __maybe_unused, - struct perf_header *ph __maybe_unused, int fd __maybe_unused, - void *data __maybe_unused) +static int process_cache(struct feat_fd *ff, void *data __maybe_unused) { struct cpu_cache_level *caches; u32 cnt, i, version; - if (readn(fd, &version, sizeof(version)) != sizeof(version)) + if (do_read_u32(ff, &version)) return -1; - if (ph->needs_swap) - version = bswap_32(version); - if (version != 1) return -1; - if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt)) + if (do_read_u32(ff, &cnt)) return -1; - if (ph->needs_swap) - cnt = bswap_32(cnt); - caches = zalloc(sizeof(*caches) * cnt); if (!caches) return -1; @@ -2160,10 +2117,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused, struct cpu_cache_level c; #define _R(v) \ - if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\ + if (do_read_u32(ff, &c.v))\ goto out_free_caches; \ - if (ph->needs_swap) \ - c.v = bswap_32(c.v); \ _R(level) _R(line_size) @@ -2171,9 +2126,9 @@ static int process_cache(struct perf_file_section *section __maybe_unused, _R(ways) #undef _R - #define _R(v) \ - c.v = do_read_string(fd, ph); \ - if (!c.v) \ + #define _R(v) \ + c.v = do_read_string(ff); \ + if (!c.v) \ goto out_free_caches; _R(type) @@ -2184,8 +2139,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused, caches[i] = c; } - ph->env.caches = caches; - ph->env.caches_cnt = cnt; + ff->ph->env.caches = caches; + ff->ph->env.caches_cnt = cnt; return 0; out_free_caches: free(caches); @@ -2193,48 +2148,62 @@ out_free_caches: } struct feature_ops { - int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); - void (*print)(struct perf_header *h, int fd, FILE *fp); - int (*process)(struct perf_file_section *section, - struct perf_header *h, int fd, void *data); + int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); + void (*print)(struct feat_fd *ff, FILE *fp); + int (*process)(struct feat_fd *ff, void *data); const char *name; bool full_only; + bool synthesize; }; -#define FEAT_OPA(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func } -#define FEAT_OPP(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func, \ - .process = process_##func } -#define FEAT_OPF(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func, \ - .process = process_##func, .full_only = true } +#define FEAT_OPR(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func, \ + .synthesize = true \ + } + +#define FEAT_OPN(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func \ + } /* feature_ops not implemented: */ #define print_tracing_data NULL #define print_build_id NULL +#define process_branch_stack NULL +#define process_stat NULL + + static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { - FEAT_OPP(HEADER_TRACING_DATA, tracing_data), - FEAT_OPP(HEADER_BUILD_ID, build_id), - FEAT_OPP(HEADER_HOSTNAME, hostname), - FEAT_OPP(HEADER_OSRELEASE, osrelease), - FEAT_OPP(HEADER_VERSION, version), - FEAT_OPP(HEADER_ARCH, arch), - FEAT_OPP(HEADER_NRCPUS, nrcpus), - FEAT_OPP(HEADER_CPUDESC, cpudesc), - FEAT_OPP(HEADER_CPUID, cpuid), - FEAT_OPP(HEADER_TOTAL_MEM, total_mem), - FEAT_OPP(HEADER_EVENT_DESC, event_desc), - FEAT_OPP(HEADER_CMDLINE, cmdline), - FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), - FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), - FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), - FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), - FEAT_OPP(HEADER_GROUP_DESC, group_desc), - FEAT_OPP(HEADER_AUXTRACE, auxtrace), - FEAT_OPA(HEADER_STAT, stat), - FEAT_OPF(HEADER_CACHE, cache), + FEAT_OPN(TRACING_DATA, tracing_data, false), + FEAT_OPN(BUILD_ID, build_id, false), + FEAT_OPR(HOSTNAME, hostname, false), + FEAT_OPR(OSRELEASE, osrelease, false), + FEAT_OPR(VERSION, version, false), + FEAT_OPR(ARCH, arch, false), + FEAT_OPR(NRCPUS, nrcpus, false), + FEAT_OPR(CPUDESC, cpudesc, false), + FEAT_OPR(CPUID, cpuid, false), + FEAT_OPR(TOTAL_MEM, total_mem, false), + FEAT_OPR(EVENT_DESC, event_desc, false), + FEAT_OPR(CMDLINE, cmdline, false), + FEAT_OPR(CPU_TOPOLOGY, cpu_topology, true), + FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), + FEAT_OPN(BRANCH_STACK, branch_stack, false), + FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), + FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPN(AUXTRACE, auxtrace, false), + FEAT_OPN(STAT, stat, false), + FEAT_OPN(CACHE, cache, true), }; struct header_print_data { @@ -2247,6 +2216,7 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, int feat, int fd, void *data) { struct header_print_data *hd = data; + struct feat_fd ff; if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -2260,8 +2230,13 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, if (!feat_ops[feat].print) return 0; + ff = (struct feat_fd) { + .fd = fd, + .ph = ph, + }; + if (!feat_ops[feat].full_only || hd->full) - feat_ops[feat].print(ph, fd, hd->fp); + feat_ops[feat].print(&ff, hd->fp); else fprintf(hd->fp, "# %s info available, use -I to display\n", feat_ops[feat].name); @@ -2302,29 +2277,32 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) return 0; } -static int do_write_feat(int fd, struct perf_header *h, int type, +static int do_write_feat(struct feat_fd *ff, int type, struct perf_file_section **p, struct perf_evlist *evlist) { int err; int ret = 0; - if (perf_header__has_feat(h, type)) { + if (perf_header__has_feat(ff->ph, type)) { if (!feat_ops[type].write) return -1; - (*p)->offset = lseek(fd, 0, SEEK_CUR); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; - err = feat_ops[type].write(fd, h, evlist); + (*p)->offset = lseek(ff->fd, 0, SEEK_CUR); + + err = feat_ops[type].write(ff, evlist); if (err < 0) { pr_debug("failed to write feature %s\n", feat_ops[type].name); /* undo anything written */ - lseek(fd, (*p)->offset, SEEK_SET); + lseek(ff->fd, (*p)->offset, SEEK_SET); return -1; } - (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset; + (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset; (*p)++; } return ret; @@ -2334,12 +2312,18 @@ static int perf_header__adds_write(struct perf_header *header, struct perf_evlist *evlist, int fd) { int nr_sections; + struct feat_fd ff; struct perf_file_section *feat_sec, *p; int sec_size; u64 sec_start; int feat; int err; + ff = (struct feat_fd){ + .fd = fd, + .ph = header, + }; + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; @@ -2354,7 +2338,7 @@ static int perf_header__adds_write(struct perf_header *header, lseek(fd, sec_start + sec_size, SEEK_SET); for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { - if (do_write_feat(fd, header, feat, &p, evlist)) + if (do_write_feat(&ff, feat, &p, evlist)) perf_header__clear_feat(header, feat); } @@ -2363,7 +2347,7 @@ static int perf_header__adds_write(struct perf_header *header, * may write more than needed due to dropped feature, but * this is okay, reader will skip the mising entries */ - err = do_write(fd, feat_sec, sec_size); + err = do_write(&ff, feat_sec, sec_size); if (err < 0) pr_debug("failed to write feature section\n"); free(feat_sec); @@ -2373,14 +2357,17 @@ static int perf_header__adds_write(struct perf_header *header, int perf_header__write_pipe(int fd) { struct perf_pipe_file_header f_header; + struct feat_fd ff; int err; + ff = (struct feat_fd){ .fd = fd }; + f_header = (struct perf_pipe_file_header){ .magic = PERF_MAGIC, .size = sizeof(f_header), }; - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf pipe header\n"); return err; @@ -2397,21 +2384,23 @@ int perf_session__write_header(struct perf_session *session, struct perf_file_attr f_attr; struct perf_header *header = &session->header; struct perf_evsel *evsel; + struct feat_fd ff; u64 attr_offset; int err; + ff = (struct feat_fd){ .fd = fd}; lseek(fd, sizeof(f_header), SEEK_SET); evlist__for_each_entry(session->evlist, evsel) { evsel->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; } } - attr_offset = lseek(fd, 0, SEEK_CUR); + attr_offset = lseek(ff.fd, 0, SEEK_CUR); evlist__for_each_entry(evlist, evsel) { f_attr = (struct perf_file_attr){ @@ -2421,7 +2410,7 @@ int perf_session__write_header(struct perf_session *session, .size = evsel->ids * sizeof(u64), } }; - err = do_write(fd, &f_attr, sizeof(f_attr)); + err = do_write(&ff, &f_attr, sizeof(f_attr)); if (err < 0) { pr_debug("failed to write perf header attribute\n"); return err; @@ -2456,7 +2445,7 @@ int perf_session__write_header(struct perf_session *session, memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); lseek(fd, 0, SEEK_SET); - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; @@ -2710,6 +2699,13 @@ static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, int feat, int fd, void *data) { + struct feat_fd fdd = { + .fd = fd, + .ph = ph, + .size = section->size, + .offset = section->offset, + }; + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " "%d, continuing...\n", section->offset, feat); @@ -2724,13 +2720,17 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, fd, data); + return feat_ops[feat].process(&fdd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, struct perf_header *ph, int fd, bool repipe) { + struct feat_fd ff = { + .fd = STDOUT_FILENO, + .ph = ph, + }; ssize_t ret; ret = readn(fd, header, sizeof(*header)); @@ -2745,7 +2745,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, if (ph->needs_swap) header->size = bswap_64(header->size); - if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) + if (repipe && do_write(&ff, header, sizeof(*header)) < 0) return -1; return 0; @@ -2995,6 +2995,103 @@ int perf_event__synthesize_attr(struct perf_tool *tool, return err; } +int perf_event__synthesize_features(struct perf_tool *tool, + struct perf_session *session, + struct perf_evlist *evlist, + perf_event__handler_t process) +{ + struct perf_header *header = &session->header; + struct feat_fd ff; + struct feature_event *fe; + size_t sz, sz_hdr; + int feat, ret; + + sz_hdr = sizeof(fe->header); + sz = sizeof(union perf_event); + /* get a nice alignment */ + sz = PERF_ALIGN(sz, page_size); + + memset(&ff, 0, sizeof(ff)); + + ff.buf = malloc(sz); + if (!ff.buf) + return -ENOMEM; + + ff.size = sz - sz_hdr; + + for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { + if (!feat_ops[feat].synthesize) { + pr_debug("No record header feature for header :%d\n", feat); + continue; + } + + ff.offset = sizeof(*fe); + + ret = feat_ops[feat].write(&ff, evlist); + if (ret || ff.offset <= (ssize_t)sizeof(*fe)) { + pr_debug("Error writing feature\n"); + continue; + } + /* ff.buf may have changed due to realloc in do_write() */ + fe = ff.buf; + memset(fe, 0, sizeof(*fe)); + + fe->feat_id = feat; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = ff.offset; + + ret = process(tool, ff.buf, NULL, NULL); + if (ret) { + free(ff.buf); + return ret; + } + } + free(ff.buf); + return 0; +} + +int perf_event__process_feature(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct feat_fd ff = { .fd = 0 }; + struct feature_event *fe = (struct feature_event *)event; + int type = fe->header.type; + u64 feat = fe->feat_id; + + if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return 0; + } + if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return -1; + } + + if (!feat_ops[feat].process) + return 0; + + ff.buf = (void *)fe->data; + ff.size = event->header.size - sizeof(event->header); + ff.ph = &session->header; + + if (feat_ops[feat].process(&ff, NULL)) + return -1; + + if (!feat_ops[feat].print || !tool->show_feat_hdr) + return 0; + + if (!feat_ops[feat].full_only || + tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { + feat_ops[feat].print(&ff, stdout); + } else { + fprintf(stdout, "# %s info available, use -I to display\n", + feat_ops[feat].name); + } + + return 0; +} + static struct event_update_event * event_update_event__new(size_t size, u64 type, u64 id) { @@ -3253,6 +3350,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, union perf_event ev; struct tracing_data *tdata; ssize_t size = 0, aligned_size = 0, padding; + struct feat_fd ff; int err __maybe_unused = 0; /* @@ -3287,7 +3385,9 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, */ tracing_data_put(tdata); - write_padded(fd, NULL, 0, padding); + ff = (struct feat_fd){ .fd = fd }; + if (write_padded(&ff, NULL, 0, padding)) + return -1; return aligned_size; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d30109b421ee..f7a16ee527b8 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -101,6 +101,15 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); +int perf_event__synthesize_features(struct perf_tool *tool, + struct perf_session *session, + struct perf_evlist *evlist, + perf_event__handler_t process); + +int perf_event__process_feature(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); @@ -144,7 +153,12 @@ bool is_perf_magic(u64 magic); #define NAME_ALIGN 64 -int write_padded(int fd, const void *bf, size_t count, size_t count_aligned); +struct feat_fd; + +int do_write(struct feat_fd *fd, const void *buf, size_t size); + +int write_padded(struct feat_fd *fd, const void *bf, + size_t count, size_t count_aligned); /* * arch specific callback diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index cf0186a088c1..9453b2e27015 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -749,12 +749,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al } static int -iter_add_single_branch_entry(struct hist_entry_iter *iter, +iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, struct addr_location *al __maybe_unused) { - /* to avoid calling callback function */ - iter->he = NULL; - return 0; } @@ -1762,6 +1759,8 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro else use_callchain = symbol_conf.use_callchain; + use_callchain |= symbol_conf.show_branchflag_count; + output_resort(evsel__hists(evsel), prog, use_callchain, NULL); } diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 7aca5d6d7e1f..10e0814bb8d2 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -25,6 +25,6 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -ifneq ($(CC), clang) +ifeq ($(CC_NO_CLANG), 1) CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init endif diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index c6a15f204c03..209b0c82eff4 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -33,7 +33,7 @@ struct llvm_param llvm_param = { int perf_llvm_config(const char *var, const char *value) { - if (prefixcmp(var, "llvm.")) + if (!strstarts(var, "llvm.")) return 0; var += sizeof("llvm.") - 1; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2e9eb6aa3ce2..5c8eacaca4f4 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -705,7 +705,8 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) if (kdso->has_build_id) { char filename[PATH_MAX]; - if (dso__build_id_filename(kdso, filename, sizeof(filename))) + if (dso__build_id_filename(kdso, filename, sizeof(filename), + false)) printed += fprintf(fp, "[0] %s\n", filename); } @@ -1137,7 +1138,8 @@ int __weak arch__fix_module_text_start(u64 *start __maybe_unused, return 0; } -static int machine__create_module(void *arg, const char *name, u64 start) +static int machine__create_module(void *arg, const char *name, u64 start, + u64 size) { struct machine *machine = arg; struct map *map; @@ -1148,6 +1150,7 @@ static int machine__create_module(void *arg, const char *name, u64 start) map = machine__findnew_module_map(machine, start, name); if (map == NULL) return -1; + map->end = start + size; dso__kernel_module_get_build_id(map->dso, machine->root_dir); @@ -1392,7 +1395,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, - event->mmap2.pid, event->mmap2.maj, + event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, event->mmap2.prot, @@ -1450,7 +1453,7 @@ 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, - event->mmap.pid, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, event->mmap.filename, type, thread); @@ -1681,7 +1684,8 @@ static int add_callchain_ip(struct thread *thread, bool branch, struct branch_flags *flags, int nr_loop_iter, - int samples) + int samples, + u64 branch_from) { struct addr_location al; @@ -1734,7 +1738,8 @@ static int add_callchain_ip(struct thread *thread, if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; return callchain_cursor_append(cursor, al.addr, al.map, al.sym, - branch, flags, nr_loop_iter, samples); + branch, flags, nr_loop_iter, samples, + branch_from); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1813,7 +1818,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr), i; u8 cpumode = PERF_RECORD_MISC_USER; - u64 ip; + u64 ip, branch_from = 0; for (i = 0; i < chain_nr; i++) { if (chain->ips[i] == PERF_CONTEXT_USER) @@ -1855,6 +1860,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; branch = true; flags = &lbr_stack->entries[0].flags; + branch_from = + lbr_stack->entries[0].from; } } else { if (j < lbr_nr) { @@ -1869,12 +1876,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; branch = true; flags = &lbr_stack->entries[0].flags; + branch_from = + lbr_stack->entries[0].from; } } err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, - branch, flags, 0, 0); + branch, flags, 0, 0, + branch_from); if (err) return (err < 0) ? err : 0; } @@ -1894,13 +1904,16 @@ static int thread__resolve_callchain_sample(struct thread *thread, { struct branch_stack *branch = sample->branch_stack; struct ip_callchain *chain = sample->callchain; - int chain_nr = chain->nr; + int chain_nr = 0; u8 cpumode = PERF_RECORD_MISC_USER; int i, j, err, nr_entries; int skip_idx = -1; int first_call = 0; int nr_loop_iter; + if (chain) + chain_nr = chain->nr; + if (perf_evsel__has_branch_callstack(evsel)) { err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, root_al, max_stack); @@ -1938,6 +1951,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < nr; i++) { if (callchain_param.order == ORDER_CALLEE) { be[i] = branch->entries[i]; + + if (chain == NULL) + continue; + /* * Check for overlap into the callchain. * The return address is one off compared to @@ -1973,24 +1990,29 @@ static int thread__resolve_callchain_sample(struct thread *thread, root_al, NULL, be[i].to, true, &be[i].flags, - nr_loop_iter, 1); + nr_loop_iter, 1, + be[i].from); else err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].to, true, &be[i].flags, - 0, 0); + 0, 0, be[i].from); if (!err) err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from, true, &be[i].flags, - 0, 0); + 0, 0, 0); if (err == -EINVAL) break; if (err) return err; } + + if (chain_nr == 0) + return 0; + chain_nr -= nr; } @@ -2015,7 +2037,7 @@ check_calls: err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, - false, NULL, 0, 0); + false, NULL, 0, 0, 0); if (err) return (err < 0) ? err : 0; @@ -2032,7 +2054,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return 0; return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, - false, NULL, 0, 0); + false, NULL, 0, 0, 0); } static int thread__resolve_callchain_unwind(struct thread *thread, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 2179b2deb730..bdaa0a4edc17 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -16,6 +16,7 @@ #include "machine.h" #include <linux/string.h> #include "srcline.h" +#include "namespaces.h" #include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -145,11 +146,13 @@ void map__init(struct map *map, enum map_type type, } struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type, struct thread *thread) { struct map *map = malloc(sizeof(*map)); + struct nsinfo *nsi = NULL; + struct nsinfo *nnsi; if (map != NULL) { char newfilename[PATH_MAX]; @@ -167,9 +170,11 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map->ino_generation = ino_gen; map->prot = prot; map->flags = flags; + nsi = nsinfo__get(thread->nsinfo); - if ((anon || no_dso) && type == MAP__FUNCTION) { - snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); + if ((anon || no_dso) && nsi && type == MAP__FUNCTION) { + snprintf(newfilename, sizeof(newfilename), + "/tmp/perf-%d.map", nsi->pid); filename = newfilename; } @@ -179,6 +184,16 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, } if (vdso) { + /* The vdso maps are always on the host and not the + * container. Ensure that we don't use setns to look + * them up. + */ + nnsi = nsinfo__copy(nsi); + if (nnsi) { + nsinfo__put(nsi); + nnsi->need_setns = false; + nsi = nnsi; + } pgoff = 0; dso = machine__findnew_vdso(machine, thread); } else @@ -200,10 +215,12 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (type != MAP__FUNCTION) dso__set_loaded(dso, map->type); } + dso->nsinfo = nsi; dso__put(dso); } return map; out_delete: + nsinfo__put(nsi); free(map); return NULL; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f9e8ac8a52cd..73aacf7a7dc4 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -141,7 +141,7 @@ struct thread; void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 06f5a3a4295c..28afe5fa84d6 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -166,11 +166,20 @@ static const char * const mem_lvl[] = { "Uncached", }; +static const char * const mem_lvlnum[] = { + [PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache", + [PERF_MEM_LVLNUM_LFB] = "LFB", + [PERF_MEM_LVLNUM_RAM] = "RAM", + [PERF_MEM_LVLNUM_PMEM] = "PMEM", + [PERF_MEM_LVLNUM_NA] = "N/A", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; u64 m = PERF_MEM_LVL_NA; u64 hit, miss; + int printed; if (mem_info) m = mem_info->data_src.mem_lvl; @@ -184,17 +193,37 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + + if (mem_info && mem_info->data_src.mem_remote) { + strcat(out, "Remote "); + l += 7; + } + + printed = 0; for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { if (!(m & 0x1)) continue; - if (l) { + if (printed++) { strcat(out, " or "); l += 4; } l += scnprintf(out + l, sz - l, mem_lvl[i]); } - if (*out == '\0') - l += scnprintf(out, sz - l, "N/A"); + + if (mem_info && mem_info->data_src.mem_lvl_num) { + int lvl = mem_info->data_src.mem_lvl_num; + if (printed++) { + strcat(out, " or "); + l += 4; + } + if (mem_lvlnum[lvl]) + l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]); + else + l += scnprintf(out + l, sz - l, "L%d", lvl); + } + + if (l == 0) + l += scnprintf(out + l, sz - l, "N/A"); if (hit) l += scnprintf(out + l, sz - l, " hit"); if (miss) @@ -231,6 +260,14 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info) } l += scnprintf(out + l, sz - l, snoop_access[i]); } + if (mem_info && + (mem_info->data_src.mem_snoopx & PERF_MEM_SNOOPX_FWD)) { + if (l) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, "Fwd"); + } if (*out == '\0') l += scnprintf(out, sz - l, "N/A"); @@ -279,6 +316,11 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) u64 lvl = data_src->mem_lvl; u64 snoop = data_src->mem_snoop; u64 lock = data_src->mem_lock; + /* + * Skylake might report unknown remote level via this + * bit, consider it when evaluating remote HITMs. + */ + bool mrem = data_src->mem_remote; int err = 0; #define HITM_INC(__f) \ @@ -324,7 +366,8 @@ do { \ } if ((lvl & P(LVL, REM_RAM1)) || - (lvl & P(LVL, REM_RAM2))) { + (lvl & P(LVL, REM_RAM2)) || + mrem) { stats->rmt_dram++; if (snoop & P(SNOOP, HIT)) stats->ld_shared++; @@ -334,7 +377,8 @@ do { \ } if ((lvl & P(LVL, REM_CCE1)) || - (lvl & P(LVL, REM_CCE2))) { + (lvl & P(LVL, REM_CCE2)) || + mrem) { if (snoop & P(SNOOP, HIT)) stats->rmt_hit++; else if (snoop & P(SNOOP, HITM)) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 67dcbcc73c7d..a58e91197729 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -9,9 +9,14 @@ #include "namespaces.h" #include "util.h" #include "event.h" +#include <sys/types.h> +#include <sys/stat.h> +#include <limits.h> +#include <sched.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <unistd.h> struct namespaces *namespaces__new(struct namespaces_event *event) { @@ -35,3 +40,209 @@ void namespaces__free(struct namespaces *namespaces) { free(namespaces); } + +int nsinfo__init(struct nsinfo *nsi) +{ + char oldns[PATH_MAX]; + char spath[PATH_MAX]; + char *newns = NULL; + char *statln = NULL; + struct stat old_stat; + struct stat new_stat; + FILE *f = NULL; + size_t linesz = 0; + int rv = -1; + + if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) + return rv; + + if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1) + return rv; + + if (stat(oldns, &old_stat) < 0) + goto out; + + if (stat(newns, &new_stat) < 0) + goto out; + + /* Check if the mount namespaces differ, if so then indicate that we + * want to switch as part of looking up dso/map data. + */ + if (old_stat.st_ino != new_stat.st_ino) { + nsi->need_setns = true; + nsi->mntns_path = newns; + newns = NULL; + } + + /* If we're dealing with a process that is in a different PID namespace, + * attempt to work out the innermost tgid for the process. + */ + if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX) + goto out; + + f = fopen(spath, "r"); + if (f == NULL) + goto out; + + while (getline(&statln, &linesz, f) != -1) { + /* Use tgid if CONFIG_PID_NS is not defined. */ + if (strstr(statln, "Tgid:") != NULL) { + nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + nsi->nstgid = nsi->tgid; + } + + if (strstr(statln, "NStgid:") != NULL) { + nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + break; + } + } + rv = 0; + +out: + if (f != NULL) + (void) fclose(f); + free(statln); + free(newns); + return rv; +} + +struct nsinfo *nsinfo__new(pid_t pid) +{ + struct nsinfo *nsi; + + if (pid == 0) + return NULL; + + nsi = calloc(1, sizeof(*nsi)); + if (nsi != NULL) { + nsi->pid = pid; + nsi->tgid = pid; + nsi->nstgid = pid; + nsi->need_setns = false; + /* Init may fail if the process exits while we're trying to look + * at its proc information. In that case, save the pid but + * don't try to enter the namespace. + */ + if (nsinfo__init(nsi) == -1) + nsi->need_setns = false; + + refcount_set(&nsi->refcnt, 1); + } + + return nsi; +} + +struct nsinfo *nsinfo__copy(struct nsinfo *nsi) +{ + struct nsinfo *nnsi; + + nnsi = calloc(1, sizeof(*nnsi)); + if (nnsi != NULL) { + nnsi->pid = nsi->pid; + nnsi->tgid = nsi->tgid; + nnsi->nstgid = nsi->nstgid; + nnsi->need_setns = nsi->need_setns; + if (nsi->mntns_path) { + nnsi->mntns_path = strdup(nsi->mntns_path); + if (!nnsi->mntns_path) { + free(nnsi); + return NULL; + } + } + refcount_set(&nnsi->refcnt, 1); + } + + return nnsi; +} + +void nsinfo__delete(struct nsinfo *nsi) +{ + zfree(&nsi->mntns_path); + free(nsi); +} + +struct nsinfo *nsinfo__get(struct nsinfo *nsi) +{ + if (nsi) + refcount_inc(&nsi->refcnt); + return nsi; +} + +void nsinfo__put(struct nsinfo *nsi) +{ + if (nsi && refcount_dec_and_test(&nsi->refcnt)) + nsinfo__delete(nsi); +} + +void nsinfo__mountns_enter(struct nsinfo *nsi, + struct nscookie *nc) +{ + char curpath[PATH_MAX]; + int oldns = -1; + int newns = -1; + + if (nc == NULL) + return; + + nc->oldns = -1; + nc->newns = -1; + + if (!nsi || !nsi->need_setns) + return; + + if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) + return; + + oldns = open(curpath, O_RDONLY); + if (oldns < 0) + return; + + newns = open(nsi->mntns_path, O_RDONLY); + if (newns < 0) + goto errout; + + if (setns(newns, CLONE_NEWNS) < 0) + goto errout; + + nc->oldns = oldns; + nc->newns = newns; + return; + +errout: + if (oldns > -1) + close(oldns); + if (newns > -1) + close(newns); +} + +void nsinfo__mountns_exit(struct nscookie *nc) +{ + if (nc == NULL || nc->oldns == -1 || nc->newns == -1) + return; + + setns(nc->oldns, CLONE_NEWNS); + + if (nc->oldns > -1) { + close(nc->oldns); + nc->oldns = -1; + } + + if (nc->newns > -1) { + close(nc->newns); + nc->newns = -1; + } +} + +char *nsinfo__realpath(const char *path, struct nsinfo *nsi) +{ + char *rpath; + struct nscookie nsc; + + nsinfo__mountns_enter(nsi, &nsc); + rpath = realpath(path, NULL); + nsinfo__mountns_exit(&nsc); + + return rpath; +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 468f1e9a1484..05d82601c9a6 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -11,6 +11,7 @@ #include "../perf.h" #include <linux/list.h> +#include <linux/refcount.h> struct namespaces_event; @@ -23,4 +24,41 @@ struct namespaces { struct namespaces *namespaces__new(struct namespaces_event *event); void namespaces__free(struct namespaces *namespaces); +struct nsinfo { + pid_t pid; + pid_t tgid; + pid_t nstgid; + bool need_setns; + char *mntns_path; + refcount_t refcnt; +}; + +struct nscookie { + int oldns; + int newns; +}; + +int nsinfo__init(struct nsinfo *nsi); +struct nsinfo *nsinfo__new(pid_t pid); +struct nsinfo *nsinfo__copy(struct nsinfo *nsi); +void nsinfo__delete(struct nsinfo *nsi); + +struct nsinfo *nsinfo__get(struct nsinfo *nsi); +void nsinfo__put(struct nsinfo *nsi); + +void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc); +void nsinfo__mountns_exit(struct nscookie *nc); + +char *nsinfo__realpath(const char *path, struct nsinfo *nsi); + +static inline void __nsinfo__zput(struct nsinfo **nsip) +{ + if (nsip) { + nsinfo__put(*nsip); + *nsip = NULL; + } +} + +#define nsinfo__zput(nsi) __nsinfo__zput(&nsi) + #endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 38fd11504015..e71fb5f31e84 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -28,6 +28,7 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND), BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP), BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL), + BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE), BRANCH_END }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 01e779b91c8e..f44aeba51d1f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -34,7 +34,7 @@ #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -int parse_events_parse(void *data, void *scanner); +int parse_events_parse(void *parse_state, void *scanner); static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused); @@ -589,7 +589,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, } struct __add_bpf_event_param { - struct parse_events_evlist *data; + struct parse_events_state *parse_state; struct list_head *list; struct list_head *head_config; }; @@ -599,7 +599,7 @@ static int add_bpf_event(const char *group, const char *event, int fd, { LIST_HEAD(new_evsels); struct __add_bpf_event_param *param = _param; - struct parse_events_evlist *evlist = param->data; + struct parse_events_state *parse_state = param->parse_state; struct list_head *list = param->list; struct perf_evsel *pos; int err; @@ -607,8 +607,8 @@ static int add_bpf_event(const char *group, const char *event, int fd, pr_debug("add bpf event %s:%s and attach bpf program %d\n", group, event, fd); - err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group, - event, evlist->error, + err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group, + event, parse_state->error, param->head_config); if (err) { struct perf_evsel *evsel, *tmp; @@ -632,14 +632,14 @@ static int add_bpf_event(const char *group, const char *event, int fd, return 0; } -int parse_events_load_bpf_obj(struct parse_events_evlist *data, +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, struct list_head *list, struct bpf_object *obj, struct list_head *head_config) { int err; char errbuf[BUFSIZ]; - struct __add_bpf_event_param param = {data, list, head_config}; + struct __add_bpf_event_param param = {parse_state, list, head_config}; static bool registered_unprobe_atexit = false; if (IS_ERR(obj) || !obj) { @@ -680,13 +680,13 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data, return 0; errout: - data->error->help = strdup("(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->help = strdup("(add -v to see detail)"); + parse_state->error->str = strdup(errbuf); return err; } static int -parse_events_config_bpf(struct parse_events_evlist *data, +parse_events_config_bpf(struct parse_events_state *parse_state, struct bpf_object *obj, struct list_head *head_config) { @@ -705,28 +705,28 @@ parse_events_config_bpf(struct parse_events_evlist *data, "Invalid config term for BPF object"); errbuf[BUFSIZ - 1] = '\0'; - data->error->idx = term->err_term; - data->error->str = strdup(errbuf); + parse_state->error->idx = term->err_term; + parse_state->error->str = strdup(errbuf); return -EINVAL; } - err = bpf__config_obj(obj, term, data->evlist, &error_pos); + err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos); if (err) { - bpf__strerror_config_obj(obj, term, data->evlist, + bpf__strerror_config_obj(obj, term, parse_state->evlist, &error_pos, err, errbuf, sizeof(errbuf)); - data->error->help = strdup( + parse_state->error->help = strdup( "Hint:\tValid config terms:\n" " \tmap:[<arraymap>].value<indices>=[value]\n" " \tmap:[<eventmap>].event<indices>=[event]\n" "\n" " \twhere <indices> is something like [0,3...5] or [all]\n" " \t(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->str = strdup(errbuf); if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) - data->error->idx = term->err_val; + parse_state->error->idx = term->err_val; else - data->error->idx = term->err_term + error_pos; + parse_state->error->idx = term->err_term + error_pos; return err; } } @@ -762,7 +762,7 @@ split_bpf_config_terms(struct list_head *evt_head_config, list_move_tail(&term->list, obj_head_config); } -int parse_events_load_bpf(struct parse_events_evlist *data, +int parse_events_load_bpf(struct parse_events_state *parse_state, struct list_head *list, char *bpf_file_name, bool source, @@ -790,15 +790,15 @@ int parse_events_load_bpf(struct parse_events_evlist *data, -err, errbuf, sizeof(errbuf)); - data->error->help = strdup("(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->help = strdup("(add -v to see detail)"); + parse_state->error->str = strdup(errbuf); return err; } - err = parse_events_load_bpf_obj(data, list, obj, head_config); + err = parse_events_load_bpf_obj(parse_state, list, obj, head_config); if (err) return err; - err = parse_events_config_bpf(data, obj, &obj_head_config); + err = parse_events_config_bpf(parse_state, obj, &obj_head_config); /* * Caller doesn't know anything about obj_head_config, @@ -1184,7 +1184,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, err, head_config); } -int parse_events_add_numeric(struct parse_events_evlist *data, +int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config) @@ -1197,7 +1197,7 @@ int parse_events_add_numeric(struct parse_events_evlist *data, attr.config = config; if (head_config) { - if (config_attr(&attr, head_config, data->error, + if (config_attr(&attr, head_config, parse_state->error, config_term_common)) return -EINVAL; @@ -1205,11 +1205,11 @@ int parse_events_add_numeric(struct parse_events_evlist *data, return -ENOMEM; } - return add_event(list, &data->idx, &attr, + return add_event(list, &parse_state->idx, &attr, get_config_name(head_config), &config_terms); } -int parse_events_add_pmu(struct parse_events_evlist *data, +int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config) { @@ -1232,7 +1232,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus, NULL); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL); return evsel ? 0 : -ENOMEM; } @@ -1243,16 +1243,16 @@ int parse_events_add_pmu(struct parse_events_evlist *data, * Configure hardcoded terms first, no need to check * return value when called with fail == 0 ;) */ - if (config_attr(&attr, head_config, data->error, config_term_pmu)) + if (config_attr(&attr, head_config, parse_state->error, config_term_pmu)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, data->error)) + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) return -EINVAL; - evsel = __add_event(list, &data->idx, &attr, + evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu->cpus, &config_terms); if (evsel) { @@ -1267,7 +1267,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, return evsel ? 0 : -ENOMEM; } -int parse_events_multi_pmu_add(struct parse_events_evlist *data, +int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { struct list_head *head; @@ -1296,7 +1296,7 @@ int parse_events_multi_pmu_add(struct parse_events_evlist *data, return -1; list_add_tail(&term->list, head); - if (!parse_events_add_pmu(data, list, + if (!parse_events_add_pmu(parse_state, list, pmu->name, head)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); @@ -1628,7 +1628,7 @@ perf_pmu__parse_check(const char *name) return r ? r->type : PMU_EVENT_SYMBOL_ERR; } -static int parse_events__scanner(const char *str, void *data, int start_token) +static int parse_events__scanner(const char *str, void *parse_state, int start_token) { YY_BUFFER_STATE buffer; void *scanner; @@ -1643,7 +1643,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token) #ifdef PARSER_DEBUG parse_events_debug = 1; #endif - ret = parse_events_parse(data, scanner); + ret = parse_events_parse(parse_state, scanner); parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); @@ -1656,45 +1656,45 @@ static int parse_events__scanner(const char *str, void *data, int start_token) */ int parse_events_terms(struct list_head *terms, const char *str) { - struct parse_events_terms data = { + struct parse_events_state parse_state = { .terms = NULL, }; int ret; - ret = parse_events__scanner(str, &data, PE_START_TERMS); + ret = parse_events__scanner(str, &parse_state, PE_START_TERMS); if (!ret) { - list_splice(data.terms, terms); - zfree(&data.terms); + list_splice(parse_state.terms, terms); + zfree(&parse_state.terms); return 0; } - parse_events_terms__delete(data.terms); + parse_events_terms__delete(parse_state.terms); return ret; } int parse_events(struct perf_evlist *evlist, const char *str, struct parse_events_error *err) { - struct parse_events_evlist data = { - .list = LIST_HEAD_INIT(data.list), + struct parse_events_state parse_state = { + .list = LIST_HEAD_INIT(parse_state.list), .idx = evlist->nr_entries, .error = err, .evlist = evlist, }; int ret; - ret = parse_events__scanner(str, &data, PE_START_EVENTS); + ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); if (!ret) { struct perf_evsel *last; - if (list_empty(&data.list)) { + if (list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing"); return -1; } - perf_evlist__splice_list_tail(evlist, &data.list); - evlist->nr_groups += data.nr_groups; + perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist->nr_groups += parse_state.nr_groups; last = perf_evlist__last(evlist); last->cmdline_group_boundary = true; @@ -2124,7 +2124,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, return; } strlist__for_each_entry(nd, bidlist) { - pcache = probe_cache__new(nd->s); + pcache = probe_cache__new(nd->s, NULL); if (!pcache) continue; list_for_each_entry(ent, &pcache->entries, node) { @@ -2520,10 +2520,10 @@ void parse_events__clear_array(struct parse_events_array *a) zfree(&a->ranges); } -void parse_events_evlist_error(struct parse_events_evlist *data, +void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str) { - struct parse_events_error *err = data->error; + struct parse_events_error *err = parse_state->error; if (!err) return; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index a235f4d6d5e5..635135125111 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -108,16 +108,13 @@ struct parse_events_error { char *help; /* optional help string */ }; -struct parse_events_evlist { +struct parse_events_state { struct list_head list; int idx; int nr_groups; struct parse_events_error *error; struct perf_evlist *evlist; -}; - -struct parse_events_terms { - struct list_head *terms; + struct list_head *terms; }; void parse_events__shrink_config_terms(void); @@ -143,18 +140,18 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *error, struct list_head *head_config); -int parse_events_load_bpf(struct parse_events_evlist *data, +int parse_events_load_bpf(struct parse_events_state *parse_state, struct list_head *list, char *bpf_file_name, bool source, struct list_head *head_config); /* Provide this function for perf test */ struct bpf_object; -int parse_events_load_bpf_obj(struct parse_events_evlist *data, +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, struct list_head *list, struct bpf_object *obj, struct list_head *head_config); -int parse_events_add_numeric(struct parse_events_evlist *data, +int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); @@ -164,11 +161,11 @@ int parse_events_add_cache(struct list_head *list, int *idx, struct list_head *head_config); int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); -int parse_events_add_pmu(struct parse_events_evlist *data, +int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config); -int parse_events_multi_pmu_add(struct parse_events_evlist *data, +int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp); @@ -180,7 +177,7 @@ perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); -void parse_events_evlist_error(struct parse_events_evlist *data, +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, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 660fca05bc93..c42edeac451f 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,6 +53,21 @@ static int str(yyscan_t scanner, int token) return token; } +static bool isbpf(yyscan_t scanner) +{ + char *text = parse_events_get_text(scanner); + int len = strlen(text); + + if (len < 2) + return false; + if ((text[len - 1] == 'c' || text[len - 1] == 'o') && + text[len - 2] == '.') + return true; + if (len > 4 && !strcmp(text + len - 4, ".obj")) + return true; + return false; +} + /* * This function is called when the parser gets two kind of input: * @@ -136,8 +151,8 @@ do { \ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ -bpf_object [^,{}]+\.(o|bpf) -bpf_source [^,{}]+\.c +bpf_object [^,{}]+\.(o|bpf)[a-zA-Z0-9._]* +bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ @@ -307,8 +322,8 @@ r{num_raw_hex} { return raw(yyscanner); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } -{bpf_object} { return str(yyscanner, PE_BPF_OBJECT); } -{bpf_source} { return str(yyscanner, PE_BPF_SOURCE); } +{bpf_object} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); } +{bpf_source} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); } {name} { return pmu_str_check(yyscanner); } "/" { BEGIN(config); return '/'; } - { return '-'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 04fd8c9af9f9..e81a20ea8d7d 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,5 +1,5 @@ %pure-parser -%parse-param {void *_data} +%parse-param {void *_parse_state} %parse-param {void *scanner} %lex-param {void* scanner} %locations @@ -17,7 +17,7 @@ #include "parse-events.h" #include "parse-events-bison.h" -void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg); +void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg); #define ABORT_ON(val) \ do { \ @@ -33,11 +33,11 @@ do { \ } while (0) static void inc_group_count(struct list_head *list, - struct parse_events_evlist *data) + struct parse_events_state *parse_state) { /* Count groups only have more than 1 members */ if (!list_is_last(list->next, list)) - data->nr_groups++; + parse_state->nr_groups++; } %} @@ -115,9 +115,9 @@ PE_START_TERMS start_terms start_events: groups { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; - parse_events_update_lists($1, &data->list); + parse_events_update_lists($1, &parse_state->list); } groups: @@ -159,7 +159,7 @@ PE_NAME '{' events '}' { struct list_head *list = $3; - inc_group_count(list, _data); + inc_group_count(list, _parse_state); parse_events__set_leader($1, list); $$ = list; } @@ -168,7 +168,7 @@ PE_NAME '{' events '}' { struct list_head *list = $2; - inc_group_count(list, _data); + inc_group_count(list, _parse_state); parse_events__set_leader(NULL, list); $$ = list; } @@ -225,14 +225,13 @@ event_def: event_pmu | event_pmu: PE_NAME opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list, *orig_terms, *terms; if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(data, list, $1, $2)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2)) { struct perf_pmu *pmu = NULL; int ok = 0; @@ -245,7 +244,7 @@ PE_NAME opt_event_config if (!strncmp($1, name, strlen($1))) { if (parse_events_copy_term_list(orig_terms, &terms)) YYABORT; - if (!parse_events_add_pmu(data, list, pmu->name, terms)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms)) ok++; parse_events_terms__delete(terms); } @@ -262,7 +261,7 @@ PE_KERNEL_PMU_EVENT sep_dc { struct list_head *list; - if (parse_events_multi_pmu_add(_data, $1, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0) YYABORT; $$ = list; } @@ -273,7 +272,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc char pmu_name[128]; snprintf(&pmu_name, 128, "%s-%s", $1, $3); - if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) YYABORT; $$ = list; } @@ -286,62 +285,60 @@ PE_VALUE_SYM_SW event_legacy_symbol: value_sym '/' event_config '/' { - struct parse_events_evlist *data = _data; struct list_head *list; int type = $1 >> 16; int config = $1 & 255; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, type, config, $3)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3)); parse_events_terms__delete($3); $$ = list; } | value_sym sep_slash_dc { - struct parse_events_evlist *data = _data; struct list_head *list; int type = $1 >> 16; int config = $1 & 255; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6)); parse_events_terms__delete($6); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4)); parse_events_terms__delete($4); $$ = list; } | PE_NAME_CACHE_TYPE opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2)); parse_events_terms__delete($2); $$ = list; } @@ -349,44 +346,44 @@ PE_NAME_CACHE_TYPE opt_event_config event_legacy_mem: PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, $6, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, NULL, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, $4, 0)); $$ = list; } | PE_PREFIX_MEM PE_VALUE sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, NULL, 0)); $$ = list; } @@ -394,15 +391,15 @@ PE_PREFIX_MEM PE_VALUE sep_dc event_legacy_tracepoint: tracepoint_name opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); if (error) error->idx = @1.first_column; - if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event, + if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, error, $2)) return -1; @@ -432,11 +429,10 @@ PE_NAME ':' PE_NAME event_legacy_numeric: PE_VALUE ':' PE_VALUE opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4)); parse_events_terms__delete($4); $$ = list; } @@ -444,11 +440,10 @@ PE_VALUE ':' PE_VALUE opt_event_config event_legacy_raw: PE_RAW opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2)); parse_events_terms__delete($2); $$ = list; } @@ -456,23 +451,22 @@ PE_RAW opt_event_config event_bpf_file: PE_BPF_OBJECT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2)); + ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2)); parse_events_terms__delete($2); $$ = list; } | PE_BPF_SOURCE opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2)); + ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2)); parse_events_terms__delete($2); $$ = list; } @@ -494,8 +488,8 @@ opt_event_config: start_terms: event_config { - struct parse_events_terms *data = _data; - data->terms = $1; + struct parse_events_state *parse_state = _parse_state; + parse_state->terms = $1; } event_config: @@ -685,9 +679,9 @@ sep_slash_dc: '/' | ':' | %% -void parse_events_error(YYLTYPE *loc, void *data, +void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner __maybe_unused, char const *msg __maybe_unused) { - parse_events_evlist_error(data, loc->last_column, "parser error"); + parse_events_evlist_error(parse_state, loc->last_column, "parser error"); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a2670e9d652d..b7aaf9b2294d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -184,13 +184,19 @@ static struct map *kernel_get_module_map(const char *module) return NULL; } -struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) { /* Init maps of given executable or kernel */ - if (user) - return dso__new_map(target); - else + if (user) { + struct map *map; + + map = dso__new_map(target); + if (map && map->dso) + map->dso->nsinfo = nsinfo__get(nsi); + return map; + } else { return kernel_get_module_map(target); + } } static int convert_exec_to_group(const char *exec, char **result) @@ -366,7 +372,8 @@ found: static int find_alternative_probe_point(struct debuginfo *dinfo, struct perf_probe_point *pp, struct perf_probe_point *result, - const char *target, bool uprobes) + const char *target, struct nsinfo *nsi, + bool uprobes) { struct map *map = NULL; struct symbol *sym; @@ -377,7 +384,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (!pp->function || pp->file) return -ENOTSUP; - map = get_target_map(target, uprobes); + map = get_target_map(target, nsi, uprobes); if (!map) return -EINVAL; @@ -421,8 +428,8 @@ static int get_alternative_probe_event(struct debuginfo *dinfo, memcpy(tmp, &pev->point, sizeof(*tmp)); memset(&pev->point, 0, sizeof(pev->point)); - ret = find_alternative_probe_point(dinfo, tmp, &pev->point, - pev->target, pev->uprobes); + ret = find_alternative_probe_point(dinfo, tmp, &pev->point, pev->target, + pev->nsi, pev->uprobes); if (ret < 0) memcpy(&pev->point, tmp, sizeof(*tmp)); @@ -444,7 +451,7 @@ static int get_alternative_line_range(struct debuginfo *dinfo, if (lr->end != INT_MAX) len = lr->end - lr->start; ret = find_alternative_probe_point(dinfo, &pp, &result, - target, user); + target, NULL, user); if (!ret) { lr->function = result.function; lr->file = result.file; @@ -457,12 +464,14 @@ static int get_alternative_line_range(struct debuginfo *dinfo, } /* Open new debuginfo of given module */ -static struct debuginfo *open_debuginfo(const char *module, bool silent) +static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi, + bool silent) { const char *path = module; char reason[STRERR_BUFSIZE]; struct debuginfo *ret = NULL; struct dso *dso = NULL; + struct nscookie nsc; int err; if (!module || !strchr(module, '/')) { @@ -480,6 +489,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent) } path = dso->long_name; } + nsinfo__mountns_enter(nsi, &nsc); ret = debuginfo__new(path); if (!ret && !silent) { pr_warning("The %s file has no debug information.\n", path); @@ -489,6 +499,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent) pr_warning("Rebuild with -g, "); pr_warning("or install an appropriate debuginfo package.\n"); } + nsinfo__mountns_exit(&nsc); return ret; } @@ -516,7 +527,7 @@ static struct debuginfo *debuginfo_cache__open(const char *module, bool silent) goto out; } - debuginfo_cache = open_debuginfo(module, silent); + debuginfo_cache = open_debuginfo(module, NULL, silent); if (!debuginfo_cache) zfree(&debuginfo_cache_path); out: @@ -531,14 +542,18 @@ static void debuginfo_cache__exit(void) } -static int get_text_start_address(const char *exec, unsigned long *address) +static int get_text_start_address(const char *exec, unsigned long *address, + struct nsinfo *nsi) { Elf *elf; GElf_Ehdr ehdr; GElf_Shdr shdr; int fd, ret = -ENOENT; + struct nscookie nsc; + nsinfo__mountns_enter(nsi, &nsc); fd = open(exec, O_RDONLY); + nsinfo__mountns_exit(&nsc); if (fd < 0) return -errno; @@ -582,7 +597,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, ret = -EINVAL; goto error; } - ret = get_text_start_address(tp->module, &stext); + ret = get_text_start_address(tp->module, &stext, NULL); if (ret < 0) goto error; addr += stext; @@ -659,7 +674,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, /* Prepare a map for offline binary */ map = dso__new_map(pathname); - if (!map || get_text_start_address(pathname, &stext) < 0) { + if (!map || get_text_start_address(pathname, &stext, NULL) < 0) { pr_warning("Failed to get ELF symbols for %s\n", pathname); return -EINVAL; } @@ -676,7 +691,8 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, } static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *exec) + int ntevs, const char *exec, + struct nsinfo *nsi) { int i, ret = 0; unsigned long stext = 0; @@ -684,7 +700,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, if (!exec) return 0; - ret = get_text_start_address(exec, &stext); + ret = get_text_start_address(exec, &stext, nsi); if (ret < 0) return ret; @@ -715,7 +731,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs, if (!module) return 0; - map = get_target_map(module, false); + map = get_target_map(module, NULL, false); if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) { pr_warning("Failed to get ELF symbols for %s\n", module); return -EINVAL; @@ -802,7 +818,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev, int ret; if (uprobe) - ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + ret = add_exec_to_probe_trace_events(tevs, ntevs, module, + pev->nsi); else if (module) /* Currently ref_reloc_sym based probe is not for drivers */ ret = post_process_module_probe_trace_events(tevs, ntevs, @@ -825,7 +842,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct debuginfo *dinfo; int ntevs, ret = 0; - dinfo = open_debuginfo(pev->target, !need_dwarf); + dinfo = open_debuginfo(pev->target, pev->nsi, !need_dwarf); if (!dinfo) { if (need_dwarf) return -ENOENT; @@ -945,7 +962,7 @@ static int __show_line_range(struct line_range *lr, const char *module, char sbuf[STRERR_BUFSIZE]; /* Search a line range */ - dinfo = open_debuginfo(module, false); + dinfo = open_debuginfo(module, NULL, false); if (!dinfo) return -ENOENT; @@ -1021,14 +1038,18 @@ end: return ret; } -int show_line_range(struct line_range *lr, const char *module, bool user) +int show_line_range(struct line_range *lr, const char *module, + struct nsinfo *nsi, bool user) { int ret; + struct nscookie nsc; ret = init_probe_symbol_maps(user); if (ret < 0) return ret; + nsinfo__mountns_enter(nsi, &nsc); ret = __show_line_range(lr, module, user); + nsinfo__mountns_exit(&nsc); exit_probe_symbol_maps(); return ret; @@ -1111,7 +1132,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, if (ret < 0) return ret; - dinfo = open_debuginfo(pevs->target, false); + dinfo = open_debuginfo(pevs->target, pevs->nsi, false); if (!dinfo) { ret = -ENOENT; goto out; @@ -1155,6 +1176,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, int show_line_range(struct line_range *lr __maybe_unused, const char *module __maybe_unused, + struct nsinfo *nsi __maybe_unused, bool user __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); @@ -2373,7 +2395,7 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist, struct kprobe_blacklist_node *node; list_for_each_entry(node, blacklist, list) { - if (node->start <= address && address <= node->end) + if (node->start <= address && address < node->end) return node; } @@ -2703,6 +2725,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tev = NULL; struct probe_cache *cache = NULL; struct strlist *namelist[2] = {NULL, NULL}; + struct nscookie nsc; up = pev->uprobes ? 1 : 0; fd[up] = __open_probe_file_and_namelist(up, &namelist[up]); @@ -2729,7 +2752,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret < 0) break; + nsinfo__mountns_enter(pev->nsi, &nsc); ret = probe_file__add_event(fd[up], tev); + nsinfo__mountns_exit(&nsc); if (ret < 0) break; @@ -2744,7 +2769,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret == -EINVAL && pev->uprobes) warn_uprobe_event_compat(tev); if (ret == 0 && probe_conf.cache) { - cache = probe_cache__new(pev->target); + cache = probe_cache__new(pev->target, pev->nsi); if (!cache || probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 || probe_cache__commit(cache) < 0) @@ -2805,7 +2830,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int ret, i, j, skipped = 0; char *mod_name; - map = get_target_map(pev->target, pev->uprobes); + map = get_target_map(pev->target, pev->nsi, pev->uprobes); if (!map) { ret = -EINVAL; goto out; @@ -3094,7 +3119,7 @@ static int find_cached_events(struct perf_probe_event *pev, int ntevs = 0; int ret = 0; - cache = probe_cache__new(target); + cache = probe_cache__new(target, pev->nsi); /* Return 0 ("not found") if the target has no probe cache. */ if (!cache) return 0; @@ -3184,7 +3209,7 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev, else return find_cached_events(pev, tevs, pev->target); } - cache = probe_cache__new(pev->target); + cache = probe_cache__new(pev->target, pev->nsi); if (!cache) return 0; @@ -3345,13 +3370,16 @@ int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs) void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs) { int i, j; + struct perf_probe_event *pev; /* Loop 3: cleanup and free trace events */ for (i = 0; i < npevs; i++) { + pev = &pevs[i]; for (j = 0; j < pevs[i].ntevs; j++) clear_probe_trace_event(&pevs[i].tevs[j]); zfree(&pevs[i].tevs); pevs[i].ntevs = 0; + nsinfo__zput(pev->nsi); clear_perf_probe_event(&pevs[i]); } } @@ -3409,8 +3437,8 @@ out: return ret; } -int show_available_funcs(const char *target, struct strfilter *_filter, - bool user) +int show_available_funcs(const char *target, struct nsinfo *nsi, + struct strfilter *_filter, bool user) { struct rb_node *nd; struct map *map; @@ -3421,7 +3449,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return ret; /* Get a symbol map */ - map = get_target_map(target, user); + map = get_target_map(target, nsi, user); if (!map) { pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5812947418dd..078681d12168 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -4,6 +4,7 @@ #include <linux/compiler.h> #include <stdbool.h> #include "intlist.h" +#include "namespaces.h" /* Probe related configurations */ struct probe_conf { @@ -92,6 +93,7 @@ struct perf_probe_event { struct perf_probe_arg *args; /* Arguments */ struct probe_trace_event *tevs; int ntevs; + struct nsinfo *nsi; /* Target namespace */ }; /* Line range */ @@ -163,10 +165,12 @@ int show_perf_probe_event(const char *group, const char *event, struct perf_probe_event *pev, const char *module, bool use_stdout); int show_perf_probe_events(struct strfilter *filter); -int show_line_range(struct line_range *lr, const char *module, bool user); +int show_line_range(struct line_range *lr, const char *module, + struct nsinfo *nsi, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); -int show_available_funcs(const char *module, struct strfilter *filter, bool user); +int show_available_funcs(const char *module, struct nsinfo *nsi, + struct strfilter *filter, bool user); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); @@ -180,7 +184,7 @@ int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4); int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); -struct map *get_target_map(const char *target, bool user); +struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user); void arch__post_process_probe_trace_events(struct perf_probe_event *pev, int ntevs); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index d679389e627c..cdf8d83a484c 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -412,13 +412,15 @@ int probe_cache_entry__get_event(struct probe_cache_entry *entry, } /* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */ -static int probe_cache__open(struct probe_cache *pcache, const char *target) +static int probe_cache__open(struct probe_cache *pcache, const char *target, + struct nsinfo *nsi) { char cpath[PATH_MAX]; char sbuildid[SBUILD_ID_SIZE]; char *dir_name = NULL; bool is_kallsyms = false; int ret, fd; + struct nscookie nsc; if (target && build_id_cache__cached(target)) { /* This is a cached buildid */ @@ -431,8 +433,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) target = DSO__NAME_KALLSYMS; is_kallsyms = true; ret = sysfs__sprintf_build_id("/", sbuildid); - } else + } else { + nsinfo__mountns_enter(nsi, &nsc); ret = filename__sprintf_build_id(target, sbuildid); + nsinfo__mountns_exit(&nsc); + } if (ret < 0) { pr_debug("Failed to get build-id from %s.\n", target); @@ -441,7 +446,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) /* If we have no buildid cache, make it */ if (!build_id_cache__cached(sbuildid)) { - ret = build_id_cache__add_s(sbuildid, target, + ret = build_id_cache__add_s(sbuildid, target, nsi, is_kallsyms, NULL); if (ret < 0) { pr_debug("Failed to add build-id cache: %s\n", target); @@ -449,7 +454,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) } } - dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms, + dir_name = build_id_cache__cachedir(sbuildid, target, nsi, is_kallsyms, false); found: if (!dir_name) { @@ -554,7 +559,7 @@ void probe_cache__delete(struct probe_cache *pcache) free(pcache); } -struct probe_cache *probe_cache__new(const char *target) +struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi) { struct probe_cache *pcache = probe_cache__alloc(); int ret; @@ -562,7 +567,7 @@ struct probe_cache *probe_cache__new(const char *target) if (!pcache) return NULL; - ret = probe_cache__open(pcache, target); + ret = probe_cache__open(pcache, target, nsi); if (ret < 0) { pr_debug("Cache open error: %d\n", ret); goto out_err; @@ -974,7 +979,7 @@ int probe_cache__show_all_caches(struct strfilter *filter) return -EINVAL; } strlist__for_each_entry(nd, bidlist) { - pcache = probe_cache__new(nd->s); + pcache = probe_cache__new(nd->s, NULL); if (!pcache) continue; if (!list_empty(&pcache->entries)) { diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 5ecc9d3925db..2ca4163abafe 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -51,7 +51,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist); int probe_cache_entry__get_event(struct probe_cache_entry *entry, struct probe_trace_event **tevs); -struct probe_cache *probe_cache__new(const char *target); +struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi); int probe_cache__add_entry(struct probe_cache *pcache, struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs); @@ -69,7 +69,7 @@ int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ -static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) +static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { return NULL; } diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 9f3b0d9754a8..e66dc495809a 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 57b7a00e6f16..c7187f067d31 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -116,6 +116,34 @@ static PyObject *get_handler(const char *handler_name) return handler; } +static int get_argument_count(PyObject *handler) +{ + int arg_count = 0; + + /* + * The attribute for the code object is func_code in Python 2, + * whereas it is __code__ in Python 3.0+. + */ + PyObject *code_obj = PyObject_GetAttrString(handler, + "func_code"); + if (PyErr_Occurred()) { + PyErr_Clear(); + code_obj = PyObject_GetAttrString(handler, + "__code__"); + } + PyErr_Clear(); + if (code_obj) { + PyObject *arg_count_obj = PyObject_GetAttrString(code_obj, + "co_argcount"); + if (arg_count_obj) { + arg_count = (int) PyInt_AsLong(arg_count_obj); + Py_DECREF(arg_count_obj); + } + Py_DECREF(code_obj); + } + return arg_count; +} + static void call_object(PyObject *handler, PyObject *args, const char *die_msg) { PyObject *retval; @@ -391,13 +419,115 @@ exit: return pylist; } +static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) +{ + PyObject *t; + + t = PyTuple_New(2); + if (!t) + Py_FatalError("couldn't create Python tuple"); + PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id)); + PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value)); + return t; +} + +static void set_sample_read_in_dict(PyObject *dict_sample, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + PyObject *values; + unsigned int i; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + pydict_set_item_string_decref(dict_sample, "time_enabled", + PyLong_FromUnsignedLongLong(sample->read.time_enabled)); + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + pydict_set_item_string_decref(dict_sample, "time_running", + PyLong_FromUnsignedLongLong(sample->read.time_running)); + } + + if (read_format & PERF_FORMAT_GROUP) + values = PyList_New(sample->read.group.nr); + else + values = PyList_New(1); + + if (!values) + Py_FatalError("couldn't create Python list"); + + if (read_format & PERF_FORMAT_GROUP) { + for (i = 0; i < sample->read.group.nr; i++) { + PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]); + PyList_SET_ITEM(values, i, t); + } + } else { + PyObject *t = get_sample_value_as_tuple(&sample->read.one); + PyList_SET_ITEM(values, 0, t); + } + pydict_set_item_string_decref(dict_sample, "values", values); +} + +static PyObject *get_perf_sample_dict(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al, + PyObject *callchain) +{ + PyObject *dict, *dict_sample; + + dict = PyDict_New(); + if (!dict) + Py_FatalError("couldn't create Python dictionary"); + + dict_sample = PyDict_New(); + if (!dict_sample) + Py_FatalError("couldn't create Python dictionary"); + + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( + (const char *)&evsel->attr, sizeof(evsel->attr))); + + pydict_set_item_string_decref(dict_sample, "pid", + PyInt_FromLong(sample->pid)); + pydict_set_item_string_decref(dict_sample, "tid", + PyInt_FromLong(sample->tid)); + pydict_set_item_string_decref(dict_sample, "cpu", + PyInt_FromLong(sample->cpu)); + pydict_set_item_string_decref(dict_sample, "ip", + PyLong_FromUnsignedLongLong(sample->ip)); + pydict_set_item_string_decref(dict_sample, "time", + PyLong_FromUnsignedLongLong(sample->time)); + pydict_set_item_string_decref(dict_sample, "period", + PyLong_FromUnsignedLongLong(sample->period)); + set_sample_read_in_dict(dict_sample, sample, evsel); + pydict_set_item_string_decref(dict, "sample", dict_sample); + + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( + (const char *)sample->raw_data, sample->raw_size)); + pydict_set_item_string_decref(dict, "comm", + PyString_FromString(thread__comm_str(al->thread))); + if (al->map) { + pydict_set_item_string_decref(dict, "dso", + PyString_FromString(al->map->dso->name)); + } + if (al->sym) { + pydict_set_item_string_decref(dict, "symbol", + PyString_FromString(al->sym->name)); + } + + pydict_set_item_string_decref(dict, "callchain", callchain); + + return dict; +} + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { struct event_format *event = evsel->tp_format; PyObject *handler, *context, *t, *obj = NULL, *callchain; - PyObject *dict = NULL; + PyObject *dict = NULL, *all_entries_dict = NULL; static char handler_name[256]; struct format_field *field; unsigned long s, ns; @@ -407,10 +537,7 @@ static void python_process_tracepoint(struct perf_sample *sample, void *data = sample->raw_data; unsigned long long nsecs = sample->time; const char *comm = thread__comm_str(al->thread); - - t = PyTuple_New(MAX_FIELDS); - if (!t) - Py_FatalError("couldn't create Python tuple"); + const char *default_handler_name = "trace_unhandled"; if (!event) { snprintf(handler_name, sizeof(handler_name), @@ -427,10 +554,19 @@ static void python_process_tracepoint(struct perf_sample *sample, handler = get_handler(handler_name); if (!handler) { + handler = get_handler(default_handler_name); + if (!handler) + return; dict = PyDict_New(); if (!dict) Py_FatalError("couldn't create Python dict"); } + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + s = nsecs / NSEC_PER_SEC; ns = nsecs - s * NSEC_PER_SEC; @@ -444,8 +580,10 @@ static void python_process_tracepoint(struct perf_sample *sample, /* ip unwinding */ callchain = python_process_callchain(sample, evsel, al); + /* Need an additional reference for the perf_sample dict */ + Py_INCREF(callchain); - if (handler) { + if (!dict) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); @@ -484,26 +622,35 @@ static void python_process_tracepoint(struct perf_sample *sample, } else { /* FIELD_IS_NUMERIC */ obj = get_field_numeric_entry(event, field, data); } - if (handler) + if (!dict) PyTuple_SetItem(t, n++, obj); else pydict_set_item_string_decref(dict, field->name, obj); } - if (!handler) + if (dict) PyTuple_SetItem(t, n++, dict); + if (get_argument_count(handler) == (int) n + 1) { + all_entries_dict = get_perf_sample_dict(sample, evsel, al, + callchain); + PyTuple_SetItem(t, n++, all_entries_dict); + } else { + Py_DECREF(callchain); + } + if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - if (handler) { + if (!dict) { call_object(handler, t, handler_name); } else { - try_call_object("trace_unhandled", t); + call_object(handler, t, default_handler_name); Py_DECREF(dict); } + Py_XDECREF(all_entries_dict); Py_DECREF(t); } @@ -795,10 +942,16 @@ static void python_process_general_event(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { - PyObject *handler, *t, *dict, *callchain, *dict_sample; + PyObject *handler, *t, *dict, *callchain; static char handler_name[64]; unsigned n = 0; + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); + + handler = get_handler(handler_name); + if (!handler) + return; + /* * Use the MAX_FIELDS to make the function expandable, though * currently there is only one item for the tuple. @@ -807,61 +960,16 @@ static void python_process_general_event(struct perf_sample *sample, if (!t) Py_FatalError("couldn't create Python tuple"); - dict = PyDict_New(); - if (!dict) - Py_FatalError("couldn't create Python dictionary"); - - dict_sample = PyDict_New(); - if (!dict_sample) - Py_FatalError("couldn't create Python dictionary"); - - snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); - - handler = get_handler(handler_name); - if (!handler) - goto exit; - - pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( - (const char *)&evsel->attr, sizeof(evsel->attr))); - - pydict_set_item_string_decref(dict_sample, "pid", - PyInt_FromLong(sample->pid)); - pydict_set_item_string_decref(dict_sample, "tid", - PyInt_FromLong(sample->tid)); - pydict_set_item_string_decref(dict_sample, "cpu", - PyInt_FromLong(sample->cpu)); - pydict_set_item_string_decref(dict_sample, "ip", - PyLong_FromUnsignedLongLong(sample->ip)); - pydict_set_item_string_decref(dict_sample, "time", - PyLong_FromUnsignedLongLong(sample->time)); - pydict_set_item_string_decref(dict_sample, "period", - PyLong_FromUnsignedLongLong(sample->period)); - pydict_set_item_string_decref(dict, "sample", dict_sample); - - pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( - (const char *)sample->raw_data, sample->raw_size)); - pydict_set_item_string_decref(dict, "comm", - PyString_FromString(thread__comm_str(al->thread))); - if (al->map) { - pydict_set_item_string_decref(dict, "dso", - PyString_FromString(al->map->dso->name)); - } - if (al->sym) { - pydict_set_item_string_decref(dict, "symbol", - PyString_FromString(al->sym->name)); - } - /* ip unwinding */ callchain = python_process_callchain(sample, evsel, al); - pydict_set_item_string_decref(dict, "callchain", callchain); + dict = get_perf_sample_dict(sample, evsel, al, callchain); PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); call_object(handler, t, handler_name); -exit: + Py_DECREF(dict); Py_DECREF(t); } @@ -1259,6 +1367,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } + if (not_first++) + fprintf(ofp, ", "); + if (++count % 5 == 0) + fprintf(ofp, "\n\t\t"); + fprintf(ofp, "perf_sample_dict"); + fprintf(ofp, "):\n"); fprintf(ofp, "\t\tprint_header(event_name, common_cpu, " @@ -1328,6 +1442,9 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, ")\n\n"); + fprintf(ofp, "\t\tprint 'Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tfor node in common_callchain:"); fprintf(ofp, "\n\t\t\tif 'sym' in node:"); fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); @@ -1338,15 +1455,20 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) } fprintf(ofp, "def trace_unhandled(event_name, context, " - "event_fields_dict):\n"); + "event_fields_dict, perf_sample_dict):\n"); - fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))" - "for k,v in sorted(event_fields_dict.items())])\n\n"); + fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n"); + fprintf(ofp, "\t\tprint 'Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); fprintf(ofp, "def print_header(" "event_name, cpu, secs, nsecs, pid, comm):\n" "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" - "(event_name, cpu, secs, nsecs, pid, comm),\n"); + "(event_name, cpu, secs, nsecs, pid, comm),\n\n"); + + fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n" + "\treturn delimiter.join" + "(['%%s=%%s'%%(k,str(v))for k,v in sorted(a_dict.items())])\n"); fclose(ofp); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d19c40a81040..ac863691605f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -428,6 +428,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->stat_round = process_stat_round_stub; if (tool->time_conv == NULL) tool->time_conv = process_event_op2_stub; + if (tool->feature == NULL) + tool->feature = process_event_op2_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -1125,6 +1127,30 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->attr.read_format); } +static void dump_read(struct perf_evsel *evsel, union perf_event *event) +{ + struct read_event *read_event = &event->read; + u64 read_format; + + if (!dump_trace) + return; + + printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, + evsel ? perf_evsel__name(evsel) : "FAIL", + event->read.value); + + read_format = evsel->attr.read_format; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("... time running : %" PRIu64 "\n", read_event->time_running); + + if (read_format & PERF_FORMAT_ID) + printf("... id : %" PRIu64 "\n", read_event->id); +} + static struct machine *machines__find_for_cpumode(struct machines *machines, union perf_event *event, struct perf_sample *sample) @@ -1269,6 +1295,7 @@ static int machines__deliver_event(struct machines *machines, evlist->stats.total_lost_samples += event->lost_samples.lost; return tool->lost_samples(tool, event, sample, machine); case PERF_RECORD_READ: + dump_read(evsel, event); return tool->read(tool, event, sample, evsel, machine); case PERF_RECORD_THROTTLE: return tool->throttle(tool, event, sample, machine); @@ -1371,6 +1398,8 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; return tool->time_conv(tool, event, session); + case PERF_RECORD_HEADER_FEATURE: + return tool->feature(tool, event, session); default: return -EINVAL; } diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c new file mode 100644 index 000000000000..ce8fc290fce8 --- /dev/null +++ b/tools/perf/util/setns.c @@ -0,0 +1,8 @@ +#include "util.h" +#include <unistd.h> +#include <sys/syscall.h> + +int setns(int fd, int nstype) +{ + return syscall(__NR_setns, fd, nstype); +} diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c new file mode 100644 index 000000000000..453f6f6f29f3 --- /dev/null +++ b/tools/perf/util/smt.c @@ -0,0 +1,44 @@ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <linux/bitops.h> +#include "api/fs/fs.h" +#include "smt.h" + +int smt_on(void) +{ + static bool cached; + static int cached_result; + int cpu; + int ncpu; + + if (cached) + return cached_result; + + ncpu = sysconf(_SC_NPROCESSORS_CONF); + for (cpu = 0; cpu < ncpu; cpu++) { + unsigned long long siblings; + char *str; + size_t strlen; + char fn[256]; + + snprintf(fn, sizeof fn, + "devices/system/cpu/cpu%d/topology/thread_siblings", + cpu); + if (sysfs__read_str(fn, &str, &strlen) < 0) + continue; + /* Entry is hex, but does not have 0x, so need custom parser */ + siblings = strtoull(str, NULL, 16); + free(str); + if (hweight64(siblings) > 1) { + cached_result = 1; + cached = true; + break; + } + } + if (!cached) { + cached_result = 0; + cached = true; + } + return cached_result; +} diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h new file mode 100644 index 000000000000..b8414b7bcbc8 --- /dev/null +++ b/tools/perf/util/smt.h @@ -0,0 +1,6 @@ +#ifndef SMT_H +#define SMT_H 1 + +int smt_on(void); + +#endif diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 8b327c955a4f..12359bd986db 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2563,7 +2563,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); - if (evlist == NULL) + if (evlist == NULL || perf_evlist__empty(evlist)) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index ebc88a74e67b..ed8e8d2de942 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -155,6 +155,9 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, &a2l->filename, &a2l->funcname, &a2l->line); + + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; } static struct a2l_data *addr2line_init(const char *path) @@ -248,6 +251,9 @@ static int addr2line(const char *dso_name, u64 addr, &a2l->funcname, &a2l->line) && cnt++ < MAX_INLINE_NEST) { + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; + if (node != NULL) { if (inline_list__append_dso_a2l(dso, node)) return 0; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 719d6cb86952..a04cf56d3517 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -70,7 +70,11 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) return a->ctx - b->ctx; if (a->cpu != b->cpu) return a->cpu - b->cpu; - return a->evsel - b->evsel; + if (a->evsel == b->evsel) + return 0; + if ((char *)a->evsel < (char *)b->evsel) + return -1; + return +1; } static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 53b9a994a3dc..35e9848734d6 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -128,6 +128,10 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { + struct perf_stat_evsel *ps = evsel->priv; + + if (ps) + free(ps->group_data); zfree(&evsel->priv); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 7522bf10b03e..eacaf958e19d 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -28,8 +28,9 @@ enum perf_stat_evsel_id { }; struct perf_stat_evsel { - struct stats res_stats[3]; - enum perf_stat_evsel_id id; + struct stats res_stats[3]; + enum perf_stat_evsel_id id; + u64 *group_data; }; enum aggr_mode { diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 502505cf236a..5c39f420111e 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -259,7 +259,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * { uint32_t nr_rel_entries, idx; GElf_Sym sym; - u64 plt_offset; + u64 plt_offset, plt_header_size, plt_entry_size; GElf_Shdr shdr_plt; struct symbol *f; GElf_Shdr shdr_rel_plt, shdr_dynsym; @@ -326,6 +326,23 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; plt_offset = shdr_plt.sh_offset; + switch (ehdr.e_machine) { + case EM_ARM: + plt_header_size = 20; + plt_entry_size = 12; + break; + + case EM_AARCH64: + plt_header_size = 32; + plt_entry_size = 16; + break; + + default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */ + plt_header_size = shdr_plt.sh_entsize; + plt_entry_size = shdr_plt.sh_entsize; + break; + } + plt_offset += plt_header_size; if (shdr_rel_plt.sh_type == SHT_RELA) { GElf_Rela pos_mem, *pos; @@ -335,7 +352,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * const char *elf_name = NULL; char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); elf_name = elf_sym__name(&sym, symstrs); @@ -346,11 +362,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * "%s@plt", elf_name); free(demangled); - f = symbol__new(plt_offset, shdr_plt.sh_entsize, + f = symbol__new(plt_offset, plt_entry_size, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; + plt_offset += plt_entry_size; symbols__insert(&dso->symbols[map->type], f); ++nr; } @@ -361,7 +378,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * const char *elf_name = NULL; char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); elf_name = elf_sym__name(&sym, symstrs); @@ -372,11 +388,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * "%s@plt", elf_name); free(demangled); - f = symbol__new(plt_offset, shdr_plt.sh_entsize, + f = symbol__new(plt_offset, plt_entry_size, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; + plt_offset += plt_entry_size; symbols__insert(&dso->symbols[map->type], f); ++nr; } @@ -391,7 +408,7 @@ out_elf_end: return 0; } -char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name) +char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { return demangle_sym(dso, kmodule, elf_name); } @@ -793,6 +810,12 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } +void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, + struct map *map __maybe_unused) +{ + sym->st_value -= shdr->sh_addr - shdr->sh_offset; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -973,7 +996,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - sym.st_value -= shdr.sh_addr - shdr.sh_offset; + arch__adjust_sym_map_offset(&sym, &shdr, map); if (strcmp(section_name, (curr_dso->short_name + @@ -1442,7 +1465,7 @@ static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci, static int kcore_copy__process_modules(void *arg, const char *name __maybe_unused, - u64 start) + u64 start, u64 size __maybe_unused) { struct kcore_copy_info *kci = arg; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 40bf5d4c0bfd..1a5aa35b0100 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -377,7 +377,7 @@ void symbol__elf_init(void) char *dso__demangle_sym(struct dso *dso __maybe_unused, int kmodule __maybe_unused, - char *elf_name __maybe_unused) + const char *elf_name __maybe_unused) { return NULL; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7a98dbd2aed..5909ee4c7ade 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -18,6 +18,7 @@ #include "symbol.h" #include "strlist.h" #include "intlist.h" +#include "namespaces.h" #include "header.h" #include "path.h" #include "sane_ctype.h" @@ -52,6 +53,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__JAVA_JIT, DSO_BINARY_TYPE__DEBUGLINK, DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, @@ -231,7 +233,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) goto out_unlock; for (next = map__next(curr); next; next = map__next(curr)) { - curr->end = next->start; + if (!curr->end) + curr->end = next->start; curr = next; } @@ -239,7 +242,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) * We still haven't the actual symbols, so guess the * last map final address. */ - curr->end = ~0ULL; + if (!curr->end) + curr->end = ~0ULL; out_unlock: pthread_rwlock_unlock(&maps->lock); @@ -550,7 +554,7 @@ void dso__sort_by_name(struct dso *dso, enum map_type type) int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, - u64 start)) + u64 start, u64 size)) { char *line = NULL; size_t n; @@ -563,8 +567,8 @@ int modules__parse(const char *filename, void *arg, while (1) { char name[PATH_MAX]; - u64 start; - char *sep; + u64 start, size; + char *sep, *endptr; ssize_t line_len; line_len = getline(&line, &n, file); @@ -596,7 +600,11 @@ int modules__parse(const char *filename, void *arg, scnprintf(name, sizeof(name), "[%s]", line); - err = process_module(arg, name, start); + size = strtoul(sep + 1, &endptr, 0); + if (*endptr != ' ' && *endptr != '\t') + continue; + + err = process_module(arg, name, start, size); if (err) break; } @@ -943,7 +951,8 @@ static struct module_info *find_module(const char *name, return NULL; } -static int __read_proc_modules(void *arg, const char *name, u64 start) +static int __read_proc_modules(void *arg, const char *name, u64 start, + u64 size __maybe_unused) { struct rb_root *modules = arg; struct module_info *mi; @@ -1325,14 +1334,15 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, return __dso__load_kallsyms(dso, filename, map, false); } -static int dso__load_perf_map(struct dso *dso, struct map *map) +static int dso__load_perf_map(const char *map_path, struct dso *dso, + struct map *map) { char *line = NULL; size_t n; FILE *file; int nr_syms = 0; - file = fopen(dso->long_name, "r"); + file = fopen(map_path, "r"); if (file == NULL) goto out_failure; @@ -1416,6 +1426,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, return kmod && dso->symtab_type == type; case DSO_BINARY_TYPE__BUILD_ID_CACHE: + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: return true; case DSO_BINARY_TYPE__NOT_FOUND: @@ -1424,6 +1435,44 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, } } +/* Checks for the existence of the perf-<pid>.map file in two different + * locations. First, if the process is a separate mount namespace, check in + * that namespace using the pid of the innermost pid namespace. If's not in a + * namespace, or the file can't be found there, try in the mount namespace of + * the tracing process using our view of its pid. + */ +static int dso__find_perf_map(char *filebuf, size_t bufsz, + struct nsinfo **nsip) +{ + struct nscookie nsc; + struct nsinfo *nsi; + struct nsinfo *nnsi; + int rc = -1; + + nsi = *nsip; + + if (nsi->need_setns) { + snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsi->nstgid); + nsinfo__mountns_enter(nsi, &nsc); + rc = access(filebuf, R_OK); + nsinfo__mountns_exit(&nsc); + if (rc == 0) + return rc; + } + + nnsi = nsinfo__copy(nsi); + if (nnsi) { + nsinfo__put(nsi); + + nnsi->need_setns = false; + snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nnsi->tgid); + *nsip = nnsi; + rc = 0; + } + + return rc; +} + int dso__load(struct dso *dso, struct map *map) { char *name; @@ -1435,8 +1484,21 @@ int dso__load(struct dso *dso, struct map *map) struct symsrc ss_[2]; struct symsrc *syms_ss = NULL, *runtime_ss = NULL; bool kmod; + bool perfmap; unsigned char build_id[BUILD_ID_SIZE]; + struct nscookie nsc; + char newmapname[PATH_MAX]; + const char *map_path = dso->long_name; + + perfmap = strncmp(dso->name, "/tmp/perf-", 10) == 0; + if (perfmap) { + if (dso->nsinfo && (dso__find_perf_map(newmapname, + sizeof(newmapname), &dso->nsinfo) == 0)) { + map_path = newmapname; + } + } + nsinfo__mountns_enter(dso->nsinfo, &nsc); pthread_mutex_lock(&dso->lock); /* check again under the dso->lock */ @@ -1461,19 +1523,19 @@ int dso__load(struct dso *dso, struct map *map) dso->adjust_symbols = 0; - if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { + if (perfmap) { struct stat st; - if (lstat(dso->name, &st) < 0) + if (lstat(map_path, &st) < 0) goto out; if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) { pr_warning("File %s not owned by current user or root, " - "ignoring it (use -f to override).\n", dso->name); + "ignoring it (use -f to override).\n", map_path); goto out; } - ret = dso__load_perf_map(dso, map); + ret = dso__load_perf_map(map_path, dso, map); dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : DSO_BINARY_TYPE__NOT_FOUND; goto out; @@ -1511,9 +1573,15 @@ int dso__load(struct dso *dso, struct map *map) for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) { struct symsrc *ss = &ss_[ss_pos]; bool next_slot = false; + bool is_reg; + bool nsexit; + int sirc; enum dso_binary_type symtab_type = binary_type_symtab[i]; + nsexit = (symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE || + symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO); + if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type)) continue; @@ -1521,12 +1589,20 @@ int dso__load(struct dso *dso, struct map *map) root_dir, name, PATH_MAX)) continue; - if (!is_regular_file(name)) - continue; + if (nsexit) + nsinfo__mountns_exit(&nsc); + + is_reg = is_regular_file(name); + sirc = symsrc__init(ss, dso, name, symtab_type); - /* Name is now the name of the next image to try */ - if (symsrc__init(ss, dso, name, symtab_type) < 0) + if (nsexit) + nsinfo__mountns_enter(dso->nsinfo, &nsc); + + if (!is_reg || sirc < 0) { + if (sirc >= 0) + symsrc__destroy(ss); continue; + } if (!syms_ss && symsrc__has_symtab(ss)) { syms_ss = ss; @@ -1584,6 +1660,7 @@ out_free: out: dso__set_loaded(dso, map->type); pthread_mutex_unlock(&dso->lock); + nsinfo__mountns_exit(&nsc); return ret; } @@ -1660,7 +1737,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map) } if (!symbol_conf.ignore_vmlinux_buildid) - filename = dso__build_id_filename(dso, NULL, 0); + filename = dso__build_id_filename(dso, NULL, 0, false); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, true); if (err > 0) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 41ebba9a2eb2..d00a012cfdfb 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -273,7 +273,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, - u64 start)); + u64 start, u64 size)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); @@ -306,7 +306,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map); -char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name); +char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name); void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root *symbols, struct symbol *sym); @@ -343,6 +343,9 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); +void arch__adjust_sym_map_offset(GElf_Sym *sym, + GElf_Shdr *shdr __maybe_unused, + struct map *map __maybe_unused); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 378c418ca0c1..aee9a42102ba 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -59,6 +59,8 @@ struct thread *thread__new(pid_t pid, pid_t tid) list_add(&comm->list, &thread->comm_list); refcount_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); + /* Thread holds first ref to nsdata. */ + thread->nsinfo = nsinfo__new(pid); } return thread; @@ -91,6 +93,7 @@ void thread__delete(struct thread *thread) comm__free(comm); } unwind__finish_access(thread); + nsinfo__zput(thread->nsinfo); free(thread); } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 4eb849e9098f..cb1a5dd5c2b9 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -34,6 +34,7 @@ struct thread { void *priv; struct thread_stack *ts; + struct nsinfo *nsinfo; #ifdef HAVE_LIBUNWIND_SUPPORT void *addr_space; struct unwind_libunwind_ops *unwind_libunwind_ops; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 829471a1c6d7..d549e50db397 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -34,6 +34,12 @@ typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +enum show_feature_header { + SHOW_FEAT_NO_HEADER = 0, + SHOW_FEAT_HEADER, + SHOW_FEAT_HEADER_FULL_INFO, +}; + struct perf_tool { event_sample sample, read; @@ -63,11 +69,13 @@ struct perf_tool { cpu_map, stat_config, stat, - stat_round; + stat_round, + feature; event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; bool namespace_events; + enum show_feature_header show_feat_hdr; }; #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 988111e0bab5..4c360daa4e24 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -143,13 +143,17 @@ out: return list; } -static int slow_copyfile(const char *from, const char *to) +static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi) { int err = -1; char *line = NULL; size_t n; - FILE *from_fp = fopen(from, "r"), *to_fp; + FILE *from_fp, *to_fp; + struct nscookie nsc; + nsinfo__mountns_enter(nsi, &nsc); + from_fp = fopen(from, "r"); + nsinfo__mountns_exit(&nsc); if (from_fp == NULL) goto out; @@ -198,15 +202,21 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) return size ? -1 : 0; } -int copyfile_mode(const char *from, const char *to, mode_t mode) +static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, + struct nsinfo *nsi) { int fromfd, tofd; struct stat st; - int err = -1; + int err; char *tmp = NULL, *ptr = NULL; + struct nscookie nsc; - if (stat(from, &st)) + nsinfo__mountns_enter(nsi, &nsc); + err = stat(from, &st); + nsinfo__mountns_exit(&nsc); + if (err) goto out; + err = -1; /* extra 'x' at the end is to reserve space for '.' */ if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) { @@ -227,11 +237,13 @@ int copyfile_mode(const char *from, const char *to, mode_t mode) goto out_close_to; if (st.st_size == 0) { /* /proc? do it slowly... */ - err = slow_copyfile(from, tmp); + err = slow_copyfile(from, tmp, nsi); goto out_close_to; } + nsinfo__mountns_enter(nsi, &nsc); fromfd = open(from, O_RDONLY); + nsinfo__mountns_exit(&nsc); if (fromfd < 0) goto out_close_to; @@ -248,6 +260,16 @@ out: return err; } +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi) +{ + return copyfile_mode_ns(from, to, 0755, nsi); +} + +int copyfile_mode(const char *from, const char *to, mode_t mode) +{ + return copyfile_mode_ns(from, to, mode, NULL); +} + int copyfile(const char *from, const char *to) { return copyfile_mode(from, to, 0755); @@ -259,6 +281,7 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n) size_t left = n; while (left) { + /* buf must be treated as const if !is_read. */ ssize_t ret = is_read ? read(fd, buf, left) : write(fd, buf, left); @@ -286,9 +309,10 @@ ssize_t readn(int fd, void *buf, size_t n) /* * Write exactly 'n' bytes or return an error. */ -ssize_t writen(int fd, void *buf, size_t n) +ssize_t writen(int fd, const void *buf, size_t n) { - return ion(false, fd, buf, n); + /* ion does not modify buf. */ + return ion(false, fd, (void *)buf, n); } size_t hex_width(u64 v) diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 2c9e58a45310..b136c271125f 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -12,6 +12,7 @@ #include <stdarg.h> #include <linux/compiler.h> #include <linux/types.h> +#include "namespaces.h" /* General helper functions */ void usage(const char *err) __noreturn; @@ -33,10 +34,11 @@ struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dire bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); ssize_t readn(int fd, void *buf, size_t n); -ssize_t writen(int fd, void *buf, size_t n); +ssize_t writen(int fd, const void *buf, size_t n); size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -58,4 +60,8 @@ const char *perf_tip(const char *dirpath); int sched_getcpu(void); #endif +#ifndef HAVE_SETNS_SUPPORT +int setns(int fd, int nstype); +#endif + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 5de2e15e2eda..8a32bb0095e5 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -12,7 +12,7 @@ int perf_read_values_init(struct perf_read_values *values) values->threads_max = 16; values->pid = malloc(values->threads_max * sizeof(*values->pid)); values->tid = malloc(values->threads_max * sizeof(*values->tid)); - values->value = malloc(values->threads_max * sizeof(*values->value)); + values->value = zalloc(values->threads_max * sizeof(*values->value)); if (!values->pid || !values->tid || !values->value) { pr_debug("failed to allocate read_values threads arrays"); goto out_free_pid; @@ -98,15 +98,16 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, return i; } - i = values->threads + 1; - values->value[i] = malloc(values->counters_max * sizeof(**values->value)); + i = values->threads; + + values->value[i] = zalloc(values->counters_max * sizeof(**values->value)); if (!values->value[i]) { pr_debug("failed to allocate read_values counters array"); return -ENOMEM; } values->pid[i] = pid; values->tid[i] = tid; - values->threads = i; + values->threads = i + 1; return i; } @@ -130,12 +131,16 @@ static int perf_read_values__enlarge_counters(struct perf_read_values *values) for (i = 0; i < values->threads; i++) { u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); + int j; - if (value) { + if (!value) { pr_debug("failed to enlarge read_values ->values array"); goto out_free_name; } + for (j = values->counters_max; j < counters_max; j++) + value[j] = 0; + values->value[i] = value; } @@ -187,7 +192,7 @@ int perf_read_values_add_value(struct perf_read_values *values, if (cindex < 0) return cindex; - values->value[tindex][cindex] = value; + values->value[tindex][cindex] += value; return 0; } diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c index 7251fdbabced..c8f415d9877b 100644 --- a/tools/perf/util/xyarray.c +++ b/tools/perf/util/xyarray.c @@ -12,6 +12,8 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) xy->entry_size = entry_size; xy->row_size = row_size; xy->entries = xlen * ylen; + xy->max_x = xlen; + xy->max_y = ylen; } return xy; diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h index 7f30af371b7e..4ba726c90870 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/util/xyarray.h @@ -7,6 +7,8 @@ struct xyarray { size_t row_size; size_t entry_size; size_t entries; + size_t max_x; + size_t max_y; char contents[]; }; @@ -19,4 +21,14 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y) return &xy->contents[x * xy->row_size + y * xy->entry_size]; } +static inline int xyarray__max_y(struct xyarray *xy) +{ + return xy->max_x; +} + +static inline int xyarray__max_x(struct xyarray *xy) +{ + return xy->max_y; +} + #endif /* _PERF_XYARRAY_H_ */ |