diff options
Diffstat (limited to 'tools/perf/util')
211 files changed, 5357 insertions, 1962 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 79dea95a7f68..a3de7916fe63 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -13,6 +13,7 @@ libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o +libperf-y += mmap.o libperf-y += memswap.o libperf-y += parse-events.o libperf-y += perf_regs.o @@ -22,6 +23,7 @@ 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 @@ -33,6 +35,7 @@ libperf-y += dso.o libperf-y += symbol.o libperf-y += symbol_fprintf.o libperf-y += color.o +libperf-y += metricgroup.o libperf-y += header.o libperf-y += callchain.o libperf-y += values.o @@ -77,6 +80,7 @@ libperf-y += data.o libperf-y += tsc.o libperf-y += cloexec.o libperf-y += call-path.o +libperf-y += rwsem.o libperf-y += thread-stack.o libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ @@ -93,6 +97,7 @@ 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 +109,10 @@ 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/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 39f17507578d..3802cee5e188 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 if [ $# -eq 1 ] ; then OUTPUT=$1 diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index be1caabb9290..da1c4c4a0dd8 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -47,7 +47,11 @@ struct arch { bool sorted_instructions; bool initialized; void *priv; - int (*init)(struct arch *arch); + unsigned int model; + unsigned int family; + int (*init)(struct arch *arch, char *cpuid); + bool (*ins_is_fused)(struct arch *arch, const char *ins1, + const char *ins2); struct { char comment_char; char skip_functions_char; @@ -127,8 +131,10 @@ static struct arch architectures[] = { }, { .name = "x86", + .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), + .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, @@ -171,6 +177,14 @@ 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 +516,11 @@ 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; @@ -586,14 +605,24 @@ static struct arch *arch__find(const char *name) int symbol__alloc_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); - const size_t size = symbol__size(sym); + size_t size = symbol__size(sym); size_t sizeof_sym_hist; + /* + * Add buffer of one element for zero length symbol. + * When sample is taken from first instruction of + * zero length symbol, perf still resolves it and + * shows symbol name in perf report and allows to + * annotate it. + */ + if (size == 0) + size = 1; + /* 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 +706,8 @@ 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 +723,15 @@ 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 +751,8 @@ 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 +761,7 @@ 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 +825,16 @@ 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 +944,12 @@ 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 +963,24 @@ 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 +1079,10 @@ 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 +1096,7 @@ 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 +1107,10 @@ 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 +1148,15 @@ 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 +1172,13 @@ 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 +1372,7 @@ 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 +1426,7 @@ 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]; @@ -1411,7 +1456,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, *parch = arch; if (arch->init) { - err = arch->init(arch); + err = arch->init(arch, cpuid); if (err) { pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name); return err; @@ -1648,19 +1693,19 @@ 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 +1715,7 @@ 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 +1724,9 @@ 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 +1795,10 @@ 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 +1816,7 @@ 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 +1834,9 @@ 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 +1900,10 @@ 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 +1954,7 @@ 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..f6ba3560de5e 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_ANNOTATE_H #define __PERF_ANNOTATE_H @@ -52,7 +53,9 @@ 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 +75,22 @@ 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 +156,22 @@ 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/auxtrace.c b/tools/perf/util/auxtrace.c index 5547457566a7..a33491416400 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -208,7 +208,7 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues, static void *auxtrace_copy_data(u64 size, struct perf_session *session) { - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); void *p; ssize_t ret; @@ -305,7 +305,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, if (session->one_mmap) { buffer->data = buffer->data_offset - session->one_mmap_offset + session->one_mmap_addr; - } else if (perf_data_file__is_pipe(session->file)) { + } else if (perf_data__is_pipe(session->data)) { buffer->data = auxtrace_copy_data(buffer->size, session); if (!buffer->data) return -ENOMEM; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 33b5e6cdf38c..d19e11b68de7 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -378,7 +378,7 @@ struct addr_filters { static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); /* Ensure all reads are done after we read the head */ rmb(); @@ -389,7 +389,7 @@ static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; #if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT) - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); #else u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0); #endif diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c index 7b3e1d75d803..f1451c987eec 100644 --- a/tools/perf/util/block-range.c +++ b/tools/perf/util/block-range.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "block-range.h" #include "annotate.h" diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h index a8c841381131..a5ba719d69fb 100644 --- a/tools/perf/util/block-range.h +++ b/tools/perf/util/block-range.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_BLOCK_RANGE_H #define __PERF_BLOCK_RANGE_H diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 4bd2d1d882af..72c107fcbc5a 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * bpf-loader.c * @@ -1246,7 +1247,7 @@ 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-loader.h b/tools/perf/util/bpf-loader.h index 48863867878b..5d3aefd6fae7 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015, Huawei Inc. diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 1356220a9f1b..29347756b0af 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * bpf-prologue.c * @@ -58,6 +59,46 @@ 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 +299,14 @@ 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/bpf-prologue.h b/tools/perf/util/bpf-prologue.h index ba564838375f..c50c7358009f 100644 --- a/tools/perf/util/bpf-prologue.h +++ b/tools/perf/util/bpf-prologue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015, He Kuang <hekuang@huawei.com> * Copyright (C) 2015, Huawei Inc. 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..7f8553630c4d 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * build-id.c * @@ -243,12 +244,15 @@ 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 +274,8 @@ 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 +290,7 @@ 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 +305,15 @@ 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 +358,8 @@ 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 +541,14 @@ 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 +564,13 @@ 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 +584,20 @@ 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 +607,56 @@ 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 +670,52 @@ 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 +732,30 @@ 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 +821,7 @@ 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..f0c565164a97 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_BUILD_ID_H_ #define PERF_BUILD_ID_H_ 1 @@ -5,10 +6,12 @@ #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 +19,8 @@ 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 +29,26 @@ 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/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index ccafcf72b37a..e513366f2ee0 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_UTIL_CLANG_C_H #define PERF_UTIL_CLANG_C_H diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index 9b11e8c82798..a4014d786676 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "clang.h" #include "clang-c.h" #include "llvm/IR/Function.h" diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 1e974152cac2..1bfc946e37dc 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llvm C frontend for perf. Support dynamically compile C file * diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h index dd8b0427550d..6ce33e22f23c 100644 --- a/tools/perf/util/c++/clang.h +++ b/tools/perf/util/c++/clang.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_UTIL_CLANG_H #define PERF_UTIL_CLANG_H diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 0175765c05b9..9f2e36ef5072 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_CACHE_H #define __PERF_CACHE_H diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index b4204b43ed58..082505d08d72 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com> * @@ -23,6 +24,7 @@ #include "sort.h" #include "machine.h" #include "callchain.h" +#include "branch.h" #define CALLCHAIN_PARAM_DEFAULT \ .mode = CHAIN_GRAPH_ABS, \ @@ -64,8 +66,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -81,8 +81,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -104,8 +102,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -123,8 +119,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -303,7 +297,7 @@ 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; @@ -318,12 +312,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { @@ -558,19 +567,38 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) call->ip = cursor_node->ip; call->ms.sym = cursor_node->sym; call->ms.map = map__get(cursor_node->map); + call->srcline = cursor_node->srcline; 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->iter_cycles = cursor_node->iter_cycles; + } } list_add_tail(&call->list, &node->val); @@ -618,66 +646,97 @@ enum match_result { MATCH_GT, }; -static enum match_result match_chain_srcline(struct callchain_cursor_node *node, - struct callchain_list *cnode) +static enum match_result match_chain_strings(const char *left, + const char *right) { - char *left = NULL; - char *right = NULL; enum match_result ret = MATCH_EQ; int cmp; - if (cnode->ms.map) - left = get_srcline(cnode->ms.map->dso, - map__rip_2objdump(cnode->ms.map, cnode->ip), - cnode->ms.sym, true, false); - if (node->map) - right = get_srcline(node->map->dso, - map__rip_2objdump(node->map, node->ip), - node->sym, true, false); - if (left && right) cmp = strcmp(left, right); else if (!left && right) cmp = 1; else if (left && !right) cmp = -1; - else if (cnode->ip == node->ip) - cmp = 0; else - cmp = (cnode->ip < node->ip) ? -1 : 1; + return MATCH_ERROR; if (cmp != 0) ret = cmp < 0 ? MATCH_LT : MATCH_GT; - free_srcline(left); - free_srcline(right); return ret; } +/* + * We need to always use relative addresses because we're aggregating + * callchains from multiple threads, i.e. different address spaces, so + * comparing absolute addresses make no sense as a symbol in a DSO may end up + * in a different address when used in a different binary or even the same + * binary but with some sort of address randomization technique, thus we need + * to compare just relative addresses. -acme + */ +static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip, + struct map *right_map, u64 right_ip) +{ + struct dso *left_dso = left_map ? left_map->dso : NULL; + struct dso *right_dso = right_map ? right_map->dso : NULL; + + if (left_dso != right_dso) + return left_dso < right_dso ? MATCH_LT : MATCH_GT; + + if (left_ip != right_ip) + return left_ip < right_ip ? MATCH_LT : MATCH_GT; + + return MATCH_EQ; +} + static enum match_result match_chain(struct callchain_cursor_node *node, struct callchain_list *cnode) { - struct symbol *sym = node->sym; - u64 left, right; - - if (callchain_param.key == CCKEY_SRCLINE) { - enum match_result match = match_chain_srcline(node, cnode); + enum match_result match = MATCH_ERROR; + switch (callchain_param.key) { + case CCKEY_SRCLINE: + match = match_chain_strings(cnode->srcline, node->srcline); if (match != MATCH_ERROR) - return match; + break; + /* otherwise fall-back to symbol-based comparison below */ + __fallthrough; + case CCKEY_FUNCTION: + if (node->sym && cnode->ms.sym) { + /* + * Compare inlined frames based on their symbol name + * because different inlined frames will have the same + * symbol start. Otherwise do a faster comparison based + * on the symbol start address. + */ + if (cnode->ms.sym->inlined || node->sym->inlined) { + match = match_chain_strings(cnode->ms.sym->name, + node->sym->name); + if (match != MATCH_ERROR) + break; + } else { + match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start, + node->map, node->sym->start); + break; + } + } + /* otherwise fall-back to IP-based comparison below */ + __fallthrough; + case CCKEY_ADDRESS: + default: + match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip); + break; } - if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) { - left = cnode->ms.sym->start; - right = sym->start; - } else { - left = cnode->ip; - right = node->ip; - } + if (match == MATCH_EQ && node->branch) { + cnode->branch_count++; - if (left == right) { - if (node->branch) { - cnode->branch_count++; + if (node->branch_from) { + /* + * It's "to" of a branch + */ + cnode->brtype_stat.branch_to = true; if (node->branch_flags.predicted) cnode->predicted_count++; @@ -685,15 +744,22 @@ static enum match_result match_chain(struct callchain_cursor_node *node, 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; + cnode->iter_cycles += node->iter_cycles; } - - return MATCH_EQ; } - return left > right ? MATCH_GT : MATCH_LT; + return match; } /* @@ -922,7 +988,7 @@ 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->srcline); list_del(&list->list); map__zput(list->ms.map); free(list); @@ -962,7 +1028,8 @@ 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, u64 iter_cycles, u64 branch_from, + const char *srcline) { struct callchain_cursor_node *node = *cursor->last; @@ -980,12 +1047,14 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->sym = sym; node->branch = branch; node->nr_loop_iter = nr_loop_iter; - node->samples = samples; + node->iter_cycles = iter_cycles; + node->srcline = srcline; if (flags) memcpy(&node->branch_flags, flags, sizeof(struct branch_flags)); + node->branch_from = branch_from; cursor->nr++; cursor->last = &node->next; @@ -998,11 +1067,11 @@ 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 +1080,8 @@ 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); } @@ -1021,10 +1091,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * { al->map = node->map; al->sym = node->sym; - if (node->map) - al->addr = node->map->map_ip(node->map, node->ip); - else - al->addr = node->ip; + al->srcline = node->srcline; + al->addr = node->ip; if (al->sym == NULL) { if (hide_unresolved) @@ -1066,16 +1134,15 @@ char *callchain_list__sym_name(struct callchain_list *cl, int printed; if (cl->ms.sym) { - if (show_srcline && cl->ms.map && !cl->srcline) - cl->srcline = get_srcline(cl->ms.map->dso, - map__rip_2objdump(cl->ms.map, - cl->ip), - cl->ms.sym, false, show_addr); - if (cl->srcline) - printed = scnprintf(bf, bfsize, "%s %s", - cl->ms.sym->name, cl->srcline); + const char *inlined = cl->ms.sym->inlined ? " (inlined)" : ""; + + if (show_srcline && cl->srcline) + printed = scnprintf(bf, bfsize, "%s %s%s", + cl->ms.sym->name, cl->srcline, + inlined); else - printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); + printed = scnprintf(bf, bfsize, "%s%s", + cl->ms.sym->name, inlined); } else printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); @@ -1214,95 +1281,124 @@ 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); - } - - 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); - } + 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, - " (abort:%" PRId64 " %s%s)", - abort_count, cstr, istr); - else - return scnprintf(bf, bfsize, - " (abort:%" PRId64 ")", - abort_count); + if (abort_count) { + printed += count_float_printf(i++, "abort", + abort_count * 100.0 / branch_count, + bf + printed, bfsize - printed, 0.1); } - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 " %s%s)", - predicted_percent, abort_count, cstr, istr); + if (i) + printed += scnprintf(bf + printed, bfsize - printed, ")"); - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 ")", - predicted_percent, abort_count); + return printed; +} + +static int branch_from_str(char *bf, int bfsize, + u64 branch_count, + u64 cycles_count, u64 iter_count, + u64 iter_cycles) +{ + 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) { + printed += count_pri64_printf(i++, "iter", + iter_count, + bf + printed, bfsize - printed); + + printed += count_pri64_printf(i++, "avg_cycles", + iter_cycles / iter_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 iter_cycles, + 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, iter_cycles); + } + + if (!printed) + bf[0] = 0; + + 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 iter_cycles, + 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, iter_cycles, brtype_stat); if (fp) return fprintf(fp, "%s", str); @@ -1310,31 +1406,24 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, return scnprintf(bf, bfsize, "%s", str); } -int callchain_list_counts__printf_value(struct callchain_node *node, - struct callchain_list *clist, +int callchain_list_counts__printf_value(struct callchain_list *clist, FILE *fp, char *bf, int bfsize) { u64 branch_count, predicted_count; u64 abort_count, cycles_count; - u64 iter_count = 0, samples_count = 0; + u64 iter_count, iter_cycles; branch_count = clist->branch_count; predicted_count = clist->predicted_count; abort_count = clist->abort_count; cycles_count = clist->cycles_count; - - if (node) { - struct callchain_list *call; - - list_for_each_entry(call, &node->val, list) { - iter_count += call->iter_count; - samples_count += call->samples_count; - } - } + iter_count = clist->iter_count; + iter_cycles = clist->iter_cycles; return callchain_counts_printf(fp, bf, bfsize, branch_count, predicted_count, abort_count, - cycles_count, iter_count, samples_count); + cycles_count, iter_count, iter_cycles, + &clist->brtype_stat); } static void free_callchain_node(struct callchain_node *node) @@ -1459,7 +1548,9 @@ 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->iter_cycles, + node->branch_from, node->srcline); if (rc) break; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c56c23dbbf72..b79ef2478a57 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_CALLCHAIN_H #define __PERF_CALLCHAIN_H @@ -7,6 +8,7 @@ #include "event.h" #include "map.h" #include "symbol.h" +#include "branch.h" #define HELP_PAD "\t\t\t\t" @@ -118,8 +120,9 @@ struct callchain_list { u64 abort_count; u64 cycles_count; u64 iter_count; - u64 samples_count; - char *srcline; + u64 iter_cycles; + struct branch_type_stat brtype_stat; + const char *srcline; struct list_head list; }; @@ -133,10 +136,12 @@ struct callchain_cursor_node { u64 ip; struct map *map; struct symbol *sym; + const char *srcline; bool branch; struct branch_flags branch_flags; + u64 branch_from; int nr_loop_iter; - int samples; + u64 iter_cycles; struct callchain_cursor_node *next; }; @@ -198,7 +203,8 @@ 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, u64 iter_cycles, u64 branch_from, + const char *srcline); /* Close a cursor writing session. Initialize for the reader */ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) @@ -279,8 +285,7 @@ char *callchain_node__scnprintf_value(struct callchain_node *node, int callchain_node__fprintf_value(struct callchain_node *node, FILE *fp, u64 total); -int callchain_list_counts__printf_value(struct callchain_node *node, - struct callchain_list *clist, +int callchain_list_counts__printf_value(struct callchain_list *clist, FILE *fp, char *bf, int bfsize); void free_callchain(struct callchain_root *root); diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 03347748f3fa..d9ffc1e6eb39 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include "../perf.h" #include <subcmd/parse-options.h> @@ -98,8 +99,10 @@ 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 +113,7 @@ 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 +132,11 @@ 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/cgroup.h b/tools/perf/util/cgroup.h index d91966b97cbd..afafc87e9201 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_H__ #define __CGROUP_H__ diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 4b4f00df58a8..ca0fff6272be 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <sched.h> #include "util.h" diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index 94a5a7d829d5..78216b1015c4 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_CLOEXEC_H #define __PERF_CLOEXEC_H diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index dbbf89b050a5..39e628b8938e 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include "cache.h" #include "config.h" diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 52122bcc3170..22777b1812ee 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_COLOR_H #define __PERF_COLOR_H diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7bc981b6bf29..7798a2cc8a86 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "comm.h" #include "util.h" #include <errno.h> @@ -5,6 +6,7 @@ #include <stdio.h> #include <string.h> #include <linux/refcount.h> +#include "rwsem.h" struct comm_str { char *str; @@ -14,6 +16,7 @@ struct comm_str { /* Should perhaps be moved to struct machine */ static struct rb_root comm_str_root; +static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}; static struct comm_str *comm_str__get(struct comm_str *cs) { @@ -25,7 +28,9 @@ static struct comm_str *comm_str__get(struct comm_str *cs) static void comm_str__put(struct comm_str *cs) { if (cs && refcount_dec_and_test(&cs->refcnt)) { + down_write(&comm_str_lock); rb_erase(&cs->rb_node, &comm_str_root); + up_write(&comm_str_lock); zfree(&cs->str); free(cs); } @@ -50,7 +55,8 @@ static struct comm_str *comm_str__alloc(const char *str) return cs; } -static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +static +struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -81,6 +87,17 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) return new; } +static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +{ + struct comm_str *cs; + + down_write(&comm_str_lock); + cs = __comm_str__findnew(str, root); + up_write(&comm_str_lock); + + return cs; +} + struct comm *comm__new(const char *str, u64 timestamp, bool exec) { struct comm *comm = zalloc(sizeof(*comm)); diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h index 71c9c39340d4..3e5c438fe85e 100644 --- a/tools/perf/util/comm.h +++ b/tools/perf/util/comm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_COMM_H #define __PERF_COMM_H diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index 67fd1bb7c2b7..ecca688a25fb 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_COMPRESS_H #define PERF_COMPRESS_H diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 31a7dea248d0..84eb9393c7db 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * config.c * @@ -19,6 +20,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include <linux/string.h> #include "sane_ctype.h" @@ -433,22 +435,22 @@ 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. */ @@ -699,10 +701,7 @@ struct perf_config_set *perf_config_set__new(void) if (set) { INIT_LIST_HEAD(&set->sections); - if (perf_config_set__init(set) < 0) { - perf_config_set__delete(set); - set = NULL; - } + perf_config_set__init(set); } return set; diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index b6bb11f3f165..baf82bf227ac 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_CONFIG_H #define __PERF_CONFIG_H diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index c4af82ab7808..03032b410c29 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <stdlib.h> #include "evsel.h" diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 34d8baaf558a..0d1050ccc586 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_COUNTS_H #define __PERF_COUNTS_H @@ -12,6 +13,7 @@ struct perf_counts_values { }; u64 values[3]; }; + bool loaded; }; struct perf_counts { diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 37b3bb79ee08..1ccbd3342069 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include <api/fs/fs.h> #include "../perf.h" diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 6b8bff87481d..ed8999d1a640 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index 4b261c2ec0f1..ee4c1e8ed54b 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Sane locale-independent, ASCII ctype. * diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 3149b70799fd..5744c12641a5 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; } @@ -1454,10 +1577,10 @@ int bt_convert__perf2ctf(const char *input, const char *path, struct perf_data_convert_opts *opts) { struct perf_session *session; - struct perf_data_file file = { - .path = input, - .mode = PERF_DATA_MODE_READ, - .force = opts->force, + struct perf_data data = { + .file.path = input, + .mode = PERF_DATA_MODE_READ, + .force = opts->force, }; struct convert c = { .tool = { @@ -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); @@ -1494,7 +1619,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, err = -1; /* perf.data session */ - session = perf_session__new(&file, 0, &c.tool); + session = perf_session__new(&data, 0, &c.tool); if (!session) goto free_writer; @@ -1525,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, fprintf(stderr, "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", - file.path, path); + data.file.path, path); fprintf(stderr, "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples", diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h index 9a3b587f76c1..821674d63c4e 100644 --- a/tools/perf/util/data-convert-bt.h +++ b/tools/perf/util/data-convert-bt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __DATA_CONVERT_BT_H #define __DATA_CONVERT_BT_H #include "data-convert.h" diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h index 5314962fe95b..af90b6076c06 100644 --- a/tools/perf/util/data-convert.h +++ b/tools/perf/util/data-convert.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __DATA_CONVERT_H #define __DATA_CONVERT_H diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e84bbc8ec058..48094fde0a68 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -1,8 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/kernel.h> #include <sys/types.h> #include <sys/stat.h> #include <errno.h> +#include <fcntl.h> #include <unistd.h> #include <string.h> @@ -10,56 +12,66 @@ #include "util.h" #include "debug.h" -static bool check_pipe(struct perf_data_file *file) +#ifndef O_CLOEXEC +#ifdef __sparc__ +#define O_CLOEXEC 0x400000 +#elif defined(__alpha__) || defined(__hppa__) +#define O_CLOEXEC 010000000 +#else +#define O_CLOEXEC 02000000 +#endif +#endif + +static bool check_pipe(struct perf_data *data) { struct stat st; bool is_pipe = false; - int fd = perf_data_file__is_read(file) ? + int fd = perf_data__is_read(data) ? STDIN_FILENO : STDOUT_FILENO; - if (!file->path) { + if (!data->file.path) { if (!fstat(fd, &st) && S_ISFIFO(st.st_mode)) is_pipe = true; } else { - if (!strcmp(file->path, "-")) + if (!strcmp(data->file.path, "-")) is_pipe = true; } if (is_pipe) - file->fd = fd; + data->file.fd = fd; - return file->is_pipe = is_pipe; + return data->is_pipe = is_pipe; } -static int check_backup(struct perf_data_file *file) +static int check_backup(struct perf_data *data) { struct stat st; - if (!stat(file->path, &st) && st.st_size) { + if (!stat(data->file.path, &st) && st.st_size) { /* TODO check errors properly */ char oldname[PATH_MAX]; snprintf(oldname, sizeof(oldname), "%s.old", - file->path); + data->file.path); unlink(oldname); - rename(file->path, oldname); + rename(data->file.path, oldname); } return 0; } -static int open_file_read(struct perf_data_file *file) +static int open_file_read(struct perf_data *data) { struct stat st; int fd; char sbuf[STRERR_BUFSIZE]; - fd = open(file->path, O_RDONLY); + fd = open(data->file.path, O_RDONLY); if (fd < 0) { int err = errno; - pr_err("failed to open %s: %s", file->path, + pr_err("failed to open %s: %s", data->file.path, str_error_r(err, sbuf, sizeof(sbuf))); - if (err == ENOENT && !strcmp(file->path, "perf.data")) + if (err == ENOENT && !strcmp(data->file.path, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); return -err; @@ -68,19 +80,19 @@ static int open_file_read(struct perf_data_file *file) if (fstat(fd, &st) < 0) goto out_close; - if (!file->force && st.st_uid && (st.st_uid != geteuid())) { + if (!data->force && st.st_uid && (st.st_uid != geteuid())) { pr_err("File %s not owned by current user or root (use -f to override)\n", - file->path); + data->file.path); goto out_close; } if (!st.st_size) { - pr_info("zero-sized file (%s), nothing to do!\n", - file->path); + pr_info("zero-sized data (%s), nothing to do!\n", + data->file.path); goto out_close; } - file->size = st.st_size; + data->size = st.st_size; return fd; out_close: @@ -88,48 +100,49 @@ static int open_file_read(struct perf_data_file *file) return -1; } -static int open_file_write(struct perf_data_file *file) +static int open_file_write(struct perf_data *data) { int fd; char sbuf[STRERR_BUFSIZE]; - if (check_backup(file)) + if (check_backup(data)) return -1; - fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC, + S_IRUSR|S_IWUSR); if (fd < 0) - pr_err("failed to open %s : %s\n", file->path, + pr_err("failed to open %s : %s\n", data->file.path, str_error_r(errno, sbuf, sizeof(sbuf))); return fd; } -static int open_file(struct perf_data_file *file) +static int open_file(struct perf_data *data) { int fd; - fd = perf_data_file__is_read(file) ? - open_file_read(file) : open_file_write(file); + fd = perf_data__is_read(data) ? + open_file_read(data) : open_file_write(data); - file->fd = fd; + data->file.fd = fd; return fd < 0 ? -1 : 0; } -int perf_data_file__open(struct perf_data_file *file) +int perf_data__open(struct perf_data *data) { - if (check_pipe(file)) + if (check_pipe(data)) return 0; - if (!file->path) - file->path = "perf.data"; + if (!data->file.path) + data->file.path = "perf.data"; - return open_file(file); + return open_file(data); } -void perf_data_file__close(struct perf_data_file *file) +void perf_data__close(struct perf_data *data) { - close(file->fd); + close(data->file.fd); } ssize_t perf_data_file__write(struct perf_data_file *file, @@ -138,42 +151,48 @@ ssize_t perf_data_file__write(struct perf_data_file *file, return writen(file->fd, buf, size); } -int perf_data_file__switch(struct perf_data_file *file, +ssize_t perf_data__write(struct perf_data *data, + void *buf, size_t size) +{ + return perf_data_file__write(&data->file, buf, size); +} + +int perf_data__switch(struct perf_data *data, const char *postfix, size_t pos, bool at_exit) { char *new_filepath; int ret; - if (check_pipe(file)) + if (check_pipe(data)) return -EINVAL; - if (perf_data_file__is_read(file)) + if (perf_data__is_read(data)) return -EINVAL; - if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0) + if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0) return -ENOMEM; /* * Only fire a warning, don't return error, continue fill * original file. */ - if (rename(file->path, new_filepath)) - pr_warning("Failed to rename %s to %s\n", file->path, new_filepath); + if (rename(data->file.path, new_filepath)) + pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath); if (!at_exit) { - close(file->fd); - ret = perf_data_file__open(file); + close(data->file.fd); + ret = perf_data__open(data); if (ret < 0) goto out; - if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) { + if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) { ret = -errno; pr_debug("Failed to lseek to %zu: %s", pos, strerror(errno)); goto out; } } - ret = file->fd; + ret = data->file.fd; out: free(new_filepath); return ret; diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index ae510ce16cb1..4828f7feea89 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_DATA_H #define __PERF_DATA_H @@ -9,51 +10,57 @@ enum perf_data_mode { }; struct perf_data_file { - const char *path; - int fd; + const char *path; + int fd; +}; + +struct perf_data { + struct perf_data_file file; bool is_pipe; bool force; unsigned long size; enum perf_data_mode mode; }; -static inline bool perf_data_file__is_read(struct perf_data_file *file) +static inline bool perf_data__is_read(struct perf_data *data) { - return file->mode == PERF_DATA_MODE_READ; + return data->mode == PERF_DATA_MODE_READ; } -static inline bool perf_data_file__is_write(struct perf_data_file *file) +static inline bool perf_data__is_write(struct perf_data *data) { - return file->mode == PERF_DATA_MODE_WRITE; + return data->mode == PERF_DATA_MODE_WRITE; } -static inline int perf_data_file__is_pipe(struct perf_data_file *file) +static inline int perf_data__is_pipe(struct perf_data *data) { - return file->is_pipe; + return data->is_pipe; } -static inline int perf_data_file__fd(struct perf_data_file *file) +static inline int perf_data__fd(struct perf_data *data) { - return file->fd; + return data->file.fd; } -static inline unsigned long perf_data_file__size(struct perf_data_file *file) +static inline unsigned long perf_data__size(struct perf_data *data) { - return file->size; + return data->size; } -int perf_data_file__open(struct perf_data_file *file); -void perf_data_file__close(struct perf_data_file *file); +int perf_data__open(struct perf_data *data); +void perf_data__close(struct perf_data *data); +ssize_t perf_data__write(struct perf_data *data, + void *buf, size_t size); ssize_t perf_data_file__write(struct perf_data_file *file, void *buf, size_t size); /* * If at_exit is set, only rename current perf.data to - * perf.data.<postfix>, continue write on original file. + * perf.data.<postfix>, continue write on original data. * Set at_exit when flushing the last output. * * Return value is fd of new output. */ -int perf_data_file__switch(struct perf_data_file *file, +int perf_data__switch(struct perf_data *data, const char *postfix, size_t pos, bool at_exit); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index a5b3777ffee6..f3a71db83947 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* For general debugging purposes */ #include "../perf.h" @@ -111,50 +112,53 @@ int dump_printf(const char *fmt, ...) return ret; } -static void trace_event_printer(enum binary_printer_ops op, - unsigned int val, void *extra) +static int trace_event_printer(enum binary_printer_ops op, + unsigned int val, void *extra, FILE *fp) { const char *color = PERF_COLOR_BLUE; union perf_event *event = (union perf_event *)extra; unsigned char ch = (unsigned char)val; + int printed = 0; switch (op) { case BINARY_PRINT_DATA_BEGIN: - printf("."); - color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n", - event->header.size); + printed += fprintf(fp, "."); + printed += color_fprintf(fp, color, "\n. ... raw event: size %d bytes\n", + event->header.size); break; case BINARY_PRINT_LINE_BEGIN: - printf("."); + printed += fprintf(fp, "."); break; case BINARY_PRINT_ADDR: - color_fprintf(stdout, color, " %04x: ", val); + printed += color_fprintf(fp, color, " %04x: ", val); break; case BINARY_PRINT_NUM_DATA: - color_fprintf(stdout, color, " %02x", val); + printed += color_fprintf(fp, color, " %02x", val); break; case BINARY_PRINT_NUM_PAD: - color_fprintf(stdout, color, " "); + printed += color_fprintf(fp, color, " "); break; case BINARY_PRINT_SEP: - color_fprintf(stdout, color, " "); + printed += color_fprintf(fp, color, " "); break; case BINARY_PRINT_CHAR_DATA: - color_fprintf(stdout, color, "%c", + printed += color_fprintf(fp, color, "%c", isprint(ch) ? ch : '.'); break; case BINARY_PRINT_CHAR_PAD: - color_fprintf(stdout, color, " "); + printed += color_fprintf(fp, color, " "); break; case BINARY_PRINT_LINE_END: - color_fprintf(stdout, color, "\n"); + printed += color_fprintf(fp, color, "\n"); break; case BINARY_PRINT_DATA_END: - printf("\n"); + printed += fprintf(fp, "\n"); break; default: break; } + + return printed; } void trace_event(union perf_event *event) diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index c818bdb1c1ab..77445dfc5c7d 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* For debugging general purposes */ #ifndef __PERF_DEBUG_H #define __PERF_DEBUG_H diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index cb66d334f532..e4c486756053 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <sys/types.h> #include <stdio.h> #include <string.h> diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h index a981c1f968fe..f936c8eabe5d 100644 --- a/tools/perf/util/demangle-java.h +++ b/tools/perf/util/demangle-java.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_DEMANGLE_JAVA #define __PERF_DEMANGLE_JAVA 1 /* diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c index f9dafa888c06..423afbbd386b 100644 --- a/tools/perf/util/demangle-rust.c +++ b/tools/perf/util/demangle-rust.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <string.h> #include "util.h" #include "debug.h" diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h index 7b41ead7e0dd..2fca618b1aa5 100644 --- a/tools/perf/util/demangle-rust.h +++ b/tools/perf/util/demangle-rust.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_DEMANGLE_RUST #define __PERF_DEMANGLE_RUST 1 diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 4e7ab611377a..d5b6f7f5baff 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/bug.h> #include <linux/kernel.h> #include <sys/time.h> @@ -6,9 +7,11 @@ #include <sys/stat.h> #include <unistd.h> #include <errno.h> +#include <fcntl.h> #include "compress.h" #include "path.h" #include "symbol.h" +#include "srcline.h" #include "dso.h" #include "machine.h" #include "auxtrace.h" @@ -32,6 +35,7 @@ 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 +101,12 @@ 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 +513,14 @@ 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); @@ -1187,6 +1203,8 @@ struct dso *dso__new(const char *name) for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; dso->data.cache = RB_ROOT; + dso->inlined_nodes = RB_ROOT; + dso->srclines = RB_ROOT; dso->data.fd = -1; dso->data.status = DSO_DATA_STATUS_UNKNOWN; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; @@ -1218,6 +1236,10 @@ void dso__delete(struct dso *dso) if (!RB_EMPTY_NODE(&dso->rb_node)) pr_err("DSO %s is still in rbtree when being deleted!\n", dso->long_name); + + /* free inlines first, as they reference symbols */ + inlines__tree_delete(&dso->inlined_nodes); + srcline__tree_delete(&dso->srclines); for (i = 0; i < MAP__NR_TYPES; ++i) symbols__delete(&dso->symbols[i]); @@ -1236,6 +1258,7 @@ 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 +1324,7 @@ 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 +1333,13 @@ 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; @@ -1348,9 +1374,9 @@ void __dsos__add(struct dsos *dsos, struct dso *dso) void dsos__add(struct dsos *dsos, struct dso *dso) { - pthread_rwlock_wrlock(&dsos->lock); + down_write(&dsos->lock); __dsos__add(dsos, dso); - pthread_rwlock_unlock(&dsos->lock); + up_write(&dsos->lock); } struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) @@ -1369,9 +1395,9 @@ struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short) { struct dso *dso; - pthread_rwlock_rdlock(&dsos->lock); + down_read(&dsos->lock); dso = __dsos__find(dsos, name, cmp_short); - pthread_rwlock_unlock(&dsos->lock); + up_read(&dsos->lock); return dso; } @@ -1398,9 +1424,9 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name) struct dso *dsos__findnew(struct dsos *dsos, const char *name) { struct dso *dso; - pthread_rwlock_wrlock(&dsos->lock); + down_write(&dsos->lock); dso = dso__get(__dsos__findnew(dsos, name)); - pthread_rwlock_unlock(&dsos->lock); + up_write(&dsos->lock); return dso; } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bd061ba7b47c..c229dbe0277a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_DSO #define __PERF_DSO @@ -6,10 +7,11 @@ #include <linux/rbtree.h> #include <sys/types.h> #include <stdbool.h> -#include <pthread.h> +#include "rwsem.h" #include <linux/types.h> #include <linux/bitops.h> #include "map.h" +#include "namespaces.h" #include "build-id.h" enum dso_binary_type { @@ -20,6 +22,7 @@ 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, @@ -127,7 +130,7 @@ struct dso_cache { struct dsos { struct list_head head; struct rb_root root; /* rbtree root sorted by long name */ - pthread_rwlock_t lock; + struct rw_semaphore lock; }; struct auxtrace_cache; @@ -139,6 +142,8 @@ struct dso { struct rb_root *root; /* root of rbtree that rb_node is in */ struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; + struct rb_root inlined_nodes; + struct rb_root srclines; struct { u64 addr; struct symbol *symbol; @@ -187,6 +192,7 @@ struct dso { void *priv; u64 db_id; }; + struct nsinfo *nsinfo; refcount_t refcnt; char name[0]; }; diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c index ffbdb19f05d0..10988d3de7ce 100644 --- a/tools/perf/util/dump-insn.c +++ b/tools/perf/util/dump-insn.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include "dump-insn.h" diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h index 90fb115981cf..0e06280a8860 100644 --- a/tools/perf/util/dump-insn.h +++ b/tools/perf/util/dump-insn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_DUMP_INSN_H #define __PERF_DUMP_INSN_H 1 diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index c708395b3cb6..db55eddce8cd 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. * diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9e21538c42ae..6276b340f893 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "cpumap.h" #include "env.h" #include "util.h" diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index b164dfd2dcbf..1eb35b190b34 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_ENV_H #define __PERF_ENV_H diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dc5c3bb69d73..97a8ef9980db 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,5 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 #include <dirent.h> #include <errno.h> +#include <fcntl.h> #include <inttypes.h> #include <linux/kernel.h> #include <linux/types.h> @@ -57,6 +59,7 @@ 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[] = { @@ -676,21 +679,21 @@ out: return err; } -int perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data, - unsigned int proc_map_timeout) +static int __perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + unsigned int proc_map_timeout, + struct dirent **dirent, + int start, + int num) { - DIR *proc; - char proc_path[PATH_MAX]; - struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; int err = -1; - - if (machine__is_default_guest(machine)) - return 0; + char *end; + pid_t pid; + int i; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) @@ -710,31 +713,25 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (namespaces_event == NULL) goto out_free_fork; - snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); - proc = opendir(proc_path); - - if (proc == NULL) - goto out_free_namespaces; - - while ((dirent = readdir(proc)) != NULL) { - char *end; - pid_t pid = strtol(dirent->d_name, &end, 10); + for (i = start; i < start + num; i++) { + if (!isdigit(dirent[i]->d_name[0])) + continue; - if (*end) /* only interested in proper numerical dirents */ + pid = (pid_t)strtol(dirent[i]->d_name, &end, 10); + /* only interested in proper numerical dirents */ + if (*end) continue; /* - * We may race with exiting thread, so don't stop just because - * one thread couldn't be synthesized. - */ + * We may race with exiting thread, so don't stop just because + * one thread couldn't be synthesized. + */ __event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, pid, 1, process, tool, machine, mmap_data, proc_map_timeout); } - err = 0; - closedir(proc); -out_free_namespaces: + free(namespaces_event); out_free_fork: free(fork_event); @@ -746,6 +743,118 @@ out: return err; } +struct synthesize_threads_arg { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + bool mmap_data; + unsigned int proc_map_timeout; + struct dirent **dirent; + int num; + int start; +}; + +static void *synthesize_threads_worker(void *arg) +{ + struct synthesize_threads_arg *args = arg; + + __perf_event__synthesize_threads(args->tool, args->process, + args->machine, args->mmap_data, + args->proc_map_timeout, args->dirent, + args->start, args->num); + return NULL; +} + +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) +{ + struct synthesize_threads_arg *args = NULL; + pthread_t *synthesize_threads = NULL; + char proc_path[PATH_MAX]; + struct dirent **dirent; + int num_per_thread; + int m, n, i, j; + int thread_nr; + int base = 0; + int err = -1; + + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); + n = scandir(proc_path, &dirent, 0, alphasort); + if (n < 0) + return err; + + if (nr_threads_synthesize == UINT_MAX) + thread_nr = sysconf(_SC_NPROCESSORS_ONLN); + else + thread_nr = nr_threads_synthesize; + + if (thread_nr <= 1) { + err = __perf_event__synthesize_threads(tool, process, + machine, mmap_data, + proc_map_timeout, + dirent, base, n); + goto free_dirent; + } + if (thread_nr > n) + thread_nr = n; + + synthesize_threads = calloc(sizeof(pthread_t), thread_nr); + if (synthesize_threads == NULL) + goto free_dirent; + + args = calloc(sizeof(*args), thread_nr); + if (args == NULL) + goto free_threads; + + num_per_thread = n / thread_nr; + m = n % thread_nr; + for (i = 0; i < thread_nr; i++) { + args[i].tool = tool; + args[i].process = process; + args[i].machine = machine; + args[i].mmap_data = mmap_data; + args[i].proc_map_timeout = proc_map_timeout; + args[i].dirent = dirent; + } + for (i = 0; i < m; i++) { + args[i].num = num_per_thread + 1; + args[i].start = i * args[i].num; + } + if (i != 0) + base = args[i-1].start + args[i-1].num; + for (j = i; j < thread_nr; j++) { + args[j].num = num_per_thread; + args[j].start = base + (j - i) * args[i].num; + } + + for (i = 0; i < thread_nr; i++) { + if (pthread_create(&synthesize_threads[i], NULL, + synthesize_threads_worker, &args[i])) + goto out_join; + } + err = 0; +out_join: + for (i = 0; i < thread_nr; i++) + pthread_join(synthesize_threads[i], NULL); + free(args); +free_threads: + free(synthesize_threads); +free_dirent: + for (i = 0; i < n; i++) + free(dirent[i]); + free(dirent); + + return err; +} + struct process_symbol_args { const char *name; u64 start; @@ -1496,6 +1605,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, al->sym = NULL; al->cpu = sample->cpu; al->socket = -1; + al->srcline = NULL; if (al->cpu >= 0) { struct perf_env *env = machine->env; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 9967c87af7a6..1ae95efbfb95 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_RECORD_H #define __PERF_RECORD_H @@ -142,7 +143,8 @@ 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 { @@ -199,6 +201,7 @@ struct perf_sample { u32 cpu; u32 raw_size; u64 data_src; + u64 phys_addr; u32 flags; u16 insn_len; u8 cpumode; @@ -244,6 +247,7 @@ 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 +613,12 @@ 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 +649,7 @@ 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); @@ -670,7 +681,8 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool, int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, - unsigned int proc_map_timeout); + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize); int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 46c0faf6c502..c6c891e154a6 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -33,9 +33,6 @@ #include <linux/log2.h> #include <linux/err.h> -static void perf_mmap__munmap(struct perf_mmap *map); -static void perf_mmap__put(struct perf_mmap *map); - #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) @@ -242,9 +239,9 @@ 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; @@ -704,129 +701,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist) return perf_evlist__set_paused(evlist, false); } -/* When check_messup is true, 'end' must points to a good entry */ -static union perf_event * -perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start, - u64 end, u64 *prev) -{ - unsigned char *data = md->base + page_size; - union perf_event *event = NULL; - int diff = end - start; - - if (check_messup) { - /* - * If we're further behind than half the buffer, there's a chance - * the writer will bite our tail and mess up the samples under us. - * - * If we somehow ended up ahead of the 'end', we got messed up. - * - * In either case, truncate and restart at 'end'. - */ - if (diff > md->mask / 2 || diff < 0) { - fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); - - /* - * 'end' points to a known good entry, start there. - */ - start = end; - diff = 0; - } - } - - if (diff >= (int)sizeof(event->header)) { - size_t size; - - event = (union perf_event *)&data[start & md->mask]; - size = event->header.size; - - if (size < sizeof(event->header) || diff < (int)size) { - event = NULL; - goto broken_event; - } - - /* - * Event straddles the mmap boundary -- header should always - * be inside due to u64 alignment of output. - */ - if ((start & md->mask) + size != ((start + size) & md->mask)) { - unsigned int offset = start; - unsigned int len = min(sizeof(*event), size), cpy; - void *dst = md->event_copy; - - do { - cpy = min(md->mask + 1 - (offset & md->mask), len); - memcpy(dst, &data[offset & md->mask], cpy); - offset += cpy; - dst += cpy; - len -= cpy; - } while (len); - - event = (union perf_event *) md->event_copy; - } - - start += size; - } - -broken_event: - if (prev) - *prev = start; - - return event; -} - -union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup) -{ - u64 head; - u64 old = md->prev; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&md->refcnt)) - return NULL; - - head = perf_mmap__read_head(md); - - return perf_mmap__read(md, check_messup, old, head, &md->prev); -} - -union perf_event * -perf_mmap__read_backward(struct perf_mmap *md) -{ - u64 head, end; - u64 start = md->prev; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&md->refcnt)) - return NULL; - - head = perf_mmap__read_head(md); - if (!head) - return NULL; - - /* - * 'head' pointer starts from 0. Kernel minus sizeof(record) form - * it each time when kernel writes to it, so in fact 'head' is - * negative. 'end' pointer is made manually by adding the size of - * the ring buffer to 'head' pointer, means the validate data can - * read is the whole ring buffer. If 'end' is positive, the ring - * buffer has not fully filled, so we must adjust 'end' to 0. - * - * However, since both 'head' and 'end' is unsigned, we can't - * simply compare 'end' against 0. Here we compare '-head' and - * the size of the ring buffer, where -head is the number of bytes - * kernel write to the ring buffer. - */ - if (-head < (u64)(md->mask + 1)) - end = 0; - else - end = head + md->mask + 1; - - return perf_mmap__read(md, false, start, end, &md->prev); -} - union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; @@ -857,96 +731,16 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) return perf_evlist__mmap_read_forward(evlist, idx); } -void perf_mmap__read_catchup(struct perf_mmap *md) -{ - u64 head; - - if (!refcount_read(&md->refcnt)) - return; - - head = perf_mmap__read_head(md); - md->prev = head; -} - void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) { perf_mmap__read_catchup(&evlist->mmap[idx]); } -static bool perf_mmap__empty(struct perf_mmap *md) -{ - return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base; -} - -static void perf_mmap__get(struct perf_mmap *map) -{ - refcount_inc(&map->refcnt); -} - -static void perf_mmap__put(struct perf_mmap *md) -{ - BUG_ON(md->base && refcount_read(&md->refcnt) == 0); - - if (refcount_dec_and_test(&md->refcnt)) - perf_mmap__munmap(md); -} - -void perf_mmap__consume(struct perf_mmap *md, bool overwrite) -{ - if (!overwrite) { - u64 old = md->prev; - - perf_mmap__write_tail(md, old); - } - - if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md)) - perf_mmap__put(md); -} - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite); } -int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, - struct auxtrace_mmap_params *mp __maybe_unused, - void *userpg __maybe_unused, - int fd __maybe_unused) -{ - return 0; -} - -void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused) -{ -} - -void __weak auxtrace_mmap_params__init( - struct auxtrace_mmap_params *mp __maybe_unused, - off_t auxtrace_offset __maybe_unused, - unsigned int auxtrace_pages __maybe_unused, - bool auxtrace_overwrite __maybe_unused) -{ -} - -void __weak auxtrace_mmap_params__set_idx( - struct auxtrace_mmap_params *mp __maybe_unused, - struct perf_evlist *evlist __maybe_unused, - int idx __maybe_unused, - bool per_cpu __maybe_unused) -{ -} - -static void perf_mmap__munmap(struct perf_mmap *map) -{ - if (map->base != NULL) { - munmap(map->base, perf_mmap__mmap_len(map)); - map->base = NULL; - map->fd = -1; - refcount_set(&map->refcnt, 0); - } - auxtrace_mmap__munmap(&map->auxtrace_mmap); -} - static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) { int i; @@ -995,48 +789,6 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) return map; } -struct mmap_params { - int prot; - int mask; - struct auxtrace_mmap_params auxtrace_mp; -}; - -static int perf_mmap__mmap(struct perf_mmap *map, - struct mmap_params *mp, int fd) -{ - /* - * The last one will be done at perf_evlist__mmap_consume(), so that we - * make sure we don't prevent tools from consuming every last event in - * the ring buffer. - * - * I.e. we can get the POLLHUP meaning that the fd doesn't exist - * anymore, but the last events for it are still in the ring buffer, - * waiting to be consumed. - * - * Tools can chose to ignore this at their own discretion, but the - * evlist layer can't just drop it when filtering events in - * perf_evlist__filter_pollfd(). - */ - refcount_set(&map->refcnt, 2); - map->prev = 0; - map->mask = mp->mask; - map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, - MAP_SHARED, fd, 0); - if (map->base == MAP_FAILED) { - pr_debug2("failed to mmap perf event ring buffer, error %d\n", - errno); - map->base = NULL; - return -1; - } - map->fd = fd; - - if (auxtrace_mmap__mmap(&map->auxtrace_mmap, - &mp->auxtrace_mp, map->base, fd)) - return -1; - - return 0; -} - static bool perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, struct perf_evsel *evsel) @@ -1419,8 +1171,6 @@ 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 +1180,7 @@ 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 +1373,9 @@ 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..e72ae64c11ac 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 @@ -6,12 +7,13 @@ #include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> +#include <fcntl.h> #include <stdio.h> #include "../perf.h" #include "event.h" #include "evsel.h" +#include "mmap.h" #include "util.h" -#include "auxtrace.h" #include <signal.h> #include <unistd.h> @@ -23,55 +25,6 @@ struct record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) -/** - * struct perf_mmap - perf's ring buffer mmap details - * - * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this - */ -struct perf_mmap { - void *base; - int mask; - int fd; - refcount_t refcnt; - u64 prev; - struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); -}; - -static inline size_t -perf_mmap__mmap_len(struct perf_mmap *map) -{ - return map->mask + 1 + page_size; -} - -/* - * State machine of bkw_mmap_state: - * - * .________________(forbid)_____________. - * | V - * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY - * ^ ^ | ^ | - * | |__(forbid)____/ |___(forbid)___/| - * | | - * \_________________(3)_______________/ - * - * NOTREADY : Backward ring buffers are not ready - * RUNNING : Backward ring buffers are recording - * DATA_PENDING : We are required to collect data from backward ring buffers - * EMPTY : We have collected data from backward ring buffers. - * - * (0): Setup backward ring buffer - * (1): Pause ring buffers for reading - * (2): Read from ring buffers - * (3): Resume ring buffers for recording - */ -enum bkw_mmap_state { - BKW_MMAP_NOTREADY, - BKW_MMAP_RUNNING, - BKW_MMAP_DATA_PENDING, - BKW_MMAP_EMPTY, -}; - struct perf_evlist { struct list_head entries; struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; @@ -115,7 +68,14 @@ 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); @@ -169,12 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state); -union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup); -union perf_event *perf_mmap__read_backward(struct perf_mmap *map); - -void perf_mmap__read_catchup(struct perf_mmap *md); -void perf_mmap__consume(struct perf_mmap *md, bool overwrite); - union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, @@ -258,6 +212,11 @@ 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); @@ -273,25 +232,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); -static inline u64 perf_mmap__read_head(struct perf_mmap *mm) -{ - struct perf_event_mmap_page *pc = mm->base; - u64 head = ACCESS_ONCE(pc->data_head); - rmb(); - return head; -} - -static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) -{ - struct perf_event_mmap_page *pc = md->base; - - /* - * ensure all reads are done before we write the tail out. - */ - mb(); - pc->data_tail = tail; -} - bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str); void perf_evlist__to_front(struct perf_evlist *evlist, struct perf_evsel *move_evsel); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 413f74df08de..f894893c203d 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) { } @@ -268,16 +271,24 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } -struct perf_evsel *perf_evsel__new_cycles(void) +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + +struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; 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 +303,7 @@ 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; @@ -672,7 +683,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel, if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); perf_evsel__set_sample_bit(evsel, STACK_USER); - attr->sample_regs_user = PERF_REGS_MASK; + attr->sample_regs_user |= PERF_REGS_MASK; attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user = 1; } else { @@ -896,8 +907,13 @@ 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); @@ -920,6 +936,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__set_sample_bit(evsel, REGS_INTR); } + if (opts->sample_user_regs) { + attr->sample_regs_user |= opts->sample_user_regs; + perf_evsel__set_sample_bit(evsel, REGS_USER); + } + if (target__has_cpu(&opts->target) || opts->sample_cpu) perf_evsel__set_sample_bit(evsel, CPU); @@ -944,6 +965,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (opts->sample_address) perf_evsel__set_sample_bit(evsel, DATA_SRC); + if (opts->sample_phys_addr) + perf_evsel__set_sample_bit(evsel, PHYS_ADDR); + if (opts->no_buffering) { attr->watermark = 0; attr->wakeup_events = 1; @@ -1045,16 +1069,13 @@ 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 +1087,9 @@ 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 +1136,14 @@ 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 +1193,12 @@ 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 +1267,148 @@ 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) { @@ -1338,7 +1477,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), - bit_name(WEIGHT), + bit_name(WEIGHT), bit_name(PHYS_ADDR), { .name = NULL, } }; #undef bit_name @@ -1545,6 +1684,8 @@ 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 +1710,8 @@ 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 +1807,45 @@ 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 +1859,12 @@ 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); } @@ -2062,6 +2219,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } + data->phys_addr = 0; + if (type & PERF_SAMPLE_PHYS_ADDR) { + data->phys_addr = *array; + array++; + } + return 0; } @@ -2167,6 +2330,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } } + if (type & PERF_SAMPLE_PHYS_ADDR) + result += sizeof(u64); + return result; } @@ -2356,6 +2522,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, } } + if (type & PERF_SAMPLE_PHYS_ADDR) { + *array = sample->phys_addr; + array++; + } + return 0; } @@ -2535,7 +2706,9 @@ 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 +2783,10 @@ 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..9277df96ffda 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_EVSEL_H #define __PERF_EVSEL_H 1 @@ -68,6 +69,8 @@ struct perf_evsel_config_term { } val; }; +struct perf_stat_evsel; + /** struct perf_evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. @@ -101,6 +104,7 @@ struct perf_evsel { const char *unit; struct event_format *tp_format; off_t id_offset; + struct perf_stat_evsel *stats; void *priv; u64 db_id; struct cgroup_sel *cgrp; @@ -131,11 +135,13 @@ struct perf_evsel { bool cmdline_group_boundary; struct list_head config_terms; int bpf_fd; + bool auto_merge_stats; bool merged_stat; const char * metric_expr; const char * metric_name; struct perf_evsel **metric_events; bool collect_stat; + bool weak_group; }; union u64_swap { @@ -185,7 +191,7 @@ 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 +232,7 @@ 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 +252,7 @@ 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 +262,7 @@ 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 +304,8 @@ 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 +443,6 @@ 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/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 583f3a602506..06dfb027879d 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <inttypes.h> #include <stdio.h> #include <stdbool.h> @@ -157,7 +158,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, } } - if (print_dso) { + if (print_dso && (!node->sym || !node->sym->inlined)) { printed += fprintf(fp, " ("); printed += map__fprintf_dsoname(node->map, fp); printed += fprintf(fp, ")"); @@ -166,41 +167,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_srcline) printed += map__fprintf_srcline(node->map, addr, "\n ", fp); + if (node->sym && node->sym->inlined) + printed += fprintf(fp, " (inlined)"); + if (!print_oneline) printed += fprintf(fp, "\n"); - if (symbol_conf.inline_name && node->map) { - struct inline_node *inode; - - addr = map__rip_2objdump(node->map, node->ip), - inode = dso__parse_addr_inlines(node->map->dso, addr); - - if (inode) { - struct inline_list *ilist; - - list_for_each_entry(ilist, &inode->val, list) { - if (print_arrow) - printed += fprintf(fp, " <-"); - - /* IP is same, just skip it */ - if (print_ip) - printed += fprintf(fp, "%c%16s", - s, ""); - if (print_sym) - printed += fprintf(fp, " %s", - ilist->funcname); - if (print_srcline) - printed += fprintf(fp, "\n %s:%d", - ilist->filename, - ilist->line_nr); - if (!print_oneline) - printed += fprintf(fp, "\n"); - } - - inline_node__delete(inode); - } - } - if (symbol_conf.bt_stop_list && node->sym && strlist__has_entry(symbol_conf.bt_stop_list, diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 9c2760a1a96e..046160831f90 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -1,7 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #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/find-vdso-map.c b/tools/perf/util/find-vdso-map.c index 95ef1cffc056..d7823e3508fc 100644 --- a/tools/perf/util/find-vdso-map.c +++ b/tools/perf/util/find-vdso-map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 static int find_vdso_map(void **start, void **end) { FILE *maps; diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index 2424bd9862a3..de322d51c7fe 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __GENELF_H__ #define __GENELF_H__ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 0ac2037c970c..9bbcec4e3365 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 echo "/* Automatically generated by $0 */ struct cmdname_help diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h index 116debe7a995..f36c7e31780a 100644 --- a/tools/perf/util/group.h +++ b/tools/perf/util/group.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef GROUP_H #define GROUP_H 1 diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 76ed7d03e500..7c0e9d587bfa 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> #include "util.h" @@ -12,6 +13,7 @@ #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 +36,7 @@ #include "data.h" #include <api/fs/fs.h> #include "asm/bug.h" +#include "tool.h" #include "sane_ctype.h" @@ -59,6 +62,15 @@ 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 +86,60 @@ 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 +147,8 @@ 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 +157,80 @@ 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 +243,30 @@ 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 +276,7 @@ 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 +286,10 @@ 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 +299,10 @@ 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 +312,16 @@ 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 +371,22 @@ 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 +394,7 @@ 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 +409,14 @@ 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 +428,7 @@ 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 +436,12 @@ 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 +452,27 @@ 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 +490,16 @@ 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 +652,8 @@ 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 +663,21 @@ 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 +687,11 @@ 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 +703,8 @@ 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 +724,7 @@ 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 +732,7 @@ 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 +762,11 @@ 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 +784,7 @@ 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 +792,8 @@ 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 +820,17 @@ 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 +853,40 @@ 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 +902,14 @@ 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 +920,15 @@ 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 +945,7 @@ 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 +957,27 @@ 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 +1124,8 @@ 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 +1137,11 @@ 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 +1149,7 @@ 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 +1160,7 @@ 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 +1176,62 @@ 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 +1272,21 @@ 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 +1308,23 @@ 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 +1336,8 @@ 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 +1356,17 @@ 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 +1391,21 @@ 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 +1416,51 @@ 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 +1483,13 @@ 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 +1662,61 @@ 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 +1753,42 @@ 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->data->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->data->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 +1797,7 @@ 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 +1806,8 @@ 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 +1816,29 @@ 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 +1850,14 @@ 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 +1873,20 @@ 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 +1905,16 @@ 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 +1923,16 @@ 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 +1942,8 @@ 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 +1951,30 @@ 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 +1985,12 @@ 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 +1998,7 @@ 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 +2010,10 @@ 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 +2024,21 @@ 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 +2082,34 @@ 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 +2118,8 @@ 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 +2127,9 @@ 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 +2140,8 @@ 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 +2149,62 @@ 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 +2217,7 @@ 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 +2231,13 @@ 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); @@ -2273,7 +2249,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) { struct header_print_data hd; struct perf_header *header = &session->header; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); struct stat st; int ret, bit; @@ -2289,7 +2265,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); - if (session->file->is_pipe) + if (session->data->is_pipe) return 0; fprintf(fp, "# missing features: "); @@ -2302,29 +2278,32 @@ 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 +2313,18 @@ 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 +2339,7 @@ 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 +2348,7 @@ 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 +2358,17 @@ 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 +2385,23 @@ 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 +2411,7 @@ 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 +2446,7 @@ 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 +2700,13 @@ 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 +2721,17 @@ 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 +2746,7 @@ 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; @@ -2757,7 +2758,7 @@ static int perf_header__read_pipe(struct perf_session *session) struct perf_pipe_file_header f_header; if (perf_file_header__read_pipe(&f_header, header, - perf_data_file__fd(session->file), + perf_data__fd(session->data), session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; @@ -2860,13 +2861,13 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, int perf_session__read_header(struct perf_session *session) { - struct perf_data_file *file = session->file; + struct perf_data *data = session->data; struct perf_header *header = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; - int fd = perf_data_file__fd(file); + int fd = perf_data__fd(data); session->evlist = perf_evlist__new(); if (session->evlist == NULL) @@ -2874,7 +2875,7 @@ int perf_session__read_header(struct perf_session *session) session->evlist->env = &header->env; session->machines.host.env = &header->env; - if (perf_data_file__is_pipe(file)) + if (perf_data__is_pipe(data)) return perf_header__read_pipe(session); if (perf_file_header__read(&f_header, header, fd) < 0) @@ -2889,7 +2890,7 @@ int perf_session__read_header(struct perf_session *session) if (f_header.data.size == 0) { pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n" "Was the 'perf record' command properly terminated?\n", - file->path); + data->file.path); } nr_attrs = f_header.attrs.size / f_header.attr_size; @@ -2995,6 +2996,103 @@ 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 +3351,7 @@ 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 +3386,9 @@ 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; } @@ -3297,7 +3398,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused, struct perf_session *session) { ssize_t size_read, padding, size = event->tracing_data.size; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); off_t offset = lseek(fd, 0, SEEK_CUR); char buf[BUFSIZ]; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d30109b421ee..29ccbfdf8724 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H @@ -101,6 +102,15 @@ 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 +154,12 @@ 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/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 15b95300d7f3..4f07a5ba5030 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "cache.h" #include "config.h" #include <poll.h> diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index cf0186a088c1..b6140950301e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include "build-id.h" #include "hist.h" @@ -167,6 +168,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen = unresolved_col_width + 4 + 2; hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + + hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR, + unresolved_col_width + 4 + 2); + } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -592,6 +597,7 @@ __hists__add_entry(struct hists *hists, .map = al->map, .sym = al->sym, }, + .srcline = al->srcline ? strdup(al->srcline) : NULL, .socket = al->socket, .cpu = al->cpu, .cpumode = al->cpumode, @@ -749,12 +755,9 @@ 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; } @@ -949,6 +952,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .map = al->map, .sym = al->sym, }, + .srcline = al->srcline ? strdup(al->srcline) : NULL, .parent = iter->parent, .raw_data = sample->raw_data, .raw_size = sample->raw_size, @@ -1140,11 +1144,6 @@ void hist_entry__delete(struct hist_entry *he) zfree(&he->mem_info); } - if (he->inline_node) { - inline_node__delete(he->inline_node); - he->inline_node = NULL; - } - zfree(&he->stat_acc); free_srcline(he->srcline); if (he->srcfile && he->srcfile[0]) @@ -1762,6 +1761,8 @@ 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/hist.h b/tools/perf/util/hist.h index ee3670a388df..f6630cb95eff 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_HIST_H #define __PERF_HIST_H @@ -47,6 +48,7 @@ enum hist_column { HISTC_GLOBAL_WEIGHT, HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, + HISTC_MEM_PHYS_DADDR, HISTC_MEM_LOCKED, HISTC_MEM_TLB, HISTC_MEM_LVL, diff --git a/tools/perf/util/include/asm/asm-offsets.h b/tools/perf/util/include/asm/asm-offsets.h index ed538942523d..3aff4cf44944 100644 --- a/tools/perf/util/include/asm/asm-offsets.h +++ b/tools/perf/util/include/asm/asm-offsets.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* stub */ diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h index acffd5e4d1d4..2270481c7e0a 100644 --- a/tools/perf/util/include/asm/cpufeature.h +++ b/tools/perf/util/include/asm/cpufeature.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_CPUFEATURE_H #define PERF_CPUFEATURE_H diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h index afe38199e922..e9876be63dbf 100644 --- a/tools/perf/util/include/asm/dwarf2.h +++ b/tools/perf/util/include/asm/dwarf2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_DWARF2_H #define PERF_DWARF2_H diff --git a/tools/perf/util/include/asm/uaccess.h b/tools/perf/util/include/asm/uaccess.h index d0f72b8fcc35..6a6f4b990547 100644 --- a/tools/perf/util/include/asm/uaccess.h +++ b/tools/perf/util/include/asm/uaccess.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_ASM_UACCESS_H_ #define _PERF_ASM_UACCESS_H_ diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index 43bfd8da7919..7d99a084e82d 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_DWARF_REGS_H_ #define _PERF_DWARF_REGS_H_ diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index 06387cffe125..f01d48a8d707 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_LINUX_LINKAGE_H_ #define PERF_LINUX_LINKAGE_H_ diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 218ee2bac9a5..5325e65f9711 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -500,7 +500,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp) } if (!buffer->data) { - int fd = perf_data_file__fd(btsq->bts->session->file); + int fd = perf_data__fd(btsq->bts->session->data); buffer->data = auxtrace_buffer__get_data(buffer, fd); if (!buffer->data) { @@ -664,10 +664,10 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session, if (!bts->data_queued) { struct auxtrace_buffer *buffer; off_t data_offset; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); int err; - if (perf_data_file__is_pipe(session->file)) { + if (perf_data__is_pipe(session->data)) { data_offset = 0; } else { data_offset = lseek(fd, 0, SEEK_CUR); 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/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk index 54e961659514..ddd5c4c21129 100644 --- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk +++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk @@ -1,4 +1,5 @@ #!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 # gen-insn-attr-x86.awk: Instruction attribute table generator # Written by Masami Hiramatsu <mhiramat@redhat.com> # diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index b58f9fd1e2ee..23f9ba676df0 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -271,7 +271,7 @@ next: ptq->buffer = buffer; if (!buffer->data) { - int fd = perf_data_file__fd(ptq->pt->session->file); + int fd = perf_data__fd(ptq->pt->session->data); buffer->data = auxtrace_buffer__get_data(buffer, fd); if (!buffer->data) @@ -2084,10 +2084,10 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session, if (!pt->data_queued) { struct auxtrace_buffer *buffer; off_t data_offset; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); int err; - if (perf_data_file__is_pipe(session->file)) { + if (perf_data__is_pipe(session->data)) { data_offset = 0; } else { data_offset = lseek(fd, 0, SEEK_CUR); diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 020b9ca1b47e..85bab8735fa9 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_INTLIST_H #define __PERF_INTLIST_H diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h index 3f42ee4d2a0b..6817ffc2a059 100644 --- a/tools/perf/util/jit.h +++ b/tools/perf/util/jit.h @@ -1,9 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __JIT_H__ #define __JIT_H__ #include <data.h> -int jit_process(struct perf_session *session, struct perf_data_file *output, +int jit_process(struct perf_session *session, struct perf_data *output, struct machine *machine, char *filename, pid_t pid, u64 *nbytes); int jit_inject_record(const char *filename); diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 9084930e1757..a1863000e972 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <sys/sysmacros.h> #include <sys/types.h> #include <errno.h> @@ -29,7 +30,7 @@ #include "sane_ctype.h" struct jit_buf_desc { - struct perf_data_file *output; + struct perf_data *output; struct perf_session *session; struct machine *machine; union jr_entry *entry; @@ -60,8 +61,8 @@ struct debug_line_info { struct jit_tool { struct perf_tool tool; - struct perf_data_file output; - struct perf_data_file input; + struct perf_data output; + struct perf_data input; u64 bytes_written; }; @@ -356,7 +357,7 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event) { ssize_t size; - size = perf_data_file__write(jd->output, event, event->header.size); + size = perf_data__write(jd->output, event, event->header.size); if (size < 0) return -1; @@ -751,7 +752,7 @@ jit_detect(char *mmap_name, pid_t pid) int jit_process(struct perf_session *session, - struct perf_data_file *output, + struct perf_data *output, struct machine *machine, char *filename, pid_t pid, diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index d01e73592f6e..7b1f06567521 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_KVM_STAT_H #define __PERF_KVM_STAT_H diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c index f616e4f65b67..a217ecf0359d 100644 --- a/tools/perf/util/levenshtein.c +++ b/tools/perf/util/levenshtein.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "levenshtein.h" #include <errno.h> #include <stdlib.h> diff --git a/tools/perf/util/levenshtein.h b/tools/perf/util/levenshtein.h index b0fcb6d8a881..34ca173c557d 100644 --- a/tools/perf/util/levenshtein.h +++ b/tools/perf/util/levenshtein.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_LEVENSHTEIN_H #define __PERF_LEVENSHTEIN_H diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index 6559bc586643..66756e6be111 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file setups defines to compile arch specific binary from the * generic one. diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index 957ffff72428..c5e568188e19 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file setups defines to compile arch specific binary from the * generic one. diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index c6a15f204c03..4952b429caa7 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015, Huawei Inc. @@ -33,7 +34,7 @@ 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/llvm-utils.h b/tools/perf/util/llvm-utils.h index c87a2a92a88f..d3ad8deb5db4 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015, Huawei Inc. diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 4ca7c5c6cdcd..07498eaddc08 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <lzma.h> #include <stdio.h> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2e9eb6aa3ce2..6a8d03c3d9b7 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <dirent.h> #include <errno.h> #include <inttypes.h> @@ -30,7 +31,21 @@ static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); dsos->root = RB_ROOT; - pthread_rwlock_init(&dsos->lock, NULL); + init_rwsem(&dsos->lock); +} + +static void machine__threads_init(struct machine *machine) +{ + int i; + + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + struct threads *threads = &machine->threads[i]; + threads->entries = RB_ROOT; + init_rwsem(&threads->lock); + threads->nr = 0; + INIT_LIST_HEAD(&threads->dead); + threads->last_match = NULL; + } } int machine__init(struct machine *machine, const char *root_dir, pid_t pid) @@ -40,11 +55,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->dsos); - machine->threads = RB_ROOT; - pthread_rwlock_init(&machine->threads_lock, NULL); - machine->nr_threads = 0; - INIT_LIST_HEAD(&machine->dead_threads); - machine->last_match = NULL; + machine__threads_init(machine); machine->vdso_info = NULL; machine->env = NULL; @@ -120,7 +131,7 @@ static void dsos__purge(struct dsos *dsos) { struct dso *pos, *n; - pthread_rwlock_wrlock(&dsos->lock); + down_write(&dsos->lock); list_for_each_entry_safe(pos, n, &dsos->head, node) { RB_CLEAR_NODE(&pos->rb_node); @@ -129,39 +140,49 @@ static void dsos__purge(struct dsos *dsos) dso__put(pos); } - pthread_rwlock_unlock(&dsos->lock); + up_write(&dsos->lock); } static void dsos__exit(struct dsos *dsos) { dsos__purge(dsos); - pthread_rwlock_destroy(&dsos->lock); + exit_rwsem(&dsos->lock); } void machine__delete_threads(struct machine *machine) { struct rb_node *nd; + int i; - pthread_rwlock_wrlock(&machine->threads_lock); - nd = rb_first(&machine->threads); - while (nd) { - struct thread *t = rb_entry(nd, struct thread, rb_node); + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + struct threads *threads = &machine->threads[i]; + down_write(&threads->lock); + nd = rb_first(&threads->entries); + while (nd) { + struct thread *t = rb_entry(nd, struct thread, rb_node); - nd = rb_next(nd); - __machine__remove_thread(machine, t, false); + nd = rb_next(nd); + __machine__remove_thread(machine, t, false); + } + up_write(&threads->lock); } - pthread_rwlock_unlock(&machine->threads_lock); } void machine__exit(struct machine *machine) { + int i; + machine__destroy_kernel_maps(machine); map_groups__exit(&machine->kmaps); dsos__exit(&machine->dsos); machine__exit_vdso(machine); zfree(&machine->root_dir); zfree(&machine->current_tid); - pthread_rwlock_destroy(&machine->threads_lock); + + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + struct threads *threads = &machine->threads[i]; + exit_rwsem(&threads->lock); + } } void machine__delete(struct machine *machine) @@ -379,10 +400,11 @@ out_err: * lookup/new thread inserted. */ static struct thread *____machine__findnew_thread(struct machine *machine, + struct threads *threads, pid_t pid, pid_t tid, bool create) { - struct rb_node **p = &machine->threads.rb_node; + struct rb_node **p = &threads->entries.rb_node; struct rb_node *parent = NULL; struct thread *th; @@ -391,14 +413,14 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * so most of the time we dont have to look up * the full rbtree: */ - th = machine->last_match; + th = threads->last_match; if (th != NULL) { if (th->tid == tid) { machine__update_thread_pid(machine, th, pid); return thread__get(th); } - machine->last_match = NULL; + threads->last_match = NULL; } while (*p != NULL) { @@ -406,7 +428,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - machine->last_match = th; + threads->last_match = th; machine__update_thread_pid(machine, th, pid); return thread__get(th); } @@ -423,7 +445,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, th = thread__new(pid, tid); if (th != NULL) { rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, &machine->threads); + rb_insert_color(&th->rb_node, &threads->entries); /* * We have to initialize map_groups separately @@ -434,7 +456,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * leader and that would screwed the rb tree. */ if (thread__init_map_groups(th, machine)) { - rb_erase_init(&th->rb_node, &machine->threads); + rb_erase_init(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); thread__put(th); return NULL; @@ -443,8 +465,8 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * It is now in the rbtree, get a ref */ thread__get(th); - machine->last_match = th; - ++machine->nr_threads; + threads->last_match = th; + ++threads->nr; } return th; @@ -452,27 +474,30 @@ static struct thread *____machine__findnew_thread(struct machine *machine, struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid) { - return ____machine__findnew_thread(machine, pid, tid, true); + return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true); } struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid) { + struct threads *threads = machine__threads(machine, tid); struct thread *th; - pthread_rwlock_wrlock(&machine->threads_lock); + down_write(&threads->lock); th = __machine__findnew_thread(machine, pid, tid); - pthread_rwlock_unlock(&machine->threads_lock); + up_write(&threads->lock); return th; } struct thread *machine__find_thread(struct machine *machine, pid_t pid, pid_t tid) { + struct threads *threads = machine__threads(machine, tid); struct thread *th; - pthread_rwlock_rdlock(&machine->threads_lock); - th = ____machine__findnew_thread(machine, pid, tid, false); - pthread_rwlock_unlock(&machine->threads_lock); + + down_read(&threads->lock); + th = ____machine__findnew_thread(machine, threads, pid, tid, false); + up_read(&threads->lock); return th; } @@ -564,7 +589,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, { struct dso *dso; - pthread_rwlock_wrlock(&machine->dsos.lock); + down_write(&machine->dsos.lock); dso = __dsos__find(&machine->dsos, m->name, true); if (!dso) { @@ -578,7 +603,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, dso__get(dso); out_unlock: - pthread_rwlock_unlock(&machine->dsos.lock); + up_write(&machine->dsos.lock); return dso; } @@ -705,7 +730,8 @@ 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); } @@ -718,21 +744,25 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) size_t machine__fprintf(struct machine *machine, FILE *fp) { - size_t ret; struct rb_node *nd; + size_t ret; + int i; - pthread_rwlock_rdlock(&machine->threads_lock); + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + struct threads *threads = &machine->threads[i]; - ret = fprintf(fp, "Threads: %u\n", machine->nr_threads); + down_read(&threads->lock); - for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { - struct thread *pos = rb_entry(nd, struct thread, rb_node); + ret = fprintf(fp, "Threads: %u\n", threads->nr); - ret += thread__fprintf(pos, fp); - } + for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); - pthread_rwlock_unlock(&machine->threads_lock); + ret += thread__fprintf(pos, fp); + } + up_read(&threads->lock); + } return ret; } @@ -1137,7 +1167,8 @@ 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 +1179,7 @@ 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); @@ -1289,7 +1321,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, struct dso *kernel = NULL; struct dso *dso; - pthread_rwlock_rdlock(&machine->dsos.lock); + down_read(&machine->dsos.lock); list_for_each_entry(dso, &machine->dsos.head, node) { @@ -1319,7 +1351,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, break; } - pthread_rwlock_unlock(&machine->dsos.lock); + up_read(&machine->dsos.lock); if (kernel == NULL) kernel = machine__findnew_dso(machine, kmmap_prefix); @@ -1392,7 +1424,7 @@ 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 +1482,7 @@ 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); @@ -1476,23 +1508,25 @@ out_problem: static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock) { - if (machine->last_match == th) - machine->last_match = NULL; + struct threads *threads = machine__threads(machine, th->tid); + + if (threads->last_match == th) + threads->last_match = NULL; BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) - pthread_rwlock_wrlock(&machine->threads_lock); - rb_erase_init(&th->rb_node, &machine->threads); + down_write(&threads->lock); + rb_erase_init(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); - --machine->nr_threads; + --threads->nr; /* * Move it first to the dead_threads list, then drop the reference, * if this is the last reference, then the thread__delete destructor * will be called and we will remove it from the dead_threads list. */ - list_add_tail(&th->node, &machine->dead_threads); + list_add_tail(&th->node, &threads->dead); if (lock) - pthread_rwlock_unlock(&machine->threads_lock); + up_write(&threads->lock); thread__put(th); } @@ -1632,10 +1666,12 @@ static void ip__resolve_ams(struct thread *thread, ams->al_addr = al.addr; ams->sym = al.sym; ams->map = al.map; + ams->phys_addr = 0; } static void ip__resolve_data(struct thread *thread, - u8 m, struct addr_map_symbol *ams, u64 addr) + u8 m, struct addr_map_symbol *ams, + u64 addr, u64 phys_addr) { struct addr_location al; @@ -1655,6 +1691,7 @@ static void ip__resolve_data(struct thread *thread, ams->al_addr = al.addr; ams->sym = al.sym; ams->map = al.map; + ams->phys_addr = phys_addr; } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -1666,12 +1703,38 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return NULL; ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); - ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr); + ip__resolve_data(al->thread, al->cpumode, &mi->daddr, + sample->addr, sample->phys_addr); mi->data_src.val = sample->data_src; return mi; } +static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip) +{ + char *srcline = NULL; + + if (!map || callchain_param.key == CCKEY_FUNCTION) + return srcline; + + srcline = srcline__tree_find(&map->dso->srclines, ip); + if (!srcline) { + bool show_sym = false; + bool show_addr = callchain_param.key == CCKEY_ADDRESS; + + srcline = get_srcline(map->dso, map__rip_2objdump(map, ip), + sym, show_sym, show_addr); + srcline__tree_insert(&map->dso->srclines, ip, srcline); + } + + return srcline; +} + +struct iterations { + int nr_loop_iter; + u64 cycles; +}; + static int add_callchain_ip(struct thread *thread, struct callchain_cursor *cursor, struct symbol **parent, @@ -1680,10 +1743,13 @@ static int add_callchain_ip(struct thread *thread, u64 ip, bool branch, struct branch_flags *flags, - int nr_loop_iter, - int samples) + struct iterations *iter, + u64 branch_from) { struct addr_location al; + int nr_loop_iter = 0; + u64 iter_cycles = 0; + const char *srcline = NULL; al.filtered = 0; al.sym = NULL; @@ -1733,8 +1799,16 @@ static int add_callchain_ip(struct thread *thread, if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; + + if (iter) { + nr_loop_iter = iter->nr_loop_iter; + iter_cycles = iter->cycles; + } + + srcline = callchain_srcline(al.map, al.sym, al.addr); return callchain_cursor_append(cursor, al.addr, al.map, al.sym, - branch, flags, nr_loop_iter, samples); + branch, flags, nr_loop_iter, + iter_cycles, branch_from, srcline); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1755,6 +1829,18 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, return bi; } +static void save_iterations(struct iterations *iter, + struct branch_entry *be, int nr) +{ + int i; + + iter->nr_loop_iter = nr; + iter->cycles = 0; + + for (i = 0; i < nr; i++) + iter->cycles += be[i].flags.cycles; +} + #define CHASHSZ 127 #define CHASHBITS 7 #define NO_ENTRY 0xff @@ -1762,7 +1848,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, #define PERF_MAX_BRANCH_DEPTH 127 /* Remove loops. */ -static int remove_loops(struct branch_entry *l, int nr) +static int remove_loops(struct branch_entry *l, int nr, + struct iterations *iter) { int i, j, off; unsigned char chash[CHASHSZ]; @@ -1787,8 +1874,18 @@ static int remove_loops(struct branch_entry *l, int nr) break; } if (is_loop) { - memmove(l + i, l + i + off, - (nr - (i + off)) * sizeof(*l)); + j = nr - (i + off); + if (j > 0) { + save_iterations(iter + i + off, + l + i, off); + + memmove(iter + i, iter + i + off, + j * sizeof(*iter)); + + memmove(l + i, l + i + off, + j * sizeof(*l)); + } + nr -= off; } } @@ -1813,7 +1910,7 @@ 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 +1952,8 @@ 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 +1968,15 @@ 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, NULL, + branch_from); if (err) return (err < 0) ? err : 0; } @@ -1894,12 +1996,14 @@ 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, @@ -1929,6 +2033,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, if (branch && callchain_param.branch_callstack) { int nr = min(max_stack, (int)branch->nr); struct branch_entry be[nr]; + struct iterations iter[nr]; if (branch->nr > PERF_MAX_BRANCH_DEPTH) { pr_warning("corrupted branch chain. skipping...\n"); @@ -1938,6 +2043,10 @@ 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 @@ -1955,42 +2064,30 @@ static int thread__resolve_callchain_sample(struct thread *thread, be[i] = branch->entries[branch->nr - i - 1]; } - nr_loop_iter = nr; - nr = remove_loops(be, nr); - - /* - * Get the number of iterations. - * It's only approximation, but good enough in practice. - */ - if (nr_loop_iter > nr) - nr_loop_iter = nr_loop_iter - nr + 1; - else - nr_loop_iter = 0; + memset(iter, 0, sizeof(struct iterations) * nr); + nr = remove_loops(be, nr, iter); for (i = 0; i < nr; i++) { - if (i == nr - 1) - err = add_callchain_ip(thread, cursor, parent, - root_al, - NULL, be[i].to, - true, &be[i].flags, - nr_loop_iter, 1); - else - err = add_callchain_ip(thread, cursor, parent, - root_al, - NULL, be[i].to, - true, &be[i].flags, - 0, 0); + err = add_callchain_ip(thread, cursor, parent, + root_al, + NULL, be[i].to, + true, &be[i].flags, + NULL, be[i].from); if (!err) err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from, true, &be[i].flags, - 0, 0); + &iter[i], 0); if (err == -EINVAL) break; if (err) return err; } + + if (chain_nr == 0) + return 0; + chain_nr -= nr; } @@ -2015,7 +2112,7 @@ check_calls: err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, - false, NULL, 0, 0); + false, NULL, NULL, 0); if (err) return (err < 0) ? err : 0; @@ -2024,15 +2121,54 @@ check_calls: return 0; } +static int append_inlines(struct callchain_cursor *cursor, + struct map *map, struct symbol *sym, u64 ip) +{ + struct inline_node *inline_node; + struct inline_list *ilist; + u64 addr; + int ret = 1; + + if (!symbol_conf.inline_name || !map || !sym) + return ret; + + addr = map__rip_2objdump(map, ip); + + inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr); + if (!inline_node) { + inline_node = dso__parse_addr_inlines(map->dso, addr, sym); + if (!inline_node) + return ret; + inlines__tree_insert(&map->dso->inlined_nodes, inline_node); + } + + list_for_each_entry(ilist, &inline_node->val, list) { + ret = callchain_cursor_append(cursor, ip, map, + ilist->symbol, false, + NULL, 0, 0, 0, ilist->srcline); + + if (ret != 0) + return ret; + } + + return ret; +} + static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; + const char *srcline = NULL; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; + + if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) + return 0; + + srcline = callchain_srcline(entry->map, entry->sym, entry->ip); return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, - false, NULL, 0, 0); + false, NULL, 0, 0, 0, srcline); } static int thread__resolve_callchain_unwind(struct thread *thread, @@ -2096,21 +2232,26 @@ int machine__for_each_thread(struct machine *machine, int (*fn)(struct thread *thread, void *p), void *priv) { + struct threads *threads; struct rb_node *nd; struct thread *thread; int rc = 0; + int i; - for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { - thread = rb_entry(nd, struct thread, rb_node); - rc = fn(thread, priv); - if (rc != 0) - return rc; - } + for (i = 0; i < THREADS__TABLE_SIZE; i++) { + threads = &machine->threads[i]; + for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) { + thread = rb_entry(nd, struct thread, rb_node); + rc = fn(thread, priv); + if (rc != 0) + return rc; + } - list_for_each_entry(thread, &machine->dead_threads, node) { - rc = fn(thread, priv); - if (rc != 0) - return rc; + list_for_each_entry(thread, &threads->dead, node) { + rc = fn(thread, priv); + if (rc != 0) + return rc; + } } return rc; } @@ -2139,12 +2280,16 @@ int machines__for_each_thread(struct machines *machines, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct thread_map *threads, perf_event__handler_t process, bool data_mmap, - unsigned int proc_map_timeout) + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) { if (target__has_task(target)) return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout); + return perf_event__synthesize_threads(tool, process, + machine, data_mmap, + proc_map_timeout, + nr_threads_synthesize); /* command specified */ return 0; } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 3cdb1340f917..5ce860b64c74 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_MACHINE_H #define __PERF_MACHINE_H @@ -6,6 +7,7 @@ #include "map.h" #include "dso.h" #include "event.h" +#include "rwsem.h" struct addr_location; struct branch_stack; @@ -23,6 +25,17 @@ extern const char *ref_reloc_sym_names[]; struct vdso_info; +#define THREADS__TABLE_BITS 8 +#define THREADS__TABLE_SIZE (1 << THREADS__TABLE_BITS) + +struct threads { + struct rb_root entries; + struct rw_semaphore lock; + unsigned int nr; + struct list_head dead; + struct thread *last_match; +}; + struct machine { struct rb_node rb_node; pid_t pid; @@ -30,11 +43,7 @@ struct machine { bool comm_exec; bool kptr_restrict_warned; char *root_dir; - struct rb_root threads; - pthread_rwlock_t threads_lock; - unsigned int nr_threads; - struct list_head dead_threads; - struct thread *last_match; + struct threads threads[THREADS__TABLE_SIZE]; struct vdso_info *vdso_info; struct perf_env *env; struct dsos dsos; @@ -48,6 +57,12 @@ struct machine { }; }; +static inline struct threads *machine__threads(struct machine *machine, pid_t tid) +{ + /* Cast it to handle tid == -1 */ + return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE]; +} + static inline struct map *__machine__kernel_map(struct machine *machine, enum map_type type) { @@ -243,15 +258,18 @@ int machines__for_each_thread(struct machines *machines, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct thread_map *threads, perf_event__handler_t process, bool data_mmap, - unsigned int proc_map_timeout); + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize); static inline int machine__synthesize_threads(struct machine *machine, struct target *target, struct thread_map *threads, bool data_mmap, - unsigned int proc_map_timeout) + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, perf_event__process, data_mmap, - proc_map_timeout); + proc_map_timeout, + nr_threads_synthesize); } pid_t machine__get_current_tid(struct machine *machine, int cpu); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 2179b2deb730..6d40efd74402 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "symbol.h" #include <errno.h> #include <inttypes.h> @@ -16,6 +17,7 @@ #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 +147,13 @@ 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 +171,11 @@ 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 +185,16 @@ 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 +216,12 @@ 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; } @@ -471,7 +489,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) static void maps__init(struct maps *maps) { maps->entries = RB_ROOT; - pthread_rwlock_init(&maps->lock, NULL); + init_rwsem(&maps->lock); } void map_groups__init(struct map_groups *mg, struct machine *machine) @@ -500,9 +518,9 @@ static void __maps__purge(struct maps *maps) static void maps__exit(struct maps *maps) { - pthread_rwlock_wrlock(&maps->lock); + down_write(&maps->lock); __maps__purge(maps); - pthread_rwlock_unlock(&maps->lock); + up_write(&maps->lock); } void map_groups__exit(struct map_groups *mg) @@ -569,7 +587,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct symbol *sym; struct rb_node *nd; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); @@ -585,7 +603,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, sym = NULL; out: - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); return sym; } @@ -621,7 +639,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) size_t printed = 0; struct rb_node *nd; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); @@ -633,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) } } - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); return printed; } @@ -665,7 +683,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp struct rb_node *next; int err = 0; - pthread_rwlock_wrlock(&maps->lock); + down_write(&maps->lock); root = &maps->entries; next = rb_first(root); @@ -733,7 +751,7 @@ put_map: err = 0; out: - pthread_rwlock_unlock(&maps->lock); + up_write(&maps->lock); return err; } @@ -754,7 +772,7 @@ int map_groups__clone(struct thread *thread, struct map *map; struct maps *maps = &parent->maps[type]; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); for (map = maps__first(maps); map; map = map__next(map)) { struct map *new = map__clone(map); @@ -771,7 +789,7 @@ int map_groups__clone(struct thread *thread, err = 0; out_unlock: - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); return err; } @@ -798,9 +816,9 @@ static void __maps__insert(struct maps *maps, struct map *map) void maps__insert(struct maps *maps, struct map *map) { - pthread_rwlock_wrlock(&maps->lock); + down_write(&maps->lock); __maps__insert(maps, map); - pthread_rwlock_unlock(&maps->lock); + up_write(&maps->lock); } static void __maps__remove(struct maps *maps, struct map *map) @@ -811,9 +829,9 @@ static void __maps__remove(struct maps *maps, struct map *map) void maps__remove(struct maps *maps, struct map *map) { - pthread_rwlock_wrlock(&maps->lock); + down_write(&maps->lock); __maps__remove(maps, map); - pthread_rwlock_unlock(&maps->lock); + up_write(&maps->lock); } struct map *maps__find(struct maps *maps, u64 ip) @@ -821,7 +839,7 @@ struct map *maps__find(struct maps *maps, u64 ip) struct rb_node **p, *parent = NULL; struct map *m; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); p = &maps->entries.rb_node; while (*p != NULL) { @@ -837,7 +855,7 @@ struct map *maps__find(struct maps *maps, u64 ip) m = NULL; out: - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); return m; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f9e8ac8a52cd..edeb7291c8e1 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_MAP_H #define __PERF_MAP_H @@ -9,6 +10,7 @@ #include <stdio.h> #include <stdbool.h> #include <linux/types.h> +#include "rwsem.h" enum map_type { MAP__FUNCTION = 0, @@ -61,7 +63,7 @@ struct kmap { struct maps { struct rb_root entries; - pthread_rwlock_t lock; + struct rw_semaphore lock; }; struct map_groups { @@ -141,7 +143,7 @@ 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..93f74d8d3cdd 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stddef.h> #include <stdlib.h> #include <string.h> @@ -166,11 +167,20 @@ 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 +194,37 @@ 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 +261,14 @@ 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 +317,11 @@ 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 +367,8 @@ 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 +378,8 @@ 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/mem-events.h b/tools/perf/util/mem-events.h index 40f72ee4f42a..a889ec2fa9f5 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_MEM_EVENTS_H #define __PERF_MEM_EVENTS_H diff --git a/tools/perf/util/memswap.c b/tools/perf/util/memswap.c index 55f7faa8d9ec..c1317e4983bc 100644 --- a/tools/perf/util/memswap.c +++ b/tools/perf/util/memswap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <byteswap.h> #include "memswap.h" #include <linux/types.h> diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h index 7d1b1c34bb57..1e29ff903ca9 100644 --- a/tools/perf/util/memswap.h +++ b/tools/perf/util/memswap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_MEMSWAP_H_ #define PERF_MEMSWAP_H_ diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c new file mode 100644 index 000000000000..0ddd9c199227 --- /dev/null +++ b/tools/perf/util/metricgroup.c @@ -0,0 +1,490 @@ +/* + * Copyright (c) 2017, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +/* Manage metrics and groups of metrics from JSON files */ + +#include "metricgroup.h" +#include "evlist.h" +#include "strbuf.h" +#include "pmu.h" +#include "expr.h" +#include "rblist.h" +#include "pmu.h" +#include <string.h> +#include <stdbool.h> +#include <errno.h> +#include "pmu-events/pmu-events.h" +#include "strbuf.h" +#include "strlist.h" +#include <assert.h> +#include <ctype.h> + +struct metric_event *metricgroup__lookup(struct rblist *metric_events, + struct perf_evsel *evsel, + bool create) +{ + struct rb_node *nd; + struct metric_event me = { + .evsel = evsel + }; + nd = rblist__find(metric_events, &me); + if (nd) + return container_of(nd, struct metric_event, nd); + if (create) { + rblist__add_node(metric_events, &me); + nd = rblist__find(metric_events, &me); + if (nd) + return container_of(nd, struct metric_event, nd); + } + return NULL; +} + +static int metric_event_cmp(struct rb_node *rb_node, const void *entry) +{ + struct metric_event *a = container_of(rb_node, + struct metric_event, + nd); + const struct metric_event *b = entry; + + if (a->evsel == b->evsel) + return 0; + if ((char *)a->evsel < (char *)b->evsel) + return -1; + return +1; +} + +static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused, + const void *entry) +{ + struct metric_event *me = malloc(sizeof(struct metric_event)); + + if (!me) + return NULL; + memcpy(me, entry, sizeof(struct metric_event)); + me->evsel = ((struct metric_event *)entry)->evsel; + INIT_LIST_HEAD(&me->head); + return &me->nd; +} + +static void metricgroup__rblist_init(struct rblist *metric_events) +{ + rblist__init(metric_events); + metric_events->node_cmp = metric_event_cmp; + metric_events->node_new = metric_event_new; +} + +struct egroup { + struct list_head nd; + int idnum; + const char **ids; + const char *metric_name; + const char *metric_expr; +}; + +static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist, + const char **ids, + int idnum, + struct perf_evsel **metric_events) +{ + struct perf_evsel *ev, *start = NULL; + int ind = 0; + + evlist__for_each_entry (perf_evlist, ev) { + if (!strcmp(ev->name, ids[ind])) { + metric_events[ind] = ev; + if (ind == 0) + start = ev; + if (++ind == idnum) { + metric_events[ind] = NULL; + return start; + } + } else { + ind = 0; + start = NULL; + } + } + /* + * This can happen when an alias expands to multiple + * events, like for uncore events. + * We don't support this case for now. + */ + return NULL; +} + +static int metricgroup__setup_events(struct list_head *groups, + struct perf_evlist *perf_evlist, + struct rblist *metric_events_list) +{ + struct metric_event *me; + struct metric_expr *expr; + int i = 0; + int ret = 0; + struct egroup *eg; + struct perf_evsel *evsel; + + list_for_each_entry (eg, groups, nd) { + struct perf_evsel **metric_events; + + metric_events = calloc(sizeof(void *), eg->idnum + 1); + if (!metric_events) { + ret = -ENOMEM; + break; + } + evsel = find_evsel(perf_evlist, eg->ids, eg->idnum, + metric_events); + if (!evsel) { + pr_debug("Cannot resolve %s: %s\n", + eg->metric_name, eg->metric_expr); + continue; + } + for (i = 0; i < eg->idnum; i++) + metric_events[i]->collect_stat = true; + me = metricgroup__lookup(metric_events_list, evsel, true); + if (!me) { + ret = -ENOMEM; + break; + } + expr = malloc(sizeof(struct metric_expr)); + if (!expr) { + ret = -ENOMEM; + break; + } + expr->metric_expr = eg->metric_expr; + expr->metric_name = eg->metric_name; + expr->metric_events = metric_events; + list_add(&expr->nd, &me->head); + } + return ret; +} + +static bool match_metric(const char *n, const char *list) +{ + int len; + char *m; + + if (!list) + return false; + if (!strcmp(list, "all")) + return true; + if (!n) + return !strcasecmp(list, "No_group"); + len = strlen(list); + m = strcasestr(n, list); + if (!m) + return false; + if ((m == n || m[-1] == ';' || m[-1] == ' ') && + (m[len] == 0 || m[len] == ';')) + return true; + return false; +} + +struct mep { + struct rb_node nd; + const char *name; + struct strlist *metrics; +}; + +static int mep_cmp(struct rb_node *rb_node, const void *entry) +{ + struct mep *a = container_of(rb_node, struct mep, nd); + struct mep *b = (struct mep *)entry; + + return strcmp(a->name, b->name); +} + +static struct rb_node *mep_new(struct rblist *rl __maybe_unused, + const void *entry) +{ + struct mep *me = malloc(sizeof(struct mep)); + + if (!me) + return NULL; + memcpy(me, entry, sizeof(struct mep)); + me->name = strdup(me->name); + if (!me->name) + goto out_me; + me->metrics = strlist__new(NULL, NULL); + if (!me->metrics) + goto out_name; + return &me->nd; +out_name: + free((char *)me->name); +out_me: + free(me); + return NULL; +} + +static struct mep *mep_lookup(struct rblist *groups, const char *name) +{ + struct rb_node *nd; + struct mep me = { + .name = name + }; + nd = rblist__find(groups, &me); + if (nd) + return container_of(nd, struct mep, nd); + rblist__add_node(groups, &me); + nd = rblist__find(groups, &me); + if (nd) + return container_of(nd, struct mep, nd); + return NULL; +} + +static void mep_delete(struct rblist *rl __maybe_unused, + struct rb_node *nd) +{ + struct mep *me = container_of(nd, struct mep, nd); + + strlist__delete(me->metrics); + free((void *)me->name); + free(me); +} + +static void metricgroup__print_strlist(struct strlist *metrics, bool raw) +{ + struct str_node *sn; + int n = 0; + + strlist__for_each_entry (sn, metrics) { + if (raw) + printf("%s%s", n > 0 ? " " : "", sn->s); + else + printf(" %s\n", sn->s); + n++; + } + if (raw) + putchar('\n'); +} + +void metricgroup__print(bool metrics, bool metricgroups, char *filter, + bool raw) +{ + struct pmu_events_map *map = perf_pmu__find_map(); + struct pmu_event *pe; + int i; + struct rblist groups; + struct rb_node *node, *next; + struct strlist *metriclist = NULL; + + if (!map) + return; + + if (!metricgroups) { + metriclist = strlist__new(NULL, NULL); + if (!metriclist) + return; + } + + rblist__init(&groups); + groups.node_new = mep_new; + groups.node_cmp = mep_cmp; + groups.node_delete = mep_delete; + for (i = 0; ; i++) { + const char *g; + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + g = pe->metric_group; + if (!g && pe->metric_name) { + if (pe->name) + continue; + g = "No_group"; + } + if (g) { + char *omg; + char *mg = strdup(g); + + if (!mg) + return; + omg = mg; + while ((g = strsep(&mg, ";")) != NULL) { + struct mep *me; + char *s; + + if (*g == 0) + g = "No_group"; + while (isspace(*g)) + g++; + if (filter && !strstr(g, filter)) + continue; + if (raw) + s = (char *)pe->metric_name; + else { + if (asprintf(&s, "%s\n\t[%s]", + pe->metric_name, pe->desc) < 0) + return; + } + + if (!s) + continue; + + if (!metricgroups) { + strlist__add(metriclist, s); + } else { + me = mep_lookup(&groups, g); + if (!me) + continue; + strlist__add(me->metrics, s); + } + } + free(omg); + } + } + + if (metricgroups && !raw) + printf("\nMetric Groups:\n\n"); + else if (metrics && !raw) + printf("\nMetrics:\n\n"); + + for (node = rb_first(&groups.entries); node; node = next) { + struct mep *me = container_of(node, struct mep, nd); + + if (metricgroups) + printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n"); + if (metrics) + metricgroup__print_strlist(me->metrics, raw); + next = rb_next(node); + rblist__remove_node(&groups, node); + } + if (!metricgroups) + metricgroup__print_strlist(metriclist, raw); + strlist__delete(metriclist); +} + +static int metricgroup__add_metric(const char *metric, struct strbuf *events, + struct list_head *group_list) +{ + struct pmu_events_map *map = perf_pmu__find_map(); + struct pmu_event *pe; + int ret = -EINVAL; + int i, j; + + if (!map) + return 0; + + for (i = 0; ; i++) { + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + if (match_metric(pe->metric_group, metric) || + match_metric(pe->metric_name, metric)) { + const char **ids; + int idnum; + struct egroup *eg; + + pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name); + + if (expr__find_other(pe->metric_expr, + NULL, &ids, &idnum) < 0) + continue; + if (events->len > 0) + strbuf_addf(events, ","); + for (j = 0; j < idnum; j++) { + pr_debug("found event %s\n", ids[j]); + strbuf_addf(events, "%s%s", + j == 0 ? "{" : ",", + ids[j]); + } + strbuf_addf(events, "}:W"); + + eg = malloc(sizeof(struct egroup)); + if (!eg) { + ret = -ENOMEM; + break; + } + eg->ids = ids; + eg->idnum = idnum; + eg->metric_name = pe->metric_name; + eg->metric_expr = pe->metric_expr; + list_add_tail(&eg->nd, group_list); + ret = 0; + } + } + return ret; +} + +static int metricgroup__add_metric_list(const char *list, struct strbuf *events, + struct list_head *group_list) +{ + char *llist, *nlist, *p; + int ret = -EINVAL; + + nlist = strdup(list); + if (!nlist) + return -ENOMEM; + llist = nlist; + + strbuf_init(events, 100); + strbuf_addf(events, "%s", ""); + + while ((p = strsep(&llist, ",")) != NULL) { + ret = metricgroup__add_metric(p, events, group_list); + if (ret == -EINVAL) { + fprintf(stderr, "Cannot find metric or group `%s'\n", + p); + break; + } + } + free(nlist); + return ret; +} + +static void metricgroup__free_egroups(struct list_head *group_list) +{ + struct egroup *eg, *egtmp; + int i; + + list_for_each_entry_safe (eg, egtmp, group_list, nd) { + for (i = 0; i < eg->idnum; i++) + free((char *)eg->ids[i]); + free(eg->ids); + free(eg); + } +} + +int metricgroup__parse_groups(const struct option *opt, + const char *str, + struct rblist *metric_events) +{ + struct parse_events_error parse_error; + struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value; + struct strbuf extra_events; + LIST_HEAD(group_list); + int ret; + + if (metric_events->nr_entries == 0) + metricgroup__rblist_init(metric_events); + ret = metricgroup__add_metric_list(str, &extra_events, &group_list); + if (ret) + return ret; + pr_debug("adding %s\n", extra_events.buf); + memset(&parse_error, 0, sizeof(struct parse_events_error)); + ret = parse_events(perf_evlist, extra_events.buf, &parse_error); + if (ret) { + parse_events_print_error(&parse_error, extra_events.buf); + goto out; + } + strbuf_release(&extra_events); + ret = metricgroup__setup_events(&group_list, perf_evlist, + metric_events); +out: + metricgroup__free_egroups(&group_list); + return ret; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h new file mode 100644 index 000000000000..06854e125ee7 --- /dev/null +++ b/tools/perf/util/metricgroup.h @@ -0,0 +1,31 @@ +#ifndef METRICGROUP_H +#define METRICGROUP_H 1 + +#include "linux/list.h" +#include "rblist.h" +#include <subcmd/parse-options.h> +#include "evlist.h" +#include "strbuf.h" + +struct metric_event { + struct rb_node nd; + struct perf_evsel *evsel; + struct list_head head; /* list of metric_expr */ +}; + +struct metric_expr { + struct list_head nd; + const char *metric_expr; + const char *metric_name; + struct perf_evsel **metric_events; +}; + +struct metric_event *metricgroup__lookup(struct rblist *metric_events, + struct perf_evsel *evsel, + bool create); +int metricgroup__parse_groups(const struct option *opt, + const char *str, + struct rblist *metric_events); + +void metricgroup__print(bool metrics, bool groups, char *filter, bool raw); +#endif diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c new file mode 100644 index 000000000000..9fe5f9c7d577 --- /dev/null +++ b/tools/perf/util/mmap.c @@ -0,0 +1,352 @@ +/* + * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include <sys/mman.h> +#include <inttypes.h> +#include <asm/bug.h> +#include "debug.h" +#include "event.h" +#include "mmap.h" +#include "util.h" /* page_size */ + +size_t perf_mmap__mmap_len(struct perf_mmap *map) +{ + return map->mask + 1 + page_size; +} + +/* When check_messup is true, 'end' must points to a good entry */ +static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup, + u64 start, u64 end, u64 *prev) +{ + unsigned char *data = map->base + page_size; + union perf_event *event = NULL; + int diff = end - start; + + if (check_messup) { + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the 'end', we got messed up. + * + * In either case, truncate and restart at 'end'. + */ + if (diff > map->mask / 2 || diff < 0) { + fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); + + /* + * 'end' points to a known good entry, start there. + */ + start = end; + diff = 0; + } + } + + if (diff >= (int)sizeof(event->header)) { + size_t size; + + event = (union perf_event *)&data[start & map->mask]; + size = event->header.size; + + if (size < sizeof(event->header) || diff < (int)size) { + event = NULL; + goto broken_event; + } + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + if ((start & map->mask) + size != ((start + size) & map->mask)) { + unsigned int offset = start; + unsigned int len = min(sizeof(*event), size), cpy; + void *dst = map->event_copy; + + do { + cpy = min(map->mask + 1 - (offset & map->mask), len); + memcpy(dst, &data[offset & map->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = (union perf_event *)map->event_copy; + } + + start += size; + } + +broken_event: + if (prev) + *prev = start; + + return event; +} + +union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup) +{ + u64 head; + u64 old = map->prev; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return NULL; + + head = perf_mmap__read_head(map); + + return perf_mmap__read(map, check_messup, old, head, &map->prev); +} + +union perf_event *perf_mmap__read_backward(struct perf_mmap *map) +{ + u64 head, end; + u64 start = map->prev; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return NULL; + + head = perf_mmap__read_head(map); + if (!head) + return NULL; + + /* + * 'head' pointer starts from 0. Kernel minus sizeof(record) form + * it each time when kernel writes to it, so in fact 'head' is + * negative. 'end' pointer is made manually by adding the size of + * the ring buffer to 'head' pointer, means the validate data can + * read is the whole ring buffer. If 'end' is positive, the ring + * buffer has not fully filled, so we must adjust 'end' to 0. + * + * However, since both 'head' and 'end' is unsigned, we can't + * simply compare 'end' against 0. Here we compare '-head' and + * the size of the ring buffer, where -head is the number of bytes + * kernel write to the ring buffer. + */ + if (-head < (u64)(map->mask + 1)) + end = 0; + else + end = head + map->mask + 1; + + return perf_mmap__read(map, false, start, end, &map->prev); +} + +void perf_mmap__read_catchup(struct perf_mmap *map) +{ + u64 head; + + if (!refcount_read(&map->refcnt)) + return; + + head = perf_mmap__read_head(map); + map->prev = head; +} + +static bool perf_mmap__empty(struct perf_mmap *map) +{ + return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base; +} + +void perf_mmap__get(struct perf_mmap *map) +{ + refcount_inc(&map->refcnt); +} + +void perf_mmap__put(struct perf_mmap *map) +{ + BUG_ON(map->base && refcount_read(&map->refcnt) == 0); + + if (refcount_dec_and_test(&map->refcnt)) + perf_mmap__munmap(map); +} + +void perf_mmap__consume(struct perf_mmap *map, bool overwrite) +{ + if (!overwrite) { + u64 old = map->prev; + + perf_mmap__write_tail(map, old); + } + + if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map)) + perf_mmap__put(map); +} + +int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, + struct auxtrace_mmap_params *mp __maybe_unused, + void *userpg __maybe_unused, + int fd __maybe_unused) +{ + return 0; +} + +void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused) +{ +} + +void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused, + off_t auxtrace_offset __maybe_unused, + unsigned int auxtrace_pages __maybe_unused, + bool auxtrace_overwrite __maybe_unused) +{ +} + +void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused, + struct perf_evlist *evlist __maybe_unused, + int idx __maybe_unused, + bool per_cpu __maybe_unused) +{ +} + +void perf_mmap__munmap(struct perf_mmap *map) +{ + if (map->base != NULL) { + munmap(map->base, perf_mmap__mmap_len(map)); + map->base = NULL; + map->fd = -1; + refcount_set(&map->refcnt, 0); + } + auxtrace_mmap__munmap(&map->auxtrace_mmap); +} + +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) +{ + /* + * The last one will be done at perf_evlist__mmap_consume(), so that we + * make sure we don't prevent tools from consuming every last event in + * the ring buffer. + * + * I.e. we can get the POLLHUP meaning that the fd doesn't exist + * anymore, but the last events for it are still in the ring buffer, + * waiting to be consumed. + * + * Tools can chose to ignore this at their own discretion, but the + * evlist layer can't just drop it when filtering events in + * perf_evlist__filter_pollfd(). + */ + refcount_set(&map->refcnt, 2); + map->prev = 0; + map->mask = mp->mask; + map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, + MAP_SHARED, fd, 0); + if (map->base == MAP_FAILED) { + pr_debug2("failed to mmap perf event ring buffer, error %d\n", + errno); + map->base = NULL; + return -1; + } + map->fd = fd; + + if (auxtrace_mmap__mmap(&map->auxtrace_mmap, + &mp->auxtrace_mp, map->base, fd)) + return -1; + + return 0; +} + +static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end) +{ + struct perf_event_header *pheader; + u64 evt_head = head; + int size = mask + 1; + + pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head); + pheader = (struct perf_event_header *)(buf + (head & mask)); + *start = head; + while (true) { + if (evt_head - head >= (unsigned int)size) { + pr_debug("Finished reading backward ring buffer: rewind\n"); + if (evt_head - head > (unsigned int)size) + evt_head -= pheader->size; + *end = evt_head; + return 0; + } + + pheader = (struct perf_event_header *)(buf + (evt_head & mask)); + + if (pheader->size == 0) { + pr_debug("Finished reading backward ring buffer: get start\n"); + *end = evt_head; + return 0; + } + + evt_head += pheader->size; + pr_debug3("move evt_head: %"PRIx64"\n", evt_head); + } + WARN_ONCE(1, "Shouldn't get here\n"); + return -1; +} + +static int rb_find_range(void *data, int mask, u64 head, u64 old, + u64 *start, u64 *end, bool backward) +{ + if (!backward) { + *start = old; + *end = head; + return 0; + } + + return backward_rb_find_range(data, mask, head, start, end); +} + +int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward, + void *to, int push(void *to, void *buf, size_t size)) +{ + u64 head = perf_mmap__read_head(md); + u64 old = md->prev; + u64 end = head, start = old; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int rc = 0; + + if (rb_find_range(data, md->mask, head, old, &start, &end, backward)) + return -1; + + if (start == end) + return 0; + + size = end - start; + if (size > (unsigned long)(md->mask) + 1) { + WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); + + md->prev = head; + perf_mmap__consume(md, overwrite || backward); + return 0; + } + + if ((start & md->mask) + size != (end & md->mask)) { + buf = &data[start & md->mask]; + size = md->mask + 1 - (start & md->mask); + start += size; + + if (push(to, buf, size) < 0) { + rc = -1; + goto out; + } + } + + buf = &data[start & md->mask]; + size = end - start; + start += size; + + if (push(to, buf, size) < 0) { + rc = -1; + goto out; + } + + md->prev = head; + perf_mmap__consume(md, overwrite || backward); +out: + return rc; +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h new file mode 100644 index 000000000000..efd78b827b05 --- /dev/null +++ b/tools/perf/util/mmap.h @@ -0,0 +1,97 @@ +#ifndef __PERF_MMAP_H +#define __PERF_MMAP_H 1 + +#include <linux/compiler.h> +#include <linux/refcount.h> +#include <linux/types.h> +#include <asm/barrier.h> +#include <stdbool.h> +#include "auxtrace.h" +#include "event.h" + +/** + * struct perf_mmap - perf's ring buffer mmap details + * + * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this + */ +struct perf_mmap { + void *base; + int mask; + int fd; + refcount_t refcnt; + u64 prev; + struct auxtrace_mmap auxtrace_mmap; + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); +}; + +/* + * State machine of bkw_mmap_state: + * + * .________________(forbid)_____________. + * | V + * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY + * ^ ^ | ^ | + * | |__(forbid)____/ |___(forbid)___/| + * | | + * \_________________(3)_______________/ + * + * NOTREADY : Backward ring buffers are not ready + * RUNNING : Backward ring buffers are recording + * DATA_PENDING : We are required to collect data from backward ring buffers + * EMPTY : We have collected data from backward ring buffers. + * + * (0): Setup backward ring buffer + * (1): Pause ring buffers for reading + * (2): Read from ring buffers + * (3): Resume ring buffers for recording + */ +enum bkw_mmap_state { + BKW_MMAP_NOTREADY, + BKW_MMAP_RUNNING, + BKW_MMAP_DATA_PENDING, + BKW_MMAP_EMPTY, +}; + +struct mmap_params { + int prot, mask; + struct auxtrace_mmap_params auxtrace_mp; +}; + +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd); +void perf_mmap__munmap(struct perf_mmap *map); + +void perf_mmap__get(struct perf_mmap *map); +void perf_mmap__put(struct perf_mmap *map); + +void perf_mmap__consume(struct perf_mmap *map, bool overwrite); + +void perf_mmap__read_catchup(struct perf_mmap *md); + +static inline u64 perf_mmap__read_head(struct perf_mmap *mm) +{ + struct perf_event_mmap_page *pc = mm->base; + u64 head = ACCESS_ONCE(pc->data_head); + rmb(); + return head; +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) +{ + struct perf_event_mmap_page *pc = md->base; + + /* + * ensure all reads are done before we write the tail out. + */ + mb(); + pc->data_tail = tail; +} + +union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup); +union perf_event *perf_mmap__read_backward(struct perf_mmap *map); + +int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward, + void *to, int push(void *to, void *buf, size_t size)); + +size_t perf_mmap__mmap_len(struct perf_mmap *map); + +#endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 67dcbcc73c7d..5be021701f34 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -9,9 +9,15 @@ #include "namespaces.h" #include "util.h" #include "event.h" +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.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 +41,209 @@ 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..760558dcfd18 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -9,8 +9,10 @@ #ifndef __PERF_NAMESPACES_H #define __PERF_NAMESPACES_H -#include "../perf.h" -#include <linux/list.h> +#include <sys/types.h> +#include <linux/perf_event.h> +#include <linux/refcount.h> +#include <linux/types.h> struct namespaces_event; @@ -23,4 +25,41 @@ 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/ordered-events.c b/tools/perf/util/ordered-events.c index 4de398cfb577..8e09fd2d842f 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> #include <linux/list.h> diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index e11468a9a6e4..96e5292d88e2 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ORDERED_EVENTS_H #define __ORDERED_EVENTS_H diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 38fd11504015..bd779d9f4d1e 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "perf.h" #include "util/util.h" #include "util/debug.h" @@ -28,6 +29,7 @@ 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-branch-options.h b/tools/perf/util/parse-branch-options.h index 6086fd90eb23..11d1722733f2 100644 --- a/tools/perf/util/parse-branch-options.h +++ b/tools/perf/util/parse-branch-options.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_PARSE_BRANCH_OPTIONS_H #define _PERF_PARSE_BRANCH_OPTIONS_H 1 #include <stdint.h> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 01e779b91c8e..a7fcd95961ef 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/hw_breakpoint.h> #include <linux/err.h> #include <dirent.h> @@ -28,13 +29,14 @@ #include "probe-file.h" #include "asm/bug.h" #include "util/parse-branch-options.h" +#include "metricgroup.h" #define MAX_NAME_LEN 100 #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); @@ -309,10 +311,11 @@ static char *get_config_name(struct list_head *head_terms) static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct cpu_map *cpus, - struct list_head *config_terms) + char *name, struct perf_pmu *pmu, + struct list_head *config_terms, bool auto_merge_stats) { struct perf_evsel *evsel; + struct cpu_map *cpus = pmu ? pmu->cpus : NULL; event_attr_init(attr); @@ -323,7 +326,8 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); - evsel->system_wide = !!cpus; + evsel->system_wide = pmu ? pmu->is_uncore : false; + evsel->auto_merge_stats = auto_merge_stats; if (name) evsel->name = strdup(name); @@ -339,7 +343,7 @@ static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct list_head *config_terms) { - return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM; } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -589,7 +593,7 @@ 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 +603,7 @@ 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 +611,8 @@ 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 +636,14 @@ 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 +684,13 @@ 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 +709,28 @@ 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 +766,7 @@ 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 +794,15 @@ 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 +1188,7 @@ 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 +1201,7 @@ 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; @@ -1205,23 +1209,29 @@ 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, +static int __parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config) + struct list_head *head_config, bool auto_merge_stats) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; + struct parse_events_error *err = parse_state->error; LIST_HEAD(config_terms); pmu = perf_pmu__find(name); - if (!pmu) + if (!pmu) { + if (asprintf(&err->str, + "Cannot find PMU `%s'. Missing kernel support?", + name) < 0) + err->str = NULL; return -EINVAL; + } if (pmu->default_config) { memcpy(&attr, pmu->default_config, @@ -1232,7 +1242,7 @@ 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, NULL, auto_merge_stats); return evsel ? 0 : -ENOMEM; } @@ -1243,18 +1253,18 @@ 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, - get_config_name(head_config), pmu->cpus, - &config_terms); + evsel = __add_event(list, &parse_state->idx, &attr, + get_config_name(head_config), pmu, + &config_terms, auto_merge_stats); if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; @@ -1267,7 +1277,14 @@ 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_add_pmu(struct parse_events_state *parse_state, + struct list_head *list, char *name, + struct list_head *head_config) +{ + return __parse_events_add_pmu(parse_state, list, name, head_config, false); +} + +int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { struct list_head *head; @@ -1296,8 +1313,8 @@ 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, - pmu->name, head)) { + if (!__parse_events_add_pmu(parse_state, list, + pmu->name, head, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1358,6 +1375,7 @@ struct event_modifier { int exclude_GH; int sample_read; int pinned; + int weak; }; static int get_event_modifier(struct event_modifier *mod, char *str, @@ -1376,6 +1394,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; + int weak = 0; memset(mod, 0, sizeof(*mod)); @@ -1413,6 +1432,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, sample_read = 1; } else if (*str == 'D') { pinned = 1; + } else if (*str == 'W') { + weak = 1; } else break; @@ -1443,6 +1464,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->exclude_GH = exclude_GH; mod->sample_read = sample_read; mod->pinned = pinned; + mod->weak = weak; return 0; } @@ -1456,7 +1478,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1)) + if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1)) return -1; while (*p) { @@ -1496,6 +1518,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->exclude_GH = mod.exclude_GH; evsel->sample_read = mod.sample_read; evsel->precise_max = mod.precise_max; + evsel->weak_group = mod.weak; if (perf_evsel__is_group_leader(evsel)) evsel->attr.pinned = mod.pinned; @@ -1628,7 +1651,7 @@ 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 +1666,7 @@ 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 +1679,45 @@ 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; @@ -1718,8 +1741,8 @@ static int get_term_width(void) return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col; } -static void parse_events_print_error(struct parse_events_error *err, - const char *event) +void parse_events_print_error(struct parse_events_error *err, + const char *event) { const char *str = "invalid or unsupported event: "; char _buf[MAX_WIDTH]; @@ -1774,8 +1797,6 @@ static void parse_events_print_error(struct parse_events_error *err, zfree(&err->str); zfree(&err->help); } - - fprintf(stderr, "Run 'perf list' for a list of valid events\n"); } #undef MAX_WIDTH @@ -1787,8 +1808,10 @@ int parse_events_option(const struct option *opt, const char *str, struct parse_events_error err = { .idx = 0, }; int ret = parse_events(evlist, str, &err); - if (ret) + if (ret) { parse_events_print_error(&err, str); + fprintf(stderr, "Run 'perf list' for a list of valid events\n"); + } return ret; } @@ -2124,7 +2147,7 @@ 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) { @@ -2366,6 +2389,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_tracepoint_events(NULL, NULL, name_only); print_sdt_events(NULL, NULL, name_only); + + metricgroup__print(true, true, NULL, name_only); } int parse_events__is_hardcoded_term(struct parse_events_term *term) @@ -2520,10 +2545,10 @@ 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..be337c266697 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_PARSE_EVENTS_H #define __PERF_PARSE_EVENTS_H /* @@ -108,16 +109,13 @@ 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 +141,18 @@ 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 +162,11 @@ 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 +178,7 @@ 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, @@ -205,6 +203,9 @@ int is_valid_tracepoint(const char *event_string); int valid_event_mount(const char *eventfs); char *parse_events_formats_error_string(char *additional_terms); +void parse_events_print_error(struct parse_events_error *err, + const char *event); + #ifdef HAVE_LIBELF_SUPPORT /* * If the probe point starts with '%', diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 660fca05bc93..655ecff636a8 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -5,9 +5,13 @@ %option stack %option bison-locations %option yylineno +%option reject %{ #include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -53,6 +57,31 @@ static int str(yyscan_t scanner, int token) return token; } +static bool isbpf_suffix(char *text) +{ + 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; +} + +static bool isbpf(yyscan_t scanner) +{ + char *text = parse_events_get_text(scanner); + struct stat st; + + if (!isbpf_suffix(text)) + return false; + + return stat(text, &st) == 0; +} + /* * This function is called when the parser gets two kind of input: * @@ -126,6 +155,10 @@ do { \ yycolumn += yyleng; \ } while (0); +#define USER_REJECT \ + yycolumn -= yyleng; \ + REJECT + %} %x mem @@ -136,8 +169,8 @@ 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]+ @@ -146,7 +179,7 @@ name [a-zA-Z_*?][a-zA-Z0-9_*?.]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ -modifier_event [ukhpPGHSDI]+ +modifier_event [ukhpPGHSDIW]+ modifier_bp [rwx]{1,3} %% @@ -273,6 +306,7 @@ cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } +duration_time { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } /* @@ -307,8 +341,8 @@ 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)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } +{bpf_source} { if (!isbpf(yyscanner)) { USER_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/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index 646ecf736aad..e6599e290f46 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "perf.h" #include "util/util.h" #include "util/debug.h" diff --git a/tools/perf/util/parse-regs-options.h b/tools/perf/util/parse-regs-options.h index 7d762b188007..cdefb1acf6be 100644 --- a/tools/perf/util/parse-regs-options.h +++ b/tools/perf/util/parse-regs-options.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_PARSE_REGS_OPTIONS_H #define _PERF_PARSE_REGS_OPTIONS_H 1 struct option; diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 50ec3bc87a60..933f5c6bffb4 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * I'm tired of doing "vsnprintf()" etc just to open a * file, so here's a "return static buffer with printf" diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h index 9a276a58e3c2..14a254ada7eb 100644 --- a/tools/perf/util/path.h +++ b/tools/perf/util/path.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_PATH_H #define _PERF_PATH_H diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c index d55092964da2..4f3aa8d99ef4 100644 --- a/tools/perf/util/perf-hooks.c +++ b/tools/perf/util/perf-hooks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * perf_hooks.c * diff --git a/tools/perf/util/perf-hooks.h b/tools/perf/util/perf-hooks.h index 838d5797bc1e..27fbec62d4fe 100644 --- a/tools/perf/util/perf-hooks.h +++ b/tools/perf/util/perf-hooks.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_UTIL_PERF_HOOKS_H #define PERF_UTIL_PERF_HOOKS_H diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index b2ae039eff85..2acfcc527cac 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include "perf_regs.h" #include "event.h" diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 32b37d19dcc3..c9319f8d17a6 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_REGS_H #define __PERF_REGS_H diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index ac16a9db1fb5..07cb2ac041d7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,7 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/list.h> #include <linux/compiler.h> #include <sys/types.h> #include <errno.h> +#include <fcntl.h> #include <sys/stat.h> #include <unistd.h> #include <stdio.h> @@ -470,17 +472,36 @@ static void pmu_read_sysfs(void) closedir(dir); } +static struct cpu_map *__pmu_cpumask(const char *path) +{ + FILE *file; + struct cpu_map *cpus; + + file = fopen(path, "r"); + if (!file) + return NULL; + + cpus = cpu_map__read(file); + fclose(file); + return cpus; +} + +/* + * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) + * may have a "cpus" file. + */ +#define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" +#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" + static struct cpu_map *pmu_cpumask(const char *name) { - struct stat st; char path[PATH_MAX]; - FILE *file; struct cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); const char *templates[] = { - "%s/bus/event_source/devices/%s/cpumask", - "%s/bus/event_source/devices/%s/cpus", - NULL + CPUS_TEMPLATE_UNCORE, + CPUS_TEMPLATE_CPU, + NULL }; const char **template; @@ -489,20 +510,25 @@ static struct cpu_map *pmu_cpumask(const char *name) for (template = templates; *template; template++) { snprintf(path, PATH_MAX, *template, sysfs, name); - if (stat(path, &st) == 0) - break; + cpus = __pmu_cpumask(path); + if (cpus) + return cpus; } - if (!*template) - return NULL; + return NULL; +} - file = fopen(path, "r"); - if (!file) - return NULL; +static bool pmu_is_uncore(const char *name) +{ + char path[PATH_MAX]; + struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); - cpus = cpu_map__read(file); - fclose(file); - return cpus; + snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); + cpus = __pmu_cpumask(path); + cpu_map__put(cpus); + + return !!cpus; } /* @@ -516,16 +542,8 @@ char * __weak get_cpuid_str(void) return NULL; } -/* - * From the pmu_events_map, find the table of PMU events that corresponds - * to the current running CPU. Then, add all PMU events from that table - * as aliases. - */ -static void pmu_add_cpu_aliases(struct list_head *head, const char *name) +static char *perf_pmu__getcpuid(void) { - int i; - struct pmu_events_map *map; - struct pmu_event *pe; char *cpuid; static bool printed; @@ -535,22 +553,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name) if (!cpuid) cpuid = get_cpuid_str(); if (!cpuid) - return; + return NULL; if (!printed) { pr_debug("Using CPUID %s\n", cpuid); printed = true; } + return cpuid; +} + +struct pmu_events_map *perf_pmu__find_map(void) +{ + struct pmu_events_map *map; + char *cpuid = perf_pmu__getcpuid(); + int i; i = 0; - while (1) { + for (;;) { map = &pmu_events_map[i++]; - if (!map->table) - goto out; + if (!map->table) { + map = NULL; + break; + } if (!strcmp(map->cpuid, cpuid)) break; } + free(cpuid); + return map; +} + +/* + * From the pmu_events_map, find the table of PMU events that corresponds + * to the current running CPU. Then, add all PMU events from that table + * as aliases. + */ +static void pmu_add_cpu_aliases(struct list_head *head, const char *name) +{ + int i; + struct pmu_events_map *map; + struct pmu_event *pe; + + map = perf_pmu__find_map(); + if (!map) + return; /* * Found a matching PMU events table. Create aliases @@ -560,8 +606,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name) const char *pname; pe = &map->table[i++]; - if (!pe->name) + if (!pe->name) { + if (pe->metric_group || pe->metric_name) + continue; break; + } pname = pe->pmu ? pe->pmu : "cpu"; if (strncmp(pname, name, strlen(pname))) @@ -575,9 +624,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name) (char *)pe->metric_expr, (char *)pe->metric_name); } - -out: - free(cpuid); } struct perf_event_attr * __weak @@ -617,6 +663,8 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->cpus = pmu_cpumask(name); + pmu->is_uncore = pmu_is_uncore(name); + INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 389e9729331f..27c75e635866 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PMU_H #define __PMU_H @@ -22,6 +23,7 @@ struct perf_pmu { char *name; __u32 type; bool selectable; + bool is_uncore; struct perf_event_attr *default_config; struct cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ @@ -90,4 +92,6 @@ int perf_pmu__test(void); struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); +struct pmu_events_map *perf_pmu__find_map(void); + #endif /* __PMU_H */ diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c index e908177b9976..23e367063446 100644 --- a/tools/perf/util/print_binary.c +++ b/tools/perf/util/print_binary.c @@ -1,41 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 #include "print_binary.h" #include <linux/log2.h> #include "sane_ctype.h" -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra) +int binary__fprintf(unsigned char *data, size_t len, + size_t bytes_per_line, binary__fprintf_t printer, + void *extra, FILE *fp) { size_t i, j, mask; + int printed = 0; if (!printer) - return; + return 0; bytes_per_line = roundup_pow_of_two(bytes_per_line); mask = bytes_per_line - 1; - printer(BINARY_PRINT_DATA_BEGIN, 0, extra); + printed += printer(BINARY_PRINT_DATA_BEGIN, 0, extra, fp); for (i = 0; i < len; i++) { if ((i & mask) == 0) { - printer(BINARY_PRINT_LINE_BEGIN, -1, extra); - printer(BINARY_PRINT_ADDR, i, extra); + printed += printer(BINARY_PRINT_LINE_BEGIN, -1, extra, fp); + printed += printer(BINARY_PRINT_ADDR, i, extra, fp); } - printer(BINARY_PRINT_NUM_DATA, data[i], extra); + printed += printer(BINARY_PRINT_NUM_DATA, data[i], extra, fp); if (((i & mask) == mask) || i == len - 1) { for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_NUM_PAD, -1, extra); + printed += printer(BINARY_PRINT_NUM_PAD, -1, extra, fp); - printer(BINARY_PRINT_SEP, i, extra); + printer(BINARY_PRINT_SEP, i, extra, fp); for (j = i & ~mask; j <= i; j++) - printer(BINARY_PRINT_CHAR_DATA, data[j], extra); + printed += printer(BINARY_PRINT_CHAR_DATA, data[j], extra, fp); for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_CHAR_PAD, i, extra); - printer(BINARY_PRINT_LINE_END, -1, extra); + printed += printer(BINARY_PRINT_CHAR_PAD, i, extra, fp); + printed += printer(BINARY_PRINT_LINE_END, -1, extra, fp); } } - printer(BINARY_PRINT_DATA_END, -1, extra); + printed += printer(BINARY_PRINT_DATA_END, -1, extra, fp); + return printed; } int is_printable_array(char *p, unsigned int len) diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h index da0427263d2d..2a1554afc957 100644 --- a/tools/perf/util/print_binary.h +++ b/tools/perf/util/print_binary.h @@ -1,7 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_PRINT_BINARY_H #define PERF_PRINT_BINARY_H #include <stddef.h> +#include <stdio.h> enum binary_printer_ops { BINARY_PRINT_DATA_BEGIN, @@ -16,12 +18,19 @@ enum binary_printer_ops { BINARY_PRINT_DATA_END, }; -typedef void (*print_binary_t)(enum binary_printer_ops op, - unsigned int val, void *extra); +typedef int (*binary__fprintf_t)(enum binary_printer_ops op, + unsigned int val, void *extra, FILE *fp); -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra); +int binary__fprintf(unsigned char *data, size_t len, + size_t bytes_per_line, binary__fprintf_t printer, + void *extra, FILE *fp); + +static inline void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, binary__fprintf_t printer, + void *extra) +{ + binary__fprintf(data, len, bytes_per_line, printer, extra, stdout); +} int is_printable_array(char *p, unsigned int len); 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..45b14f020558 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -1,9 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PROBE_EVENT_H #define _PROBE_EVENT_H #include <linux/compiler.h> #include <stdbool.h> #include "intlist.h" +#include "namespaces.h" /* Probe related configurations */ struct probe_conf { @@ -92,6 +94,7 @@ 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 +166,12 @@ 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 +185,7 @@ 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..4ae1123c6794 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -15,6 +15,7 @@ * */ #include <errno.h> +#include <fcntl.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/uio.h> @@ -412,13 +413,15 @@ 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 +434,11 @@ 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 +447,7 @@ 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 +455,7 @@ 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 +560,7 @@ 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 +568,7 @@ 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 +980,7 @@ 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..63f29b1d22c1 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PROBE_FILE_H #define __PROBE_FILE_H @@ -51,7 +52,7 @@ 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 +70,7 @@ 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/probe-finder.h b/tools/perf/util/probe-finder.h index 27f061551012..16252980ff00 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PROBE_FINDER_H #define _PROBE_FINDER_H diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index b234a6e3d0d4..797fe1ae2d2e 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Simple pointer stack * diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index ded7f2e36624..8729b8be061d 100644 --- a/tools/perf/util/pstack.h +++ b/tools/perf/util/pstack.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_PSTACK_ #define _PERF_PSTACK_ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 9f3b0d9754a8..b4f2f06722a7 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,8 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +util/mmap.c +util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index c129e99114ae..8e49d9cafcfc 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <Python.h> #include <structmember.h> #include <inttypes.h> diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index 1ba8920151d8..22eaa201aa27 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <stdlib.h> #include "strbuf.h" diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h index 055ca45bed99..274bf26d3511 100644 --- a/tools/perf/util/quote.h +++ b/tools/perf/util/quote.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_QUOTE_H #define __PERF_QUOTE_H diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h index 808cc45611fe..a920f702a74d 100644 --- a/tools/perf/util/rb_resort.h +++ b/tools/perf/util/rb_resort.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_RESORT_RB_H_ #define _PERF_RESORT_RB_H_ /* @@ -143,7 +144,8 @@ struct __name##_sorted *__name = __name##_sorted__new __ilist->rblist.nr_entries) /* For 'struct machine->threads' */ -#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine) \ - DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads) +#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket) \ + DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries, \ + __machine->threads[hash_bucket].nr) #endif /* _PERF_RESORT_RB_H_ */ diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h index ff9913b994c2..4c8638a22571 100644 --- a/tools/perf/util/rblist.h +++ b/tools/perf/util/rblist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_RBLIST_H #define __PERF_RBLIST_H diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index d91bdf5a1aa4..1e97937b03a9 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "evlist.h" #include "evsel.h" #include "cpumap.h" diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c new file mode 100644 index 000000000000..5e52e7baa7b6 --- /dev/null +++ b/tools/perf/util/rwsem.c @@ -0,0 +1,32 @@ +#include "util.h" +#include "rwsem.h" + +int init_rwsem(struct rw_semaphore *sem) +{ + return pthread_rwlock_init(&sem->lock, NULL); +} + +int exit_rwsem(struct rw_semaphore *sem) +{ + return pthread_rwlock_destroy(&sem->lock); +} + +int down_read(struct rw_semaphore *sem) +{ + return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock); +} + +int up_read(struct rw_semaphore *sem) +{ + return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock); +} + +int down_write(struct rw_semaphore *sem) +{ + return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock); +} + +int up_write(struct rw_semaphore *sem) +{ + return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock); +} diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h new file mode 100644 index 000000000000..94565ad4d494 --- /dev/null +++ b/tools/perf/util/rwsem.h @@ -0,0 +1,19 @@ +#ifndef _PERF_RWSEM_H +#define _PERF_RWSEM_H + +#include <pthread.h> + +struct rw_semaphore { + pthread_rwlock_t lock; +}; + +int init_rwsem(struct rw_semaphore *sem); +int exit_rwsem(struct rw_semaphore *sem); + +int down_read(struct rw_semaphore *sem); +int up_read(struct rw_semaphore *sem); + +int down_write(struct rw_semaphore *sem); +int up_write(struct rw_semaphore *sem); + +#endif /* _PERF_RWSEM_H */ diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h index 4308c22c22ad..c2b42ff9ff32 100644 --- a/tools/perf/util/sane_ctype.h +++ b/tools/perf/util/sane_ctype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_SANE_CTYPE_H #define _PERF_SANE_CTYPE_H 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..5c412310f266 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> #include <linux/kernel.h> @@ -32,14 +33,14 @@ static int perf_session__deliver_event(struct perf_session *session, static int perf_session__open(struct perf_session *session) { - struct perf_data_file *file = session->file; + struct perf_data *data = session->data; if (perf_session__read_header(session) < 0) { pr_err("incompatible file format (rerun with -v to learn more)\n"); return -1; } - if (perf_data_file__is_pipe(file)) + if (perf_data__is_pipe(data)) return 0; if (perf_header__has_feat(&session->header, HEADER_STAT)) @@ -120,7 +121,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe, session->tool, event->file_offset); } -struct perf_session *perf_session__new(struct perf_data_file *file, +struct perf_session *perf_session__new(struct perf_data *data, bool repipe, struct perf_tool *tool) { struct perf_session *session = zalloc(sizeof(*session)); @@ -134,13 +135,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file, machines__init(&session->machines); ordered_events__init(&session->ordered_events, ordered_events__deliver_event); - if (file) { - if (perf_data_file__open(file)) + if (data) { + if (perf_data__open(data)) goto out_delete; - session->file = file; + session->data = data; - if (perf_data_file__is_read(file)) { + if (perf_data__is_read(data)) { if (perf_session__open(session) < 0) goto out_close; @@ -148,7 +149,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, * set session attributes that are present in perf.data * but not in pipe-mode. */ - if (!file->is_pipe) { + if (!data->is_pipe) { perf_session__set_id_hdr_size(session); perf_session__set_comm_exec(session); } @@ -157,7 +158,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, session->machines.host.env = &perf_env; } - if (!file || perf_data_file__is_write(file)) { + if (!data || perf_data__is_write(data)) { /* * In O_RDONLY mode this will be performed when reading the * kernel MMAP event, in perf_event__process_mmap(). @@ -170,7 +171,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is * processed, so perf_evlist__sample_id_all is not meaningful here. */ - if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps && + if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps && tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; @@ -179,7 +180,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, return session; out_close: - perf_data_file__close(file); + perf_data__close(data); out_delete: perf_session__delete(session); out: @@ -201,8 +202,8 @@ void perf_session__delete(struct perf_session *session) perf_session__delete_threads(session); perf_env__exit(&session->header.env); machines__exit(&session->machines); - if (session->file) - perf_data_file__close(session->file); + if (session->data) + perf_data__close(session->data); free(session); } @@ -290,8 +291,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused, __maybe_unused) { dump_printf(": unhandled!\n"); - if (perf_data_file__is_pipe(session->file)) - skipn(perf_data_file__fd(session->file), event->auxtrace.size); + if (perf_data__is_pipe(session->data)) + skipn(perf_data__fd(session->data), event->auxtrace.size); return event->auxtrace.size; } @@ -374,6 +375,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; + if (tool->namespaces == NULL) + tool->namespaces = process_event_stub; if (tool->fork == NULL) tool->fork = process_event_stub; if (tool->exit == NULL) @@ -428,6 +431,8 @@ 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) @@ -1118,6 +1123,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + if (sample_type & PERF_SAMPLE_PHYS_ADDR) + printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr); + if (sample_type & PERF_SAMPLE_TRANSACTION) printf("... transaction: %" PRIx64 "\n", sample->transaction); @@ -1125,6 +1133,30 @@ 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 +1301,7 @@ 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); @@ -1317,7 +1350,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); int err; dump_event(session->evlist, event, file_offset, NULL); @@ -1371,6 +1404,8 @@ 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; } @@ -1415,10 +1450,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, goto out_parse_sample; } - if (perf_data_file__is_pipe(session->file)) + if (perf_data__is_pipe(session->data)) return -1; - fd = perf_data_file__fd(session->file); + fd = perf_data__fd(session->data); hdr_sz = sizeof(struct perf_event_header); if (buf_sz < hdr_sz) @@ -1653,7 +1688,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -1794,7 +1829,7 @@ static int __perf_session__process_events(struct perf_session *session, { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; - int fd = perf_data_file__fd(session->file); + int fd = perf_data__fd(session->data); u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; @@ -1815,7 +1850,7 @@ static int __perf_session__process_events(struct perf_session *session, if (data_offset + data_size < file_size) file_size = data_offset + data_size; - ui_progress__init(&prog, file_size, "Processing events..."); + ui_progress__init_size(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; if (mmap_size > file_size) { @@ -1911,13 +1946,13 @@ out_err: int perf_session__process_events(struct perf_session *session) { - u64 size = perf_data_file__size(session->file); + u64 size = perf_data__size(session->data); int err; if (perf_session__register_idle_thread(session) < 0) return -ENOMEM; - if (!perf_data_file__is_pipe(session->file)) + if (!perf_data__is_pipe(session->data)) err = __perf_session__process_events(session, session->header.data_offset, session->header.data_size, size); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 47b5e7dbcb18..da1434a7c120 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SESSION_H #define __PERF_SESSION_H @@ -32,13 +33,13 @@ struct perf_session { void *one_mmap_addr; u64 one_mmap_offset; struct ordered_events ordered_events; - struct perf_data_file *file; + struct perf_data *data; struct perf_tool *tool; }; struct perf_tool; -struct perf_session *perf_session__new(struct perf_data_file *file, +struct perf_session *perf_session__new(struct perf_data *data, bool repipe, struct perf_tool *tool); void perf_session__delete(struct perf_session *session); @@ -113,7 +114,7 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; -#define session_done() ACCESS_ONCE(session_done) +#define session_done() READ_ONCE(session_done) int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, 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..a00eacdf02ed 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> #include <regex.h> @@ -225,6 +226,9 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) if (sym_l == sym_r) return 0; + if (sym_l->inlined || sym_r->inlined) + return strcmp(sym_l->name, sym_r->name); + if (sym_l->start != sym_r->start) return (int64_t)(sym_r->start - sym_l->start); @@ -283,6 +287,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, ret += repsep_snprintf(bf + ret, size - ret, "%.*s", width - ret, sym->name); + if (sym->inlined) + ret += repsep_snprintf(bf + ret, size - ret, + " (inlined)"); } } else { size_t len = BITS_PER_LONG / 4; @@ -1316,6 +1323,47 @@ struct sort_entry sort_mem_dcacheline = { }; static int64_t +sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.phys_addr; + if (right->mem_info) + r = right->mem_info->daddr.phys_addr; + + return (int64_t)(r - l); +} + +static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + uint64_t addr = 0; + size_t ret = 0; + size_t len = BITS_PER_LONG / 4; + + addr = he->mem_info->daddr.phys_addr; + + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level); + + ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr); + + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, ""); + + if (ret > width) + bf[width] = '\0'; + + return width; +} + +struct sort_entry sort_mem_phys_daddr = { + .se_header = "Data Physical Address", + .se_cmp = sort__phys_daddr_cmp, + .se_snprintf = hist_entry__phys_daddr_snprintf, + .se_width_idx = HISTC_MEM_PHYS_DADDR, +}; + +static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->branch_info || !right->branch_info) @@ -1547,6 +1595,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), + DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr), }; #undef DIM @@ -2563,7 +2612,7 @@ 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/sort.h b/tools/perf/util/sort.h index b7c75597e18f..f5901c10a563 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SORT_H #define __PERF_SORT_H #include "../builtin.h" @@ -129,7 +130,6 @@ struct hist_entry { }; char *srcline; char *srcfile; - struct inline_node *inline_node; struct symbol *parent; struct branch_info *branch_info; struct hists *hists; @@ -245,6 +245,7 @@ enum sort_type { SORT_MEM_SNOOP, SORT_MEM_DCACHELINE, SORT_MEM_IADDR_SYMBOL, + SORT_MEM_PHYS_DADDR, }; /* diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index ebc88a74e67b..d19f05c56de6 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <inttypes.h> #include <stdio.h> #include <stdlib.h> @@ -10,7 +11,7 @@ #include "util/debug.h" #include "util/callchain.h" #include "srcline.h" - +#include "string2.h" #include "symbol.h" bool srcline_full_filename; @@ -33,28 +34,17 @@ static const char *dso__name(struct dso *dso) return dso_name; } -static int inline_list__append(char *filename, char *funcname, int line_nr, - struct inline_node *node, struct dso *dso) +static int inline_list__append(struct symbol *symbol, char *srcline, + struct inline_node *node) { struct inline_list *ilist; - char *demangled; ilist = zalloc(sizeof(*ilist)); if (ilist == NULL) return -1; - ilist->filename = filename; - ilist->line_nr = line_nr; - - if (dso != NULL) { - demangled = dso__demangle_sym(dso, 0, funcname); - if (demangled == NULL) { - ilist->funcname = funcname; - } else { - ilist->funcname = demangled; - free(funcname); - } - } + ilist->symbol = symbol; + ilist->srcline = srcline; if (callchain_param.order == ORDER_CALLEE) list_add_tail(&ilist->list, &node->val); @@ -64,6 +54,65 @@ static int inline_list__append(char *filename, char *funcname, int line_nr, return 0; } +/* basename version that takes a const input string */ +static const char *gnu_basename(const char *path) +{ + const char *base = strrchr(path, '/'); + + return base ? base + 1 : path; +} + +static char *srcline_from_fileline(const char *file, unsigned int line) +{ + char *srcline; + + if (!file) + return NULL; + + if (!srcline_full_filename) + file = gnu_basename(file); + + if (asprintf(&srcline, "%s:%u", file, line) < 0) + return NULL; + + return srcline; +} + +static struct symbol *new_inline_sym(struct dso *dso, + struct symbol *base_sym, + const char *funcname) +{ + struct symbol *inline_sym; + char *demangled = NULL; + + if (dso) { + demangled = dso__demangle_sym(dso, 0, funcname); + if (demangled) + funcname = demangled; + } + + if (base_sym && strcmp(funcname, base_sym->name) == 0) { + /* reuse the real, existing symbol */ + inline_sym = base_sym; + /* ensure that we don't alias an inlined symbol, which could + * lead to double frees in inline_node__delete + */ + assert(!base_sym->inlined); + } else { + /* create a fake symbol for the inline frame */ + inline_sym = symbol__new(base_sym ? base_sym->start : 0, + base_sym ? base_sym->end : 0, + base_sym ? base_sym->binding : 0, + funcname); + if (inline_sym) + inline_sym->inlined = 1; + } + + free(demangled); + + return inline_sym; +} + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -155,6 +204,9 @@ 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) @@ -204,18 +256,23 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 static int inline_list__append_dso_a2l(struct dso *dso, - struct inline_node *node) + struct inline_node *node, + struct symbol *sym) { struct a2l_data *a2l = dso->a2l; - char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL; - char *filename = a2l->filename ? strdup(a2l->filename) : NULL; + struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname); + char *srcline = NULL; - return inline_list__append(filename, funcname, a2l->line, node, dso); + if (a2l->filename) + srcline = srcline_from_fileline(a2l->filename, a2l->line); + + return inline_list__append(inline_sym, srcline, node); } static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso, - bool unwind_inlines, struct inline_node *node) + bool unwind_inlines, struct inline_node *node, + struct symbol *sym) { int ret = 0; struct a2l_data *a2l = dso->a2l; @@ -241,15 +298,18 @@ static int addr2line(const char *dso_name, u64 addr, if (unwind_inlines) { int cnt = 0; - if (node && inline_list__append_dso_a2l(dso, node)) + if (node && inline_list__append_dso_a2l(dso, node, sym)) return 0; while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, &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)) + if (inline_list__append_dso_a2l(dso, node, sym)) return 0; // found at least one inline frame ret = 1; @@ -281,7 +341,7 @@ void dso__free_a2l(struct dso *dso) } static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso) + struct dso *dso, struct symbol *sym) { struct inline_node *node; @@ -294,17 +354,8 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr, INIT_LIST_HEAD(&node->val); node->addr = addr; - if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node)) - goto out_free_inline_node; - - if (list_empty(&node->val)) - goto out_free_inline_node; - + addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); return node; - -out_free_inline_node: - inline_node__delete(node); - return NULL; } #else /* HAVE_LIBBFD_SUPPORT */ @@ -334,7 +385,8 @@ static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, struct dso *dso __maybe_unused, bool unwind_inlines __maybe_unused, - struct inline_node *node __maybe_unused) + struct inline_node *node __maybe_unused, + struct symbol *sym __maybe_unused) { FILE *fp; char cmd[PATH_MAX]; @@ -374,16 +426,18 @@ void dso__free_a2l(struct dso *dso __maybe_unused) } static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso __maybe_unused) + struct dso *dso __maybe_unused, + struct symbol *sym) { FILE *fp; char cmd[PATH_MAX]; struct inline_node *node; char *filename = NULL; - size_t len; + char *funcname = NULL; + size_t filelen, funclen; unsigned int line_nr = 0; - scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64, + scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64, dso_name, addr); fp = popen(cmd, "r"); @@ -401,26 +455,34 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr, INIT_LIST_HEAD(&node->val); node->addr = addr; - while (getline(&filename, &len, fp) != -1) { - if (filename_split(filename, &line_nr) != 1) { - free(filename); + /* addr2line -f generates two lines for each inlined functions */ + while (getline(&funcname, &funclen, fp) != -1) { + char *srcline; + struct symbol *inline_sym; + + rtrim(funcname); + + if (getline(&filename, &filelen, fp) == -1) goto out; - } - if (inline_list__append(filename, NULL, line_nr, node, - NULL) != 0) + if (filename_split(filename, &line_nr) != 1) goto out; - filename = NULL; + srcline = srcline_from_fileline(filename, line_nr); + inline_sym = new_inline_sym(dso, sym, funcname); + + if (inline_list__append(inline_sym, srcline, node) != 0) { + free(srcline); + if (inline_sym && inline_sym->inlined) + symbol__delete(inline_sym); + goto out; + } } out: pclose(fp); - - if (list_empty(&node->val)) { - inline_node__delete(node); - return NULL; - } + free(filename); + free(funcname); return node; } @@ -448,19 +510,18 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, if (dso_name == NULL) goto out; - if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL)) + if (!addr2line(dso_name, addr, &file, &line, dso, + unwind_inlines, NULL, sym)) goto out; - if (asprintf(&srcline, "%s:%u", - srcline_full_filename ? file : basename(file), - line) < 0) { - free(file); + srcline = srcline_from_fileline(file, line); + free(file); + + if (!srcline) goto out; - } dso->a2l_fails = 0; - free(file); return srcline; out: @@ -494,7 +555,74 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, return __get_srcline(dso, addr, sym, show_sym, show_addr, false); } -struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr) +struct srcline_node { + u64 addr; + char *srcline; + struct rb_node rb_node; +}; + +void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *parent = NULL; + struct srcline_node *i, *node; + + node = zalloc(sizeof(struct srcline_node)); + if (!node) { + perror("not enough memory for the srcline node"); + return; + } + + node->addr = addr; + node->srcline = srcline; + + while (*p != NULL) { + parent = *p; + i = rb_entry(parent, struct srcline_node, rb_node); + if (addr < i->addr) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&node->rb_node, parent, p); + rb_insert_color(&node->rb_node, tree); +} + +char *srcline__tree_find(struct rb_root *tree, u64 addr) +{ + struct rb_node *n = tree->rb_node; + + while (n) { + struct srcline_node *i = rb_entry(n, struct srcline_node, + rb_node); + + if (addr < i->addr) + n = n->rb_left; + else if (addr > i->addr) + n = n->rb_right; + else + return i->srcline; + } + + return NULL; +} + +void srcline__tree_delete(struct rb_root *tree) +{ + struct srcline_node *pos; + struct rb_node *next = rb_first(tree); + + while (next) { + pos = rb_entry(next, struct srcline_node, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, tree); + free_srcline(pos->srcline); + zfree(&pos); + } +} + +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr, + struct symbol *sym) { const char *dso_name; @@ -502,7 +630,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr) if (dso_name == NULL) return NULL; - return addr2inlines(dso_name, addr, dso); + return addr2inlines(dso_name, addr, dso, sym); } void inline_node__delete(struct inline_node *node) @@ -511,10 +639,63 @@ void inline_node__delete(struct inline_node *node) list_for_each_entry_safe(ilist, tmp, &node->val, list) { list_del_init(&ilist->list); - zfree(&ilist->filename); - zfree(&ilist->funcname); + free_srcline(ilist->srcline); + /* only the inlined symbols are owned by the list */ + if (ilist->symbol && ilist->symbol->inlined) + symbol__delete(ilist->symbol); free(ilist); } free(node); } + +void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *parent = NULL; + const u64 addr = inlines->addr; + struct inline_node *i; + + while (*p != NULL) { + parent = *p; + i = rb_entry(parent, struct inline_node, rb_node); + if (addr < i->addr) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&inlines->rb_node, parent, p); + rb_insert_color(&inlines->rb_node, tree); +} + +struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr) +{ + struct rb_node *n = tree->rb_node; + + while (n) { + struct inline_node *i = rb_entry(n, struct inline_node, + rb_node); + + if (addr < i->addr) + n = n->rb_left; + else if (addr > i->addr) + n = n->rb_right; + else + return i; + } + + return NULL; +} + +void inlines__tree_delete(struct rb_root *tree) +{ + struct inline_node *pos; + struct rb_node *next = rb_first(tree); + + while (next) { + pos = rb_entry(next, struct inline_node, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, tree); + inline_node__delete(pos); + } +} diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h index 7b52ba88676e..847b7086182c 100644 --- a/tools/perf/util/srcline.h +++ b/tools/perf/util/srcline.h @@ -1,7 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_SRCLINE_H #define PERF_SRCLINE_H #include <linux/list.h> +#include <linux/rbtree.h> #include <linux/types.h> struct dso; @@ -14,21 +16,38 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym, bool show_addr, bool unwind_inlines); void free_srcline(char *srcline); +/* insert the srcline into the DSO, which will take ownership */ +void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline); +/* find previously inserted srcline */ +char *srcline__tree_find(struct rb_root *tree, u64 addr); +/* delete all srclines within the tree */ +void srcline__tree_delete(struct rb_root *tree); + #define SRCLINE_UNKNOWN ((char *) "??:0") struct inline_list { - char *filename; - char *funcname; - unsigned int line_nr; + struct symbol *symbol; + char *srcline; struct list_head list; }; struct inline_node { u64 addr; struct list_head val; + struct rb_node rb_node; }; -struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr); +/* parse inlined frames for the given address */ +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr, + struct symbol *sym); +/* free resources associated to the inline node list */ void inline_node__delete(struct inline_node *node); +/* insert the inline node list into the DSO, which will take ownership */ +void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines); +/* find previously inserted inline node list */ +struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr); +/* delete all nodes within the tree of inline_node s */ +void inlines__tree_delete(struct rb_root *tree); + #endif /* PERF_SRCLINE_H */ diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 719d6cb86952..855e35cbb1dc 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include "evsel.h" #include "stat.h" @@ -6,6 +7,7 @@ #include "rblist.h" #include "evlist.h" #include "expr.h" +#include "metricgroup.h" enum { CTX_BIT_USER = 1 << 0, @@ -55,7 +57,6 @@ struct saved_value { struct rb_node rb_node; struct perf_evsel *evsel; int cpu; - int ctx; struct stats stats; }; @@ -66,11 +67,13 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) rb_node); const struct saved_value *b = entry; - if (a->ctx != b->ctx) - 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, @@ -85,13 +88,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, } static struct saved_value *saved_value_lookup(struct perf_evsel *evsel, - int cpu, int ctx, + int cpu, bool create) { struct rb_node *nd; struct saved_value dm = { .cpu = cpu, - .ctx = ctx, .evsel = evsel, }; nd = rblist__find(&runtime_saved_values, &dm); @@ -177,59 +179,60 @@ void perf_stat__reset_shadow_stats(void) * more semantic information such as miss/hit ratios, * instruction rates, etc: */ -void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, +void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, int cpu) { int ctx = evsel_context(counter); + count *= counter->scale; + if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) || perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK)) - update_stats(&runtime_nsecs_stats[cpu], count[0]); + update_stats(&runtime_nsecs_stats[cpu], count); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_stats(&runtime_cycles_stats[ctx][cpu], count[0]); + update_stats(&runtime_cycles_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]); + update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_stats(&runtime_transaction_stats[ctx][cpu], count[0]); + update_stats(&runtime_transaction_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, ELISION_START)) - update_stats(&runtime_elision_stats[ctx][cpu], count[0]); + update_stats(&runtime_elision_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) - update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]); + update_stats(&runtime_topdown_total_slots[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) - update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]); + update_stats(&runtime_topdown_slots_issued[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) - update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]); + update_stats(&runtime_topdown_slots_retired[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) - update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]); + update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count); else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) - update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]); + update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]); + update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]); + update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_stats(&runtime_branches_stats[ctx][cpu], count[0]); + update_stats(&runtime_branches_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]); + update_stats(&runtime_cacherefs_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]); + update_stats(&runtime_l1_dcache_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]); + update_stats(&runtime_ll_cache_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]); + update_stats(&runtime_ll_cache_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]); + update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]); + update_stats(&runtime_itlb_cache_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]); + update_stats(&runtime_smi_num_stats[ctx][cpu], count); else if (perf_stat_evsel__is(counter, APERF)) - update_stats(&runtime_aperf_stats[ctx][cpu], count[0]); + update_stats(&runtime_aperf_stats[ctx][cpu], count); if (counter->collect_stat) { - struct saved_value *v = saved_value_lookup(counter, cpu, ctx, - true); - update_stats(&v->stats, count[0]); + struct saved_value *v = saved_value_lookup(counter, cpu, true); + update_stats(&v->stats, count); } } @@ -623,15 +626,68 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel, out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num); } +static void generic_metric(const char *metric_expr, + struct perf_evsel **metric_events, + char *name, + const char *metric_name, + double avg, + int cpu, + struct perf_stat_output_ctx *out) +{ + print_metric_t print_metric = out->print_metric; + struct parse_ctx pctx; + double ratio; + int i; + void *ctxp = out->ctx; + + expr__ctx_init(&pctx); + expr__add_id(&pctx, name, avg); + for (i = 0; metric_events[i]; i++) { + struct saved_value *v; + struct stats *stats; + double scale; + + if (!strcmp(metric_events[i]->name, "duration_time")) { + stats = &walltime_nsecs_stats; + scale = 1e-9; + } else { + v = saved_value_lookup(metric_events[i], cpu, false); + if (!v) + break; + stats = &v->stats; + scale = 1.0; + } + expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale); + } + if (!metric_events[i]) { + const char *p = metric_expr; + + if (expr__parse(&ratio, &pctx, &p) == 0) + print_metric(ctxp, NULL, "%8.1f", + metric_name ? + metric_name : + out->force_header ? name : "", + ratio); + else + print_metric(ctxp, NULL, NULL, + out->force_header ? + (metric_name ? metric_name : name) : "", 0); + } else + print_metric(ctxp, NULL, NULL, "", 0); +} + void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, - struct perf_stat_output_ctx *out) + struct perf_stat_output_ctx *out, + struct rblist *metric_events) { void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; const char *color = NULL; int ctx = evsel_context(evsel); + struct metric_event *me; + int num = 1; if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = avg_stats(&runtime_cycles_stats[ctx][cpu]); @@ -815,33 +871,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, else print_metric(ctxp, NULL, NULL, name, 0); } else if (evsel->metric_expr) { - struct parse_ctx pctx; - int i; - - expr__ctx_init(&pctx); - expr__add_id(&pctx, evsel->name, avg); - for (i = 0; evsel->metric_events[i]; i++) { - struct saved_value *v; - - v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false); - if (!v) - break; - expr__add_id(&pctx, evsel->metric_events[i]->name, - avg_stats(&v->stats)); - } - if (!evsel->metric_events[i]) { - const char *p = evsel->metric_expr; - - if (expr__parse(&ratio, &pctx, &p) == 0) - print_metric(ctxp, NULL, "%8.1f", - evsel->metric_name ? - evsel->metric_name : - out->force_header ? evsel->name : "", - ratio); - else - print_metric(ctxp, NULL, NULL, "", 0); - } else - print_metric(ctxp, NULL, NULL, "", 0); + generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name, + evsel->metric_name, avg, cpu, out); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; char unit_buf[10]; @@ -859,6 +890,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { print_smi_cost(cpu, evsel, out); } else { - print_metric(ctxp, NULL, NULL, NULL, 0); + num = 0; } + + if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) { + struct metric_expr *mexp; + + list_for_each_entry (mexp, &me->head, nd) { + if (num++ > 0) + out->new_line(ctxp); + generic_metric(mexp->metric_expr, mexp->metric_events, + evsel->name, mexp->metric_name, + avg, cpu, out); + } + } + if (num == 0) + print_metric(ctxp, NULL, NULL, NULL, 0); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 53b9a994a3dc..151e9efd7286 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> #include <math.h> @@ -69,7 +70,7 @@ double rel_stddev_stats(double stddev, double avg) bool __perf_evsel_stat__is(struct perf_evsel *evsel, enum perf_stat_evsel_id id) { - struct perf_stat_evsel *ps = evsel->priv; + struct perf_stat_evsel *ps = evsel->stats; return ps->id == id; } @@ -93,7 +94,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { void perf_stat_evsel_id_init(struct perf_evsel *evsel) { - struct perf_stat_evsel *ps = evsel->priv; + struct perf_stat_evsel *ps = evsel->stats; int i; /* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */ @@ -109,7 +110,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; - struct perf_stat_evsel *ps = evsel->priv; + struct perf_stat_evsel *ps = evsel->stats; for (i = 0; i < 3; i++) init_stats(&ps->res_stats[i]); @@ -119,8 +120,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { - evsel->priv = zalloc(sizeof(struct perf_stat_evsel)); - if (evsel->priv == NULL) + evsel->stats = zalloc(sizeof(struct perf_stat_evsel)); + if (evsel->stats == NULL) return -ENOMEM; perf_evsel__reset_stat_priv(evsel); return 0; @@ -128,7 +129,11 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { - zfree(&evsel->priv); + struct perf_stat_evsel *ps = evsel->stats; + + if (ps) + free(ps->group_data); + zfree(&evsel->stats); } static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, @@ -273,7 +278,9 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel perf_evsel__compute_deltas(evsel, cpu, thread, count); perf_counts_values__scale(count, config->scale, NULL); if (config->aggr_mode == AGGR_NONE) - perf_stat__update_shadow_stats(evsel, count->values, cpu); + perf_stat__update_shadow_stats(evsel, count->val, cpu); + if (config->aggr_mode == AGGR_THREAD) + perf_stat__update_shadow_stats(evsel, count->val, 0); break; case AGGR_GLOBAL: aggr->val += count->val; @@ -314,9 +321,8 @@ int perf_stat_process_counter(struct perf_stat_config *config, struct perf_evsel *counter) { struct perf_counts_values *aggr = &counter->counts->aggr; - struct perf_stat_evsel *ps = counter->priv; + struct perf_stat_evsel *ps = counter->stats; u64 *count = counter->counts->aggr.values; - u64 val; int i, ret; aggr->val = aggr->ena = aggr->run = 0; @@ -356,8 +362,7 @@ int perf_stat_process_counter(struct perf_stat_config *config, /* * Save the full runtime - to allow normalization during printout: */ - val = counter->scale * *count; - perf_stat__update_shadow_stats(counter, &val, 0); + perf_stat__update_shadow_stats(counter, *count, 0); return 0; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 7522bf10b03e..eefca5c981fd 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_STATS_H #define __PERF_STATS_H @@ -28,8 +29,9 @@ 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 { @@ -81,7 +83,7 @@ typedef void (*new_line_t )(void *ctx); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); -void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, +void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, int cpu); struct perf_stat_output_ctx { void *ctx; @@ -90,9 +92,11 @@ struct perf_stat_output_ctx { bool force_header; }; +struct rblist; void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, - struct perf_stat_output_ctx *out); + struct perf_stat_output_ctx *out, + struct rblist *metric_events); void perf_stat__collect_metric_expr(struct perf_evlist *); int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index aafe908b82b5..3d1cf5bf7f18 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "debug.h" #include "util.h" #include <linux/kernel.h> diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 802d743378af..ea94d8628980 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_STRBUF_H #define __PERF_STRBUF_H diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index 4dc0af669a30..7f3253d44afd 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include "string2.h" #include "strfilter.h" diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h index cff5eda88728..e0c25a40f796 100644 --- a/tools/perf/util/strfilter.h +++ b/tools/perf/util/strfilter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_STRFILTER_H #define __PERF_STRFILTER_H /* General purpose glob matching filter */ diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index cca53b693a48..aaa08ee8c717 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "string2.h" #include <linux/kernel.h> #include <linux/string.h> diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h index 2f619681bd6a..ee14ca5451ab 100644 --- a/tools/perf/util/string2.h +++ b/tools/perf/util/string2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_STRING_H #define PERF_STRING_H diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 19207e50fce5..d58f1e08b170 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_STRLIST_H #define __PERF_STRLIST_H diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index 946fdf2db97c..e55338d5c3bd 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SVGHELPER_H #define __PERF_SVGHELPER_H diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 502505cf236a..2de770511e70 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <fcntl.h> #include <stdio.h> #include <errno.h> @@ -259,7 +260,7 @@ 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 +327,23 @@ 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 +353,6 @@ 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 +363,12 @@ 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 +379,6 @@ 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 +389,12 @@ 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 +409,7 @@ 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); } @@ -1442,7 +1460,7 @@ 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..ff48d0d49584 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "symbol.h" #include "util.h" @@ -377,7 +378,7 @@ 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..1b67a8639dfe 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <dirent.h> #include <errno.h> #include <stdlib.h> @@ -18,6 +19,7 @@ #include "symbol.h" #include "strlist.h" #include "intlist.h" +#include "namespaces.h" #include "header.h" #include "path.h" #include "sane_ctype.h" @@ -44,6 +46,7 @@ struct symbol_conf symbol_conf = { .show_hist_headers = true, .symfs = "", .event_group = true, + .inline_name = true, }; static enum dso_binary_type binary_type_symtab[] = { @@ -52,6 +55,7 @@ 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, @@ -224,14 +228,15 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) struct maps *maps = &mg->maps[type]; struct map *next, *curr; - pthread_rwlock_wrlock(&maps->lock); + down_write(&maps->lock); curr = maps__first(maps); if (curr == NULL) 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; } @@ -239,10 +244,11 @@ 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); + up_write(&maps->lock); } struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) @@ -550,7 +556,7 @@ 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 +569,8 @@ 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 +602,11 @@ 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 +953,8 @@ 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 +1336,15 @@ 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 +1428,7 @@ 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 +1437,44 @@ 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 +1486,21 @@ 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 +1525,19 @@ 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 +1575,15 @@ 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 +1591,20 @@ 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 +1662,7 @@ out_free: out: dso__set_loaded(dso, map->type); pthread_mutex_unlock(&dso->lock); + nsinfo__mountns_exit(&nsc); return ret; } @@ -1594,7 +1673,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg, struct maps *maps = &mg->maps[type]; struct map *map; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); for (map = maps__first(maps); map; map = map__next(map)) { if (map->dso && strcmp(map->dso->short_name, name) == 0) @@ -1604,7 +1683,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg, map = NULL; out_unlock: - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); return map; } @@ -1660,7 +1739,7 @@ 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..a4f0075b4e5c 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SYMBOL #define __PERF_SYMBOL 1 @@ -59,6 +60,7 @@ struct symbol { u8 binding; u8 idle:1; u8 ignore:1; + u8 inlined:1; u8 arch_sym; char name[0]; }; @@ -186,6 +188,7 @@ struct addr_map_symbol { struct symbol *sym; u64 addr; u64 al_addr; + u64 phys_addr; }; struct branch_info { @@ -207,6 +210,7 @@ struct addr_location { struct thread *thread; struct map *map; struct symbol *sym; + const char *srcline; u64 addr; char level; u8 filtered; @@ -273,7 +277,7 @@ 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 +310,7 @@ 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); diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 63694e174e5c..6dd2cb88ccbe 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <elf.h> #include <inttypes.h> #include <stdio.h> diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index bbb4c1957578..6eea7cff3d4e 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,10 +15,11 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <linux/compiler.h> #ifdef HAVE_SYSCALL_TABLE -#include <linux/compiler.h> #include <string.h> +#include "string2.h" #include "util.h" #if defined(__x86_64__) @@ -105,6 +106,27 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return sc ? sc->id : -1; } +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + int i; + struct syscall *syscalls = tbl->syscalls.entries; + + for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) { + if (strglobmatch(syscalls[i].name, syscall_glob)) { + *idx = i; + return syscalls[i].id; + } + } + + return -1; +} + +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + *idx = -1; + return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); +} + #else /* HAVE_SYSCALL_TABLE */ #include <libaudit.h> @@ -131,4 +153,15 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) { return audit_name_to_syscall(name, tbl->audit_machine); } + +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, + const char *syscall_glob __maybe_unused, int *idx __maybe_unused) +{ + return -1; +} + +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); +} #endif /* HAVE_SYSCALL_TABLE */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index e2951510484f..c8e7e9ce0f01 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SYSCALLTBL_H #define __PERF_SYSCALLTBL_H @@ -17,4 +18,7 @@ void syscalltbl__delete(struct syscalltbl *tbl); const char *syscalltbl__name(const struct syscalltbl *tbl, int id); int syscalltbl__id(struct syscalltbl *tbl, const char *name); +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx); + #endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index 7381b1ca4041..446aa7a56f25 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_TARGET_H #define _PERF_TARGET_H diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c index 8f254a74d97d..e7aa82c06c76 100644 --- a/tools/perf/util/term.c +++ b/tools/perf/util/term.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "term.h" #include <stdlib.h> #include <termios.h> diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h index 2c06a61846a1..607b170a9017 100644 --- a/tools/perf/util/term.h +++ b/tools/perf/util/term.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_TERM_H #define __PERF_TERM_H diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 378c418ca0c1..68b65b10579b 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "../perf.h" #include <errno.h> #include <stdlib.h> @@ -45,6 +46,8 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->cpu = -1; INIT_LIST_HEAD(&thread->namespaces_list); INIT_LIST_HEAD(&thread->comm_list); + init_rwsem(&thread->namespaces_lock); + init_rwsem(&thread->comm_lock); comm_str = malloc(32); if (!comm_str) @@ -59,6 +62,8 @@ 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; @@ -81,17 +86,26 @@ void thread__delete(struct thread *thread) map_groups__put(thread->mg); thread->mg = NULL; } + down_write(&thread->namespaces_lock); list_for_each_entry_safe(namespaces, tmp_namespaces, &thread->namespaces_list, list) { list_del(&namespaces->list); namespaces__free(namespaces); } + up_write(&thread->namespaces_lock); + + down_write(&thread->comm_lock); list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } + up_write(&thread->comm_lock); + unwind__finish_access(thread); + nsinfo__zput(thread->nsinfo); + exit_rwsem(&thread->namespaces_lock); + exit_rwsem(&thread->comm_lock); free(thread); } @@ -122,8 +136,8 @@ struct namespaces *thread__namespaces(const struct thread *thread) return list_first_entry(&thread->namespaces_list, struct namespaces, list); } -int thread__set_namespaces(struct thread *thread, u64 timestamp, - struct namespaces_event *event) +static int __thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) { struct namespaces *new, *curr = thread__namespaces(thread); @@ -146,6 +160,17 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp, return 0; } +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) +{ + int ret; + + down_write(&thread->namespaces_lock); + ret = __thread__set_namespaces(thread, timestamp, event); + up_write(&thread->namespaces_lock); + return ret; +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) @@ -167,8 +192,8 @@ struct comm *thread__exec_comm(const struct thread *thread) return last; } -int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, - bool exec) +static int ____thread__set_comm(struct thread *thread, const char *str, + u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); @@ -192,6 +217,17 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, return 0; } +int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, + bool exec) +{ + int ret; + + down_write(&thread->comm_lock); + ret = ____thread__set_comm(thread, str, timestamp, exec); + up_write(&thread->comm_lock); + return ret; +} + int thread__set_comm_from_proc(struct thread *thread) { char path[64]; @@ -209,7 +245,7 @@ int thread__set_comm_from_proc(struct thread *thread) return err; } -const char *thread__comm_str(const struct thread *thread) +static const char *__thread__comm_str(const struct thread *thread) { const struct comm *comm = thread__comm(thread); @@ -219,6 +255,17 @@ const char *thread__comm_str(const struct thread *thread) return comm__str(comm); } +const char *thread__comm_str(const struct thread *thread) +{ + const char *str; + + down_read((struct rw_semaphore *)&thread->comm_lock); + str = __thread__comm_str(thread); + up_read((struct rw_semaphore *)&thread->comm_lock); + + return str; +} + /* CHECKME: it should probably better return the max comm len from its comm list */ int thread__comm_len(struct thread *thread) { @@ -261,7 +308,7 @@ static int __thread__prepare_access(struct thread *thread) struct maps *maps = &thread->mg->maps[i]; struct map *map; - pthread_rwlock_rdlock(&maps->lock); + down_read(&maps->lock); for (map = maps__first(maps); map; map = map__next(map)) { err = unwind__prepare_access(thread, map, &initialized); @@ -269,7 +316,7 @@ static int __thread__prepare_access(struct thread *thread) break; } - pthread_rwlock_unlock(&maps->lock); + up_read(&maps->lock); } return err; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 4eb849e9098f..40cfa36c022a 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_THREAD_H #define __PERF_THREAD_H @@ -9,6 +10,7 @@ #include "symbol.h" #include <strlist.h> #include <intlist.h> +#include "rwsem.h" struct thread_stack; struct unwind_libunwind_ops; @@ -29,11 +31,14 @@ struct thread { int comm_len; bool dead; /* if set thread has exited */ struct list_head namespaces_list; + struct rw_semaphore namespaces_lock; struct list_head comm_list; + struct rw_semaphore comm_lock; u64 db_id; 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/thread_map.c b/tools/perf/util/thread_map.c index 63ead7b06324..be0d5a736dea 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <dirent.h> #include <errno.h> #include <limits.h> diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index bd34d7a0b9fa..f15803985435 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_THREAD_MAP_H #define __PERF_THREAD_MAP_H diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 5b5d0214debd..81927d027417 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stdlib.h> #include <string.h> #include <sys/time.h> diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index 8656be08513b..15b475c50ccf 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TIME_UTILS_H_ #define _TIME_UTILS_H_ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 829471a1c6d7..2532b558099b 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_TOOL_H #define __PERF_TOOL_H @@ -34,6 +35,12 @@ 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 +70,13 @@ 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/top.h b/tools/perf/util/top.h index 9bdfb78a9a35..9892323cdd7c 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_TOP_H #define __PERF_TOP_H 1 @@ -37,6 +38,7 @@ struct perf_top { int sym_pcnt_filter; const char *sym_filter; float min_percent; + unsigned int nr_threads_synthesize; }; #define CONSOLE_CLEAR "[H[2J" diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index e7d60d05596d..d7f2113462fb 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -28,7 +28,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/wait.h> -#include <pthread.h> #include <fcntl.h> #include <unistd.h> #include <errno.h> diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 8a9a677f7576..40b425949aa3 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -27,7 +27,6 @@ #include <sys/stat.h> #include <sys/wait.h> #include <sys/mman.h> -#include <pthread.h> #include <fcntl.h> #include <unistd.h> #include <errno.h> diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index c330780674fc..16a776371d03 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <unistd.h> diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 1fbc044f9eb0..dcbdb53dc702 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_UTIL_TRACE_EVENT_H #define _PERF_UTIL_TRACE_EVENT_H diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index e97d7016d771..370138e7e35c 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __TRIGGER_H_ #define __TRIGGER_H_ 1 diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c index 1b741646eed0..bfa782421cbd 100644 --- a/tools/perf/util/tsc.c +++ b/tools/perf/util/tsc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/types.h> diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index d5b11e2b85e0..e0c3af34ac8d 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_TSC_H #define __PERF_TSC_H diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index 4767ec2c5ef6..a46762aec4c9 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "units.h" #include <inttypes.h> #include <limits.h> diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h index f02c87317150..99263b6a23f7 100644 --- a/tools/perf/util/units.h +++ b/tools/perf/util/units.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef PERF_UNIT_H #define PERF_UNIT_H diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7755a5e0fe5e..1e9c974faf67 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <elfutils/libdw.h> #include <elfutils/libdwfl.h> diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 4a2b269a7b3b..0cbd2650e280 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_UNWIND_LIBDW_H #define __PERF_UNWIND_LIBDW_H diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 672c2ada9357..7a42f703e858 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps. * diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 8aef572d0889..647a1e6b4c7b 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "unwind.h" #include "thread.h" #include "session.h" diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index bfbdcc6198c9..8a44a1569a21 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UNWIND_H #define __UNWIND_H diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 6cc9d9888ce0..070d25ceea6a 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * usage.c * diff --git a/tools/perf/util/util-cxx.h b/tools/perf/util/util-cxx.h index 0e0e019c9f34..80a99e458d4e 100644 --- a/tools/perf/util/util-cxx.h +++ b/tools/perf/util/util-cxx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Support C++ source use utilities defined in util.h */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 988111e0bab5..a789f952b3e9 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "../perf.h" #include "util.h" #include "debug.h" @@ -6,6 +7,7 @@ #include <sys/stat.h> #include <sys/utsname.h> #include <dirent.h> +#include <fcntl.h> #include <inttypes.h> #include <signal.h> #include <stdio.h> @@ -22,6 +24,19 @@ /* * XXX We need to find a better place for these things... */ + +bool perf_singlethreaded = true; + +void perf_set_singlethreaded(void) +{ + perf_singlethreaded = true; +} + +void perf_set_multithreaded(void) +{ + perf_singlethreaded = false; +} + unsigned int page_size; int cacheline_size; @@ -143,13 +158,17 @@ 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; @@ -170,7 +189,7 @@ out: return err; } -int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) +static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) { void *ptr; loff_t pgoff; @@ -198,15 +217,21 @@ 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 +252,13 @@ 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 +275,16 @@ 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 +296,7 @@ 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 +324,10 @@ 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..01434509c2e9 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H @@ -5,13 +6,13 @@ /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 -#include <fcntl.h> #include <stdbool.h> #include <stddef.h> #include <stdlib.h> #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 +34,10 @@ 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_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); 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 +59,13 @@ const char *perf_tip(const char *dirpath); int sched_getcpu(void); #endif +#ifndef HAVE_SETNS_SUPPORT +int setns(int fd, int nstype); +#endif + +extern bool perf_singlethreaded; + +void perf_set_singlethreaded(void); +void perf_set_multithreaded(void); + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 5de2e15e2eda..4b7a303e4ba8 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <inttypes.h> #include <stdio.h> #include <stdlib.h> @@ -12,7 +13,7 @@ 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 +99,16 @@ 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 +132,16 @@ 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 +193,7 @@ 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/values.h b/tools/perf/util/values.h index 808ff9c73bf5..8c41f22f42cf 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_VALUES_H #define __PERF_VALUES_H diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index d3c39eec89a8..0acb1ec0e2f0 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <unistd.h> #include <stdio.h> @@ -319,7 +320,7 @@ struct dso *machine__findnew_vdso(struct machine *machine, struct vdso_info *vdso_info; struct dso *dso = NULL; - pthread_rwlock_wrlock(&machine->dsos.lock); + down_write(&machine->dsos.lock); if (!machine->vdso_info) machine->vdso_info = vdso_info__new(); @@ -347,7 +348,7 @@ struct dso *machine__findnew_vdso(struct machine *machine, out_unlock: dso__get(dso); - pthread_rwlock_unlock(&machine->dsos.lock); + up_write(&machine->dsos.lock); return dso; } diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h index cdc4fabfc212..bc74ace603ae 100644 --- a/tools/perf/util/vdso.h +++ b/tools/perf/util/vdso.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_VDSO__ #define __PERF_VDSO__ diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c index 7251fdbabced..dc95154f5646 100644 --- a/tools/perf/util/xyarray.c +++ b/tools/perf/util/xyarray.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "xyarray.h" #include "util.h" #include <stdlib.h> @@ -12,6 +13,8 @@ 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..7ffe562e7ae7 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/util/xyarray.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_XYARRAY_H_ #define _PERF_XYARRAY_H_ 1 @@ -7,6 +8,8 @@ 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 +22,14 @@ 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_y; +} + +static inline int xyarray__max_x(struct xyarray *xy) +{ + return xy->max_x; +} + #endif /* _PERF_XYARRAY_H_ */ diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 1329d843eb7b..a725b958cf31 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/stat.h> |