diff options
Diffstat (limited to 'tools/perf/util')
216 files changed, 10269 insertions, 10970 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 14f812bb07a7..07da6c790b63 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,7 +1,10 @@ perf-y += annotate.o +perf-y += block-info.o perf-y += block-range.o perf-y += build-id.o +perf-y += cacheline.o perf-y += config.o +perf-y += copyfile.o perf-y += ctype.o perf-y += db-export.o perf-y += env.o @@ -9,6 +12,8 @@ perf-y += event.o perf-y += evlist.o perf-y += evsel.o perf-y += evsel_fprintf.o +perf-y += perf_event_attr_fprintf.o +perf-y += evswitch.o perf-y += find_bit.o perf-y += get_current_dir_name.o perf-y += kallsyms.o @@ -26,7 +31,6 @@ perf-y += rbtree.o perf-y += libstring.o perf-y += bitmap.o perf-y += hweight.o -perf-y += zalloc.o perf-y += smt.o perf-y += strbuf.o perf-y += string.o @@ -35,6 +39,7 @@ perf-y += strfilter.o perf-y += top.o perf-y += usage.o perf-y += dso.o +perf-y += dsos.o perf-y += symbol.o perf-y += symbol_fprintf.o perf-y += color.o @@ -44,6 +49,7 @@ perf-y += header.o perf-y += callchain.o perf-y += values.o perf-y += debug.o +perf-y += fncache.o perf-y += machine.o perf-y += map.o perf-y += pstack.o @@ -70,8 +76,8 @@ perf-y += svghelper.o perf-y += sort.o perf-y += hist.o perf-y += util.o -perf-y += xyarray.o perf-y += cpumap.o +perf-y += affinity.o perf-y += cputopo.o perf-y += cgroup.o perf-y += target.o @@ -85,12 +91,14 @@ perf-y += stat-display.o perf-y += record.o perf-y += srcline.o perf-y += srccode.o +perf-y += synthetic-events.o perf-y += data.o perf-y += tsc.o perf-y += cloexec.o perf-y += call-path.o perf-y += rwsem.o perf-y += thread-stack.o +perf-y += spark.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ perf-$(CONFIG_AUXTRACE) += intel-pt.o @@ -150,6 +158,8 @@ perf-$(CONFIG_ZLIB) += zlib.o perf-$(CONFIG_LZMA) += lzma.o perf-$(CONFIG_ZSTD) += zstd.o +perf-$(CONFIG_LIBCAP) += cap.o + perf-y += demangle-java.o perf-y += demangle-rust.o @@ -243,7 +253,3 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) - -$(OUTPUT)util/zalloc.o: ../lib/zalloc.c FORCE - $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c new file mode 100644 index 000000000000..a5e31f826828 --- /dev/null +++ b/tools/perf/util/affinity.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Manage affinity to optimize IPIs inside the kernel perf API. */ +#define _GNU_SOURCE 1 +#include <sched.h> +#include <stdlib.h> +#include <linux/bitmap.h> +#include <linux/zalloc.h> +#include "perf.h" +#include "cpumap.h" +#include "affinity.h" + +static int get_cpu_set_size(void) +{ + int sz = cpu__max_cpu() + 8 - 1; + /* + * sched_getaffinity doesn't like masks smaller than the kernel. + * Hopefully that's big enough. + */ + if (sz < 4096) + sz = 4096; + return sz / 8; +} + +int affinity__setup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + a->orig_cpus = bitmap_alloc(cpu_set_size * 8); + if (!a->orig_cpus) + return -1; + sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + a->sched_cpus = bitmap_alloc(cpu_set_size * 8); + if (!a->sched_cpus) { + zfree(&a->orig_cpus); + return -1; + } + bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size); + a->changed = false; + return 0; +} + +/* + * perf_event_open does an IPI internally to the target CPU. + * It is more efficient to change perf's affinity to the target + * CPU and then set up all events on that CPU, so we amortize + * CPU communication. + */ +void affinity__set(struct affinity *a, int cpu) +{ + int cpu_set_size = get_cpu_set_size(); + + if (cpu == -1) + return; + a->changed = true; + set_bit(cpu, a->sched_cpus); + /* + * We ignore errors because affinity is just an optimization. + * This could happen for example with isolated CPUs or cpusets. + * In this case the IPIs inside the kernel's perf API still work. + */ + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus); + clear_bit(cpu, a->sched_cpus); +} + +void affinity__cleanup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + if (a->changed) + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + zfree(&a->sched_cpus); + zfree(&a->orig_cpus); +} diff --git a/tools/perf/util/affinity.h b/tools/perf/util/affinity.h new file mode 100644 index 000000000000..0ad6a18ef20c --- /dev/null +++ b/tools/perf/util/affinity.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef PERF_AFFINITY_H +#define PERF_AFFINITY_H 1 + +#include <stdbool.h> + +struct affinity { + unsigned long *orig_cpus; + unsigned long *sched_cpus; + bool changed; +}; + +void affinity__cleanup(struct affinity *a); +void affinity__set(struct affinity *a, int cpu); +int affinity__setup(struct affinity *a); + +#endif // PERF_AFFINITY_H diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 163536720149..ca73fb74ad03 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -9,19 +9,23 @@ #include <errno.h> #include <inttypes.h> #include <libgen.h> +#include <stdlib.h> #include <bpf/bpf.h> #include <bpf/btf.h> #include <bpf/libbpf.h> #include <linux/btf.h> -#include "util.h" +#include "util.h" // hex_width() #include "ui/ui.h" #include "sort.h" #include "build-id.h" #include "color.h" #include "config.h" -#include "cache.h" +#include "dso.h" +#include "env.h" #include "map.h" +#include "maps.h" #include "symbol.h" +#include "srcline.h" #include "units.h" #include "debug.h" #include "annotate.h" @@ -30,6 +34,7 @@ #include "bpf-event.h" #include "block-range.h" #include "string2.h" +#include "util/event.h" #include "arch/common.h" #include <regex.h> #include <pthread.h> @@ -37,6 +42,8 @@ #include <linux/kernel.h> #include <linux/string.h> #include <bpf/libbpf.h> +#include <subcmd/parse-options.h> +#include <subcmd/run-command.h> /* FIXME: For the HE_COLORSET */ #include "ui/browser.h" @@ -236,7 +243,7 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s char *endptr, *tok, *name; struct map *map = ms->map; struct addr_map_symbol target = { - .map = map, + .ms = { .map = map, }, }; ops->target.addr = strtoull(ops->raw, &endptr, 16); @@ -264,9 +271,9 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s find_target: target.addr = map__objdump_2mem(map, ops->target.addr); - if (map_groups__find_ams(&target) == 0 && - map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) - ops->target.sym = target.sym; + if (maps__find_ams(ms->maps, &target) == 0 && + map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; return 0; @@ -325,7 +332,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s struct map *map = ms->map; struct symbol *sym = ms->sym; struct addr_map_symbol target = { - .map = map, + .ms = { .map = map, }, }; const char *c = strchr(ops->raw, ','); u64 start, end; @@ -384,9 +391,9 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * Actual navigation will come next, with further understanding of how * the symbol searching and disassembly should be done. */ - if (map_groups__find_ams(&target) == 0 && - map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) - ops->target.sym = target.sym; + if (maps__find_ams(ms->maps, &target) == 0 && + map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; if (!ops->target.outside) { ops->target.offset = target.addr - start; @@ -847,6 +854,10 @@ static int __symbol__account_cycles(struct cyc_hist *ch, ch[offset].start < start) return 0; } + + if (ch[offset].num < NUM_SPARKS) + ch[offset].cycles_spark[ch[offset].num] = cycles; + ch[offset].have_start = have_start; ch[offset].start = start; ch[offset].cycles += cycles; @@ -854,14 +865,15 @@ static int __symbol__account_cycles(struct cyc_hist *ch, return 0; } -static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, +static int __symbol__inc_addr_samples(struct map_symbol *ms, struct annotated_source *src, int evidx, u64 addr, struct perf_sample *sample) { + struct symbol *sym = ms->sym; unsigned offset; struct sym_hist *h; - pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); + pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, ms->map->unmap_ip(ms->map, addr)); if ((addr < sym->start || addr >= sym->end) && (addr != sym->end || sym->start != sym->end)) { @@ -928,17 +940,17 @@ alloc_histograms: return notes->src; } -static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, u64 addr, +static int symbol__inc_addr_samples(struct map_symbol *ms, + struct evsel *evsel, u64 addr, struct perf_sample *sample) { + struct symbol *sym = ms->sym; struct annotated_source *src; if (sym == NULL) return 0; - src = symbol__hists(sym, evsel->evlist->nr_entries); - return (src) ? __symbol__inc_addr_samples(sym, map, src, evsel->idx, - addr, sample) : 0; + src = symbol__hists(sym, evsel->evlist->core.nr_entries); + return src ? __symbol__inc_addr_samples(ms, src, evsel->idx, addr, sample) : 0; } static int symbol__account_cycles(u64 addr, u64 start, @@ -986,17 +998,17 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, * it starts on the function start. */ if (start && - (start->sym == ams->sym || - (ams->sym && - start->addr == ams->sym->start + ams->map->start))) + (start->ms.sym == ams->ms.sym || + (ams->ms.sym && + start->addr == ams->ms.sym->start + ams->ms.map->start))) saddr = start->al_addr; if (saddr == 0) pr_debug2("BB with bad start: addr %"PRIx64" start %"PRIx64" sym %"PRIx64" saddr %"PRIx64"\n", ams->addr, start ? start->addr : 0, - ams->sym ? ams->sym->start + ams->map->start : 0, + ams->ms.sym ? ams->ms.sym->start + ams->ms.map->start : 0, saddr); - err = symbol__account_cycles(ams->al_addr, saddr, ams->sym, cycles); + err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles); if (err) pr_debug2("account_cycles failed %d\n", err); return err; @@ -1080,15 +1092,15 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { - return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample); + return symbol__inc_addr_samples(&ams->ms, evsel, ams->al_addr, sample); } int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - struct perf_evsel *evsel, u64 ip) + struct evsel *evsel, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample); + return symbol__inc_addr_samples(&he->ms, evsel, ip, sample); } static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) @@ -1134,7 +1146,7 @@ struct annotate_args { size_t privsize; struct arch *arch; struct map_symbol ms; - struct perf_evsel *evsel; + struct evsel *evsel; struct annotation_options *options; s64 offset; char *line; @@ -1165,12 +1177,12 @@ static struct annotation_line * annotation_line__new(struct annotate_args *args, size_t privsize) { struct annotation_line *al; - struct perf_evsel *evsel = args->evsel; + struct evsel *evsel = args->evsel; size_t size = privsize + sizeof(*al); int nr = 1; if (perf_evsel__is_group_event(evsel)) - nr = evsel->nr_members; + nr = evsel->core.nr_members; size += sizeof(al->data[0]) * nr; @@ -1359,7 +1371,7 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi static int annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, - struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, + struct evsel *evsel, u64 len, int min_pcnt, int printed, int max_lines, struct annotation_line *queue, int addr_fmt_width, int percent_type) { @@ -1448,7 +1460,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start return -1; if (perf_evsel__is_group_event(evsel)) - width *= evsel->nr_members; + width *= evsel->core.nr_members; if (!*al->line) printf(" %*s:\n", width, " "); @@ -1479,44 +1491,26 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start * means that it's not a disassembly line so should be treated differently. * The ops.raw part will be parsed further according to type of the instruction. */ -static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, +static int symbol__parse_objdump_line(struct symbol *sym, struct annotate_args *args, - int *line_nr) + char *parsed_line, int *line_nr) { struct map *map = args->ms.map; struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; - char *line = NULL, *parsed_line, *tmp, *tmp2; - size_t line_len; + char *tmp; s64 line_ip, offset = -1; regmatch_t match[2]; - if (getline(&line, &line_len, file) < 0) - return -1; - - if (!line) - return -1; - - line_ip = -1; - parsed_line = strim(line); - /* /filename:linenr ? Save line number and ignore. */ if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) { *line_nr = atoi(parsed_line + match[1].rm_so); return 0; } - tmp = skip_spaces(parsed_line); - if (*tmp) { - /* - * Parse hexa addresses followed by ':' - */ - line_ip = strtoull(tmp, &tmp2, 16); - if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') - line_ip = -1; - } - - if (line_ip != -1) { + /* Process hex address followed by ':'. */ + line_ip = strtoull(parsed_line, &tmp, 16); + if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') { u64 start = map__rip_2objdump(map, sym->start), end = map__rip_2objdump(map, sym->end); @@ -1524,7 +1518,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, if ((u64)line_ip < start || (u64)line_ip >= end) offset = -1; else - parsed_line = tmp2 + 1; + parsed_line = tmp + 1; } args->offset = offset; @@ -1533,7 +1527,6 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, args->ms.sym = sym; dl = disasm_line__new(args); - free(line); (*line_nr)++; if (dl == NULL) @@ -1548,13 +1541,13 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, /* kcore has no symbols, so add the call target symbol */ if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) { struct addr_map_symbol target = { - .map = map, .addr = dl->ops.target.addr, + .ms = { .map = map, }, }; - if (!map_groups__find_ams(&target) && - target.sym->start == target.al_addr) - dl->ops.target.sym = target.sym; + if (!maps__find_ams(args->ms.maps, &target) && + target.ms.sym->start == target.al_addr) + dl->ops.target.sym = target.ms.sym; } annotation_line__add(&dl->al, ¬es->src->source); @@ -1591,10 +1584,9 @@ static void delete_last_nop(struct symbol *sym) } } -int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *map, - int errnum, char *buf, size_t buflen) +int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; BUG_ON(buflen == 0); @@ -1625,6 +1617,19 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map * case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF: scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation"); break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP: + scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions."); + break; + case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING: + scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization."); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE: + scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name); + break; + case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF: + scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.", + dso->long_name); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -1656,7 +1661,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil build_id_path = strdup(filename); if (!build_id_path) - return -1; + return ENOMEM; /* * old style build-id cache has name of XX/XXXXXXX.. while @@ -1707,13 +1712,13 @@ static int symbol__disassemble_bpf(struct symbol *sym, char tpath[PATH_MAX]; size_t buf_size; int nr_skip = 0; - int ret = -1; char *buf; bfd *bfdf; + int ret; FILE *s; if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) - return -1; + return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, sym->name, sym->start, sym->end - sym->start); @@ -1726,8 +1731,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, assert(bfd_check_format(bfdf, bfd_object)); s = open_memstream(&buf, &buf_size); - if (!s) + if (!s) { + ret = errno; goto out; + } init_disassemble_info(&info, s, (fprintf_ftype) fprintf); @@ -1736,8 +1743,10 @@ static int symbol__disassemble_bpf(struct symbol *sym, info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id); - if (!info_node) + if (!info_node) { + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; goto out; + } info_linear = info_node->info_linear; sub_id = dso->bpf_prog.sub_id; @@ -1834,6 +1843,67 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, } #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +/* + * Possibly create a new version of line with tabs expanded. Returns the + * existing or new line, storage is updated if a new line is allocated. If + * allocation fails then NULL is returned. + */ +static char *expand_tabs(char *line, char **storage, size_t *storage_len) +{ + size_t i, src, dst, len, new_storage_len, num_tabs; + char *new_line; + size_t line_len = strlen(line); + + for (num_tabs = 0, i = 0; i < line_len; i++) + if (line[i] == '\t') + num_tabs++; + + if (num_tabs == 0) + return line; + + /* + * Space for the line and '\0', less the leading and trailing + * spaces. Each tab may introduce 7 additional spaces. + */ + new_storage_len = line_len + 1 + (num_tabs * 7); + + new_line = malloc(new_storage_len); + if (new_line == NULL) { + pr_err("Failure allocating memory for tab expansion\n"); + return NULL; + } + + /* + * Copy regions starting at src and expand tabs. If there are two + * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces + * are inserted. + */ + for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) { + if (line[i] == '\t') { + len = i - src; + memcpy(&new_line[dst], &line[src], len); + dst += len; + new_line[dst++] = ' '; + while (dst % 8 != 0) + new_line[dst++] = ' '; + src = i + 1; + num_tabs--; + } + } + + /* Expand the last region. */ + len = line_len - src; + memcpy(&new_line[dst], &line[src], len); + dst += len; + new_line[dst] = '\0'; + + free(*storage); + *storage = new_line; + *storage_len = new_storage_len; + return new_line; + +} + static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *opts = args->options; @@ -1845,10 +1915,19 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) struct kcore_extract kce; bool delete_extract = false; bool decomp = false; - int stdout_fd[2]; int lineno = 0; int nline; - pid_t pid; + char *line; + size_t line_len; + const char *objdump_argv[] = { + "/bin/sh", + "-c", + NULL, /* Will be the objdump command to run. */ + "--", + NULL, /* Will be the symfs path. */ + NULL, + }; + struct child_process objdump_process; int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); if (err) @@ -1878,7 +1957,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) if (dso__decompress_kmodule_path(dso, symfs_filename, tmp, sizeof(tmp)) < 0) - goto out; + return -1; decomp = true; strcpy(symfs_filename, tmp); @@ -1887,14 +1966,20 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand", + " -l -d %s %s %s %c%s%c %s%s -C \"$1\"", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), - opts->show_asm_raw ? "" : "--no-show-raw", - opts->annotate_src ? "-S" : ""); + opts->show_asm_raw ? "" : "--no-show-raw-insn", + opts->annotate_src ? "-S" : "", + opts->prefix ? "--prefix " : "", + opts->prefix ? '"' : ' ', + opts->prefix ?: "", + opts->prefix ? '"' : ' ', + opts->prefix_strip ? "--prefix-strip=" : "", + opts->prefix_strip ?: ""); if (err < 0) { pr_err("Failure allocating memory for the command to run\n"); @@ -1903,55 +1988,73 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) pr_debug("Executing: %s\n", command); - err = -1; - if (pipe(stdout_fd) < 0) { - pr_err("Failure creating the pipe to run %s\n", command); - goto out_free_command; - } - - pid = fork(); - if (pid < 0) { - pr_err("Failure forking to run %s\n", command); - goto out_close_stdout; - } + objdump_argv[2] = command; + objdump_argv[4] = symfs_filename; - if (pid == 0) { - close(stdout_fd[0]); - dup2(stdout_fd[1], 1); - close(stdout_fd[1]); - execl("/bin/sh", "sh", "-c", command, "--", symfs_filename, - NULL); - perror(command); - exit(-1); + /* Create a pipe to read from for stdout */ + memset(&objdump_process, 0, sizeof(objdump_process)); + objdump_process.argv = objdump_argv; + objdump_process.out = -1; + if (start_command(&objdump_process)) { + pr_err("Failure starting to run %s\n", command); + err = -1; + goto out_free_command; } - close(stdout_fd[1]); - - file = fdopen(stdout_fd[0], "r"); + file = fdopen(objdump_process.out, "r"); if (!file) { pr_err("Failure creating FILE stream for %s\n", command); /* * If we were using debug info should retry with * original binary. */ - goto out_free_command; + err = -1; + goto out_close_stdout; } + /* Storage for getline. */ + line = NULL; + line_len = 0; + nline = 0; while (!feof(file)) { + const char *match; + char *expanded_line; + + if (getline(&line, &line_len, file) < 0 || !line) + break; + + /* Skip lines containing "filename:" */ + match = strstr(line, symfs_filename); + if (match && match[strlen(symfs_filename)] == ':') + continue; + + expanded_line = strim(line); + expanded_line = expand_tabs(expanded_line, &line, &line_len); + if (!expanded_line) + break; + /* * The source code line number (lineno) needs to be kept in * across calls to symbol__parse_objdump_line(), so that it * can associate it with the instructions till the next one. * See disasm_line__new() and struct disasm_line::line_nr. */ - if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0) + if (symbol__parse_objdump_line(sym, args, expanded_line, + &lineno) < 0) break; nline++; } + free(line); + + err = finish_command(&objdump_process); + if (err) + pr_err("Error running %s\n", command); - if (nline == 0) + if (nline == 0) { + err = -1; pr_err("No output from %s\n", command); + } /* * kallsyms does not have symbol sizes so there may a nop at the end. @@ -1961,23 +2064,21 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) delete_last_nop(sym); fclose(file); - err = 0; + +out_close_stdout: + close(objdump_process.out); + out_free_command: free(command); -out_remove_tmp: - close(stdout_fd[0]); +out_remove_tmp: if (decomp) unlink(symfs_filename); if (delete_extract) kcore_extract__delete(&kce); -out: - return err; -out_close_stdout: - close(stdout_fd[1]); - goto out_free_command; + return err; } static void calc_percent(struct sym_hist *sym_hist, @@ -2011,10 +2112,10 @@ static void calc_percent(struct sym_hist *sym_hist, } static void annotation__calc_percent(struct annotation *notes, - struct perf_evsel *leader, s64 len) + struct evsel *leader, s64 len) { struct annotation_line *al, *next; - struct perf_evsel *evsel; + struct evsel *evsel; list_for_each_entry(al, ¬es->src->source, node) { s64 end; @@ -2041,18 +2142,17 @@ static void annotation__calc_percent(struct annotation *notes, } } -void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel) +void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); annotation__calc_percent(notes, evsel, symbol__size(sym)); } -int symbol__annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, size_t privsize, - struct annotation_options *options, - struct arch **parch) +int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch) { + struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { .privsize = privsize, @@ -2065,11 +2165,11 @@ int symbol__annotate(struct symbol *sym, struct map *map, int err; if (!arch_name) - return -1; + return errno; args.arch = arch = arch__find(arch_name); if (arch == NULL) - return -ENOTSUP; + return ENOTSUP; if (parch) *parch = arch; @@ -2082,9 +2182,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, } } - args.ms.map = map; - args.ms.sym = sym; - notes->start = map__rip_2objdump(map, sym->start); + args.ms = *ms; + notes->start = map__rip_2objdump(ms->map, sym->start); return symbol__disassemble(sym, &args); } @@ -2214,7 +2313,7 @@ static void print_summary(struct rb_root *root, const char *filename) } } -static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) +static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evsel->idx); @@ -2240,10 +2339,11 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) return 0; } -int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { + struct map *map = ms->map; + struct symbol *sym = ms->sym; struct dso *dso = map->dso; char *filename; const char *d_filename; @@ -2272,7 +2372,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, len = symbol__size(sym); if (perf_evsel__is_group_event(evsel)) { - width *= evsel->nr_members; + width *= evsel->core.nr_members; perf_evsel__group_desc(evsel, buf, sizeof(buf)); evsel_name = buf; } @@ -2405,7 +2505,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, return 0; } -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { const char *ev_name = perf_evsel__name(evsel); @@ -2647,30 +2747,29 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, resort_source_line(root, &tmp_root); } -static void symbol__calc_lines(struct symbol *sym, struct map *map, - struct rb_root *root, +static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root, struct annotation_options *opts) { - struct annotation *notes = symbol__annotation(sym); + struct annotation *notes = symbol__annotation(ms->sym); - annotation__calc_lines(notes, map, root, opts); + annotation__calc_lines(notes, ms->map, root, opts); } -int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; + struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; struct hists *hists = evsel__hists(evsel); char buf[1024]; - if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0) + if (symbol__annotate2(ms, evsel, opts, NULL) < 0) return -1; if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line, opts); + symbol__calc_lines(ms, &source_line, opts); print_summary(&source_line, dso->long_name); } @@ -2684,25 +2783,25 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, return 0; } -int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = map->dso; + struct dso *dso = ms->map->dso; + struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(sym, map, evsel, 0, opts, NULL) < 0) + if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); if (opts->print_lines) { srcline_full_filename = opts->full_path; - symbol__calc_lines(sym, map, &source_line, opts); + symbol__calc_lines(ms, &source_line, opts); print_summary(&source_line, dso->long_name); } - symbol__annotate_printf(sym, map, evsel, opts); + symbol__annotate_printf(ms, evsel, opts); annotated_source__purge(symbol__annotation(sym)->src); @@ -2956,21 +3055,22 @@ void annotation_line__write(struct annotation_line *al, struct annotation *notes wops->write_graph); } -int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel, +int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct arch **parch) { + struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); size_t size = symbol__size(sym); int nr_pcnt = 1, err; notes->offsets = zalloc(size * sizeof(struct annotation_line *)); if (notes->offsets == NULL) - return -1; + return ENOMEM; if (perf_evsel__is_group_event(evsel)) - nr_pcnt = evsel->nr_members; + nr_pcnt = evsel->core.nr_members; - err = symbol__annotate(sym, map, evsel, 0, options, parch); + err = symbol__annotate(ms, evsel, 0, options, parch); if (err) goto out_free_offsets; @@ -2991,7 +3091,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev out_free_offsets: zfree(¬es->offsets); - return -1; + return err; } #define ANNOTATION__CFG(n) \ @@ -3110,3 +3210,12 @@ out: free(str1); return err; } + +int annotate_check_args(struct annotation_options *args) +{ + if (args->prefix_strip && !args->prefix) { + pr_err("--prefix-strip requires --prefix\n"); + return -1; + } + return 0; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 5bc0cf655d37..455403e8fede 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -11,6 +11,7 @@ #include <pthread.h> #include <asm/bug.h> #include "symbol_conf.h" +#include "spark.h" struct hist_browser_timer; struct hist_entry; @@ -20,7 +21,7 @@ struct map_symbol; struct addr_map_symbol; struct option; struct perf_sample; -struct perf_evsel; +struct evsel; struct symbol; struct ins { @@ -93,6 +94,8 @@ struct annotation_options { int context; const char *objdump_path; const char *disassembler_style; + const char *prefix; + const char *prefix_strip; unsigned int percent_type; }; @@ -216,12 +219,12 @@ void annotation_line__write(struct annotation_line *al, struct annotation *notes int __annotation__scnprintf_samples_period(struct annotation *notes, char *bf, size_t size, - struct perf_evsel *evsel, + struct evsel *evsel, bool show_freq); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name); size_t disasm__fprintf(struct list_head *head, FILE *fp); -void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel); +void symbol__calc_percent(struct symbol *sym, struct evsel *evsel); struct sym_hist { u64 nr_samples; @@ -235,6 +238,7 @@ struct cyc_hist { u64 cycles_aggr; u64 cycles_max; u64 cycles_min; + s64 cycles_spark[NUM_SPARKS]; u32 num; u32 num_aggr; u8 have_start; @@ -245,7 +249,7 @@ struct cyc_hist { /** struct annotated_source - symbols with hits have this attached as in sannotation * * @histograms: Array of addr hit histograms per event being monitored - * nr_histograms: This may not be the same as evsel->evlist->nr_entries if + * nr_histograms: This may not be the same as evsel->evlist->core.nr_entries if * we have more than a group in a evlist, where we will want * to see each group separately, that is why symbol__annotate2() * sets src->nr_histograms to evsel->nr_members. @@ -335,24 +339,24 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - struct perf_evsel *evsel); + struct evsel *evsel); 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, struct perf_sample *sample, - struct perf_evsel *evsel, u64 addr); + struct evsel *evsel, u64 addr); struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, size_t privsize, +int symbol__annotate(struct map_symbol *ms, + struct evsel *evsel, size_t privsize, struct annotation_options *options, struct arch **parch); -int symbol__annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__annotate2(struct map_symbol *ms, + struct evsel *evsel, struct annotation_options *options, struct arch **parch); @@ -370,40 +374,38 @@ enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START, SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING, + SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP, + SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE, + SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF, __SYMBOL_ANNOTATE_ERRNO__END, }; -int symbol__strerror_disassemble(struct symbol *sym, struct map *map, - int errnum, char *buf, size_t buflen); +int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); -int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void annotated_source__purge(struct annotated_source *as); -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); bool ui__has_annotation(void); -int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); -int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); #ifdef HAVE_SLANG_SUPPORT -int symbol__tui_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, +int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts); #else -static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, - struct map *map __maybe_unused, - struct perf_evsel *evsel __maybe_unused, +static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *opts __maybe_unused) { @@ -415,4 +417,7 @@ void annotation_config__init(void); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); + +int annotate_check_args(struct annotation_options *args); + #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index a314e5b26e9d..53be12b23ff4 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -8,19 +8,18 @@ #include <errno.h> #include <byteswap.h> #include <inttypes.h> +#include <unistd.h> +#include <stdlib.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> #include <linux/zalloc.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" -#include "evlist.h" #include "machine.h" #include "session.h" -#include "thread.h" #include "debug.h" #include "auxtrace.h" #include "arm-spe.h" @@ -181,7 +180,7 @@ static const char * const arm_spe_info_fmts[] = { [ARM_SPE_PMU_TYPE] = " PMU Type %"PRId64"\n", }; -static void arm_spe_print_info(u64 *arr) +static void arm_spe_print_info(__u64 *arr) { if (!dump_trace) return; @@ -192,12 +191,12 @@ static void arm_spe_print_info(u64 *arr) int arm_spe_process_auxtrace_info(union perf_event *event, struct perf_session *session) { - struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; size_t min_sz = sizeof(u64) * ARM_SPE_PMU_TYPE; struct arm_spe *spe; int err; - if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) + + if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) + min_sz) return -EINVAL; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ec0af36697c4..eb087e7df6f4 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -26,14 +26,14 @@ #include <linux/list.h> #include <linux/zalloc.h> -#include "../perf.h" #include "evlist.h" #include "dso.h" #include "map.h" #include "pmu.h" #include "evsel.h" -#include "cpumap.h" +#include "evsel_config.h" #include "symbol.h" +#include "util/synthetic-events.h" #include "thread_map.h" #include "asm/bug.h" #include "auxtrace.h" @@ -41,6 +41,7 @@ #include <linux/hash.h> #include "event.h" +#include "record.h" #include "session.h" #include "debug.h" #include <subcmd/parse-options.h> @@ -50,9 +51,78 @@ #include "intel-bts.h" #include "arm-spe.h" #include "s390-cpumsf.h" +#include "util/mmap.h" #include <linux/ctype.h> +#include <linux/kernel.h> #include "symbol/kallsyms.h" +#include <internal/lib.h> + +static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel) +{ + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (pmu->type == evsel->core.attr.type) + break; + } + + return pmu; +} + +static bool perf_evsel__is_aux_event(struct evsel *evsel) +{ + struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); + + return pmu && pmu->auxtrace; +} + +/* + * Make a group from 'leader' to 'last', requiring that the events were not + * already grouped to a different leader. + */ +static int perf_evlist__regroup(struct evlist *evlist, + struct evsel *leader, + struct evsel *last) +{ + struct evsel *evsel; + bool grp; + + if (!perf_evsel__is_group_leader(leader)) + return -EINVAL; + + grp = false; + evlist__for_each_entry(evlist, evsel) { + if (grp) { + if (!(evsel->leader == leader || + (evsel->leader == evsel && + evsel->core.nr_members <= 1))) + return -EINVAL; + } else if (evsel == leader) { + grp = true; + } + if (evsel == last) + break; + } + + grp = false; + evlist__for_each_entry(evlist, evsel) { + if (grp) { + if (evsel->leader != leader) { + evsel->leader = leader; + if (leader->core.nr_members < 1) + leader->core.nr_members = 1; + leader->core.nr_members += 1; + } + } else if (evsel == leader) { + grp = true; + } + if (evsel == last) + break; + } + + return 0; +} static bool auxtrace__dont_decode(struct perf_session *session) { @@ -124,20 +194,20 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, } void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu) { mp->idx = idx; if (per_cpu) { - mp->cpu = evlist->cpus->map[idx]; - if (evlist->threads) - mp->tid = thread_map__pid(evlist->threads, 0); + mp->cpu = evlist->core.cpus->map[idx]; + if (evlist->core.threads) + mp->tid = perf_thread_map__pid(evlist->core.threads, 0); else mp->tid = -1; } else { mp->cpu = -1; - mp->tid = thread_map__pid(evlist->threads, idx); + mp->tid = perf_thread_map__pid(evlist->core.threads, idx); } } @@ -385,7 +455,7 @@ static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues, return err; if (event->header.type == PERF_RECORD_AUXTRACE) { - if (event->header.size < sizeof(struct auxtrace_event) || + if (event->header.size < sizeof(struct perf_record_auxtrace) || event->header.size != sz) { err = -EINVAL; goto out; @@ -503,7 +573,7 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap) } size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, - struct perf_evlist *evlist) + struct evlist *evlist) { if (itr) return itr->info_priv_size(itr, evlist); @@ -518,7 +588,7 @@ static int auxtrace_not_supported(void) int auxtrace_record__info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size) { if (itr) @@ -539,9 +609,9 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr) return 0; } -int auxtrace_record__snapshot_finish(struct auxtrace_record *itr) +int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit) { - if (itr && itr->snapshot_finish) + if (!on_exit && itr && itr->snapshot_finish) return itr->snapshot_finish(itr); return 0; } @@ -556,7 +626,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, } int auxtrace_record__options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { if (itr) @@ -577,6 +647,16 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, if (!str) return 0; + /* PMU-agnostic options */ + switch (*str) { + case 'e': + opts->auxtrace_snapshot_on_exit = true; + str++; + break; + default: + break; + } + if (itr) return itr->parse_snapshot_options(itr, opts, str); @@ -584,8 +664,134 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, return -EINVAL; } +/* + * Event record size is 16-bit which results in a maximum size of about 64KiB. + * Allow about 4KiB for the rest of the sample record, to give a maximum + * AUX area sample size of 60KiB. + */ +#define MAX_AUX_SAMPLE_SIZE (60 * 1024) + +/* Arbitrary default size if no other default provided */ +#define DEFAULT_AUX_SAMPLE_SIZE (4 * 1024) + +static int auxtrace_validate_aux_sample_size(struct evlist *evlist, + struct record_opts *opts) +{ + struct evsel *evsel; + bool has_aux_leader = false; + u32 sz; + + evlist__for_each_entry(evlist, evsel) { + sz = evsel->core.attr.aux_sample_size; + if (perf_evsel__is_group_leader(evsel)) { + has_aux_leader = perf_evsel__is_aux_event(evsel); + if (sz) { + if (has_aux_leader) + pr_err("Cannot add AUX area sampling to an AUX area event\n"); + else + pr_err("Cannot add AUX area sampling to a group leader\n"); + return -EINVAL; + } + } + if (sz > MAX_AUX_SAMPLE_SIZE) { + pr_err("AUX area sample size %u too big, max. %d\n", + sz, MAX_AUX_SAMPLE_SIZE); + return -EINVAL; + } + if (sz) { + if (!has_aux_leader) { + pr_err("Cannot add AUX area sampling because group leader is not an AUX area event\n"); + return -EINVAL; + } + perf_evsel__set_sample_bit(evsel, AUX); + opts->auxtrace_sample_mode = true; + } else { + perf_evsel__reset_sample_bit(evsel, AUX); + } + } + + if (!opts->auxtrace_sample_mode) { + pr_err("AUX area sampling requires an AUX area event group leader plus other events to which to add samples\n"); + return -EINVAL; + } + + if (!perf_can_aux_sample()) { + pr_err("AUX area sampling is not supported by kernel\n"); + return -EINVAL; + } + + return 0; +} + +int auxtrace_parse_sample_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts, const char *str) +{ + struct perf_evsel_config_term *term; + struct evsel *aux_evsel; + bool has_aux_sample_size = false; + bool has_aux_leader = false; + struct evsel *evsel; + char *endptr; + unsigned long sz; + + if (!str) + goto no_opt; + + if (!itr) { + pr_err("No AUX area event to sample\n"); + return -EINVAL; + } + + sz = strtoul(str, &endptr, 0); + if (*endptr || sz > UINT_MAX) { + pr_err("Bad AUX area sampling option: '%s'\n", str); + return -EINVAL; + } + + if (!sz) + sz = itr->default_aux_sample_size; + + if (!sz) + sz = DEFAULT_AUX_SAMPLE_SIZE; + + /* Set aux_sample_size based on --aux-sample option */ + evlist__for_each_entry(evlist, evsel) { + if (perf_evsel__is_group_leader(evsel)) { + has_aux_leader = perf_evsel__is_aux_event(evsel); + } else if (has_aux_leader) { + evsel->core.attr.aux_sample_size = sz; + } + } +no_opt: + aux_evsel = NULL; + /* Override with aux_sample_size from config term */ + evlist__for_each_entry(evlist, evsel) { + if (perf_evsel__is_aux_event(evsel)) + aux_evsel = evsel; + term = perf_evsel__get_config_term(evsel, AUX_SAMPLE_SIZE); + if (term) { + has_aux_sample_size = true; + evsel->core.attr.aux_sample_size = term->val.aux_sample_size; + /* If possible, group with the AUX event */ + if (aux_evsel && evsel->core.attr.aux_sample_size) + perf_evlist__regroup(evlist, aux_evsel, evsel); + } + } + + if (!str && !has_aux_sample_size) + return 0; + + if (!itr) { + pr_err("No AUX area event to sample\n"); + return -EINVAL; + } + + return auxtrace_validate_aux_sample_size(evlist, opts); +} + struct auxtrace_record *__weak -auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err) +auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err) { *err = 0; return NULL; @@ -798,6 +1004,113 @@ struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue, } } +struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *queues, + struct perf_sample *sample, + struct perf_session *session) +{ + struct perf_sample_id *sid; + unsigned int idx; + u64 id; + + id = sample->id; + if (!id) + return NULL; + + sid = perf_evlist__id2sid(session->evlist, id); + if (!sid) + return NULL; + + idx = sid->idx; + + if (idx >= queues->nr_queues) + return NULL; + + return &queues->queue_array[idx]; +} + +int auxtrace_queues__add_sample(struct auxtrace_queues *queues, + struct perf_session *session, + struct perf_sample *sample, u64 data_offset, + u64 reference) +{ + struct auxtrace_buffer buffer = { + .pid = -1, + .data_offset = data_offset, + .reference = reference, + .size = sample->aux_sample.size, + }; + struct perf_sample_id *sid; + u64 id = sample->id; + unsigned int idx; + + if (!id) + return -EINVAL; + + sid = perf_evlist__id2sid(session->evlist, id); + if (!sid) + return -ENOENT; + + idx = sid->idx; + buffer.tid = sid->tid; + buffer.cpu = sid->cpu; + + return auxtrace_queues__add_buffer(queues, session, idx, &buffer, NULL); +} + +struct queue_data { + bool samples; + bool events; +}; + +static int auxtrace_queue_data_cb(struct perf_session *session, + union perf_event *event, u64 offset, + void *data) +{ + struct queue_data *qd = data; + struct perf_sample sample; + int err; + + if (qd->events && event->header.type == PERF_RECORD_AUXTRACE) { + if (event->header.size < sizeof(struct perf_record_auxtrace)) + return -EINVAL; + offset += event->header.size; + return session->auxtrace->queue_data(session, NULL, event, + offset); + } + + if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) + return 0; + + err = perf_evlist__parse_sample(session->evlist, event, &sample); + if (err) + return err; + + if (!sample.aux_sample.size) + return 0; + + offset += sample.aux_sample.data - (void *)event; + + return session->auxtrace->queue_data(session, &sample, NULL, offset); +} + +int auxtrace_queue_data(struct perf_session *session, bool samples, bool events) +{ + struct queue_data qd = { + .samples = samples, + .events = events, + }; + + if (auxtrace__dont_decode(session)) + return 0; + + if (!session->auxtrace || !session->auxtrace->queue_data) + return -EINVAL; + + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + auxtrace_queue_data_cb, &qd); +} + void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd) { size_t adj = buffer->data_offset & (page_size - 1); @@ -848,13 +1161,13 @@ void auxtrace_buffer__free(struct auxtrace_buffer *buffer) free(buffer); } -void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type, +void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type, int code, int cpu, pid_t pid, pid_t tid, u64 ip, const char *msg, u64 timestamp) { size_t size; - memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event)); + memset(auxtrace_error, 0, sizeof(struct perf_record_auxtrace_error)); auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR; auxtrace_error->type = type; @@ -883,12 +1196,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, pr_debug2("Synthesizing auxtrace information\n"); priv_size = auxtrace_record__info_priv_size(itr, session->evlist); - ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size); + ev = zalloc(sizeof(struct perf_record_auxtrace_info) + priv_size); if (!ev) return -ENOMEM; ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO; - ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) + + ev->auxtrace_info.header.size = sizeof(struct perf_record_auxtrace_info) + priv_size; err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info, priv_size); @@ -932,7 +1245,7 @@ s64 perf_event__process_auxtrace(struct perf_session *session, s64 err; if (dump_trace) - fprintf(stdout, " size: %#"PRIx64" offset: %#"PRIx64" ref: %#"PRIx64" idx: %u tid: %d cpu: %d\n", + fprintf(stdout, " size: %#"PRI_lx64" offset: %#"PRI_lx64" ref: %#"PRI_lx64" idx: %u tid: %d cpu: %d\n", event->auxtrace.size, event->auxtrace.offset, event->auxtrace.reference, event->auxtrace.idx, event->auxtrace.tid, event->auxtrace.cpu); @@ -964,6 +1277,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->transactions = true; synth_opts->ptwrites = true; synth_opts->pwr_events = true; + synth_opts->other_events = true; synth_opts->errors = true; if (no_sample) { synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS; @@ -1061,6 +1375,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'p': synth_opts->pwr_events = true; break; + case 'o': + synth_opts->other_events = true; + break; case 'e': synth_opts->errors = true; break; @@ -1154,7 +1471,7 @@ static const char *auxtrace_error_name(int type) size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp) { - struct auxtrace_error_event *e = &event->auxtrace_error; + struct perf_record_auxtrace_error *e = &event->auxtrace_error; unsigned long long nsecs = e->time; const char *msg = e->msg; int ret; @@ -1174,7 +1491,7 @@ size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp) if (!e->fmt) msg = (const char *)&e->time; - ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n", + ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRI_lx64" code %u: %s\n", e->cpu, e->pid, e->tid, e->ip, e->code, msg); return ret; } @@ -1182,7 +1499,7 @@ size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp) void perf_session__auxtrace_error_inc(struct perf_session *session, union perf_event *event) { - struct auxtrace_error_event *e = &event->auxtrace_error; + struct perf_record_auxtrace_error *e = &event->auxtrace_error; if (e->type < PERF_AUXTRACE_ERROR_MAX) session->evlist->stats.nr_auxtrace_errors[e->type] += 1; @@ -1211,7 +1528,7 @@ int perf_event__process_auxtrace_error(struct perf_session *session, return 0; } -static int __auxtrace_mmap__read(struct perf_mmap *map, +static int __auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, bool snapshot, size_t snapshot_size) @@ -1322,13 +1639,13 @@ static int __auxtrace_mmap__read(struct perf_mmap *map, return 1; } -int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn) { return __auxtrace_mmap__read(map, itr, tool, fn, false, 0); } -int auxtrace_mmap__read_snapshot(struct perf_mmap *map, +int auxtrace_mmap__read_snapshot(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size) @@ -1440,6 +1757,34 @@ int auxtrace_cache__add(struct auxtrace_cache *c, u32 key, return 0; } +static struct auxtrace_cache_entry *auxtrace_cache__rm(struct auxtrace_cache *c, + u32 key) +{ + struct auxtrace_cache_entry *entry; + struct hlist_head *hlist; + struct hlist_node *n; + + if (!c) + return NULL; + + hlist = &c->hashtable[hash_32(key, c->bits)]; + hlist_for_each_entry_safe(entry, n, hlist, hash) { + if (entry->key == key) { + hlist_del(&entry->hash); + return entry; + } + } + + return NULL; +} + +void auxtrace_cache__remove(struct auxtrace_cache *c, u32 key) +{ + struct auxtrace_cache_entry *entry = auxtrace_cache__rm(c, key); + + auxtrace_cache__free_entry(c, entry); +} + void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key) { struct auxtrace_cache_entry *entry; @@ -2084,7 +2429,7 @@ static char *addr_filter__to_str(struct addr_filter *filt) return err < 0 ? NULL : filter; } -static int parse_addr_filter(struct perf_evsel *evsel, const char *filter, +static int parse_addr_filter(struct evsel *evsel, const char *filter, int max_nr) { struct addr_filters filts; @@ -2135,19 +2480,7 @@ out_exit: return err; } -static struct perf_pmu *perf_evsel__find_pmu(struct perf_evsel *evsel) -{ - struct perf_pmu *pmu = NULL; - - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - if (pmu->type == evsel->attr.type) - break; - } - - return pmu; -} - -static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel) +static int perf_evsel__nr_addr_filter(struct evsel *evsel) { struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); int nr_addr_filters = 0; @@ -2160,9 +2493,9 @@ static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel) return nr_addr_filters; } -int auxtrace_parse_filters(struct perf_evlist *evlist) +int auxtrace_parse_filters(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; char *filter; int err, max_nr; @@ -2181,3 +2514,46 @@ int auxtrace_parse_filters(struct perf_evlist *evlist) return 0; } + +int auxtrace__process_event(struct perf_session *session, union perf_event *event, + struct perf_sample *sample, struct perf_tool *tool) +{ + if (!session->auxtrace) + return 0; + + return session->auxtrace->process_event(session, event, sample, tool); +} + +void auxtrace__dump_auxtrace_sample(struct perf_session *session, + struct perf_sample *sample) +{ + if (!session->auxtrace || !session->auxtrace->dump_auxtrace_sample || + auxtrace__dont_decode(session)) + return; + + session->auxtrace->dump_auxtrace_sample(session, sample); +} + +int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool) +{ + if (!session->auxtrace) + return 0; + + return session->auxtrace->flush_events(session, tool); +} + +void auxtrace__free_events(struct perf_session *session) +{ + if (!session->auxtrace) + return; + + return session->auxtrace->free_events(session); +} + +void auxtrace__free(struct perf_session *session) +{ + if (!session->auxtrace) + return; + + return session->auxtrace->free(session); +} diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index e9b4c5edf78b..749d72cd9c7b 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -11,26 +11,30 @@ #include <errno.h> #include <stdbool.h> #include <stddef.h> +#include <stdio.h> // FILE #include <linux/list.h> #include <linux/perf_event.h> #include <linux/types.h> #include <asm/bitsperlong.h> - -#include "../perf.h" -#include "event.h" -#include "session.h" -#include "debug.h" +#include <asm/barrier.h> union perf_event; struct perf_session; -struct perf_evlist; +struct evlist; struct perf_tool; -struct perf_mmap; +struct mmap; +struct perf_sample; struct option; struct record_opts; -struct auxtrace_info_event; +struct perf_record_auxtrace_error; +struct perf_record_auxtrace_info; struct events_stats; +enum auxtrace_error_type { + PERF_AUXTRACE_ERROR_ITRACE = 1, + PERF_AUXTRACE_ERROR_MAX +}; + /* Auxtrace records must have the same alignment as perf event records */ #define PERF_AUXTRACE_RECORD_ALIGNMENT 8 @@ -60,6 +64,8 @@ enum itrace_period_type { * @transactions: whether to synthesize events for transactions * @ptwrites: whether to synthesize events for ptwrites * @pwr_events: whether to synthesize power events + * @other_events: whether to synthesize other events recorded due to the use of + * aux_output * @errors: whether to synthesize decoder error events * @dont_decode: whether to skip decoding entirely * @log: write a decoding log @@ -86,6 +92,7 @@ struct itrace_synth_opts { bool transactions; bool ptwrites; bool pwr_events; + bool other_events; bool errors; bool dont_decode; bool log; @@ -134,6 +141,9 @@ struct auxtrace_index { * struct auxtrace - session callbacks to allow AUX area data decoding. * @process_event: lets the decoder see all session events * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event + * @queue_data: queue an AUX sample or PERF_RECORD_AUXTRACE event for later + * processing + * @dump_auxtrace_sample: dump AUX area sample data * @flush_events: process any remaining data * @free_events: free resources associated with event processing * @free: free resources associated with the session @@ -146,6 +156,11 @@ struct auxtrace { int (*process_auxtrace_event)(struct perf_session *session, union perf_event *event, struct perf_tool *tool); + int (*queue_data)(struct perf_session *session, + struct perf_sample *sample, union perf_event *event, + u64 data_offset); + void (*dump_auxtrace_sample)(struct perf_session *session, + struct perf_sample *sample); int (*flush_events)(struct perf_session *session, struct perf_tool *tool); void (*free_events)(struct perf_session *session); @@ -306,16 +321,17 @@ struct auxtrace_mmap_params { * @reference: provide a 64-bit reference number for auxtrace_event * @read_finish: called after reading from an auxtrace mmap * @alignment: alignment (if any) for AUX area data + * @default_aux_sample_size: default sample size for --aux sample option */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts); size_t (*info_priv_size)(struct auxtrace_record *itr, - struct perf_evlist *evlist); + struct evlist *evlist); int (*info_fill)(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size); void (*free)(struct auxtrace_record *itr); int (*snapshot_start)(struct auxtrace_record *itr); @@ -329,6 +345,7 @@ struct auxtrace_record { u64 (*reference)(struct auxtrace_record *itr); int (*read_finish)(struct auxtrace_record *itr, int idx); unsigned int alignment; + unsigned int default_aux_sample_size; }; /** @@ -373,6 +390,8 @@ struct addr_filters { int cnt; }; +struct auxtrace_cache; + #ifdef HAVE_AUXTRACE_SUPPORT /* @@ -432,18 +451,18 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, unsigned int auxtrace_pages, bool auxtrace_overwrite); void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool, - struct perf_mmap *map, + struct mmap *map, union perf_event *event, void *data1, size_t len1, void *data2, size_t len2); -int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn); -int auxtrace_mmap__read_snapshot(struct perf_mmap *map, +int auxtrace_mmap__read_snapshot(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size); @@ -453,9 +472,19 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct perf_session *session, union perf_event *event, off_t data_offset, struct auxtrace_buffer **buffer_ptr); +struct auxtrace_queue * +auxtrace_queues__sample_queue(struct auxtrace_queues *queues, + struct perf_sample *sample, + struct perf_session *session); +int auxtrace_queues__add_sample(struct auxtrace_queues *queues, + struct perf_session *session, + struct perf_sample *sample, u64 data_offset, + u64 reference); void auxtrace_queues__free(struct auxtrace_queues *queues); int auxtrace_queues__process_index(struct auxtrace_queues *queues, struct perf_session *session); +int auxtrace_queue_data(struct perf_session *session, bool samples, + bool events); struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue, struct auxtrace_buffer *buffer); void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd); @@ -480,26 +509,30 @@ void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c); void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry); int auxtrace_cache__add(struct auxtrace_cache *c, u32 key, struct auxtrace_cache_entry *entry); +void auxtrace_cache__remove(struct auxtrace_cache *c, u32 key); void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key); -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err); int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, struct record_opts *opts, const char *str); +int auxtrace_parse_sample_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts, const char *str); int auxtrace_record__options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts); size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, - struct perf_evlist *evlist); + struct evlist *evlist); int auxtrace_record__info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size); void auxtrace_record__free(struct auxtrace_record *itr); int auxtrace_record__snapshot_start(struct auxtrace_record *itr); -int auxtrace_record__snapshot_finish(struct auxtrace_record *itr); +int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit); int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, unsigned char *data, u64 *head, u64 *old); @@ -512,14 +545,10 @@ int auxtrace_index__process(int fd, u64 size, struct perf_session *session, bool needs_swap); void auxtrace_index__free(struct list_head *head); -void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type, +void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type, int code, int cpu, pid_t pid, pid_t tid, u64 ip, const char *msg, u64 timestamp); -int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, - struct perf_tool *tool, - struct perf_session *session, - perf_event__handler_t process); int perf_event__process_auxtrace_info(struct perf_session *session, union perf_event *event); s64 perf_event__process_auxtrace(struct perf_session *session, @@ -540,43 +569,15 @@ void addr_filters__init(struct addr_filters *filts); void addr_filters__exit(struct addr_filters *filts); int addr_filters__parse_bare_filter(struct addr_filters *filts, const char *filter); -int auxtrace_parse_filters(struct perf_evlist *evlist); - -static inline int auxtrace__process_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool) -{ - if (!session->auxtrace) - return 0; - - return session->auxtrace->process_event(session, event, sample, tool); -} +int auxtrace_parse_filters(struct evlist *evlist); -static inline int auxtrace__flush_events(struct perf_session *session, - struct perf_tool *tool) -{ - if (!session->auxtrace) - return 0; - - return session->auxtrace->flush_events(session, tool); -} - -static inline void auxtrace__free_events(struct perf_session *session) -{ - if (!session->auxtrace) - return; - - return session->auxtrace->free_events(session); -} - -static inline void auxtrace__free(struct perf_session *session) -{ - if (!session->auxtrace) - return; - - return session->auxtrace->free(session); -} +int auxtrace__process_event(struct perf_session *session, union perf_event *event, + struct perf_sample *sample, struct perf_tool *tool); +void auxtrace__dump_auxtrace_sample(struct perf_session *session, + struct perf_sample *sample); +int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool); +void auxtrace__free_events(struct perf_session *session); +void auxtrace__free(struct perf_session *session); #define ITRACE_HELP \ " i: synthesize instructions events\n" \ @@ -611,9 +612,10 @@ void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts) } #else +#include "debug.h" static inline struct auxtrace_record * -auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, +auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err) { *err = 0; @@ -625,18 +627,9 @@ void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused) { } -static inline int -perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, - struct perf_tool *tool __maybe_unused, - struct perf_session *session __maybe_unused, - perf_event__handler_t process __maybe_unused) -{ - return -EINVAL; -} - static inline int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, struct record_opts *opts __maybe_unused) { return 0; @@ -681,6 +674,18 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, } static inline +int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused, + struct evlist *evlist __maybe_unused, + struct record_opts *opts __maybe_unused, + const char *str) +{ + if (!str) + return 0; + pr_err("AUX area tracing not supported\n"); + return -EINVAL; +} + +static inline int auxtrace__process_event(struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, @@ -690,6 +695,12 @@ int auxtrace__process_event(struct perf_session *session __maybe_unused, } static inline +void auxtrace__dump_auxtrace_sample(struct perf_session *session __maybe_unused, + struct perf_sample *sample __maybe_unused) +{ +} + +static inline int auxtrace__flush_events(struct perf_session *session __maybe_unused, struct perf_tool *tool __maybe_unused) { @@ -733,7 +744,7 @@ void auxtrace_index__free(struct list_head *head __maybe_unused) } static inline -int auxtrace_parse_filters(struct perf_evlist *evlist __maybe_unused) +int auxtrace_parse_filters(struct evlist *evlist __maybe_unused) { return 0; } @@ -747,7 +758,7 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, unsigned int auxtrace_pages, bool auxtrace_overwrite); void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu); #define ITRACE_HELP "" diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c new file mode 100644 index 000000000000..c4b030bf6ec2 --- /dev/null +++ b/tools/perf/util/block-info.c @@ -0,0 +1,477 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdlib.h> +#include <string.h> +#include <linux/zalloc.h> +#include "block-info.h" +#include "sort.h" +#include "annotate.h" +#include "symbol.h" +#include "dso.h" +#include "map.h" +#include "srcline.h" +#include "evlist.h" +#include "hist.h" +#include "ui/browsers/hists.h" + +static struct block_header_column { + const char *name; + int width; +} block_columns[PERF_HPP_REPORT__BLOCK_MAX_INDEX] = { + [PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT] = { + .name = "Sampled Cycles%", + .width = 15, + }, + [PERF_HPP_REPORT__BLOCK_LBR_CYCLES] = { + .name = "Sampled Cycles", + .width = 14, + }, + [PERF_HPP_REPORT__BLOCK_CYCLES_PCT] = { + .name = "Avg Cycles%", + .width = 11, + }, + [PERF_HPP_REPORT__BLOCK_AVG_CYCLES] = { + .name = "Avg Cycles", + .width = 10, + }, + [PERF_HPP_REPORT__BLOCK_RANGE] = { + .name = "[Program Block Range]", + .width = 70, + }, + [PERF_HPP_REPORT__BLOCK_DSO] = { + .name = "Shared Object", + .width = 20, + } +}; + +struct block_info *block_info__get(struct block_info *bi) +{ + if (bi) + refcount_inc(&bi->refcnt); + return bi; +} + +void block_info__put(struct block_info *bi) +{ + if (bi && refcount_dec_and_test(&bi->refcnt)) + free(bi); +} + +struct block_info *block_info__new(void) +{ + struct block_info *bi = zalloc(sizeof(*bi)); + + if (bi) + refcount_set(&bi->refcnt, 1); + return bi; +} + +int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + struct block_info *bi_l = left->block_info; + struct block_info *bi_r = right->block_info; + int cmp; + + if (!bi_l->sym || !bi_r->sym) { + if (!bi_l->sym && !bi_r->sym) + return 0; + else if (!bi_l->sym) + return -1; + else + return 1; + } + + if (bi_l->sym == bi_r->sym) { + if (bi_l->start == bi_r->start) { + if (bi_l->end == bi_r->end) + return 0; + else + return (int64_t)(bi_r->end - bi_l->end); + } else + return (int64_t)(bi_r->start - bi_l->start); + } else { + cmp = strcmp(bi_l->sym->name, bi_r->sym->name); + return cmp; + } + + if (bi_l->sym->start != bi_r->sym->start) + return (int64_t)(bi_r->sym->start - bi_l->sym->start); + + return (int64_t)(bi_r->sym->end - bi_l->sym->end); +} + +static void init_block_info(struct block_info *bi, struct symbol *sym, + struct cyc_hist *ch, int offset, + u64 total_cycles) +{ + bi->sym = sym; + bi->start = ch->start; + bi->end = offset; + bi->cycles = ch->cycles; + bi->cycles_aggr = ch->cycles_aggr; + bi->num = ch->num; + bi->num_aggr = ch->num_aggr; + bi->total_cycles = total_cycles; + + memcpy(bi->cycles_spark, ch->cycles_spark, + NUM_SPARKS * sizeof(u64)); +} + +int block_info__process_sym(struct hist_entry *he, struct block_hist *bh, + u64 *block_cycles_aggr, u64 total_cycles) +{ + struct annotation *notes; + struct cyc_hist *ch; + static struct addr_location al; + u64 cycles = 0; + + if (!he->ms.map || !he->ms.sym) + return 0; + + memset(&al, 0, sizeof(al)); + al.map = he->ms.map; + al.sym = he->ms.sym; + + notes = symbol__annotation(he->ms.sym); + if (!notes || !notes->src || !notes->src->cycles_hist) + return 0; + ch = notes->src->cycles_hist; + for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) { + if (ch[i].num_aggr) { + struct block_info *bi; + struct hist_entry *he_block; + + bi = block_info__new(); + if (!bi) + return -1; + + init_block_info(bi, he->ms.sym, &ch[i], i, + total_cycles); + cycles += bi->cycles_aggr / bi->num_aggr; + + he_block = hists__add_entry_block(&bh->block_hists, + &al, bi); + if (!he_block) { + block_info__put(bi); + return -1; + } + } + } + + if (block_cycles_aggr) + *block_cycles_aggr += cycles; + + return 0; +} + +static int block_column_header(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hists *hists __maybe_unused, + int line __maybe_unused, + int *span __maybe_unused) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + block_fmt->header); +} + +static int block_column_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct hists *hists __maybe_unused) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + + return block_fmt->width; +} + +static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + double ratio = 0.0; + char buf[16]; + + if (block_fmt->total_cycles) + ratio = (double)bi->cycles / (double)block_fmt->total_cycles; + + sprintf(buf, "%.2f%%", 100.0 * ratio); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt, + struct hist_entry *left, + struct hist_entry *right) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi_l = left->block_info; + struct block_info *bi_r = right->block_info; + double l, r; + + if (block_fmt->total_cycles) { + l = ((double)bi_l->cycles / + (double)block_fmt->total_cycles) * 100000.0; + r = ((double)bi_r->cycles / + (double)block_fmt->total_cycles) * 100000.0; + return (int64_t)l - (int64_t)r; + } + + return 0; +} + +static void cycles_string(u64 cycles, char *buf, int size) +{ + if (cycles >= 1000000) + scnprintf(buf, size, "%.1fM", (double)cycles / 1000000.0); + else if (cycles >= 1000) + scnprintf(buf, size, "%.1fK", (double)cycles / 1000.0); + else + scnprintf(buf, size, "%1d", cycles); +} + +static int block_cycles_lbr_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char cycles_buf[16]; + + cycles_string(bi->cycles_aggr, cycles_buf, sizeof(cycles_buf)); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + cycles_buf); +} + +static int block_cycles_pct_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + double ratio = 0.0; + u64 avg; + char buf[16]; + + if (block_fmt->block_cycles && bi->num_aggr) { + avg = bi->cycles_aggr / bi->num_aggr; + ratio = (double)avg / (double)block_fmt->block_cycles; + } + + sprintf(buf, "%.2f%%", 100.0 * ratio); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int block_avg_cycles_entry(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char cycles_buf[16]; + + cycles_string(bi->cycles_aggr / bi->num_aggr, cycles_buf, + sizeof(cycles_buf)); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + cycles_buf); +} + +static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct block_info *bi = he->block_info; + char buf[128]; + char *start_line, *end_line; + + symbol_conf.disable_add2line_warn = true; + + start_line = map__srcline(he->ms.map, bi->sym->start + bi->start, + he->ms.sym); + + end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, + he->ms.sym); + + if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + scnprintf(buf, sizeof(buf), "[%s -> %s]", + start_line, end_line); + } else { + scnprintf(buf, sizeof(buf), "[%7lx -> %7lx]", + bi->start, bi->end); + } + + free_srcline(start_line); + free_srcline(end_line); + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf); +} + +static int block_dso_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); + struct map *map = he->ms.map; + + if (map && map->dso) { + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + map->dso->short_name); + } + + return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, + "[unknown]"); +} + +static void init_block_header(struct block_fmt *block_fmt) +{ + struct perf_hpp_fmt *fmt = &block_fmt->fmt; + + BUG_ON(block_fmt->idx >= PERF_HPP_REPORT__BLOCK_MAX_INDEX); + + block_fmt->header = block_columns[block_fmt->idx].name; + block_fmt->width = block_columns[block_fmt->idx].width; + + fmt->header = block_column_header; + fmt->width = block_column_width; +} + +static void hpp_register(struct block_fmt *block_fmt, int idx, + struct perf_hpp_list *hpp_list) +{ + struct perf_hpp_fmt *fmt = &block_fmt->fmt; + + block_fmt->idx = idx; + INIT_LIST_HEAD(&fmt->list); + INIT_LIST_HEAD(&fmt->sort_list); + + switch (idx) { + case PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT: + fmt->entry = block_total_cycles_pct_entry; + fmt->cmp = block_info__cmp; + fmt->sort = block_total_cycles_pct_sort; + break; + case PERF_HPP_REPORT__BLOCK_LBR_CYCLES: + fmt->entry = block_cycles_lbr_entry; + break; + case PERF_HPP_REPORT__BLOCK_CYCLES_PCT: + fmt->entry = block_cycles_pct_entry; + break; + case PERF_HPP_REPORT__BLOCK_AVG_CYCLES: + fmt->entry = block_avg_cycles_entry; + break; + case PERF_HPP_REPORT__BLOCK_RANGE: + fmt->entry = block_range_entry; + break; + case PERF_HPP_REPORT__BLOCK_DSO: + fmt->entry = block_dso_entry; + break; + default: + return; + } + + init_block_header(block_fmt); + perf_hpp_list__column_register(hpp_list, fmt); +} + +static void register_block_columns(struct perf_hpp_list *hpp_list, + struct block_fmt *block_fmts) +{ + for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) + hpp_register(&block_fmts[i], i, hpp_list); +} + +static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts) +{ + __hists__init(&bh->block_hists, &bh->block_list); + perf_hpp_list__init(&bh->block_list); + bh->block_list.nr_header_lines = 1; + + register_block_columns(&bh->block_list, block_fmts); + + perf_hpp_list__register_sort_field(&bh->block_list, + &block_fmts[PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT].fmt); +} + +static void process_block_report(struct hists *hists, + struct block_report *block_report, + u64 total_cycles) +{ + struct rb_node *next = rb_first_cached(&hists->entries); + struct block_hist *bh = &block_report->hist; + struct hist_entry *he; + + init_block_hist(bh, block_report->fmts); + + while (next) { + he = rb_entry(next, struct hist_entry, rb_node); + block_info__process_sym(he, bh, &block_report->cycles, + total_cycles); + next = rb_next(&he->rb_node); + } + + for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) { + block_report->fmts[i].total_cycles = total_cycles; + block_report->fmts[i].block_cycles = block_report->cycles; + } + + hists__output_resort(&bh->block_hists, NULL); +} + +struct block_report *block_info__create_report(struct evlist *evlist, + u64 total_cycles) +{ + struct block_report *block_reports; + int nr_hists = evlist->core.nr_entries, i = 0; + struct evsel *pos; + + block_reports = calloc(nr_hists, sizeof(struct block_report)); + if (!block_reports) + return NULL; + + evlist__for_each_entry(evlist, pos) { + struct hists *hists = evsel__hists(pos); + + process_block_report(hists, &block_reports[i], total_cycles); + i++; + } + + return block_reports; +} + +int report__browse_block_hists(struct block_hist *bh, float min_percent, + struct evsel *evsel, struct perf_env *env, + struct annotation_options *annotation_opts) +{ + int ret; + + switch (use_browser) { + case 0: + symbol_conf.report_individual_block = true; + hists__fprintf(&bh->block_hists, true, 0, 0, min_percent, + stdout, true); + hists__delete_entries(&bh->block_hists); + return 0; + case 1: + symbol_conf.report_individual_block = true; + ret = block_hists_tui_browse(bh, evsel, min_percent, + env, annotation_opts); + hists__delete_entries(&bh->block_hists); + return ret; + default: + return -1; + } + + return 0; +} + +float block_info__total_cycles_percent(struct hist_entry *he) +{ + struct block_info *bi = he->block_info; + + if (bi->total_cycles) + return bi->cycles * 100.0 / bi->total_cycles; + + return 0.0; +} diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h new file mode 100644 index 000000000000..bef0d75e9819 --- /dev/null +++ b/tools/perf/util/block-info.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_BLOCK_H +#define __PERF_BLOCK_H + +#include <linux/types.h> +#include <linux/refcount.h> +#include "hist.h" +#include "symbol.h" +#include "sort.h" +#include "ui/ui.h" + +struct block_info { + struct symbol *sym; + u64 start; + u64 end; + u64 cycles; + u64 cycles_aggr; + s64 cycles_spark[NUM_SPARKS]; + u64 total_cycles; + int num; + int num_aggr; + refcount_t refcnt; +}; + +struct block_fmt { + struct perf_hpp_fmt fmt; + int idx; + int width; + const char *header; + u64 total_cycles; + u64 block_cycles; +}; + +enum { + PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT, + PERF_HPP_REPORT__BLOCK_LBR_CYCLES, + PERF_HPP_REPORT__BLOCK_CYCLES_PCT, + PERF_HPP_REPORT__BLOCK_AVG_CYCLES, + PERF_HPP_REPORT__BLOCK_RANGE, + PERF_HPP_REPORT__BLOCK_DSO, + PERF_HPP_REPORT__BLOCK_MAX_INDEX +}; + +struct block_report { + struct block_hist hist; + u64 cycles; + struct block_fmt fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX]; +}; + +struct block_hist; + +struct block_info *block_info__new(void); +struct block_info *block_info__get(struct block_info *bi); +void block_info__put(struct block_info *bi); + +static inline void __block_info__zput(struct block_info **bi) +{ + block_info__put(*bi); + *bi = NULL; +} + +#define block_info__zput(bi) __block_info__zput(&bi) + +int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right); + +int block_info__process_sym(struct hist_entry *he, struct block_hist *bh, + u64 *block_cycles_aggr, u64 total_cycles); + +struct block_report *block_info__create_report(struct evlist *evlist, + u64 total_cycles); + +int report__browse_block_hists(struct block_hist *bh, float min_percent, + struct evsel *evsel, struct perf_env *env, + struct annotation_options *annotation_opts); + +float block_info__total_cycles_percent(struct hist_entry *he); + +#endif /* __PERF_BLOCK_H */ diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 2a4a0da35632..a3207d900339 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -8,12 +8,15 @@ #include <linux/err.h> #include "bpf-event.h" #include "debug.h" +#include "dso.h" #include "symbol.h" #include "machine.h" #include "env.h" #include "session.h" #include "map.h" #include "evlist.h" +#include "record.h" +#include "util/synthetic-events.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -34,7 +37,7 @@ static int machine__process_bpf_event_load(struct machine *machine, struct bpf_prog_info_linear *info_linear; struct bpf_prog_info_node *info_node; struct perf_env *env = machine->env; - int id = event->bpf_event.id; + int id = event->bpf.id; unsigned int i; /* perf-record, no need to handle bpf-event */ @@ -49,9 +52,7 @@ static int machine__process_bpf_event_load(struct machine *machine, for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) { u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms); u64 addr = addrs[i]; - struct map *map; - - map = map_groups__find(&machine->kmaps, addr); + struct map *map = maps__find(&machine->kmaps, addr); if (map) { map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO; @@ -63,14 +64,13 @@ static int machine__process_bpf_event_load(struct machine *machine, return 0; } -int machine__process_bpf_event(struct machine *machine __maybe_unused, - union perf_event *event, - struct perf_sample *sample __maybe_unused) +int machine__process_bpf(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { if (dump_trace) - perf_event__fprintf_bpf_event(event, stdout); + perf_event__fprintf_bpf(event, stdout); - switch (event->bpf_event.type) { + switch (event->bpf.type) { case PERF_BPF_EVENT_PROG_LOAD: return machine__process_bpf_event_load(machine, event, sample); @@ -82,8 +82,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused, */ break; default: - pr_debug("unexpected bpf_event type of %d\n", - event->bpf_event.type); + pr_debug("unexpected bpf event type of %d\n", event->bpf.type); break; } return 0; @@ -160,8 +159,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, union perf_event *event, struct record_opts *opts) { - struct ksymbol_event *ksymbol_event = &event->ksymbol_event; - struct bpf_event *bpf_event = &event->bpf_event; + struct perf_record_ksymbol *ksymbol_event = &event->ksymbol; + struct perf_record_bpf_event *bpf_event = &event->bpf; struct bpf_prog_info_linear *info_linear; struct perf_tool *tool = session->tool; struct bpf_prog_info_node *info_node; @@ -229,10 +228,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); int name_len; - *ksymbol_event = (struct ksymbol_event){ + *ksymbol_event = (struct perf_record_ksymbol) { .header = { .type = PERF_RECORD_KSYMBOL, - .size = offsetof(struct ksymbol_event, name), + .size = offsetof(struct perf_record_ksymbol, name), }, .addr = prog_addrs[i], .len = prog_lens[i], @@ -253,10 +252,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, if (!opts->no_bpf_event) { /* Synthesize PERF_RECORD_BPF_EVENT */ - *bpf_event = (struct bpf_event){ + *bpf_event = (struct perf_record_bpf_event) { .header = { .type = PERF_RECORD_BPF_EVENT, - .size = sizeof(struct bpf_event), + .size = sizeof(struct perf_record_bpf_event), }, .type = PERF_BPF_EVENT_PROG_LOAD, .flags = 0, @@ -301,7 +300,7 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, int err; int fd; - event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN + machine->id_hdr_size); + event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size); if (!event) return -1; while (true) { @@ -398,9 +397,9 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) if (event->header.type != PERF_RECORD_BPF_EVENT) return -1; - switch (event->bpf_event.type) { + switch (event->bpf.type) { case PERF_BPF_EVENT_PROG_LOAD: - perf_env__add_bpf_info(env, event->bpf_event.id); + perf_env__add_bpf_info(env, event->bpf.id); case PERF_BPF_EVENT_PROG_UNLOAD: /* @@ -410,15 +409,14 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) */ break; default: - pr_debug("unexpected bpf_event type of %d\n", - event->bpf_event.type); + pr_debug("unexpected bpf event type of %d\n", event->bpf.type); break; } return 0; } -int bpf_event__add_sb_event(struct perf_evlist **evlist, +int bpf_event__add_sb_event(struct evlist **evlist, struct perf_env *env) { struct perf_event_attr attr = { diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 04c33b3bfe28..81fdc88e6c1a 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -6,13 +6,14 @@ #include <linux/rbtree.h> #include <pthread.h> #include <api/fd/array.h> -#include "event.h" #include <stdio.h> +struct bpf_prog_info; struct machine; union perf_event; struct perf_env; struct perf_sample; +struct perf_session; struct record_opts; struct evlist; struct target; @@ -30,35 +31,22 @@ struct btf_node { }; #ifdef HAVE_LIBBPF_SUPPORT -int machine__process_bpf_event(struct machine *machine, union perf_event *event, - struct perf_sample *sample); - -int perf_event__synthesize_bpf_events(struct perf_session *session, - perf_event__handler_t process, - struct machine *machine, - struct record_opts *opts); -int bpf_event__add_sb_event(struct perf_evlist **evlist, +int machine__process_bpf(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int bpf_event__add_sb_event(struct evlist **evlist, struct perf_env *env); void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, struct perf_env *env, FILE *fp); #else -static inline int machine__process_bpf_event(struct machine *machine __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ - return 0; -} - -static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused, - struct record_opts *opts __maybe_unused) +static inline int machine__process_bpf(struct machine *machine __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused) { return 0; } -static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused, +static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused, struct perf_env *env __maybe_unused) { return 0; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index c61974a50aa5..10c187b8b8ea 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -14,7 +14,7 @@ #include <linux/string.h> #include <linux/zalloc.h> #include <errno.h> -#include "perf.h" +#include <stdlib.h> #include "debug.h" #include "evlist.h" #include "bpf-loader.h" @@ -23,9 +23,12 @@ #include "probe-finder.h" // for MAX_PROBES #include "parse-events.h" #include "strfilter.h" +#include "util.h" #include "llvm-utils.h" #include "c++/clang-c.h" +#include <internal/xyarray.h> + static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), const char *fmt, va_list args) { @@ -763,7 +766,7 @@ int bpf__foreach_event(struct bpf_object *obj, if (priv->is_tp) { fd = bpf_program__fd(prog); - err = (*func)(priv->sys_name, priv->evt_name, fd, arg); + err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg); if (err) { pr_debug("bpf: tracepoint call back failed, stop iterate\n"); return err; @@ -788,7 +791,7 @@ int bpf__foreach_event(struct bpf_object *obj, return fd; } - err = (*func)(tev->group, tev->event, fd, arg); + err = (*func)(tev->group, tev->event, fd, obj, arg); if (err) { pr_debug("bpf: call back failed, stop iterate\n"); return err; @@ -817,7 +820,7 @@ struct bpf_map_op { } k; union { u64 value; - struct perf_evsel *evsel; + struct evsel *evsel; } v; }; @@ -1043,7 +1046,7 @@ __bpf_map__config_value(struct bpf_map *map, static int bpf_map__config_value(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { if (!term->err_val) { pr_debug("Config value not set\n"); @@ -1061,9 +1064,9 @@ bpf_map__config_value(struct bpf_map *map, static int __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); @@ -1103,7 +1106,7 @@ __bpf_map__config_event(struct bpf_map *map, static int bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist) + struct evlist *evlist) { if (!term->err_val) { pr_debug("Config value not set\n"); @@ -1121,7 +1124,7 @@ bpf_map__config_event(struct bpf_map *map, struct bpf_obj_config__map_func { const char *config_opt; int (*config_func)(struct bpf_map *, struct parse_events_term *, - struct perf_evlist *); + struct evlist *); }; struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = { @@ -1169,7 +1172,7 @@ config_map_indices_range_check(struct parse_events_term *term, static int bpf__obj_config_map(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *key_scan_pos) { /* key is "map:<mapname>.<config opt>" */ @@ -1228,7 +1231,7 @@ out: int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *error_pos) { int key_scan_pos = 0; @@ -1401,9 +1404,9 @@ apply_config_value_for_key(int map_fd, void *pkey, static int apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, - struct perf_evsel *evsel) + struct evsel *evsel) { - struct xyarray *xy = evsel->fd; + struct xyarray *xy = evsel->core.fd; struct perf_event_attr *attr; unsigned int key, events; bool check_pass = false; @@ -1421,7 +1424,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM; } - attr = &evsel->attr; + attr = &evsel->core.attr; if (attr->inherit) { pr_debug("ERROR: Can't put inherit event into map %s\n", name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH; @@ -1523,11 +1526,11 @@ int bpf__apply_obj_config(void) (strcmp(name, \ bpf_map__name(pos)) == 0)) -struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name) +struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name) { struct bpf_map_priv *tmpl_priv = NULL; struct bpf_object *obj, *tmp; - struct perf_evsel *evsel = NULL; + struct evsel *evsel = NULL; struct bpf_map *map; int err; bool need_init = false; @@ -1565,7 +1568,7 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha return ERR_PTR(-err); } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); } bpf__for_each_map_named(map, obj, tmp, name) { @@ -1600,9 +1603,9 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha return evsel; } -int bpf__setup_stdout(struct perf_evlist *evlist) +int bpf__setup_stdout(struct evlist *evlist) { - struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); + struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); return PTR_ERR_OR_ZERO(evsel); } @@ -1756,7 +1759,7 @@ int bpf__strerror_load(struct bpf_object *obj, int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused, int err, char *buf, size_t size) { @@ -1780,7 +1783,7 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) return 0; } -int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, +int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, int err, char *buf, size_t size) { bpf__strerror_head(err, buf, size); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 3f46856e3330..25251d63164c 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -39,14 +39,14 @@ enum bpf_loader_errno { __BPF_LOADER_ERRNO__END, }; -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct bpf_object; struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event, - int fd, void *arg); + int fd, struct bpf_object *obj, void *arg); #ifdef HAVE_LIBBPF_SUPPORT struct bpf_object *bpf__prepare_load(const char *filename, bool source); @@ -70,18 +70,18 @@ int bpf__foreach_event(struct bpf_object *obj, bpf_prog_iter_callback_t func, void *arg); int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, int *error_pos); + struct evlist *evlist, int *error_pos); int bpf__strerror_config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *error_pos, int err, char *buf, size_t size); int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); -int bpf__setup_stdout(struct perf_evlist *evlist); -struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name); -int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size); +int bpf__setup_stdout(struct evlist *evlist); +struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name); +int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size); #else #include <errno.h> #include <string.h> @@ -119,7 +119,7 @@ bpf__foreach_event(struct bpf_object *obj __maybe_unused, static inline int bpf__config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused) { return 0; @@ -132,13 +132,13 @@ bpf__apply_obj_config(void) } static inline int -bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +bpf__setup_stdout(struct evlist *evlist __maybe_unused) { return 0; } -static inline struct perf_evsel * -bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused) +static inline struct evsel * +bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused) { return NULL; } @@ -182,7 +182,7 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused, static inline int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused, int err __maybe_unused, char *buf, size_t size) @@ -198,7 +198,7 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, } static inline int -bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, +bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, int err __maybe_unused, char *buf, size_t size) { return __bpf_strerror(buf, size); @@ -206,7 +206,7 @@ bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, #endif -static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size) +static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size) { return bpf__strerror_setup_output_event(evlist, err, buf, size); } diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 77e4891e17b0..b020a8678eb9 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -8,12 +8,12 @@ */ #include <bpf/libbpf.h> -#include "perf.h" #include "debug.h" #include "bpf-loader.h" #include "bpf-prologue.h" #include "probe-finder.h" #include <errno.h> +#include <stdlib.h> #include <dwarf-regs.h> #include <linux/filter.h> diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index a4fce2729e50..2285b1eb3128 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -1,7 +1,6 @@ -#include "perf.h" -#include "util/util.h" -#include "util/debug.h" +#include "util/map_symbol.h" #include "util/branch.h" +#include <linux/kernel.h> static bool cross_area(u64 addr1, u64 addr2, int size) { diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index 64f96b79f1d7..88e00d268f6f 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -1,8 +1,15 @@ #ifndef _PERF_BRANCH_H #define _PERF_BRANCH_H 1 - +/* + * The linux/stddef.h isn't need here, but is needed for __always_inline used + * in files included from uapi/linux/perf_event.h such as + * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h, + * detected in at least musl libc, used in Alpine Linux. -acme + */ #include <stdio.h> #include <stdint.h> +#include <linux/compiler.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/types.h> @@ -16,6 +23,14 @@ struct branch_flags { u64 reserved:40; }; +struct branch_info { + struct addr_map_symbol from; + struct addr_map_symbol to; + struct branch_flags flags; + char *srcline_from; + char *srcline_to; +}; + struct branch_entry { u64 from; u64 to; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index f1abfab7aa8c..c076fc7fe025 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -7,12 +7,14 @@ * Copyright (C) 2009, 2010 Red Hat Inc. * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include "util.h" +#include "util.h" // lsdir(), mkdir_p(), rm_rf() #include <dirent.h> #include <errno.h> #include <stdio.h> #include <sys/stat.h> #include <sys/types.h> +#include "util/copyfile.h" +#include "dso.h" #include "build-id.h" #include "event.h" #include "namespaces.h" @@ -37,7 +39,7 @@ static bool no_buildid_cache; int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; @@ -295,7 +297,7 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, pid_t pid, u16 misc, struct feat_fd *fd) { int err; - struct build_id_event b; + struct perf_record_header_build_id b; size_t len; len = name_len + 1; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 93668f38f1ed..aad419bb165c 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -24,7 +24,7 @@ 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, + struct perf_sample *sample, struct evsel *evsel, struct machine *machine); int dsos__hit_all(struct perf_session *session); diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index e513366f2ee0..2df8a45bd088 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -3,7 +3,6 @@ #define PERF_UTIL_CLANG_C_H #include <stddef.h> /* for size_t */ -#include <util-cxx.h> /* for __maybe_unused */ #ifdef __cplusplus extern "C" { @@ -22,6 +21,7 @@ extern int perf_clang__compile_bpf(const char *filename, #else #include <errno.h> +#include <linux/compiler.h> /* for __maybe_unused */ static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index 7b042a5ebc68..21b23605f78b 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include "clang.h" #include "clang-c.h" +extern "C" { +#include "../util.h" +} #include "llvm/IR/Function.h" #include "llvm/IR/LLVMContext.h" -#include <util-cxx.h> #include <tests/llvm.h> #include <string> diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index fc361c3f8570..c8885dfa3667 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -71,7 +71,11 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags, CompilerInstance Clang; Clang.createDiagnostics(); +#if CLANG_VERSION_MAJOR < 9 Clang.setVirtualFileSystem(&*VFS); +#else + Clang.createFileManager(&*VFS); +#endif #if CLANG_VERSION_MAJOR < 4 IntrusiveRefCntPtr<CompilerInvocation> CI = diff --git a/tools/perf/util/cacheline.c b/tools/perf/util/cacheline.c new file mode 100644 index 000000000000..e98b5250a517 --- /dev/null +++ b/tools/perf/util/cacheline.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "cacheline.h" +#include <unistd.h> + +#ifdef _SC_LEVEL1_DCACHE_LINESIZE +#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) +#else +#include <api/fs/fs.h> +#include "debug.h" +static void cache_line_size(int *cacheline_sizep) +{ + if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) + pr_debug("cannot determine cache line size"); +} +#endif + +int cacheline_size(void) +{ + static int size; + + if (!size) + cache_line_size(&size); + + return size; +} diff --git a/tools/perf/util/cacheline.h b/tools/perf/util/cacheline.h new file mode 100644 index 000000000000..dec8c0fb1f4a --- /dev/null +++ b/tools/perf/util/cacheline.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef PERF_CACHELINE_H +#define PERF_CACHELINE_H + +#include <linux/compiler.h> + +int __pure cacheline_size(void); + +static inline u64 cl_address(u64 address) +{ + /* return the cacheline of the address */ + return (address & ~(cacheline_size() - 1)); +} + +static inline u64 cl_offset(u64 address) +{ + /* return the cacheline of the address */ + return (address & (cacheline_size() - 1)); +} + +#endif // PERF_CACHELINE_H diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8d7d8f62fcca..818aa4efd386 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -16,10 +16,14 @@ #include <stdbool.h> #include <errno.h> #include <math.h> +#include <linux/string.h> #include <linux/zalloc.h> #include "asm/bug.h" +#include "debug.h" +#include "dso.h" +#include "event.h" #include "hist.h" #include "sort.h" #include "machine.h" @@ -27,6 +31,7 @@ #include "callchain.h" #include "branch.h" #include "symbol.h" +#include "../perf.h" #define CALLCHAIN_PARAM_DEFAULT \ .mode = CHAIN_GRAPH_ABS, \ @@ -577,8 +582,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) return -1; } call->ip = cursor_node->ip; - call->ms.sym = cursor_node->sym; - call->ms.map = map__get(cursor_node->map); + call->ms = cursor_node->ms; + map__get(call->ms.map); call->srcline = cursor_node->srcline; if (cursor_node->branch) { @@ -715,21 +720,21 @@ static enum match_result match_chain(struct callchain_cursor_node *node, /* otherwise fall-back to symbol-based comparison below */ __fallthrough; case CCKEY_FUNCTION: - if (node->sym && cnode->ms.sym) { + if (node->ms.sym && cnode->ms.sym) { /* * Compare inlined frames based on their symbol name * because different inlined frames will have the same * symbol start. Otherwise do a faster comparison based * on the symbol start address. */ - if (cnode->ms.sym->inlined || node->sym->inlined) { + if (cnode->ms.sym->inlined || node->ms.sym->inlined) { match = match_chain_strings(cnode->ms.sym->name, - node->sym->name); + node->ms.sym->name); if (match != MATCH_ERROR) break; } else { match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start, - node->map, node->sym->start); + node->ms.map, node->ms.sym->start); break; } } @@ -737,7 +742,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, __fallthrough; case CCKEY_ADDRESS: default: - match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip); + match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->ms.map, node->ip); break; } @@ -999,8 +1004,7 @@ merge_chain_branch(struct callchain_cursor *cursor, int err = 0; list_for_each_entry_safe(list, next_list, &src->val, list) { - callchain_cursor_append(cursor, list->ip, - list->ms.map, list->ms.sym, + callchain_cursor_append(cursor, list->ip, &list->ms, false, NULL, 0, 0, 0, list->srcline); list_del_init(&list->list); map__zput(list->ms.map); @@ -1039,7 +1043,7 @@ int callchain_merge(struct callchain_cursor *cursor, } int callchain_cursor_append(struct callchain_cursor *cursor, - u64 ip, struct map *map, struct symbol *sym, + u64 ip, struct map_symbol *ms, bool branch, struct branch_flags *flags, int nr_loop_iter, u64 iter_cycles, u64 branch_from, const char *srcline) @@ -1055,9 +1059,9 @@ int callchain_cursor_append(struct callchain_cursor *cursor, } node->ip = ip; - map__zput(node->map); - node->map = map__get(map); - node->sym = sym; + map__zput(node->ms.map); + node->ms = *ms; + map__get(node->ms.map); node->branch = branch; node->nr_loop_iter = nr_loop_iter; node->iter_cycles = iter_cycles; @@ -1077,7 +1081,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, int sample__resolve_callchain(struct perf_sample *sample, struct callchain_cursor *cursor, struct symbol **parent, - struct perf_evsel *evsel, struct addr_location *al, + struct evsel *evsel, struct addr_location *al, int max_stack) { if (sample->callchain == NULL && !symbol_conf.show_branchflag_count) @@ -1102,8 +1106,9 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - al->map = node->map; - al->sym = node->sym; + al->maps = node->ms.maps; + al->map = node->ms.map; + al->sym = node->ms.sym; al->srcline = node->srcline; al->addr = node->ip; @@ -1114,8 +1119,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * goto out; } - if (al->map->groups == &al->machine->kmaps) { - if (machine__is_host(al->machine)) { + if (al->maps == &al->maps->machine->kmaps) { + if (machine__is_host(al->maps->machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; } else { @@ -1123,7 +1128,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * al->level = 'g'; } } else { - if (machine__is_host(al->machine)) { + if (machine__is_host(al->maps->machine)) { al->cpumode = PERF_RECORD_MISC_USER; al->level = '.'; } else if (perf_guest) { @@ -1566,7 +1571,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst, if (node == NULL) break; - rc = callchain_cursor_append(dst, node->ip, node->map, node->sym, + rc = callchain_cursor_append(dst, node->ip, &node->ms, node->branch, &node->branch_flags, node->nr_loop_iter, node->iter_cycles, @@ -1592,5 +1597,5 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) cursor->last = &cursor->first; for (node = cursor->first; node != NULL; node = node->next) - map__zput(node->map); + map__zput(node->ms.map); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 80e056a3d882..706bb7bbe1e1 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -4,11 +4,15 @@ #include <linux/list.h> #include <linux/rbtree.h> -#include "event.h" #include "map_symbol.h" #include "branch.h" +struct addr_location; +struct evsel; +struct ip_callchain; struct map; +struct perf_sample; +struct thread; #define HELP_PAD "\t\t\t\t" @@ -137,8 +141,7 @@ struct callchain_list { */ struct callchain_cursor_node { u64 ip; - struct map *map; - struct symbol *sym; + struct map_symbol ms; const char *srcline; bool branch; struct branch_flags branch_flags; @@ -191,7 +194,7 @@ int callchain_merge(struct callchain_cursor *cursor, void callchain_cursor_reset(struct callchain_cursor *cursor); int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, - struct map *map, struct symbol *sym, + struct map_symbol *ms, bool branch, struct branch_flags *flags, int nr_loop_iter, u64 iter_cycles, u64 branch_from, const char *srcline); @@ -236,7 +239,7 @@ int record_opts__parse_callchain(struct record_opts *record, int sample__resolve_callchain(struct perf_sample *sample, struct callchain_cursor *cursor, struct symbol **parent, - struct perf_evsel *evsel, struct addr_location *al, + struct evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c new file mode 100644 index 000000000000..c3ba841bbf37 --- /dev/null +++ b/tools/perf/util/cap.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Capability utilities + */ + +#ifdef HAVE_LIBCAP_SUPPORT + +#include "cap.h" +#include <stdbool.h> +#include <sys/capability.h> + +bool perf_cap__capable(cap_value_t cap) +{ + cap_flag_value_t val; + cap_t caps = cap_get_proc(); + + if (!caps) + return false; + + if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val) != 0) + val = CAP_CLEAR; + + if (cap_free(caps) != 0) + return false; + + return val == CAP_SET; +} + +#endif /* HAVE_LIBCAP_SUPPORT */ diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h new file mode 100644 index 000000000000..051dc590ceee --- /dev/null +++ b/tools/perf/util/cap.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_CAP_H +#define __PERF_CAP_H + +#include <stdbool.h> +#include <linux/capability.h> +#include <linux/compiler.h> + +#ifdef HAVE_LIBCAP_SUPPORT + +#include <sys/capability.h> + +bool perf_cap__capable(cap_value_t cap); + +#else + +#include <unistd.h> +#include <sys/types.h> + +static inline bool perf_cap__capable(int cap __maybe_unused) +{ + return geteuid() == 0; +} + +#endif /* HAVE_LIBCAP_SUPPORT */ + +/* For older systems */ +#ifndef CAP_SYSLOG +#define CAP_SYSLOG 34 +#endif + +#endif /* __PERF_CAP_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 484c29830a81..4881d4af3381 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../perf.h" #include <subcmd/parse-options.h> #include "evsel.h" #include "cgroup.h" @@ -9,6 +8,8 @@ #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> +#include <stdlib.h> +#include <string.h> int nr_cgroups; @@ -90,9 +91,9 @@ static int open_cgroup(const char *name) return fd; } -static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str) +static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str) { - struct perf_evsel *counter; + struct evsel *counter; /* * check if cgrp is already defined, if so we reuse it */ @@ -130,16 +131,16 @@ out_err: return NULL; } -struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name) +struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name) { struct cgroup *cgroup = evlist__find_cgroup(evlist, name); return cgroup ?: cgroup__new(name); } -static int add_cgroup(struct perf_evlist *evlist, const char *str) +static int add_cgroup(struct evlist *evlist, const char *str) { - struct perf_evsel *counter; + struct evsel *counter; struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str); int n; @@ -184,15 +185,15 @@ struct cgroup *cgroup__get(struct cgroup *cgroup) return cgroup; } -static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup) +static void evsel__set_default_cgroup(struct evsel *evsel, struct cgroup *cgroup) { if (evsel->cgrp == NULL) evsel->cgrp = cgroup__get(cgroup); } -void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup) +void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) evsel__set_default_cgroup(evsel, cgroup); @@ -201,14 +202,14 @@ void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgrou int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; - struct perf_evsel *counter; + struct evlist *evlist = *(struct evlist **)opt->value; + struct evsel *counter; struct cgroup *cgrp = NULL; const char *p, *e, *eos = str + strlen(str); char *s; int ret, i; - if (list_empty(&evlist->entries)) { + if (list_empty(&evlist->core.entries)) { fprintf(stderr, "must define events before cgroups\n"); return -1; } diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index f033a80c1b14..2ec11f01090d 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -18,11 +18,11 @@ extern int nr_cgroups; /* number of explicit cgroups defined */ struct cgroup *cgroup__get(struct cgroup *cgroup); void cgroup__put(struct cgroup *cgroup); -struct perf_evlist; +struct evlist; -struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name); +struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name); -void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup); +void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup); int parse_cgroups(const struct option *opt, const char *str, int unset); diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 06f48312c5ed..a12872f2856a 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,13 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <sched.h> -#include "util.h" -#include "../perf.h" +#include "util.h" // for sched_getcpu() +#include "../perf-sys.h" #include "cloexec.h" +#include "event.h" #include "asm/bug.h" #include "debug.h" #include <unistd.h> #include <sys/syscall.h> +#include <linux/string.h> static unsigned long flag = PERF_FLAG_FD_CLOEXEC; diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 39b8c4ec4e2e..bffbdd216a6a 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> -#include "cache.h" +#include <subcmd/pager.h> #include <stdlib.h> #include <stdio.h> +#include <string.h> #include "color.h" #include <math.h> #include <unistd.h> diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c index 817dc56e7e95..dc09ba7cb31e 100644 --- a/tools/perf/util/color_config.c +++ b/tools/perf/util/color_config.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> -#include "cache.h" +#include <subcmd/pager.h> +#include <string.h> #include "config.h" #include <stdlib.h> #include <stdio.h> diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 042ffbc8c53f..0bc9c4d7fdc5 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -17,9 +17,13 @@ #include "util/event.h" /* proc_map_timeout */ #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ +#include "build-id.h" +#include "debug.h" #include "config.h" +#include "debug.h" #include <sys/types.h> #include <sys/stat.h> +#include <stdlib.h> #include <unistd.h> #include <linux/string.h> #include <linux/zalloc.h> diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c new file mode 100644 index 000000000000..47e03de7c235 --- /dev/null +++ b/tools/perf/util/copyfile.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "util/copyfile.h" +#include "util/namespaces.h" +#include <internal/lib.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +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, *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; + + to_fp = fopen(to, "w"); + if (to_fp == NULL) + goto out_fclose_from; + + while (getline(&line, &n, from_fp) > 0) + if (fputs(line, to_fp) == EOF) + goto out_fclose_to; + err = 0; +out_fclose_to: + fclose(to_fp); + free(line); +out_fclose_from: + fclose(from_fp); +out: + return err; +} + +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) +{ + void *ptr; + loff_t pgoff; + + pgoff = off_in & ~(page_size - 1); + off_in -= pgoff; + + ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff); + if (ptr == MAP_FAILED) + return -1; + + while (size) { + ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out); + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + break; + + size -= ret; + off_in += ret; + off_out += ret; + } + munmap(ptr, off_in + size); + + return size ? -1 : 0; +} + +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; + char *tmp = NULL, *ptr = NULL; + struct nscookie nsc; + + 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) { + tmp = NULL; + goto out; + } + ptr = strrchr(tmp, '/'); + if (!ptr) + goto out; + ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1); + *ptr = '.'; + + tofd = mkstemp(tmp); + if (tofd < 0) + goto out; + + if (st.st_size == 0) { /* /proc? do it slowly... */ + err = slow_copyfile(from, tmp, nsi); + if (!err && fchmod(tofd, mode)) + err = -1; + goto out_close_to; + } + + if (fchmod(tofd, mode)) + goto out_close_to; + + nsinfo__mountns_enter(nsi, &nsc); + fromfd = open(from, O_RDONLY); + nsinfo__mountns_exit(&nsc); + if (fromfd < 0) + goto out_close_to; + + err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size); + + close(fromfd); +out_close_to: + close(tofd); + if (!err) + err = link(tmp, to); + unlink(tmp); +out: + free(tmp); + 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); +} diff --git a/tools/perf/util/copyfile.h b/tools/perf/util/copyfile.h new file mode 100644 index 000000000000..e85d2f22f3cc --- /dev/null +++ b/tools/perf/util/copyfile.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef PERF_COPYFILE_H_ +#define PERF_COPYFILE_H_ + +#include <linux/types.h> +#include <sys/types.h> +#include <fcntl.h> + +struct nsinfo; + +int copyfile(const char *from, const char *to); +int copyfile_mode(const char *from, const char *to, mode_t mode); +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); + +#endif // PERF_COPYFILE_H_ diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index 88be9c4365e0..f94e1a23dad6 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -19,6 +19,15 @@ struct perf_counts *perf_counts__new(int ncpus, int nthreads) } counts->values = values; + + values = xyarray__new(ncpus, nthreads, sizeof(bool)); + if (!values) { + xyarray__delete(counts->values); + free(counts); + return NULL; + } + + counts->loaded = values; } return counts; @@ -27,6 +36,7 @@ struct perf_counts *perf_counts__new(int ncpus, int nthreads) void perf_counts__delete(struct perf_counts *counts) { if (counts) { + xyarray__delete(counts->loaded); xyarray__delete(counts->values); free(counts); } @@ -34,21 +44,22 @@ void perf_counts__delete(struct perf_counts *counts) static void perf_counts__reset(struct perf_counts *counts) { + xyarray__reset(counts->loaded); xyarray__reset(counts->values); } -void perf_evsel__reset_counts(struct perf_evsel *evsel) +void perf_evsel__reset_counts(struct evsel *evsel) { perf_counts__reset(evsel->counts); } -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) +int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads) { evsel->counts = perf_counts__new(ncpus, nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } -void perf_evsel__free_counts(struct perf_evsel *evsel) +void perf_evsel__free_counts(struct evsel *evsel) { perf_counts__delete(evsel->counts); evsel->counts = NULL; diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 0d1050ccc586..92196df4945f 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -2,24 +2,18 @@ #ifndef __PERF_COUNTS_H #define __PERF_COUNTS_H -#include "xyarray.h" - -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; - bool loaded; -}; +#include <linux/types.h> +#include <internal/xyarray.h> +#include <perf/evsel.h> +#include <stdbool.h> + +struct evsel; struct perf_counts { s8 scaled; struct perf_counts_values aggr; struct xyarray *values; + struct xyarray *loaded; }; @@ -29,11 +23,23 @@ perf_counts(struct perf_counts *counts, int cpu, int thread) return xyarray__entry(counts->values, cpu, thread); } +static inline bool +perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread) +{ + return *((bool *) xyarray__entry(counts->loaded, cpu, thread)); +} + +static inline void +perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded) +{ + *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded; +} + struct perf_counts *perf_counts__new(int ncpus, int nthreads); void perf_counts__delete(struct perf_counts *counts); -void perf_evsel__reset_counts(struct perf_evsel *evsel); -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__free_counts(struct perf_evsel *evsel); +void perf_evsel__reset_counts(struct evsel *evsel); +int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads); +void perf_evsel__free_counts(struct evsel *evsel); #endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 39cce66b4ebc..983b7388f22b 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <api/fs/fs.h> -#include "../perf.h" #include "cpumap.h" +#include "debug.h" +#include "event.h" #include <assert.h> #include <dirent.h> #include <stdio.h> @@ -17,190 +18,11 @@ static int max_present_cpu_num; static int max_node_num; static int *cpunode_map; -static struct cpu_map *cpu_map__default_new(void) +static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) { - struct cpu_map *cpus; - int nr_cpus; + struct perf_cpu_map *map; - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - if (nr_cpus < 0) - return NULL; - - cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); - if (cpus != NULL) { - int i; - for (i = 0; i < nr_cpus; ++i) - cpus->map[i] = i; - - cpus->nr = nr_cpus; - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) -{ - size_t payload_size = nr_cpus * sizeof(int); - struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); - - if (cpus != NULL) { - cpus->nr = nr_cpus; - memcpy(cpus->map, tmp_cpus, payload_size); - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -struct cpu_map *cpu_map__read(FILE *file) -{ - struct cpu_map *cpus = NULL; - int nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; - int max_entries = 0; - int n, cpu, prev; - char sep; - - sep = 0; - prev = -1; - for (;;) { - n = fscanf(file, "%u%c", &cpu, &sep); - if (n <= 0) - break; - if (prev >= 0) { - int new_max = nr_cpus + cpu - prev - 1; - - if (new_max >= max_entries) { - max_entries = new_max + MAX_NR_CPUS / 2; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - while (++prev < cpu) - tmp_cpus[nr_cpus++] = prev; - } - if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - tmp_cpus[nr_cpus++] = cpu; - if (n == 2 && sep == '-') - prev = cpu; - else - prev = -1; - if (n == 1 || sep == '\n') - break; - } - - if (nr_cpus > 0) - cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else - cpus = cpu_map__default_new(); -out_free_tmp: - free(tmp_cpus); - return cpus; -} - -static struct cpu_map *cpu_map__read_all_cpu_map(void) -{ - struct cpu_map *cpus = NULL; - FILE *onlnf; - - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (!onlnf) - return cpu_map__default_new(); - - cpus = cpu_map__read(onlnf); - fclose(onlnf); - return cpus; -} - -struct cpu_map *cpu_map__new(const char *cpu_list) -{ - struct cpu_map *cpus = NULL; - unsigned long start_cpu, end_cpu = 0; - char *p = NULL; - int i, nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; - int max_entries = 0; - - if (!cpu_list) - return cpu_map__read_all_cpu_map(); - - /* - * must handle the case of empty cpumap to cover - * TOPOLOGY header for NUMA nodes with no CPU - * ( e.g., because of CPU hotplug) - */ - if (!isdigit(*cpu_list) && *cpu_list != '\0') - goto out; - - while (isdigit(*cpu_list)) { - p = NULL; - start_cpu = strtoul(cpu_list, &p, 0); - if (start_cpu >= INT_MAX - || (*p != '\0' && *p != ',' && *p != '-')) - goto invalid; - - if (*p == '-') { - cpu_list = ++p; - p = NULL; - end_cpu = strtoul(cpu_list, &p, 0); - - if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) - goto invalid; - - if (end_cpu < start_cpu) - goto invalid; - } else { - end_cpu = start_cpu; - } - - for (; start_cpu <= end_cpu; start_cpu++) { - /* check for duplicates */ - for (i = 0; i < nr_cpus; i++) - if (tmp_cpus[i] == (int)start_cpu) - goto invalid; - - if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto invalid; - tmp_cpus = tmp; - } - tmp_cpus[nr_cpus++] = (int)start_cpu; - } - if (*p) - ++p; - - cpu_list = p; - } - - if (nr_cpus > 0) - cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else if (*cpu_list != '\0') - cpus = cpu_map__default_new(); - else - cpus = cpu_map__dummy_new(); -invalid: - free(tmp_cpus); -out: - return cpus; -} - -static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) -{ - struct cpu_map *map; - - map = cpu_map__empty_new(cpus->nr); + map = perf_cpu_map__empty_new(cpus->nr); if (map) { unsigned i; @@ -220,14 +42,14 @@ static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) return map; } -static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) +static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask) { - struct cpu_map *map; + struct perf_cpu_map *map; int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE; nr = bitmap_weight(mask->mask, nbits); - map = cpu_map__empty_new(nr); + map = perf_cpu_map__empty_new(nr); if (map) { int cpu, i = 0; @@ -238,15 +60,15 @@ static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) } -struct cpu_map *cpu_map__new_data(struct cpu_map_data *data) +struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data) { if (data->type == PERF_CPU_MAP__CPUS) return cpu_map__from_entries((struct cpu_map_entries *)data->data); else - return cpu_map__from_mask((struct cpu_map_mask *)data->data); + return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data); } -size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) +size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp) { #define BUFSIZE 1024 char buf[BUFSIZE]; @@ -256,22 +78,9 @@ size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) #undef BUFSIZE } -struct cpu_map *cpu_map__dummy_new(void) +struct perf_cpu_map *perf_cpu_map__empty_new(int nr) { - struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); - - if (cpus != NULL) { - cpus->nr = 1; - cpus->map[0] = -1; - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -struct cpu_map *cpu_map__empty_new(int nr) -{ - struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr); if (cpus != NULL) { int i; @@ -286,28 +95,6 @@ struct cpu_map *cpu_map__empty_new(int nr) return cpus; } -static void cpu_map__delete(struct cpu_map *map) -{ - if (map) { - WARN_ONCE(refcount_read(&map->refcnt) != 0, - "cpu_map refcnt unbalanced\n"); - free(map); - } -} - -struct cpu_map *cpu_map__get(struct cpu_map *map) -{ - if (map) - refcount_inc(&map->refcnt); - return map; -} - -void cpu_map__put(struct cpu_map *map) -{ - if (map && refcount_dec_and_test(&map->refcnt)) - cpu_map__delete(map); -} - static int cpu__get_topology_int(int cpu, const char *name, int *value) { char path[PATH_MAX]; @@ -324,7 +111,7 @@ int cpu_map__get_socket_id(int cpu) return ret ?: value; } -int cpu_map__get_socket(struct cpu_map *map, int idx, void *data __maybe_unused) +int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused) { int cpu; @@ -341,11 +128,11 @@ static int cmp_ids(const void *a, const void *b) return *(int *)a - *(int *)b; } -int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, - int (*f)(struct cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, + int (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data) { - struct cpu_map *c; + struct perf_cpu_map *c; int nr = cpus->nr; int cpu, s1, s2; @@ -380,7 +167,7 @@ int cpu_map__get_die_id(int cpu) return ret ?: value; } -int cpu_map__get_die(struct cpu_map *map, int idx, void *data) +int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) { int cpu, die_id, s; @@ -419,7 +206,12 @@ int cpu_map__get_core_id(int cpu) return ret ?: value; } -int cpu_map__get_core(struct cpu_map *map, int idx, void *data) +int cpu_map__get_node_id(int cpu) +{ + return cpu__get_node(cpu); +} + +int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) { int cpu, s_die; @@ -448,21 +240,34 @@ int cpu_map__get_core(struct cpu_map *map, int idx, void *data) return (s_die << 16) | (cpu & 0xffff); } -int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +{ + if (idx < 0 || idx >= map->nr) + return -1; + + return cpu_map__get_node_id(map->map[idx]); +} + +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp) { return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); } -int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep) +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep) { return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); } -int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); } +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap) +{ + return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); +} + /* setup simple routines to easily access node numbers given a cpu number */ static int get_max_num(char *path, int *max) { @@ -670,29 +475,17 @@ int cpu__setup_cpunode_map(void) return 0; } -bool cpu_map__has(struct cpu_map *cpus, int cpu) -{ - return cpu_map__idx(cpus, cpu) != -1; -} - -int cpu_map__idx(struct cpu_map *cpus, int cpu) +bool cpu_map__has(struct perf_cpu_map *cpus, int cpu) { - int i; - - for (i = 0; i < cpus->nr; ++i) { - if (cpus->map[i] == cpu) - return i; - } - - return -1; + return perf_cpu_map__idx(cpus, cpu) != -1; } -int cpu_map__cpu(struct cpu_map *cpus, int idx) +int cpu_map__cpu(struct perf_cpu_map *cpus, int idx) { return cpus->map[idx]; } -size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) +size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) { int i, cpu, start = -1; bool first = true; @@ -744,7 +537,7 @@ static char hex_char(unsigned char val) return '?'; } -size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) +size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) { int i, cpu; char *ptr = buf; @@ -784,12 +577,12 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) return ptr - buf; } -const struct cpu_map *cpu_map__online(void) /* thread unsafe */ +const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ { - static const struct cpu_map *online = NULL; + static const struct perf_cpu_map *online = NULL; if (!online) - online = cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ + online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ return online; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 1265f0e33920..3a442f021468 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -4,40 +4,31 @@ #include <stdio.h> #include <stdbool.h> -#include <linux/refcount.h> +#include <internal/cpumap.h> +#include <perf/cpumap.h> -#include "perf.h" -#include "util/debug.h" +struct perf_record_cpu_map_data; -struct cpu_map { - refcount_t refcnt; - int nr; - int map[]; -}; - -struct cpu_map *cpu_map__new(const char *cpu_list); -struct cpu_map *cpu_map__empty_new(int nr); -struct cpu_map *cpu_map__dummy_new(void); -struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); -struct cpu_map *cpu_map__read(FILE *file); -size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); -size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size); -size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); +struct perf_cpu_map *perf_cpu_map__empty_new(int nr); +struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); +size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); +size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); +size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); -int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); +int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_die_id(int cpu); -int cpu_map__get_die(struct cpu_map *map, int idx, void *data); +int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_core_id(int cpu); -int cpu_map__get_core(struct cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); -int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep); -int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); -const struct cpu_map *cpu_map__online(void); /* thread unsafe */ - -struct cpu_map *cpu_map__get(struct cpu_map *map); -void cpu_map__put(struct cpu_map *map); +int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__get_node_id(int cpu); +int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp); +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep); +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep); +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep); +const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ -static inline int cpu_map__socket(struct cpu_map *sock, int s) +static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) { if (!sock || s > sock->nr || s < 0) return 0; @@ -59,16 +50,6 @@ static inline int cpu_map__id_to_cpu(int id) return id & 0xffff; } -static inline int cpu_map__nr(const struct cpu_map *map) -{ - return map ? map->nr : 1; -} - -static inline bool cpu_map__empty(const struct cpu_map *map) -{ - return map ? map->map[0] == -1 : true; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); @@ -76,11 +57,11 @@ int cpu__max_cpu(void); int cpu__max_present_cpu(void); int cpu__get_node(int cpu); -int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, - int (*f)(struct cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, + int (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data); -int cpu_map__cpu(struct cpu_map *cpus, int idx); -bool cpu_map__has(struct cpu_map *cpus, int cpu); -int cpu_map__idx(struct cpu_map *cpus, int cpu); +int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); +bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 64336a280967..1b52402a8923 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -3,11 +3,14 @@ #include <sys/utsname.h> #include <inttypes.h> #include <stdlib.h> +#include <string.h> #include <api/fs/fs.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> #include "cputopo.h" #include "cpumap.h" +#include "debug.h" #include "env.h" #define CORE_SIB_FMT \ @@ -176,13 +179,13 @@ struct cpu_topology *cpu_topology__new(void) size_t sz; long ncpus; int ret = -1; - struct cpu_map *map; + struct perf_cpu_map *map; bool has_die = has_die_topology(); ncpus = cpu__max_present_cpu(); /* build online CPU map */ - map = cpu_map__new(NULL); + map = perf_cpu_map__new(NULL); if (map == NULL) { pr_debug("failed to get system cpumap\n"); return NULL; @@ -219,7 +222,7 @@ struct cpu_topology *cpu_topology__new(void) } out_free: - cpu_map__put(map); + perf_cpu_map__put(map); if (ret) { cpu_topology__delete(tp); tp = NULL; @@ -289,7 +292,7 @@ err: struct numa_topology *numa_topology__new(void) { - struct cpu_map *node_map = NULL; + struct perf_cpu_map *node_map = NULL; struct numa_topology *tp = NULL; char path[MAXPATHLEN]; char *buf = NULL; @@ -312,7 +315,7 @@ struct numa_topology *numa_topology__new(void) if (c) *c = '\0'; - node_map = cpu_map__new(buf); + node_map = perf_cpu_map__new(buf); if (!node_map) goto out; @@ -335,7 +338,7 @@ struct numa_topology *numa_topology__new(void) out: free(buf); fclose(fp); - cpu_map__put(node_map); + perf_cpu_map__put(node_map); return tp; } diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h index bae2f1d41856..7bf6b811f715 100644 --- a/tools/perf/util/cputopo.h +++ b/tools/perf/util/cputopo.h @@ -3,7 +3,6 @@ #define __PERF_CPUTOPO_H #include <linux/types.h> -#include "env.h" struct cpu_topology { u32 core_sib; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 37d7c492b155..cd92a99eb89d 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -17,7 +17,6 @@ #include "cs-etm.h" #include "cs-etm-decoder.h" #include "intlist.h" -#include "util.h" /* use raw logging */ #ifdef CS_DEBUG_RAW diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 3d1c34fc4d68..5471045ebf5c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -21,17 +21,21 @@ #include "cs-etm.h" #include "cs-etm-decoder/cs-etm-decoder.h" #include "debug.h" +#include "dso.h" #include "evlist.h" #include "intlist.h" #include "machine.h" #include "map.h" #include "perf.h" +#include "session.h" +#include "map_symbol.h" +#include "branch.h" #include "symbol.h" +#include "tool.h" #include "thread.h" -#include "thread_map.h" #include "thread-stack.h" #include <tools/libc_compat.h> -#include "util.h" +#include "util/synthetic-events.h" #define MAX_TIMESTAMP (~0ULL) @@ -106,7 +110,7 @@ static int cs_etm__decode_data_block(struct cs_etm_queue *etmq); * encode the etm queue number as the upper 16 bit and the channel as * the lower 16 bit. */ -#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan) \ +#define TO_CS_QUEUE_NR(queue_nr, trace_chan_id) \ (queue_nr << 16 | trace_chan_id) #define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16) #define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff) @@ -815,7 +819,7 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, * Note that packets decoded above are still in the traceID's packet * queue and will be processed in cs_etm__process_queues(). */ - cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan); + cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id); ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp); out: return ret; @@ -1076,6 +1080,35 @@ bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq) return !!etmq->etm->timeless_decoding; } +static void cs_etm__copy_insn(struct cs_etm_queue *etmq, + u64 trace_chan_id, + const struct cs_etm_packet *packet, + struct perf_sample *sample) +{ + /* + * It's pointless to read instructions for the CS_ETM_DISCONTINUITY + * packet, so directly bail out with 'insn_len' = 0. + */ + if (packet->sample_type == CS_ETM_DISCONTINUITY) { + sample->insn_len = 0; + return; + } + + /* + * T32 instruction size might be 32-bit or 16-bit, decide by calling + * cs_etm__t32_instr_size(). + */ + if (packet->isa == CS_ETM_ISA_T32) + sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id, + sample->ip); + /* Otherwise, A64 and A32 instruction size are always 32-bit. */ + else + sample->insn_len = 4; + + cs_etm__mem_access(etmq, trace_chan_id, sample->ip, + sample->insn_len, (void *)sample->insn); +} + static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 addr, u64 period) @@ -1097,9 +1130,10 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, sample.period = period; sample.cpu = tidq->packet->cpu; sample.flags = tidq->prev_packet->flags; - sample.insn_len = 1; sample.cpumode = event->sample.header.misc; + cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample); + if (etm->synth_opts.last_branch) { cs_etm__copy_last_branch_rb(etmq, tidq); sample.branch_stack = tidq->last_branch; @@ -1159,6 +1193,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, sample.flags = tidq->prev_packet->flags; sample.cpumode = event->sample.header.misc; + cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet, + &sample); + /* * perf report cannot handle events without a branch stack */ @@ -1222,15 +1259,15 @@ static int cs_etm__synth_event(struct perf_session *session, static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; struct perf_event_attr attr; bool found = false; u64 id; int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == etm->pmu_type) { + if (evsel->core.attr.type == etm->pmu_type) { found = true; break; } @@ -1244,7 +1281,7 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; if (etm->timeless_decoding) @@ -1252,16 +1289,16 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, else attr.sample_type |= PERF_SAMPLE_TIME; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; /* create new id val to be a fixed offset from evsel id */ - id = evsel->id[0] + 1000000000; + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; @@ -2294,8 +2331,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) { - struct perf_evsel *evsel; - struct perf_evlist *evlist = etm->session->evlist; + struct evsel *evsel; + struct evlist *evlist = etm->session->evlist; bool timeless_decoding = true; /* @@ -2303,7 +2340,7 @@ static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) * with the time bit set. */ evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.sample_type & PERF_SAMPLE_TIME)) + if ((evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) timeless_decoding = false; } @@ -2337,7 +2374,7 @@ static const char * const cs_etmv4_priv_fmts[] = { [CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", }; -static void cs_etm__print_auxtrace_info(u64 *val, int num) +static void cs_etm__print_auxtrace_info(__u64 *val, int num) { int i, j, cpu = 0; @@ -2360,7 +2397,7 @@ static void cs_etm__print_auxtrace_info(u64 *val, int num) int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { - struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; struct int_node *inode; unsigned int pmu_type; @@ -2532,7 +2569,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - if (thread__init_map_groups(etm->unknown_thread, etm->machine)) { + if (thread__init_maps(etm->unknown_thread, etm->machine)) { err = -ENOMEM; goto err_delete_thread; } diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index bc848fd095f4..650ecc2a6349 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -8,9 +8,10 @@ #define INCLUDE__UTIL_PERF_CS_ETM_H__ #include "util/event.h" -#include "util/session.h" #include <linux/bits.h> +struct perf_session; + /* Versionning header in case things need tro change in the future. That way * decoding of old snapshot is still possible. */ diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index ddbcd59f2d9b..dbc772bfb04e 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -30,6 +30,7 @@ #include "machine.h" #include "config.h" #include <linux/ctype.h> +#include <linux/err.h> #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -413,7 +414,7 @@ static int add_tracepoint_fields_values(struct ctf_writer *cw, static int add_tracepoint_values(struct ctf_writer *cw, struct bt_ctf_event_class *event_class, struct bt_ctf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; @@ -584,10 +585,10 @@ put_len_type: static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; int ret; /* @@ -753,11 +754,11 @@ static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu) } static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { int cpu = 0; - if (evsel->attr.sample_type & PERF_SAMPLE_CPU) + if (evsel->core.attr.sample_type & PERF_SAMPLE_CPU) cpu = sample->cpu; if (cpu > cw->stream_cnt) { @@ -785,7 +786,7 @@ static bool is_flush_needed(struct ctf_stream *cs) static int process_sample_event(struct perf_tool *tool, union perf_event *_event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine __maybe_unused) { struct convert *c = container_of(tool, struct convert, tool); @@ -795,7 +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; + unsigned long type = evsel->core.attr.sample_type; if (WARN_ONCE(!priv, "Failed to setup all events.\n")) return 0; @@ -820,7 +821,7 @@ static int process_sample_event(struct perf_tool *tool, if (ret) return -1; - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { ret = add_tracepoint_values(cw, event_class, event, evsel, sample); if (ret) @@ -1051,7 +1052,7 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw, } static int add_tracepoint_types(struct ctf_writer *cw, - struct perf_evsel *evsel, + struct evsel *evsel, struct bt_ctf_event_class *class) { struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; @@ -1084,10 +1085,10 @@ static int add_bpf_output_types(struct ctf_writer *cw, return bt_ctf_event_class_add_field(class, seq_type, "raw_data"); } -static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, +static int add_generic_types(struct ctf_writer *cw, struct evsel *evsel, struct bt_ctf_event_class *event_class) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; /* * missing: @@ -1150,14 +1151,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, return 0; } -static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) +static int add_event(struct ctf_writer *cw, struct evsel *evsel) { struct bt_ctf_event_class *event_class; struct evsel_priv *priv; const char *name = perf_evsel__name(evsel); int ret; - pr("Adding event '%s' (type %d)\n", name, evsel->attr.type); + pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type); event_class = bt_ctf_event_class_create(name); if (!event_class) @@ -1167,7 +1168,7 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) if (ret) goto err; - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { ret = add_tracepoint_types(cw, evsel, event_class); if (ret) goto err; @@ -1201,8 +1202,8 @@ err: static int setup_events(struct ctf_writer *cw, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; int ret; evlist__for_each_entry(evlist, evsel) { @@ -1308,8 +1309,8 @@ static int setup_non_sample_events(struct ctf_writer *cw, static void cleanup_events(struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { struct evsel_priv *priv; @@ -1319,7 +1320,7 @@ static void cleanup_events(struct perf_session *session) zfree(&evsel->priv); } - perf_evlist__delete(evlist); + evlist__delete(evlist); session->evlist = NULL; } @@ -1619,8 +1620,10 @@ int bt_convert__perf2ctf(const char *input, const char *path, err = -1; /* perf.data session */ session = perf_session__new(&data, 0, &c.tool); - if (!session) + if (IS_ERR(session)) { + err = PTR_ERR(session); goto free_writer; + } if (c.queue_size) { ordered_events__set_alloc_size(&session->ordered_events, diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 1d1b97a92c3f..c47aa34fdc0a 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/kernel.h> +#include <linux/string.h> #include <linux/zalloc.h> #include <sys/types.h> #include <sys/stat.h> @@ -9,13 +10,13 @@ #include <unistd.h> #include <string.h> #include <asm/bug.h> -#include <sys/types.h> #include <dirent.h> #include "data.h" -#include "util.h" +#include "util.h" // rm_rf_perf_data() #include "debug.h" #include "header.h" +#include <internal/lib.h> static void close_dir(struct perf_data_file *files, int nr) { @@ -75,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + /* + * Directory containing a single regular perf data file which is already + * open, means there is nothing more to do here. + */ + if (perf_data__is_single_file(data)) + return 0; + if (WARN_ON(!data->is_dir)) return -EINVAL; @@ -95,7 +103,7 @@ int perf_data__open_dir(struct perf_data *data) if (stat(path, &st)) continue; - if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4)) + if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data.", 5)) continue; ret = -ENOMEM; @@ -305,7 +313,7 @@ static int open_dir(struct perf_data *data) * So far we open only the header, so we can read the data version and * layout. */ - if (asprintf(&data->file.path, "%s/header", data->path) < 0) + if (asprintf(&data->file.path, "%s/data", data->path) < 0) return -1; if (perf_data__is_write(data) && @@ -405,7 +413,7 @@ unsigned long perf_data__size(struct perf_data *data) u64 size = data->file.size; int i; - if (!data->is_dir) + if (perf_data__is_single_file(data)) return size; for (i = 0; i < data->dir.nr; i++) { @@ -416,3 +424,36 @@ unsigned long perf_data__size(struct perf_data *data) return size; } + +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz) +{ + int ret; + + if (!data->is_dir) + return -1; + + ret = snprintf(buf, buf_sz, "%s/kcore_dir", data->path); + if (ret < 0 || (size_t)ret >= buf_sz) + return -1; + + return mkdir(buf, S_IRWXU); +} + +char *perf_data__kallsyms_name(struct perf_data *data) +{ + char *kallsyms_name; + struct stat st; + + if (!data->is_dir) + return NULL; + + if (asprintf(&kallsyms_name, "%s/kcore_dir/kallsyms", data->path) < 0) + return NULL; + + if (stat(kallsyms_name, &st)) { + free(kallsyms_name); + return NULL; + } + + return kallsyms_name; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 259868a39019..75947ef6bc17 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -9,6 +9,11 @@ enum perf_data_mode { PERF_DATA_MODE_READ, }; +enum perf_dir_version { + PERF_DIR_SINGLE_FILE = 0, + PERF_DIR_VERSION = 1, +}; + struct perf_data_file { char *path; int fd; @@ -50,6 +55,11 @@ static inline bool perf_data__is_dir(struct perf_data *data) return data->is_dir; } +static inline bool perf_data__is_single_file(struct perf_data *data) +{ + return data->dir.version == PERF_DIR_SINGLE_FILE; +} + static inline int perf_data__fd(struct perf_data *data) { return data->file.fd; @@ -77,4 +87,6 @@ int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); +char *perf_data__kallsyms_name(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index ffbb3e7d3288..db7447154622 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -7,6 +7,7 @@ #include <errno.h> #include <stdlib.h> +#include "dso.h" #include "evsel.h" #include "machine.h" #include "thread.h" @@ -32,7 +33,7 @@ void db_export__exit(struct db_export *dbe) dbe->crp = NULL; } -int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel) +int db_export__evsel(struct db_export *dbe, struct evsel *evsel) { if (evsel->db_id) return 0; @@ -180,7 +181,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (al->map) { struct dso *dso = al->map->dso; - err = db_export__dso(dbe, dso, al->machine); + err = db_export__dso(dbe, dso, al->maps->machine); if (err) return err; *dso_db_id = dso->db_id; @@ -209,7 +210,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, struct machine *machine, struct thread *thread, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { u64 kernel_start = machine__kernel_start(machine); struct call_path *current = &dbe->cpr->call_path; @@ -248,9 +249,9 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, * constructing an addr_location struct and then passing it to * db_ids_from_al() to perform the export. */ - al.sym = node->sym; - al.map = node->map; - al.machine = machine; + al.sym = node->ms.sym; + al.map = node->ms.map; + al.maps = thread->maps; al.addr = node->ip; if (al.map && !al.sym) @@ -341,7 +342,7 @@ static int db_export__threads(struct db_export *dbe, struct thread *thread, } int db_export__sample(struct db_export *dbe, union perf_event *event, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct addr_location *al) { struct thread *thread = al->thread; @@ -359,13 +360,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, if (err) return err; - err = db_export__machine(dbe, al->machine); + err = db_export__machine(dbe, al->maps->machine); if (err) return err; - main_thread = thread__main_thread(al->machine, thread); + main_thread = thread__main_thread(al->maps->machine, thread); - err = db_export__threads(dbe, thread, main_thread, al->machine, &comm); + err = db_export__threads(dbe, thread, main_thread, al->maps->machine, &comm); if (err) goto out_put; @@ -379,7 +380,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, goto out_put; if (dbe->cpr) { - struct call_path *cp = call_path_from_sample(dbe, al->machine, + struct call_path *cp = call_path_from_sample(dbe, al->maps->machine, thread, sample, evsel); if (cp) { @@ -388,8 +389,8 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, } } - if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - sample_addr_correlates_sym(&evsel->attr)) { + if ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && + sample_addr_correlates_sym(&evsel->core.attr)) { struct addr_location addr_al; thread__resolve(thread, &addr_al, sample); diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h index ba1f62a5fe10..9c3d38f5a40d 100644 --- a/tools/perf/util/db-export.h +++ b/tools/perf/util/db-export.h @@ -10,7 +10,7 @@ #include <linux/types.h> #include <linux/list.h> -struct perf_evsel; +struct evsel; struct machine; struct thread; struct comm; @@ -25,7 +25,7 @@ struct call_return; struct export_sample { union perf_event *event; struct perf_sample *sample; - struct perf_evsel *evsel; + struct evsel *evsel; struct addr_location *al; u64 db_id; u64 comm_db_id; @@ -39,7 +39,7 @@ struct export_sample { }; struct db_export { - int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel); + int (*export_evsel)(struct db_export *dbe, struct evsel *evsel); int (*export_machine)(struct db_export *dbe, struct machine *machine); int (*export_thread)(struct db_export *dbe, struct thread *thread, u64 main_thread_db_id, struct machine *machine); @@ -79,7 +79,7 @@ struct db_export { int db_export__init(struct db_export *dbe); void db_export__exit(struct db_export *dbe); -int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel); +int db_export__evsel(struct db_export *dbe, struct evsel *evsel); int db_export__machine(struct db_export *dbe, struct machine *machine); int db_export__thread(struct db_export *dbe, struct thread *thread, struct machine *machine, struct thread *main_thread); @@ -96,7 +96,7 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym, int db_export__branch_type(struct db_export *dbe, u32 branch_type, const char *name); int db_export__sample(struct db_export *dbe, union perf_event *event, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct addr_location *al); int db_export__branch_types(struct db_export *dbe); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 3780fe42453b..adb656745ecc 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* For general debugging purposes */ -#include "../perf.h" - #include <inttypes.h> #include <string.h> #include <stdarg.h> @@ -10,21 +8,23 @@ #include <stdlib.h> #include <sys/wait.h> #include <api/debug.h> +#include <linux/kernel.h> #include <linux/time64.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif -#include "cache.h" #include "color.h" #include "event.h" #include "debug.h" #include "print_binary.h" -#include "util.h" #include "target.h" +#include "ui/helpline.h" +#include "ui/ui.h" #include <linux/ctype.h> int verbose; +int debug_peo_args; bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; @@ -181,6 +181,7 @@ static struct debug_variable { { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = "stderr", .ptr = &redirect_to_stderr}, { .name = "data-convert", .ptr = &debug_data_convert }, + { .name = "perf-event-open", .ptr = &debug_peo_args }, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 77445dfc5c7d..f1734abd98dd 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -3,15 +3,12 @@ #ifndef __PERF_DEBUG_H #define __PERF_DEBUG_H +#include <stdarg.h> #include <stdbool.h> -#include <string.h> #include <linux/compiler.h> -#include "event.h" -#include "../ui/helpline.h" -#include "../ui/progress.h" -#include "../ui/util.h" extern int verbose; +extern int debug_peo_args; extern bool quiet, dump_trace; extern int debug_ordered_events; extern int debug_data_convert; @@ -34,6 +31,14 @@ extern int debug_data_convert; #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +/* Special macro to print perf_event_open arguments/return value. */ +#define pr_debug2_peo(fmt, ...) { \ + if (debug_peo_args) \ + pr_debugN(0, pr_fmt(fmt), ##__VA_ARGS__); \ + else \ + pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__); \ +} + #define pr_time_N(n, var, t, fmt, ...) \ eprintf_time(n, var, t, fmt, ##__VA_ARGS__) @@ -42,6 +47,8 @@ extern int debug_data_convert; #define STRERR_BUFSIZE 128 /* For the buffer size of str_error_r */ +union perf_event; + int dump_printf(const char *fmt, ...) __printf(1, 2); void trace_event(union perf_event *event); diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index 763328c151e9..6fb7f34c0814 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -3,7 +3,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include "debug.h" #include "symbol.h" #include "demangle-java.h" diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c index 423afbbd386b..a659fc69f73a 100644 --- a/tools/perf/util/demangle-rust.c +++ b/tools/perf/util/demangle-rust.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> -#include "util.h" #include "debug.h" #include "demangle-rust.h" diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index ebc9d46c15a7..91f21239608b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -10,16 +10,18 @@ #include <unistd.h> #include <errno.h> #include <fcntl.h> -#include <libgen.h> +#include <stdlib.h> #include <bpf/libbpf.h> #include "bpf-event.h" #include "compress.h" +#include "env.h" #include "namespaces.h" #include "path.h" #include "map.h" #include "symbol.h" #include "srcline.h" #include "dso.h" +#include "dsos.h" #include "machine.h" #include "auxtrace.h" #include "util.h" /* O_CLOEXEC for older systems */ @@ -766,7 +768,7 @@ dso_cache__free(struct dso *dso) pthread_mutex_unlock(&dso->lock); } -static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset) +static struct dso_cache *__dso_cache__find(struct dso *dso, u64 offset) { const struct rb_root *root = &dso->data.cache; struct rb_node * const *p = &root->rb_node; @@ -825,14 +827,16 @@ out: return cache; } -static ssize_t -dso_cache__memcpy(struct dso_cache *cache, u64 offset, - u8 *data, u64 size) +static ssize_t dso_cache__memcpy(struct dso_cache *cache, u64 offset, u8 *data, + u64 size, bool out) { u64 cache_offset = offset - cache->offset; u64 cache_size = min(cache->size - cache_offset, size); - memcpy(data, cache->data + cache_offset, cache_size); + if (out) + memcpy(data, cache->data + cache_offset, cache_size); + else + memcpy(cache->data + cache_offset, data, cache_size); return cache_size; } @@ -861,63 +865,73 @@ out: return ret; } -static ssize_t -dso_cache__read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static struct dso_cache *dso_cache__populate(struct dso *dso, + struct machine *machine, + u64 offset, ssize_t *ret) { u64 cache_offset = offset & DSO__DATA_CACHE_MASK; struct dso_cache *cache; struct dso_cache *old; - ssize_t ret; cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); - if (!cache) - return -ENOMEM; + if (!cache) { + *ret = -ENOMEM; + return NULL; + } if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) - ret = bpf_read(dso, cache_offset, cache->data); + *ret = bpf_read(dso, cache_offset, cache->data); else - ret = file_read(dso, machine, cache_offset, cache->data); + *ret = file_read(dso, machine, cache_offset, cache->data); - if (ret > 0) { - cache->offset = cache_offset; - cache->size = ret; + if (*ret <= 0) { + free(cache); + return NULL; + } - old = dso_cache__insert(dso, cache); - if (old) { - /* we lose the race */ - free(cache); - cache = old; - } + cache->offset = cache_offset; + cache->size = *ret; - ret = dso_cache__memcpy(cache, offset, data, size); + old = dso_cache__insert(dso, cache); + if (old) { + /* we lose the race */ + free(cache); + cache = old; } - if (ret <= 0) - free(cache); + return cache; +} - return ret; +static struct dso_cache *dso_cache__find(struct dso *dso, + struct machine *machine, + u64 offset, + ssize_t *ret) +{ + struct dso_cache *cache = __dso_cache__find(dso, offset); + + return cache ? cache : dso_cache__populate(dso, machine, offset, ret); } -static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t dso_cache_io(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, bool out) { struct dso_cache *cache; + ssize_t ret = 0; - cache = dso_cache__find(dso, offset); - if (cache) - return dso_cache__memcpy(cache, offset, data, size); - else - return dso_cache__read(dso, machine, offset, data, size); + cache = dso_cache__find(dso, machine, offset, &ret); + if (!cache) + return ret; + + return dso_cache__memcpy(cache, offset, data, size, out); } /* * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks * in the rb_tree. Any read to already cached data is served - * by cached data. + * by cached data. Writes update the cache only, not the backing file. */ -static ssize_t cached_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t cached_io(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, bool out) { ssize_t r = 0; u8 *p = data; @@ -925,7 +939,7 @@ static ssize_t cached_read(struct dso *dso, struct machine *machine, do { ssize_t ret; - ret = dso_cache_read(dso, machine, offset, p, size); + ret = dso_cache_io(dso, machine, offset, p, size, out); if (ret < 0) return ret; @@ -1009,8 +1023,9 @@ off_t dso__data_size(struct dso *dso, struct machine *machine) return dso->data.file_size; } -static ssize_t data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t data_read_write_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size, + bool out) { if (dso__data_file_size(dso, machine)) return -1; @@ -1022,7 +1037,7 @@ static ssize_t data_read_offset(struct dso *dso, struct machine *machine, if (offset + size < offset) return -1; - return cached_read(dso, machine, offset, data, size); + return cached_io(dso, machine, offset, data, size, out); } /** @@ -1042,7 +1057,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, if (dso->data.status == DSO_DATA_STATUS_ERROR) return -1; - return data_read_offset(dso, machine, offset, data, size); + return data_read_write_offset(dso, machine, offset, data, size, true); } /** @@ -1063,6 +1078,46 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, return dso__data_read_offset(dso, machine, offset, data, size); } +/** + * dso__data_write_cache_offs - Write data to dso data cache at file offset + * @dso: dso object + * @machine: machine object + * @offset: file offset + * @data: buffer to write + * @size: size of the @data buffer + * + * Write into the dso file data cache, but do not change the file itself. + */ +ssize_t dso__data_write_cache_offs(struct dso *dso, struct machine *machine, + u64 offset, const u8 *data_in, ssize_t size) +{ + u8 *data = (u8 *)data_in; /* cast away const to use same fns for r/w */ + + if (dso->data.status == DSO_DATA_STATUS_ERROR) + return -1; + + return data_read_write_offset(dso, machine, offset, data, size, false); +} + +/** + * dso__data_write_cache_addr - Write data to dso data cache at dso address + * @dso: dso object + * @machine: machine object + * @add: virtual memory address + * @data: buffer to write + * @size: size of the @data buffer + * + * External interface to write into the dso file data cache, but do not change + * the file itself. + */ +ssize_t dso__data_write_cache_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + const u8 *data, ssize_t size) +{ + u64 offset = map->map_ip(map, addr); + return dso__data_write_cache_offs(dso, machine, offset, data, size); +} + struct map *dso__new_map(const char *name) { struct map *map = NULL; @@ -1094,67 +1149,7 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name, return dso; } -/* - * Find a matching entry and/or link current entry to RB tree. - * Either one of the dso or name parameter must be non-NULL or the - * function will not work. - */ -static struct dso *__dso__findlink_by_longname(struct rb_root *root, - struct dso *dso, const char *name) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - - if (!name) - name = dso->long_name; - /* - * Find node with the matching name - */ - while (*p) { - struct dso *this = rb_entry(*p, struct dso, rb_node); - int rc = strcmp(name, this->long_name); - - parent = *p; - if (rc == 0) { - /* - * In case the new DSO is a duplicate of an existing - * one, print a one-time warning & put the new entry - * at the end of the list of duplicates. - */ - if (!dso || (dso == this)) - return this; /* Find matching dso */ - /* - * The core kernel DSOs may have duplicated long name. - * In this case, the short name should be different. - * Comparing the short names to differentiate the DSOs. - */ - rc = strcmp(dso->short_name, this->short_name); - if (rc == 0) { - pr_err("Duplicated dso name: %s\n", name); - return NULL; - } - } - if (rc < 0) - p = &parent->rb_left; - else - p = &parent->rb_right; - } - if (dso) { - /* Add new node and rebalance tree */ - rb_link_node(&dso->rb_node, parent, p); - rb_insert_color(&dso->rb_node, root); - dso->root = root; - } - return NULL; -} - -static inline struct dso *__dso__find_by_longname(struct rb_root *root, - const char *name) -{ - return __dso__findlink_by_longname(root, NULL, name); -} - -void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) +static void dso__set_long_name_id(struct dso *dso, const char *name, struct dso_id *id, bool name_allocated) { struct rb_root *root = dso->root; @@ -1167,8 +1162,8 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) if (root) { rb_erase(&dso->rb_node, root); /* - * __dso__findlink_by_longname() isn't guaranteed to add it - * back, so a clean removal is required here. + * __dsos__findnew_link_by_longname_id() isn't guaranteed to + * add it back, so a clean removal is required here. */ RB_CLEAR_NODE(&dso->rb_node); dso->root = NULL; @@ -1179,7 +1174,12 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) dso->long_name_allocated = name_allocated; if (root) - __dso__findlink_by_longname(root, dso, NULL); + __dsos__findnew_link_by_longname_id(root, dso, NULL, id); +} + +void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) +{ + dso__set_long_name_id(dso, name, NULL, name_allocated); } void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) @@ -1195,38 +1195,6 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) dso->short_name_allocated = name_allocated; } -static void dso__set_basename(struct dso *dso) -{ - char *base, *lname; - int tid; - - if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) { - if (asprintf(&base, "[JIT] tid %d", tid) < 0) - return; - } else { - /* - * basename() may modify path buffer, so we must pass - * a copy. - */ - lname = strdup(dso->long_name); - if (!lname) - return; - - /* - * basename() may return a pointer to internal - * storage which is reused in subsequent calls - * so copy the result. - */ - base = strdup(basename(lname)); - - free(lname); - - if (!base) - return; - } - dso__set_short_name(dso, base, true); -} - int dso__name_len(const struct dso *dso) { if (!dso) @@ -1252,13 +1220,15 @@ void dso__set_sorted_by_name(struct dso *dso) dso->sorted_by_name = true; } -struct dso *dso__new(const char *name) +struct dso *dso__new_id(const char *name, struct dso_id *id) { struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); if (dso != NULL) { strcpy(dso->name, name); - dso__set_long_name(dso, dso->name, false); + if (id) + dso->id = *id; + dso__set_long_name_id(dso, dso->name, id, false); dso__set_short_name(dso, dso->name, false); dso->symbols = dso->symbol_names = RB_ROOT_CACHED; dso->data.cache = RB_ROOT; @@ -1289,6 +1259,11 @@ struct dso *dso__new(const char *name) return dso; } +struct dso *dso__new(const char *name) +{ + return dso__new_id(name, NULL); +} + void dso__delete(struct dso *dso) { if (!RB_EMPTY_NODE(&dso->rb_node)) @@ -1377,143 +1352,6 @@ int dso__kernel_module_get_build_id(struct dso *dso, return 0; } -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)) - continue; - if (pos->has_build_id) { - 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; -} - -void __dsos__add(struct dsos *dsos, struct dso *dso) -{ - list_add_tail(&dso->node, &dsos->head); - __dso__findlink_by_longname(&dsos->root, dso, NULL); - /* - * It is now in the linked list, grab a reference, then garbage collect - * this when needing memory, by looking at LRU dso instances in the - * list with atomic_read(&dso->refcnt) == 1, i.e. no references - * anywhere besides the one for the list, do, under a lock for the - * list: remove it from the list, then a dso__put(), that probably will - * be the last and will then call dso__delete(), end of life. - * - * That, or at the end of the 'struct machine' lifetime, when all - * 'struct dso' instances will be removed from the list, in - * dsos__exit(), if they have no other reference from some other data - * structure. - * - * E.g.: after processing a 'perf.data' file and storing references - * to objects instantiated while processing events, we will have - * references to the 'thread', 'map', 'dso' structs all from 'struct - * hist_entry' instances, but we may not need anything not referenced, - * so we might as well call machines__exit()/machines__delete() and - * garbage collect it. - */ - dso__get(dso); -} - -void dsos__add(struct dsos *dsos, struct dso *dso) -{ - down_write(&dsos->lock); - __dsos__add(dsos, dso); - up_write(&dsos->lock); -} - -struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) -{ - struct dso *pos; - - if (cmp_short) { - list_for_each_entry(pos, &dsos->head, node) - if (strcmp(pos->short_name, name) == 0) - return pos; - return NULL; - } - return __dso__find_by_longname(&dsos->root, name); -} - -struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short) -{ - struct dso *dso; - down_read(&dsos->lock); - dso = __dsos__find(dsos, name, cmp_short); - up_read(&dsos->lock); - return dso; -} - -struct dso *__dsos__addnew(struct dsos *dsos, const char *name) -{ - struct dso *dso = dso__new(name); - - if (dso != NULL) { - __dsos__add(dsos, dso); - dso__set_basename(dso); - /* Put dso here because __dsos_add already got it */ - dso__put(dso); - } - return dso; -} - -struct dso *__dsos__findnew(struct dsos *dsos, const char *name) -{ - struct dso *dso = __dsos__find(dsos, name, false); - - return dso ? dso : __dsos__addnew(dsos, name); -} - -struct dso *dsos__findnew(struct dsos *dsos, const char *name) -{ - struct dso *dso; - down_write(&dsos->lock); - dso = dso__get(__dsos__findnew(dsos, name)); - up_write(&dsos->lock); - return dso; -} - -size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool (skip)(struct dso *dso, int parm), int parm) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - if (skip && skip(pos, parm)) - continue; - ret += dso__fprintf_buildid(pos, fp); - ret += fprintf(fp, " %s\n", pos->long_name); - } - return ret; -} - -size_t __dsos__fprintf(struct list_head *head, FILE *fp) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - ret += dso__fprintf(pos, fp); - } - - return ret; -} - size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) { char sbuild_id[SBUILD_ID_SIZE]; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 6e3f63781e51..2db64b79617a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -2,13 +2,13 @@ #ifndef __PERF_DSO #define __PERF_DSO +#include <pthread.h> #include <linux/refcount.h> #include <linux/types.h> #include <linux/rbtree.h> #include <sys/types.h> #include <stdbool.h> #include <stdio.h> -#include "rwsem.h" #include <linux/bitops.h> #include "build-id.h" @@ -16,6 +16,9 @@ struct machine; struct map; struct perf_env; +#define DSO__NAME_KALLSYMS "[kernel.kallsyms]" +#define DSO__NAME_KCORE "[kernel.kcore]" + enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, DSO_BINARY_TYPE__GUEST_KALLSYMS, @@ -119,6 +122,16 @@ enum dso_load_errno { #define DSO__DATA_CACHE_SIZE 4096 #define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) +/* + * Data about backing storage DSO, comes from PERF_RECORD_MMAP2 meta events + */ +struct dso_id { + u32 maj; + u32 min; + u64 ino; + u64 ino_generation; +}; + struct dso_cache { struct rb_node rb_node; u64 offset; @@ -126,16 +139,6 @@ struct dso_cache { char data[0]; }; -/* - * DSOs are put into both a list for fast iteration and rbtree for fast - * long name lookup. - */ -struct dsos { - struct list_head head; - struct rb_root root; /* rbtree root sorted by long name */ - struct rw_semaphore lock; -}; - struct auxtrace_cache; struct dso { @@ -203,6 +206,7 @@ struct dso { u64 db_id; }; struct nsinfo *nsinfo; + struct dso_id id; refcount_t refcnt; char name[0]; }; @@ -221,9 +225,11 @@ static inline void dso__set_loaded(struct dso *dso) dso->loaded = true; } +struct dso *dso__new_id(const char *name, struct dso_id *id); struct dso *dso__new(const char *name); void dso__delete(struct dso *dso); +int dso__cmp_id(struct dso *a, struct dso *b); void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated); void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated); @@ -292,6 +298,8 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * dso__data_size * dso__data_read_offset * dso__data_read_addr + * dso__data_write_cache_offs + * dso__data_write_cache_addr * * Please refer to the dso.c object code for each function and * arguments documentation. Following text tries to explain the @@ -339,26 +347,18 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by); +ssize_t dso__data_write_cache_offs(struct dso *dso, struct machine *machine, + u64 offset, const u8 *data, ssize_t size); +ssize_t dso__data_write_cache_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + const u8 *data, ssize_t size); struct map *dso__new_map(const char *name); struct dso *machine__findnew_kernel(struct machine *machine, const char *name, const char *short_name, int dso_type); -void __dsos__add(struct dsos *dsos, struct dso *dso); -void dsos__add(struct dsos *dsos, struct dso *dso); -struct dso *__dsos__addnew(struct dsos *dsos, const char *name); -struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short); -struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short); -struct dso *__dsos__findnew(struct dsos *dsos, const char *name); -struct dso *dsos__findnew(struct dsos *dsos, const char *name); -bool __dsos__read_build_ids(struct list_head *head, bool with_hits); - void dso__reset_find_symbol_cache(struct dso *dso); -size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool (skip)(struct dso *dso, int parm), int parm); -size_t __dsos__fprintf(struct list_head *head, FILE *fp); - size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp); size_t dso__fprintf(struct dso *dso, FILE *fp); diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c new file mode 100644 index 000000000000..591707c69c39 --- /dev/null +++ b/tools/perf/util/dsos.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "debug.h" +#include "dsos.h" +#include "dso.h" +#include "vdso.h" +#include "namespaces.h" +#include <libgen.h> +#include <stdlib.h> +#include <string.h> +#include <symbol.h> // filename__read_build_id + +static int __dso_id__cmp(struct dso_id *a, struct dso_id *b) +{ + if (a->maj > b->maj) return -1; + if (a->maj < b->maj) return 1; + + if (a->min > b->min) return -1; + if (a->min < b->min) return 1; + + if (a->ino > b->ino) return -1; + if (a->ino < b->ino) return 1; + + if (a->ino_generation > b->ino_generation) return -1; + if (a->ino_generation < b->ino_generation) return 1; + + return 0; +} + +static int dso_id__cmp(struct dso_id *a, struct dso_id *b) +{ + /* + * The second is always dso->id, so zeroes if not set, assume passing + * NULL for a means a zeroed id + */ + if (a == NULL) + return 0; + + return __dso_id__cmp(a, b); +} + +int dso__cmp_id(struct dso *a, struct dso *b) +{ + return __dso_id__cmp(&a->id, &b->id); +} + +bool __dsos__read_build_ids(struct list_head *head, bool with_hits) +{ + bool have_build_id = false; + struct dso *pos; + struct nscookie nsc; + + list_for_each_entry(pos, head, node) { + if (with_hits && !pos->hit && !dso__is_vdso(pos)) + continue; + if (pos->has_build_id) { + 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; +} + +static int __dso__cmp_long_name(const char *long_name, struct dso_id *id, struct dso *b) +{ + int rc = strcmp(long_name, b->long_name); + return rc ?: dso_id__cmp(id, &b->id); +} + +static int __dso__cmp_short_name(const char *short_name, struct dso_id *id, struct dso *b) +{ + int rc = strcmp(short_name, b->short_name); + return rc ?: dso_id__cmp(id, &b->id); +} + +static int dso__cmp_short_name(struct dso *a, struct dso *b) +{ + return __dso__cmp_short_name(a->short_name, &a->id, b); +} + +/* + * Find a matching entry and/or link current entry to RB tree. + * Either one of the dso or name parameter must be non-NULL or the + * function will not work. + */ +struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso, + const char *name, struct dso_id *id) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + if (!name) + name = dso->long_name; + /* + * Find node with the matching name + */ + while (*p) { + struct dso *this = rb_entry(*p, struct dso, rb_node); + int rc = __dso__cmp_long_name(name, id, this); + + parent = *p; + if (rc == 0) { + /* + * In case the new DSO is a duplicate of an existing + * one, print a one-time warning & put the new entry + * at the end of the list of duplicates. + */ + if (!dso || (dso == this)) + return this; /* Find matching dso */ + /* + * The core kernel DSOs may have duplicated long name. + * In this case, the short name should be different. + * Comparing the short names to differentiate the DSOs. + */ + rc = dso__cmp_short_name(dso, this); + if (rc == 0) { + pr_err("Duplicated dso name: %s\n", name); + return NULL; + } + } + if (rc < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + if (dso) { + /* Add new node and rebalance tree */ + rb_link_node(&dso->rb_node, parent, p); + rb_insert_color(&dso->rb_node, root); + dso->root = root; + } + return NULL; +} + +void __dsos__add(struct dsos *dsos, struct dso *dso) +{ + list_add_tail(&dso->node, &dsos->head); + __dsos__findnew_link_by_longname_id(&dsos->root, dso, NULL, &dso->id); + /* + * It is now in the linked list, grab a reference, then garbage collect + * this when needing memory, by looking at LRU dso instances in the + * list with atomic_read(&dso->refcnt) == 1, i.e. no references + * anywhere besides the one for the list, do, under a lock for the + * list: remove it from the list, then a dso__put(), that probably will + * be the last and will then call dso__delete(), end of life. + * + * That, or at the end of the 'struct machine' lifetime, when all + * 'struct dso' instances will be removed from the list, in + * dsos__exit(), if they have no other reference from some other data + * structure. + * + * E.g.: after processing a 'perf.data' file and storing references + * to objects instantiated while processing events, we will have + * references to the 'thread', 'map', 'dso' structs all from 'struct + * hist_entry' instances, but we may not need anything not referenced, + * so we might as well call machines__exit()/machines__delete() and + * garbage collect it. + */ + dso__get(dso); +} + +void dsos__add(struct dsos *dsos, struct dso *dso) +{ + down_write(&dsos->lock); + __dsos__add(dsos, dso); + up_write(&dsos->lock); +} + +static struct dso *__dsos__findnew_by_longname_id(struct rb_root *root, const char *name, struct dso_id *id) +{ + return __dsos__findnew_link_by_longname_id(root, NULL, name, id); +} + +static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id, bool cmp_short) +{ + struct dso *pos; + + if (cmp_short) { + list_for_each_entry(pos, &dsos->head, node) + if (__dso__cmp_short_name(name, id, pos) == 0) + return pos; + return NULL; + } + return __dsos__findnew_by_longname_id(&dsos->root, name, id); +} + +struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short) +{ + return __dsos__find_id(dsos, name, NULL, cmp_short); +} + +static void dso__set_basename(struct dso *dso) +{ + char *base, *lname; + int tid; + + if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) { + if (asprintf(&base, "[JIT] tid %d", tid) < 0) + return; + } else { + /* + * basename() may modify path buffer, so we must pass + * a copy. + */ + lname = strdup(dso->long_name); + if (!lname) + return; + + /* + * basename() may return a pointer to internal + * storage which is reused in subsequent calls + * so copy the result. + */ + base = strdup(basename(lname)); + + free(lname); + + if (!base) + return; + } + dso__set_short_name(dso, base, true); +} + +static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, struct dso_id *id) +{ + struct dso *dso = dso__new_id(name, id); + + if (dso != NULL) { + __dsos__add(dsos, dso); + dso__set_basename(dso); + /* Put dso here because __dsos_add already got it */ + dso__put(dso); + } + return dso; +} + +struct dso *__dsos__addnew(struct dsos *dsos, const char *name) +{ + return __dsos__addnew_id(dsos, name, NULL); +} + +static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id) +{ + struct dso *dso = __dsos__find_id(dsos, name, id, false); + return dso ? dso : __dsos__addnew_id(dsos, name, id); +} + +struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id) +{ + struct dso *dso; + down_write(&dsos->lock); + dso = dso__get(__dsos__findnew_id(dsos, name, id)); + up_write(&dsos->lock); + return dso; +} + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + if (skip && skip(pos, parm)) + continue; + ret += dso__fprintf_buildid(pos, fp); + ret += fprintf(fp, " %s\n", pos->long_name); + } + return ret; +} + +size_t __dsos__fprintf(struct list_head *head, FILE *fp) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + ret += dso__fprintf(pos, fp); + } + + return ret; +} diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h new file mode 100644 index 000000000000..5dbec2bc6966 --- /dev/null +++ b/tools/perf/util/dsos.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_DSOS +#define __PERF_DSOS + +#include <stdbool.h> +#include <stdio.h> +#include <linux/list.h> +#include <linux/rbtree.h> +#include "rwsem.h" + +struct dso; +struct dso_id; + +/* + * DSOs are put into both a list for fast iteration and rbtree for fast + * long name lookup. + */ +struct dsos { + struct list_head head; + struct rb_root root; /* rbtree root sorted by long name */ + struct rw_semaphore lock; +}; + +void __dsos__add(struct dsos *dsos, struct dso *dso); +void dsos__add(struct dsos *dsos, struct dso *dso); +struct dso *__dsos__addnew(struct dsos *dsos, const char *name); +struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short); + +struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id); + +struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso, + const char *name, struct dso_id *id); + +bool __dsos__read_build_ids(struct list_head *head, bool with_hits); + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t __dsos__fprintf(struct list_head *head, FILE *fp); + +#endif /* __PERF_DSOS */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 03b2de1f5a35..aa898014ad12 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -9,6 +9,7 @@ #include <stdlib.h> #include "debug.h" #include "dwarf-aux.h" +#include "strbuf.h" #include "string2.h" /** @@ -58,6 +59,51 @@ const char *cu_get_comp_dir(Dwarf_Die *cu_die) return dwarf_formstring(&attr); } +/* Unlike dwarf_getsrc_die(), cu_getsrc_die() only returns statement line */ +static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) +{ + Dwarf_Addr laddr; + Dwarf_Lines *lines; + Dwarf_Line *line; + size_t nlines, l, u, n; + bool flag; + + if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0 || + nlines == 0) + return NULL; + + /* Lines are sorted by address, use binary search */ + l = 0; u = nlines - 1; + while (l < u) { + n = u - (u - l) / 2; + line = dwarf_onesrcline(lines, n); + if (!line || dwarf_lineaddr(line, &laddr) != 0) + return NULL; + if (addr < laddr) + u = n - 1; + else + l = n; + } + /* Going backward to find the lowest line */ + do { + line = dwarf_onesrcline(lines, --l); + if (!line || dwarf_lineaddr(line, &laddr) != 0) + return NULL; + } while (laddr == addr); + l++; + /* Going foward to find the statement line */ + do { + line = dwarf_onesrcline(lines, l++); + if (!line || dwarf_lineaddr(line, &laddr) != 0 || + dwarf_linebeginstatement(line, &flag) != 0) + return NULL; + if (laddr > addr) + return NULL; + } while (!flag); + + return line; +} + /** * cu_find_lineinfo - Get a line number and file name for given address * @cu_die: a CU DIE @@ -71,17 +117,26 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, const char **fname, int *lineno) { Dwarf_Line *line; - Dwarf_Addr laddr; + Dwarf_Die die_mem; + Dwarf_Addr faddr; + + if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem) + && die_entrypc(&die_mem, &faddr) == 0 && + faddr == addr) { + *fname = dwarf_decl_file(&die_mem); + dwarf_decl_line(&die_mem, lineno); + goto out; + } - line = dwarf_getsrc_die(cu_die, (Dwarf_Addr)addr); - if (line && dwarf_lineaddr(line, &laddr) == 0 && - addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) { + line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr); + if (line && dwarf_lineno(line, lineno) == 0) { *fname = dwarf_linesrc(line, NULL, NULL); if (!*fname) /* line number is useless without filename */ *lineno = 0; } +out: return *lineno ?: -ENOENT; } @@ -307,20 +362,50 @@ bool die_is_func_def(Dwarf_Die *dw_die) } /** + * die_entrypc - Returns entry PC (the lowest address) of a DIE + * @dw_die: a DIE + * @addr: where to store entry PC + * + * Since dwarf_entrypc() does not return entry PC if the DIE has only address + * range, we have to use this to retrieve the lowest address from the address + * range attribute. + */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) +{ + Dwarf_Addr base, end; + + if (!addr) + return -EINVAL; + + if (dwarf_entrypc(dw_die, addr) == 0) + return 0; + + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; +} + +/** * die_is_func_instance - Ensure that this DIE is an instance of a subprogram * @dw_die: a DIE * * Ensure that this DIE is an instance (which has an entry address). - * This returns true if @dw_die is a function instance. If not, you need to - * call die_walk_instances() to find actual instances. + * This returns true if @dw_die is a function instance. If not, the @dw_die + * must be a prototype. You can use die_walk_instances() to find actual + * instances. **/ bool die_is_func_instance(Dwarf_Die *dw_die) { Dwarf_Addr tmp; + Dwarf_Attribute attr_mem; + int tag = dwarf_tag(dw_die); + + if (tag != DW_TAG_subprogram && + tag != DW_TAG_inlined_subroutine) + return false; - /* Actually gcc optimizes non-inline as like as inlined */ - return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; + return dwarf_entrypc(dw_die, &tmp) == 0 || + dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL; } + /** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure @@ -597,6 +682,9 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) Dwarf_Die *origin; int tmp; + if (!die_is_func_instance(inst)) + return DIE_FIND_CB_CONTINUE; + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); if (attr == NULL) return DIE_FIND_CB_CONTINUE; @@ -668,15 +756,14 @@ static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { fname = die_get_call_file(in_die); lineno = die_get_call_lineno(in_die); - if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + if (fname && lineno > 0 && die_entrypc(in_die, &addr) == 0) { lw->retval = lw->callback(fname, lineno, addr, lw->data); if (lw->retval != 0) return DIE_FIND_CB_END; } + if (!lw->recursive) + return DIE_FIND_CB_SIBLING; } - if (!lw->recursive) - /* Don't need to search recursively */ - return DIE_FIND_CB_SIBLING; if (addr) { fname = dwarf_decl_file(in_die); @@ -709,7 +796,7 @@ static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, /* Handle function declaration line */ fname = dwarf_decl_file(sp_die); if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && - dwarf_entrypc(sp_die, &addr) == 0) { + die_entrypc(sp_die, &addr) == 0) { lw.retval = callback(fname, lineno, addr, data); if (lw.retval != 0) goto done; @@ -723,6 +810,10 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) { struct __line_walk_param *lw = data; + /* + * Since inlined function can include another inlined function in + * the same file, we need to walk in it recursively. + */ lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); if (lw->retval != 0) return DWARF_CB_ABORT; @@ -747,11 +838,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) Dwarf_Lines *lines; Dwarf_Line *line; Dwarf_Addr addr; - const char *fname, *decf = NULL; + const char *fname, *decf = NULL, *inf = NULL; int lineno, ret = 0; int decl = 0, inl; Dwarf_Die die_mem, *cu_die; size_t nlines, i; + bool flag; /* Get the CU die */ if (dwarf_tag(rt_die) != DW_TAG_compile_unit) { @@ -782,6 +874,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) "Possible error in debuginfo.\n"); continue; } + /* Skip end-of-sequence */ + if (dwarf_lineendsequence(line, &flag) != 0 || flag) + continue; + /* Skip Non statement line-info */ + if (dwarf_linebeginstatement(line, &flag) != 0 || !flag) + continue; /* Filter lines based on address */ if (rt_die != cu_die) { /* @@ -791,13 +889,21 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (!dwarf_haspc(rt_die, addr)) continue; + if (die_find_inlinefunc(rt_die, addr, &die_mem)) { + /* Call-site check */ + inf = die_get_call_file(&die_mem); + if ((inf && !strcmp(inf, decf)) && + die_get_call_lineno(&die_mem) == lineno) + goto found; + dwarf_decl_line(&die_mem, &inl); if (inl != decl || decf != dwarf_decl_file(&die_mem)) continue; } } +found: /* Get source line */ fname = dwarf_linesrc(line, NULL, NULL); @@ -812,8 +918,9 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (rt_die != cu_die) /* - * Don't need walk functions recursively, because nested - * inlined functions don't have lines of the specified DIE. + * Don't need walk inlined functions recursively, because + * inner inlined functions don't have the lines of the + * specified function. */ ret = __die_walk_funclines(rt_die, false, callback, data); else { @@ -988,7 +1095,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die, bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; @@ -1051,7 +1158,7 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 0489b0cf8e2c..506006e0cf66 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -10,6 +10,8 @@ #include <elfutils/libdwfl.h> #include <elfutils/version.h> +struct strbuf; + /* Find the realpath of the target file */ const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname); @@ -27,6 +29,9 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Get DW_AT_linkage_name (should be NULL for C binary) */ const char *die_get_linkage_name(Dwarf_Die *dw_die); +/* Get the lowest PC in DIE (including range list) */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr); + /* Ensure that this DIE is a subprogram and definition (not declaration) */ bool die_is_func_def(Dwarf_Die *dw_die); diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index db55eddce8cd..1b49ecee5aff 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -5,7 +5,6 @@ * Written by: Masami Hiramatsu <mhiramat@kernel.org> */ -#include <util.h> #include <debug.h> #include <dwarf-regs.h> #include <elf.h> diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9909ec40c6d2..6242a9215df7 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "cpumap.h" +#include "debug.h" #include "env.h" +#include "util/header.h" #include <linux/ctype.h> #include <linux/zalloc.h> #include "bpf-event.h" @@ -8,6 +10,7 @@ #include <sys/utsname.h> #include <bpf/libbpf.h> #include <stdlib.h> +#include <string.h> struct perf_env perf_env; @@ -177,9 +180,10 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) - cpu_map__put(env->numa_nodes[i].map); + perf_cpu_map__put(env->numa_nodes[i].map); zfree(&env->numa_nodes); for (i = 0; i < env->caches_cnt; i++) @@ -254,6 +258,21 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; } +int perf_env__read_cpuid(struct perf_env *env) +{ + char cpuid[128]; + int err = get_cpuid(cpuid, sizeof(cpuid)); + + if (err) + return err; + + free(env->cpuid); + env->cpuid = strdup(cpuid); + if (env->cpuid == NULL) + return ENOMEM; + return 0; +} + static int perf_env__read_arch(struct perf_env *env) { struct utsname uts; @@ -336,3 +355,42 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } + + +int perf_env__numa_node(struct perf_env *env, int cpu) +{ + if (!env->nr_numa_map) { + struct numa_node *nn; + int i, nr = 0; + + for (i = 0; i < env->nr_numa_nodes; i++) { + nn = &env->numa_nodes[i]; + nr = max(nr, perf_cpu_map__max(nn->map)); + } + + nr++; + + /* + * We initialize the numa_map array to prepare + * it for missing cpus, which return node -1 + */ + env->numa_map = malloc(nr * sizeof(int)); + if (!env->numa_map) + return -1; + + for (i = 0; i < nr; i++) + env->numa_map[i] = -1; + + env->nr_numa_map = nr; + + for (i = 0; i < env->nr_numa_nodes; i++) { + int tmp, j; + + nn = &env->numa_nodes[i]; + perf_cpu_map__for_each_cpu(j, tmp, nn->map) + env->numa_map[j] = i; + } + } + + return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; +} diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index d5d9865aa812..11d05ae3606a 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -4,9 +4,10 @@ #include <linux/types.h> #include <linux/rbtree.h> -#include "cpumap.h" #include "rwsem.h" +struct perf_cpu_map; + struct cpu_topology_map { int socket_id; int die_id; @@ -27,7 +28,7 @@ struct numa_node { u32 node; u64 mem_total; u64 mem_free; - struct cpu_map *map; + struct perf_cpu_map *map; }; struct memory_node { @@ -86,6 +87,10 @@ struct perf_env { struct rb_root btfs; u32 btfs_cnt; } bpf_progs; + + /* For fast cpu to numa node lookup via perf_env__numa_node */ + int *numa_map; + int nr_numa_map; }; enum perf_compress_type { @@ -103,6 +108,7 @@ void perf_env__exit(struct perf_env *env); int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]); +int perf_env__read_cpuid(struct perf_env *env); int perf_env__read_cpu_topology_map(struct perf_env *env); void cpu_cache_level__free(struct cpu_cache_level *cache); @@ -118,4 +124,6 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); + +int perf_env__numa_node(struct perf_env *env, int cpu); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f1f4848947ce..c5447ff516a2 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,17 +1,17 @@ -// 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> +#include <perf/cpumap.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ -#include <api/fs/fs.h> #include <linux/perf_event.h> #include <linux/zalloc.h> +#include "cpumap.h" +#include "dso.h" #include "event.h" #include "debug.h" #include "hist.h" @@ -21,16 +21,18 @@ #include "strlist.h" #include "thread.h" #include "thread_map.h" +#include "time-utils.h" #include <linux/ctype.h> #include "map.h" +#include "util/namespaces.h" #include "symbol.h" #include "symbol/kallsyms.h" #include "asm/bug.h" #include "stat.h" #include "session.h" #include "bpf-event.h" - -#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500 +#include "tool.h" +#include "../perf.h" static const char *perf_event__names[] = { [0] = "TOTAL", @@ -72,18 +74,6 @@ static const char *perf_event__names[] = { [PERF_RECORD_COMPRESSED] = "COMPRESSED", }; -static const char *perf_ns__names[] = { - [NET_NS_INDEX] = "net", - [UTS_NS_INDEX] = "uts", - [IPC_NS_INDEX] = "ipc", - [PID_NS_INDEX] = "pid", - [USER_NS_INDEX] = "user", - [MNT_NS_INDEX] = "mnt", - [CGROUP_NS_INDEX] = "cgroup", -}; - -unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT; - const char *perf_event__name(unsigned int id) { if (id >= ARRAY_SIZE(perf_event__names)) @@ -93,775 +83,6 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } -static const char *perf_ns__name(unsigned int id) -{ - if (id >= ARRAY_SIZE(perf_ns__names)) - return "UNKNOWN"; - return perf_ns__names[id]; -} - -int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process) -{ - struct perf_sample synth_sample = { - .pid = -1, - .tid = -1, - .time = -1, - .stream_id = -1, - .cpu = -1, - .period = 1, - .cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK, - }; - - return process(tool, event, &synth_sample, machine); -}; - -/* - * Assumes that the first 4095 bytes of /proc/pid/stat contains - * the comm, tgid and ppid. - */ -static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, - pid_t *tgid, pid_t *ppid) -{ - char filename[PATH_MAX]; - char bf[4096]; - int fd; - size_t size = 0; - ssize_t n; - char *name, *tgids, *ppids; - - *tgid = -1; - *ppid = -1; - - snprintf(filename, sizeof(filename), "/proc/%d/status", pid); - - fd = open(filename, O_RDONLY); - if (fd < 0) { - pr_debug("couldn't open %s\n", filename); - return -1; - } - - n = read(fd, bf, sizeof(bf) - 1); - close(fd); - if (n <= 0) { - pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", - pid); - return -1; - } - bf[n] = '\0'; - - name = strstr(bf, "Name:"); - tgids = strstr(bf, "Tgid:"); - ppids = strstr(bf, "PPid:"); - - if (name) { - char *nl; - - name = skip_spaces(name + 5); /* strlen("Name:") */ - nl = strchr(name, '\n'); - if (nl) - *nl = '\0'; - - size = strlen(name); - if (size >= len) - size = len - 1; - memcpy(comm, name, size); - comm[size] = '\0'; - } else { - pr_debug("Name: string not found for pid %d\n", pid); - } - - if (tgids) { - tgids += 5; /* strlen("Tgid:") */ - *tgid = atoi(tgids); - } else { - pr_debug("Tgid: string not found for pid %d\n", pid); - } - - if (ppids) { - ppids += 5; /* strlen("PPid:") */ - *ppid = atoi(ppids); - } else { - pr_debug("PPid: string not found for pid %d\n", pid); - } - - return 0; -} - -static int perf_event__prepare_comm(union perf_event *event, pid_t pid, - struct machine *machine, - pid_t *tgid, pid_t *ppid) -{ - size_t size; - - *ppid = -1; - - memset(&event->comm, 0, sizeof(event->comm)); - - if (machine__is_host(machine)) { - if (perf_event__get_comm_ids(pid, event->comm.comm, - sizeof(event->comm.comm), - tgid, ppid) != 0) { - return -1; - } - } else { - *tgid = machine->pid; - } - - if (*tgid < 0) - return -1; - - event->comm.pid = *tgid; - event->comm.header.type = PERF_RECORD_COMM; - - size = strlen(event->comm.comm) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - memset(event->comm.comm + size, 0, machine->id_hdr_size); - event->comm.header.size = (sizeof(event->comm) - - (sizeof(event->comm.comm) - size) + - machine->id_hdr_size); - event->comm.tid = pid; - - return 0; -} - -pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, - struct machine *machine) -{ - pid_t tgid, ppid; - - if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) - return -1; - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return tgid; -} - -static void perf_event__get_ns_link_info(pid_t pid, const char *ns, - struct perf_ns_link_info *ns_link_info) -{ - struct stat64 st; - char proc_ns[128]; - - sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); - if (stat64(proc_ns, &st) == 0) { - ns_link_info->dev = st.st_dev; - ns_link_info->ino = st.st_ino; - } -} - -int perf_event__synthesize_namespaces(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine) -{ - u32 idx; - struct perf_ns_link_info *ns_link_info; - - if (!tool || !tool->namespace_events) - return 0; - - memset(&event->namespaces, 0, (sizeof(event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size)); - - event->namespaces.pid = tgid; - event->namespaces.tid = pid; - - event->namespaces.nr_namespaces = NR_NAMESPACES; - - ns_link_info = event->namespaces.link_info; - - for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) - perf_event__get_ns_link_info(pid, perf_ns__name(idx), - &ns_link_info[idx]); - - event->namespaces.header.type = PERF_RECORD_NAMESPACES; - - event->namespaces.header.size = (sizeof(event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return 0; -} - -static int perf_event__synthesize_fork(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, pid_t ppid, - perf_event__handler_t process, - struct machine *machine) -{ - memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - - /* - * for main thread set parent to ppid from status file. For other - * threads set parent pid to main thread. ie., assume main thread - * spawns all threads in a process - */ - if (tgid == pid) { - event->fork.ppid = ppid; - event->fork.ptid = ppid; - } else { - event->fork.ppid = tgid; - event->fork.ptid = tgid; - } - event->fork.pid = tgid; - event->fork.tid = pid; - event->fork.header.type = PERF_RECORD_FORK; - event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC; - - event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return 0; -} - -int perf_event__synthesize_mmap_events(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data) -{ - char filename[PATH_MAX]; - FILE *fp; - unsigned long long t; - bool truncation = false; - unsigned long long timeout = proc_map_timeout * 1000000ULL; - int rc = 0; - const char *hugetlbfs_mnt = hugetlbfs__mountpoint(); - int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0; - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", - machine->root_dir, pid, pid); - - fp = fopen(filename, "r"); - if (fp == NULL) { - /* - * We raced with a task exiting - just return: - */ - pr_debug("couldn't open %s\n", filename); - return -1; - } - - event->header.type = PERF_RECORD_MMAP2; - t = rdclock(); - - while (1) { - char bf[BUFSIZ]; - char prot[5]; - char execname[PATH_MAX]; - char anonstr[] = "//anon"; - unsigned int ino; - size_t size; - ssize_t n; - - if (fgets(bf, sizeof(bf), fp) == NULL) - break; - - if ((rdclock() - t) > timeout) { - pr_warning("Reading %s time out. " - "You may want to increase " - "the time limit by --proc-map-timeout\n", - filename); - truncation = true; - goto out; - } - - /* ensure null termination since stack will be reused. */ - strcpy(execname, ""); - - /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n", - &event->mmap2.start, &event->mmap2.len, prot, - &event->mmap2.pgoff, &event->mmap2.maj, - &event->mmap2.min, - &ino, execname); - - /* - * Anon maps don't have the execname. - */ - if (n < 7) - continue; - - event->mmap2.ino = (u64)ino; - - /* - * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c - */ - if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_USER; - else - event->header.misc = PERF_RECORD_MISC_GUEST_USER; - - /* map protection and flags bits */ - event->mmap2.prot = 0; - event->mmap2.flags = 0; - if (prot[0] == 'r') - event->mmap2.prot |= PROT_READ; - if (prot[1] == 'w') - event->mmap2.prot |= PROT_WRITE; - if (prot[2] == 'x') - event->mmap2.prot |= PROT_EXEC; - - if (prot[3] == 's') - event->mmap2.flags |= MAP_SHARED; - else - event->mmap2.flags |= MAP_PRIVATE; - - if (prot[2] != 'x') { - if (!mmap_data || prot[0] != 'r') - continue; - - event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; - } - -out: - if (truncation) - event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT; - - if (!strcmp(execname, "")) - strcpy(execname, anonstr); - - if (hugetlbfs_mnt_len && - !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) { - strcpy(execname, anonstr); - event->mmap2.flags |= MAP_HUGETLB; - } - - size = strlen(execname) + 1; - memcpy(event->mmap2.filename, execname, size); - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap2.len -= event->mmap.start; - event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); - event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.pid = tgid; - event->mmap2.tid = pid; - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { - rc = -1; - break; - } - - if (truncation) - break; - } - - fclose(fp); - return rc; -} - -int perf_event__synthesize_modules(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - int rc = 0; - struct map *pos; - struct maps *maps = machine__kernel_maps(machine); - union perf_event *event = zalloc((sizeof(event->mmap) + - machine->id_hdr_size)); - if (event == NULL) { - pr_debug("Not enough memory synthesizing mmap event " - "for kernel modules\n"); - return -1; - } - - event->header.type = PERF_RECORD_MMAP; - - /* - * kernel uses 0 for user space maps, see kernel/perf_event.c - * __perf_event_mmap - */ - if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_KERNEL; - else - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - - for (pos = maps__first(maps); pos; pos = map__next(pos)) { - size_t size; - - if (!__map__is_kmodule(pos)) - continue; - - size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = pos->start; - event->mmap.len = pos->end - pos->start; - event->mmap.pid = machine->pid; - - memcpy(event->mmap.filename, pos->dso->long_name, - pos->dso->long_name_len + 1); - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { - rc = -1; - break; - } - } - - free(event); - return rc; -} - -static int __event__synthesize_thread(union perf_event *comm_event, - union perf_event *mmap_event, - union perf_event *fork_event, - union perf_event *namespaces_event, - pid_t pid, int full, - perf_event__handler_t process, - struct perf_tool *tool, - struct machine *machine, - bool mmap_data) -{ - char filename[PATH_MAX]; - DIR *tasks; - struct dirent *dirent; - pid_t tgid, ppid; - int rc = 0; - - /* special case: only send one comm event using passed in pid */ - if (!full) { - tgid = perf_event__synthesize_comm(tool, comm_event, pid, - process, machine); - - if (tgid == -1) - return -1; - - if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, - tgid, process, machine) < 0) - return -1; - - /* - * send mmap only for thread group leader - * see thread__init_map_groups - */ - if (pid == tgid && - perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data)) - return -1; - - return 0; - } - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task", - machine->root_dir, pid); - - tasks = opendir(filename); - if (tasks == NULL) { - pr_debug("couldn't open %s\n", filename); - return 0; - } - - while ((dirent = readdir(tasks)) != NULL) { - char *end; - pid_t _pid; - - _pid = strtol(dirent->d_name, &end, 10); - if (*end) - continue; - - rc = -1; - if (perf_event__prepare_comm(comm_event, _pid, machine, - &tgid, &ppid) != 0) - break; - - if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - ppid, process, machine) < 0) - break; - - if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, - tgid, process, machine) < 0) - break; - - /* - * Send the prepared comm event - */ - if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0) - break; - - rc = 0; - if (_pid == pid) { - /* process the parent's maps too */ - rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data); - if (rc) - break; - } - } - - closedir(tasks); - return rc; -} - -int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct thread_map *threads, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data) -{ - union perf_event *comm_event, *mmap_event, *fork_event; - union perf_event *namespaces_event; - int err = -1, thread, j; - - comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); - if (comm_event == NULL) - goto out; - - mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); - if (mmap_event == NULL) - goto out_free_comm; - - fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); - if (fork_event == NULL) - goto out_free_mmap; - - namespaces_event = malloc(sizeof(namespaces_event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - if (namespaces_event == NULL) - goto out_free_fork; - - err = 0; - for (thread = 0; thread < threads->nr; ++thread) { - if (__event__synthesize_thread(comm_event, mmap_event, - fork_event, namespaces_event, - thread_map__pid(threads, thread), 0, - process, tool, machine, - mmap_data)) { - err = -1; - break; - } - - /* - * comm.pid is set to thread group id by - * perf_event__synthesize_comm - */ - if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) { - bool need_leader = true; - - /* is thread group leader in thread_map? */ - for (j = 0; j < threads->nr; ++j) { - if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) { - need_leader = false; - break; - } - } - - /* if not, generate events for it */ - if (need_leader && - __event__synthesize_thread(comm_event, mmap_event, - fork_event, namespaces_event, - comm_event->comm.pid, 0, - process, tool, machine, - mmap_data)) { - err = -1; - break; - } - } - } - free(namespaces_event); -out_free_fork: - free(fork_event); -out_free_mmap: - free(mmap_event); -out_free_comm: - free(comm_event); -out: - return err; -} - -static int __perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data, - struct dirent **dirent, - int start, - int num) -{ - union perf_event *comm_event, *mmap_event, *fork_event; - union perf_event *namespaces_event; - int err = -1; - char *end; - pid_t pid; - int i; - - comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); - if (comm_event == NULL) - goto out; - - mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); - if (mmap_event == NULL) - goto out_free_comm; - - fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); - if (fork_event == NULL) - goto out_free_mmap; - - namespaces_event = malloc(sizeof(namespaces_event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - if (namespaces_event == NULL) - goto out_free_fork; - - for (i = start; i < start + num; i++) { - if (!isdigit(dirent[i]->d_name[0])) - continue; - - 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. - */ - __event__synthesize_thread(comm_event, mmap_event, fork_event, - namespaces_event, pid, 1, process, - tool, machine, mmap_data); - } - err = 0; - - free(namespaces_event); -out_free_fork: - free(fork_event); -out_free_mmap: - free(mmap_event); -out_free_comm: - free(comm_event); -out: - return err; -} - -struct synthesize_threads_arg { - struct perf_tool *tool; - perf_event__handler_t process; - struct machine *machine; - bool mmap_data; - 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->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 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, - 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].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++) - zfree(&dirent[i]); - free(dirent); - - return err; -} - struct process_symbol_args { const char *name; u64 start; @@ -896,328 +117,8 @@ int kallsyms__get_function_start(const char *kallsyms_filename, return 0; } -int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused) -{ - return 0; -} - -static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - size_t size; - struct map *map = machine__kernel_map(machine); - struct kmap *kmap; - int err; - union perf_event *event; - - if (symbol_conf.kptr_restrict) - return -1; - if (map == NULL) - return -1; - - /* - * We should get this from /sys/kernel/sections/.text, but till that is - * available use this, and after it is use this as a fallback for older - * kernels. - */ - event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); - if (event == NULL) { - pr_debug("Not enough memory synthesizing mmap event " - "for kernel modules\n"); - return -1; - } - - if (machine__is_host(machine)) { - /* - * kernel uses PERF_RECORD_MISC_USER for user space maps, - * see kernel/perf_event.c __perf_event_mmap - */ - event->header.misc = PERF_RECORD_MISC_KERNEL; - } else { - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - } - - kmap = map__kmap(map); - size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), - "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); - event->mmap.pgoff = kmap->ref_reloc_sym->addr; - event->mmap.start = map->start; - event->mmap.len = map->end - event->mmap.start; - event->mmap.pid = machine->pid; - - err = perf_tool__process_synth_event(tool, event, machine, process); - free(event); - - return err; -} - -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - int err; - - err = __perf_event__synthesize_kernel_mmap(tool, process, machine); - if (err < 0) - return err; - - return perf_event__synthesize_extra_kmaps(tool, process, machine); -} - -int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct thread_map *threads, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event *event; - int i, err, size; - - size = sizeof(event->thread_map); - size += threads->nr * sizeof(event->thread_map.entries[0]); - - event = zalloc(size); - if (!event) - return -ENOMEM; - - event->header.type = PERF_RECORD_THREAD_MAP; - event->header.size = size; - event->thread_map.nr = threads->nr; - - for (i = 0; i < threads->nr; i++) { - struct thread_map_event_entry *entry = &event->thread_map.entries[i]; - char *comm = thread_map__comm(threads, i); - - if (!comm) - comm = (char *) ""; - - entry->pid = thread_map__pid(threads, i); - strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); - } - - err = process(tool, event, NULL, machine); - - free(event); - return err; -} - -static void synthesize_cpus(struct cpu_map_entries *cpus, - struct cpu_map *map) -{ - int i; - - cpus->nr = map->nr; - - for (i = 0; i < map->nr; i++) - cpus->cpu[i] = map->map[i]; -} - -static void synthesize_mask(struct cpu_map_mask *mask, - struct cpu_map *map, int max) -{ - int i; - - mask->nr = BITS_TO_LONGS(max); - mask->long_size = sizeof(long); - - for (i = 0; i < map->nr; i++) - set_bit(map->map[i], mask->mask); -} - -static size_t cpus_size(struct cpu_map *map) -{ - return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); -} - -static size_t mask_size(struct cpu_map *map, int *max) -{ - int i; - - *max = 0; - - for (i = 0; i < map->nr; i++) { - /* bit possition of the cpu is + 1 */ - int bit = map->map[i] + 1; - - if (bit > *max) - *max = bit; - } - - return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long); -} - -void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max) -{ - size_t size_cpus, size_mask; - bool is_dummy = cpu_map__empty(map); - - /* - * Both array and mask data have variable size based - * on the number of cpus and their actual values. - * The size of the 'struct cpu_map_data' is: - * - * array = size of 'struct cpu_map_entries' + - * number of cpus * sizeof(u64) - * - * mask = size of 'struct cpu_map_mask' + - * maximum cpu bit converted to size of longs - * - * and finaly + the size of 'struct cpu_map_data'. - */ - size_cpus = cpus_size(map); - size_mask = mask_size(map, max); - - if (is_dummy || (size_cpus < size_mask)) { - *size += size_cpus; - *type = PERF_CPU_MAP__CPUS; - } else { - *size += size_mask; - *type = PERF_CPU_MAP__MASK; - } - - *size += sizeof(struct cpu_map_data); - *size = PERF_ALIGN(*size, sizeof(u64)); - return zalloc(*size); -} - -void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, - u16 type, int max) -{ - data->type = type; - - switch (type) { - case PERF_CPU_MAP__CPUS: - synthesize_cpus((struct cpu_map_entries *) data->data, map); - break; - case PERF_CPU_MAP__MASK: - synthesize_mask((struct cpu_map_mask *) data->data, map, max); - default: - break; - }; -} - -static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map) -{ - size_t size = sizeof(struct cpu_map_event); - struct cpu_map_event *event; - int max; - u16 type; - - event = cpu_map_data__alloc(map, &size, &type, &max); - if (!event) - return NULL; - - event->header.type = PERF_RECORD_CPU_MAP; - event->header.size = size; - event->data.type = type; - - cpu_map_data__synthesize(&event->data, map, type, max); - return event; -} - -int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct cpu_map *map, - perf_event__handler_t process, - struct machine *machine) -{ - struct cpu_map_event *event; - int err; - - event = cpu_map_event__new(map); - if (!event) - return -ENOMEM; - - err = process(tool, (union perf_event *) event, NULL, machine); - - free(event); - return err; -} - -int perf_event__synthesize_stat_config(struct perf_tool *tool, - struct perf_stat_config *config, - perf_event__handler_t process, - struct machine *machine) -{ - struct stat_config_event *event; - int size, i = 0, err; - - size = sizeof(*event); - size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0])); - - event = zalloc(size); - if (!event) - return -ENOMEM; - - event->header.type = PERF_RECORD_STAT_CONFIG; - event->header.size = size; - event->nr = PERF_STAT_CONFIG_TERM__MAX; - -#define ADD(__term, __val) \ - event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \ - event->data[i].val = __val; \ - i++; - - ADD(AGGR_MODE, config->aggr_mode) - ADD(INTERVAL, config->interval) - ADD(SCALE, config->scale) - - WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, - "stat config terms unbalanced\n"); -#undef ADD - - err = process(tool, (union perf_event *) event, NULL, machine); - - free(event); - return err; -} - -int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, - struct perf_counts_values *count, - perf_event__handler_t process, - struct machine *machine) -{ - struct stat_event event; - - event.header.type = PERF_RECORD_STAT; - event.header.size = sizeof(event); - event.header.misc = 0; - - event.id = id; - event.cpu = cpu; - event.thread = thread; - event.val = count->val; - event.ena = count->ena; - event.run = count->run; - - return process(tool, (union perf_event *) &event, NULL, machine); -} - -int perf_event__synthesize_stat_round(struct perf_tool *tool, - u64 evtime, u64 type, - perf_event__handler_t process, - struct machine *machine) -{ - struct stat_round_event event; - - event.header.type = PERF_RECORD_STAT_ROUND; - event.header.size = sizeof(event); - event.header.misc = 0; - - event.time = evtime; - event.type = type; - - return process(tool, (union perf_event *) &event, NULL, machine); -} - void perf_event__read_stat_config(struct perf_stat_config *config, - struct stat_config_event *event) + struct perf_record_stat_config *event) { unsigned i; @@ -1234,7 +135,7 @@ void perf_event__read_stat_config(struct perf_stat_config *config, CASE(INTERVAL, interval) #undef CASE default: - pr_warning("unknown stat config term %" PRIu64 "\n", + pr_warning("unknown stat config term %" PRI_lu64 "\n", event->data[i].tag); } } @@ -1343,17 +244,17 @@ int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused, return machine__process_ksymbol(machine, event, sample); } -int perf_event__process_bpf_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_sample *sample __maybe_unused, - struct machine *machine) +int perf_event__process_bpf(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - return machine__process_bpf_event(machine, event, sample); + return machine__process_bpf(machine, event, sample); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) { - return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n", + return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 "]: %c %s\n", event->mmap.pid, event->mmap.tid, event->mmap.start, event->mmap.len, event->mmap.pgoff, (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x', @@ -1362,8 +263,8 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { - return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 - " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n", + return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 + " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n", event->mmap2.pid, event->mmap2.tid, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, @@ -1377,7 +278,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) { - struct thread_map *threads = thread_map__new_event(&event->thread_map); + struct perf_thread_map *threads = thread_map__new_event(&event->thread_map); size_t ret; ret = fprintf(fp, " nr: "); @@ -1387,13 +288,13 @@ size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) else ret += fprintf(fp, "failed to get threads from event\n"); - thread_map__put(threads); + perf_thread_map__put(threads); return ret; } size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) { - struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); + struct perf_cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); size_t ret; ret = fprintf(fp, ": "); @@ -1403,7 +304,7 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) else ret += fprintf(fp, "failed to get cpumap from event\n"); - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return ret; } @@ -1448,7 +349,7 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused, size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp) { - return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n", + return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s]\n", event->aux.aux_offset, event->aux.aux_size, event->aux.flags, event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "", @@ -1480,22 +381,21 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp) { - return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost); + return fprintf(fp, " lost %" PRI_lu64 "\n", event->lost.lost); } size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp) { - return fprintf(fp, " addr %" PRIx64 " len %u type %u flags 0x%x name %s\n", - event->ksymbol_event.addr, event->ksymbol_event.len, - event->ksymbol_event.ksym_type, - event->ksymbol_event.flags, event->ksymbol_event.name); + return fprintf(fp, " addr %" PRI_lx64 " len %u type %u flags 0x%x name %s\n", + event->ksymbol.addr, event->ksymbol.len, + event->ksymbol.ksym_type, + event->ksymbol.flags, event->ksymbol.name); } -size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp) +size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp) { return fprintf(fp, " type %u, flags %u, id %u\n", - event->bpf_event.type, event->bpf_event.flags, - event->bpf_event.id); + event->bpf.type, event->bpf.flags, event->bpf.id); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -1537,7 +437,7 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) ret += perf_event__fprintf_ksymbol(event, fp); break; case PERF_RECORD_BPF_EVENT: - ret += perf_event__fprintf_bpf_event(event, fp); + ret += perf_event__fprintf_bpf(event, fp); break; default: ret += fprintf(fp, "\n"); @@ -1557,11 +457,11 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { - struct map_groups *mg = thread->mg; - struct machine *machine = mg->machine; + struct maps *maps = thread->maps; + struct machine *machine = maps->machine; bool load_map = false; - al->machine = machine; + al->maps = maps; al->thread = thread; al->addr = addr; al->cpumode = cpumode; @@ -1574,13 +474,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - mg = &machine->kmaps; + al->maps = maps = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - mg = &machine->kmaps; + al->maps = maps = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { al->level = 'u'; @@ -1600,7 +500,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } - al->map = map_groups__find(mg, al->addr); + al->map = maps__find(maps, al->addr); if (al->map != NULL) { /* * Kernel maps might be changed when loading symbols so loading @@ -1623,7 +523,7 @@ struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { struct map *map = thread__find_map(thread, cpumode, addr, al); - struct machine *machine = thread->mg->machine; + struct machine *machine = thread->maps->machine; u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr); if (map || addr_cpumode == cpumode) diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1f1da6082806..85223159737c 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -1,114 +1,39 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_RECORD_H #define __PERF_RECORD_H - -#include <limits.h> +/* + * The linux/stddef.h isn't need here, but is needed for __always_inline used + * in files included from uapi/linux/perf_event.h such as + * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h, + * detected in at least musl libc, used in Alpine Linux. -acme + */ #include <stdio.h> -#include <linux/kernel.h> -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include <linux/stddef.h> +#include <perf/event.h> +#include <linux/types.h> -#include "../perf.h" -#include "build-id.h" #include "perf_regs.h" -struct mmap_event { - struct perf_event_header header; - u32 pid, tid; - u64 start; - u64 len; - u64 pgoff; - char filename[PATH_MAX]; -}; - -struct mmap2_event { - struct perf_event_header header; - u32 pid, tid; - u64 start; - u64 len; - u64 pgoff; - u32 maj; - u32 min; - u64 ino; - u64 ino_generation; - u32 prot; - u32 flags; - char filename[PATH_MAX]; -}; - -struct comm_event { - struct perf_event_header header; - u32 pid, tid; - char comm[16]; -}; - -struct namespaces_event { - struct perf_event_header header; - u32 pid, tid; - u64 nr_namespaces; - struct perf_ns_link_info link_info[]; -}; - -struct fork_event { - struct perf_event_header header; - u32 pid, ppid; - u32 tid, ptid; - u64 time; -}; - -struct lost_event { - struct perf_event_header header; - u64 id; - u64 lost; -}; - -struct lost_samples_event { - struct perf_event_header header; - u64 lost; -}; +struct dso; +struct machine; +struct perf_event_attr; +#ifdef __LP64__ /* - * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID + * /usr/include/inttypes.h uses just 'lu' for PRIu64, but we end up defining + * __u64 as long long unsigned int, and then -Werror=format= kicks in and + * complains of the mismatched types, so use these two special extra PRI + * macros to overcome that. */ -struct read_event { - struct perf_event_header header; - u32 pid, tid; - u64 value; - u64 time_enabled; - u64 time_running; - u64 id; -}; - -struct throttle_event { - struct perf_event_header header; - u64 time; - u64 id; - u64 stream_id; -}; - -#ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define PRI_lu64 "l" PRIu64 +#define PRI_lx64 "l" PRIx64 +#define PRI_ld64 "l" PRId64 +#else +#define PRI_lu64 PRIu64 +#define PRI_lx64 PRIx64 +#define PRI_ld64 PRId64 #endif -struct ksymbol_event { - struct perf_event_header header; - u64 addr; - u32 len; - u16 ksym_type; - u16 flags; - char name[KSYM_NAME_LEN]; -}; - -struct bpf_event { - struct perf_event_header header; - u16 type; - u16 flags; - u32 id; - - /* for bpf_prog types */ - u8 tag[BPF_TAG_SIZE]; // prog tag -}; - #define PERF_SAMPLE_MASK \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ @@ -119,11 +44,6 @@ struct bpf_event { /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) -struct sample_event { - struct perf_event_header header; - u64 array[]; -}; - struct regs_dump { u64 abi; u64 mask; @@ -194,6 +114,11 @@ enum { #define MAX_INSN 16 +struct aux_sample { + u64 size; + void *data; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -222,6 +147,7 @@ struct perf_sample { struct regs_dump intr_regs; struct stack_dump user_stack; struct sample_read read; + struct aux_sample aux_sample; }; #define PERF_MEM_DATA_SRC_NONE \ @@ -231,41 +157,6 @@ struct perf_sample { PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) -struct build_id_event { - struct perf_event_header header; - pid_t pid; - u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; - char filename[]; -}; - -enum perf_user_event_type { /* above any possible kernel type */ - PERF_RECORD_USER_TYPE_START = 64, - PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ - PERF_RECORD_HEADER_TRACING_DATA = 66, - PERF_RECORD_HEADER_BUILD_ID = 67, - PERF_RECORD_FINISHED_ROUND = 68, - PERF_RECORD_ID_INDEX = 69, - PERF_RECORD_AUXTRACE_INFO = 70, - PERF_RECORD_AUXTRACE = 71, - PERF_RECORD_AUXTRACE_ERROR = 72, - PERF_RECORD_THREAD_MAP = 73, - PERF_RECORD_CPU_MAP = 74, - PERF_RECORD_STAT_CONFIG = 75, - PERF_RECORD_STAT = 76, - PERF_RECORD_STAT_ROUND = 77, - PERF_RECORD_EVENT_UPDATE = 78, - PERF_RECORD_TIME_CONV = 79, - PERF_RECORD_HEADER_FEATURE = 80, - PERF_RECORD_COMPRESSED = 81, - PERF_RECORD_HEADER_MAX -}; - -enum auxtrace_error_type { - PERF_AUXTRACE_ERROR_ITRACE = 1, - PERF_AUXTRACE_ERROR_MAX -}; - /* Attribute type for custom synthesized events */ #define PERF_TYPE_SYNTH (INT_MAX + 1U) @@ -387,340 +278,20 @@ static inline void *perf_synth__raw_data(void *p) #define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4) -/* - * The kernel collects the number of events it couldn't send in a stretch and - * when possible sends this number in a PERF_RECORD_LOST event. The number of - * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while - * total_lost tells exactly how many events the kernel in fact lost, i.e. it is - * the sum of all struct lost_event.lost fields reported. - * - * The kernel discards mixed up samples and sends the number in a - * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored - * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells - * exactly how many samples the kernel in fact dropped, i.e. it is the sum of - * all struct lost_samples_event.lost fields reported. - * - * The total_period is needed because by default auto-freq is used, so - * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get - * the total number of low level events, it is necessary to to sum all struct - * sample_event.period and stash the result in total_period. - */ -struct events_stats { - u64 total_period; - u64 total_non_filtered_period; - u64 total_lost; - u64 total_lost_samples; - u64 total_aux_lost; - u64 total_aux_partial; - u64 total_invalid_chains; - u32 nr_events[PERF_RECORD_HEADER_MAX]; - u32 nr_non_filtered_samples; - u32 nr_lost_warned; - u32 nr_unknown_events; - u32 nr_invalid_chains; - u32 nr_unknown_id; - u32 nr_unprocessable_samples; - u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX]; - u32 nr_proc_map_timeout; -}; - -enum { - PERF_CPU_MAP__CPUS = 0, - PERF_CPU_MAP__MASK = 1, -}; - -struct cpu_map_entries { - u16 nr; - u16 cpu[]; -}; - -struct cpu_map_mask { - u16 nr; - u16 long_size; - unsigned long mask[]; -}; - -struct cpu_map_data { - u16 type; - char data[]; -}; - -struct cpu_map_event { - struct perf_event_header header; - struct cpu_map_data data; -}; - -struct attr_event { - struct perf_event_header header; - struct perf_event_attr attr; - u64 id[]; -}; - -enum { - PERF_EVENT_UPDATE__UNIT = 0, - PERF_EVENT_UPDATE__SCALE = 1, - PERF_EVENT_UPDATE__NAME = 2, - PERF_EVENT_UPDATE__CPUS = 3, -}; - -struct event_update_event_cpus { - struct cpu_map_data cpus; -}; - -struct event_update_event_scale { - double scale; -}; - -struct event_update_event { - struct perf_event_header header; - u64 type; - u64 id; - - char data[]; -}; - -#define MAX_EVENT_NAME 64 - -struct perf_trace_event_type { - u64 event_id; - char name[MAX_EVENT_NAME]; -}; - -struct event_type_event { - struct perf_event_header header; - struct perf_trace_event_type event_type; -}; - -struct tracing_data_event { - struct perf_event_header header; - u32 size; -}; - -struct id_index_entry { - u64 id; - u64 idx; - u64 cpu; - u64 tid; -}; - -struct id_index_event { - struct perf_event_header header; - u64 nr; - struct id_index_entry entries[0]; -}; - -struct auxtrace_info_event { - struct perf_event_header header; - u32 type; - u32 reserved__; /* For alignment */ - u64 priv[]; -}; - -struct auxtrace_event { - struct perf_event_header header; - u64 size; - u64 offset; - u64 reference; - u32 idx; - u32 tid; - u32 cpu; - u32 reserved__; /* For alignment */ -}; - -#define MAX_AUXTRACE_ERROR_MSG 64 - -struct auxtrace_error_event { - struct perf_event_header header; - u32 type; - u32 code; - u32 cpu; - u32 pid; - u32 tid; - u32 fmt; - u64 ip; - u64 time; - char msg[MAX_AUXTRACE_ERROR_MSG]; -}; - -struct aux_event { - struct perf_event_header header; - u64 aux_offset; - u64 aux_size; - u64 flags; -}; - -struct itrace_start_event { - struct perf_event_header header; - u32 pid, tid; -}; - -struct context_switch_event { - struct perf_event_header header; - u32 next_prev_pid; - u32 next_prev_tid; -}; - -struct thread_map_event_entry { - u64 pid; - char comm[16]; -}; - -struct thread_map_event { - struct perf_event_header header; - u64 nr; - struct thread_map_event_entry entries[]; -}; - -enum { - PERF_STAT_CONFIG_TERM__AGGR_MODE = 0, - PERF_STAT_CONFIG_TERM__INTERVAL = 1, - PERF_STAT_CONFIG_TERM__SCALE = 2, - PERF_STAT_CONFIG_TERM__MAX = 3, -}; - -struct stat_config_event_entry { - u64 tag; - u64 val; -}; - -struct stat_config_event { - struct perf_event_header header; - u64 nr; - struct stat_config_event_entry data[]; -}; - -struct stat_event { - struct perf_event_header header; - - u64 id; - u32 cpu; - u32 thread; - - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; -}; - enum { PERF_STAT_ROUND_TYPE__INTERVAL = 0, PERF_STAT_ROUND_TYPE__FINAL = 1, }; -struct stat_round_event { - struct perf_event_header header; - u64 type; - u64 time; -}; - -struct time_conv_event { - struct perf_event_header header; - u64 time_shift; - u64 time_mult; - u64 time_zero; -}; - -struct feature_event { - struct perf_event_header header; - u64 feat_id; - char data[]; -}; - -struct compressed_event { - struct perf_event_header header; - char data[]; -}; - -union perf_event { - struct perf_event_header header; - struct mmap_event mmap; - struct mmap2_event mmap2; - struct comm_event comm; - struct namespaces_event namespaces; - struct fork_event fork; - struct lost_event lost; - struct lost_samples_event lost_samples; - struct read_event read; - struct throttle_event throttle; - struct sample_event sample; - struct attr_event attr; - struct event_update_event event_update; - struct event_type_event event_type; - struct tracing_data_event tracing_data; - struct build_id_event build_id; - struct id_index_event id_index; - struct auxtrace_info_event auxtrace_info; - struct auxtrace_event auxtrace; - struct auxtrace_error_event auxtrace_error; - struct aux_event aux; - struct itrace_start_event itrace_start; - struct context_switch_event context_switch; - struct thread_map_event thread_map; - struct cpu_map_event cpu_map; - struct stat_config_event stat_config; - struct stat_event stat; - struct stat_round_event stat_round; - struct time_conv_event time_conv; - struct feature_event feat; - struct ksymbol_event ksymbol_event; - struct bpf_event bpf_event; - struct compressed_event pack; -}; - void perf_event__print_totals(void); -struct perf_tool; -struct thread_map; -struct cpu_map; +struct perf_cpu_map; +struct perf_record_stat_config; struct perf_stat_config; -struct perf_counts_values; - -typedef int (*perf_event__handler_t)(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine); +struct perf_tool; -int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct thread_map *threads, - perf_event__handler_t process, - struct machine *machine, bool mmap_data); -int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct thread_map *threads, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct cpu_map *cpus, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, bool mmap_data, - unsigned int nr_threads_synthesize); -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_stat_config(struct perf_tool *tool, - struct perf_stat_config *config, - perf_event__handler_t process, - struct machine *machine); void perf_event__read_stat_config(struct perf_stat_config *config, - struct stat_config_event *event); -int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, - struct perf_counts_values *count, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_stat_round(struct perf_tool *tool, - u64 time, u64 type, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_modules(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); + struct perf_record_stat_config *event); int perf_event__process_comm(struct perf_tool *tool, union perf_event *event, @@ -770,14 +341,10 @@ int perf_event__process_ksymbol(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -int perf_event__process_bpf_event(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine); -int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process); +int perf_event__process_bpf(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -799,34 +366,6 @@ void thread__resolve(struct thread *thread, struct addr_location *al, const char *perf_event__name(unsigned int id); -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 read_format); -int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 read_format, - const struct perf_sample *sample); - -pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, - struct machine *machine); - -int perf_event__synthesize_namespaces(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine); - -int perf_event__synthesize_mmap_events(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data); - -int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); - size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); @@ -838,19 +377,20 @@ size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp); -size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr); -void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); -void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, +void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max); +void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, u16 type, int max); void event_attr_init(struct perf_event_attr *attr); int perf_event_paranoid(void); +bool perf_event_paranoid_check(int max_level); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h new file mode 100644 index 000000000000..859cb34fcff2 --- /dev/null +++ b/tools/perf/util/events_stats.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_EVENTS_STATS_ +#define __PERF_EVENTS_STATS_ + +#include <stdio.h> +#include <perf/event.h> +#include <linux/types.h> +#include "auxtrace.h" + +/* + * The kernel collects the number of events it couldn't send in a stretch and + * when possible sends this number in a PERF_RECORD_LOST event. The number of + * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while + * total_lost tells exactly how many events the kernel in fact lost, i.e. it is + * the sum of all struct perf_record_lost.lost fields reported. + * + * The kernel discards mixed up samples and sends the number in a + * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored + * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells + * exactly how many samples the kernel in fact dropped, i.e. it is the sum of + * all struct perf_record_lost_samples.lost fields reported. + * + * The total_period is needed because by default auto-freq is used, so + * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get + * the total number of low level events, it is necessary to to sum all struct + * perf_record_sample.period and stash the result in total_period. + */ +struct events_stats { + u64 total_period; + u64 total_non_filtered_period; + u64 total_lost; + u64 total_lost_samples; + u64 total_aux_lost; + u64 total_aux_partial; + u64 total_invalid_chains; + u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_non_filtered_samples; + u32 nr_lost_warned; + u32 nr_unknown_events; + u32 nr_invalid_chains; + u32 nr_unknown_id; + u32 nr_unprocessable_samples; + u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX]; + u32 nr_proc_map_timeout; +}; + +void events_stats__inc(struct events_stats *stats, u32 type); + +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); + +#endif /* __PERF_EVENTS_STATS_ */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b0364d923f76..1548237b6558 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -10,16 +10,23 @@ #include <inttypes.h> #include <poll.h> #include "cpumap.h" +#include "util/mmap.h" #include "thread_map.h" #include "target.h" #include "evlist.h" #include "evsel.h" #include "debug.h" #include "units.h" +#include <internal/lib.h> // page_size +#include "affinity.h" +#include "../perf.h" #include "asm/bug.h" #include "bpf-event.h" +#include "util/string2.h" #include <signal.h> #include <unistd.h> +#include <sched.h> +#include <stdlib.h> #include "parse-events.h" #include <subcmd/parse-options.h> @@ -32,57 +39,59 @@ #include <linux/hash.h> #include <linux/log2.h> #include <linux/err.h> +#include <linux/string.h> #include <linux/zalloc.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/mmap.h> + +#include <internal/xyarray.h> #ifdef LACKS_SIGQUEUE_PROTOTYPE int sigqueue(pid_t pid, int sig, const union sigval value); #endif -#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) +#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y) -void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads) +void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) { - int i; - - for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) - INIT_HLIST_HEAD(&evlist->heads[i]); - INIT_LIST_HEAD(&evlist->entries); - perf_evlist__set_maps(evlist, cpus, threads); - fdarray__init(&evlist->pollfd, 64); + perf_evlist__init(&evlist->core); + perf_evlist__set_maps(&evlist->core, cpus, threads); evlist->workload.pid = -1; evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; } -struct perf_evlist *perf_evlist__new(void) +struct evlist *evlist__new(void) { - struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + struct evlist *evlist = zalloc(sizeof(*evlist)); if (evlist != NULL) - perf_evlist__init(evlist, NULL, NULL); + evlist__init(evlist, NULL, NULL); return evlist; } -struct perf_evlist *perf_evlist__new_default(void) +struct evlist *perf_evlist__new_default(void) { - struct perf_evlist *evlist = perf_evlist__new(); + struct evlist *evlist = evlist__new(); if (evlist && perf_evlist__add_default(evlist)) { - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; } return evlist; } -struct perf_evlist *perf_evlist__new_dummy(void) +struct evlist *perf_evlist__new_dummy(void) { - struct perf_evlist *evlist = perf_evlist__new(); + struct evlist *evlist = evlist__new(); if (evlist && perf_evlist__add_dummy(evlist)) { - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; } @@ -96,17 +105,17 @@ struct perf_evlist *perf_evlist__new_dummy(void) * Events with compatible sample types all have the same id_pos * and is_pos. For convenience, put a copy on evlist. */ -void perf_evlist__set_id_pos(struct perf_evlist *evlist) +void perf_evlist__set_id_pos(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); evlist->id_pos = first->id_pos; evlist->is_pos = first->is_pos; } -static void perf_evlist__update_id_pos(struct perf_evlist *evlist) +static void perf_evlist__update_id_pos(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) perf_evsel__calc_id_pos(evsel); @@ -114,161 +123,152 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist) perf_evlist__set_id_pos(evlist); } -static void perf_evlist__purge(struct perf_evlist *evlist) +static void evlist__purge(struct evlist *evlist) { - struct perf_evsel *pos, *n; + struct evsel *pos, *n; evlist__for_each_entry_safe(evlist, n, pos) { - list_del_init(&pos->node); + list_del_init(&pos->core.node); pos->evlist = NULL; - perf_evsel__delete(pos); + evsel__delete(pos); } - evlist->nr_entries = 0; + evlist->core.nr_entries = 0; } -void perf_evlist__exit(struct perf_evlist *evlist) +void evlist__exit(struct evlist *evlist) { zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); - fdarray__exit(&evlist->pollfd); + perf_evlist__exit(&evlist->core); } -void perf_evlist__delete(struct perf_evlist *evlist) +void evlist__delete(struct evlist *evlist) { if (evlist == NULL) return; - perf_evlist__munmap(evlist); - perf_evlist__close(evlist); - cpu_map__put(evlist->cpus); - thread_map__put(evlist->threads); - evlist->cpus = NULL; - evlist->threads = NULL; - perf_evlist__purge(evlist); - perf_evlist__exit(evlist); + evlist__munmap(evlist); + evlist__close(evlist); + evlist__purge(evlist); + evlist__exit(evlist); free(evlist); } -static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. - */ - if (!evsel->own_cpus || evlist->has_user_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evlist->cpus); - } else if (evsel->cpus != evsel->own_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evsel->own_cpus); - } - - thread_map__put(evsel->threads); - evsel->threads = thread_map__get(evlist->threads); -} - -static void perf_evlist__propagate_maps(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __perf_evlist__propagate_maps(evlist, evsel); -} - -void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) +void evlist__add(struct evlist *evlist, struct evsel *entry) { entry->evlist = evlist; - list_add_tail(&entry->node, &evlist->entries); - entry->idx = evlist->nr_entries; + entry->idx = evlist->core.nr_entries; entry->tracking = !entry->idx; - if (!evlist->nr_entries++) - perf_evlist__set_id_pos(evlist); + perf_evlist__add(&evlist->core, &entry->core); - __perf_evlist__propagate_maps(evlist, entry); + if (evlist->core.nr_entries == 1) + perf_evlist__set_id_pos(evlist); } -void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel) +void evlist__remove(struct evlist *evlist, struct evsel *evsel) { evsel->evlist = NULL; - list_del_init(&evsel->node); - evlist->nr_entries -= 1; + perf_evlist__remove(&evlist->core, &evsel->core); } -void perf_evlist__splice_list_tail(struct perf_evlist *evlist, +void perf_evlist__splice_list_tail(struct evlist *evlist, struct list_head *list) { - struct perf_evsel *evsel, *temp; + struct evsel *evsel, *temp; __evlist__for_each_entry_safe(list, temp, evsel) { - list_del_init(&evsel->node); - perf_evlist__add(evlist, evsel); + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); } } +int __evlist__set_tracepoints_handlers(struct evlist *evlist, + const struct evsel_str_handler *assocs, size_t nr_assocs) +{ + struct evsel *evsel; + size_t i; + int err; + + for (i = 0; i < nr_assocs; i++) { + // Adding a handler for an event not in this evlist, just ignore it. + evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name); + if (evsel == NULL) + continue; + + err = -EEXIST; + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; + } + + err = 0; +out: + return err; +} + void __perf_evlist__set_leader(struct list_head *list) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - leader = list_entry(list->next, struct perf_evsel, node); - evsel = list_entry(list->prev, struct perf_evsel, node); + leader = list_entry(list->next, struct evsel, core.node); + evsel = list_entry(list->prev, struct evsel, core.node); - leader->nr_members = evsel->idx - leader->idx + 1; + leader->core.nr_members = evsel->idx - leader->idx + 1; __evlist__for_each_entry(list, evsel) { evsel->leader = leader; } } -void perf_evlist__set_leader(struct perf_evlist *evlist) +void perf_evlist__set_leader(struct evlist *evlist) { - if (evlist->nr_entries) { - evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->entries); + if (evlist->core.nr_entries) { + evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0; + __perf_evlist__set_leader(&evlist->core.entries); } } -int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) +int __perf_evlist__add_default(struct evlist *evlist, bool precise) { - struct perf_evsel *evsel = perf_evsel__new_cycles(precise); + struct evsel *evsel = perf_evsel__new_cycles(precise); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -int perf_evlist__add_dummy(struct perf_evlist *evlist) +int perf_evlist__add_dummy(struct evlist *evlist) { struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, .size = sizeof(attr), /* to capture ABI version */ }; - struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries); + struct evsel *evsel = perf_evsel__new_idx(&attr, evlist->core.nr_entries); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -static int perf_evlist__add_attrs(struct perf_evlist *evlist, +static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { - struct perf_evsel *evsel, *n; + struct evsel *evsel, *n; LIST_HEAD(head); size_t i; for (i = 0; i < nr_attrs; i++) { - evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i); + evsel = perf_evsel__new_idx(attrs + i, evlist->core.nr_entries + i); if (evsel == NULL) goto out_delete_partial_list; - list_add_tail(&evsel->node, &head); + list_add_tail(&evsel->core.node, &head); } perf_evlist__splice_list_tail(evlist, &head); @@ -277,11 +277,11 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist, out_delete_partial_list: __evlist__for_each_entry_safe(&head, n, evsel) - perf_evsel__delete(evsel); + evsel__delete(evsel); return -1; } -int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, +int __perf_evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { size_t i; @@ -289,31 +289,31 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, for (i = 0; i < nr_attrs; i++) event_attr_init(attrs + i); - return perf_evlist__add_attrs(evlist, attrs, nr_attrs); + return evlist__add_attrs(evlist, attrs, nr_attrs); } -struct perf_evsel * -perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +struct evsel * +perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == PERF_TYPE_TRACEPOINT && - (int)evsel->attr.config == id) + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT && + (int)evsel->core.attr.config == id) return evsel; } return NULL; } -struct perf_evsel * -perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, +struct evsel * +perf_evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) && + if ((evsel->core.attr.type == PERF_TYPE_TRACEPOINT) && (strcmp(evsel->name, name) == 0)) return evsel; } @@ -321,66 +321,132 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, return NULL; } -int perf_evlist__add_newtp(struct perf_evlist *evlist, +int perf_evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler) { - struct perf_evsel *evsel = perf_evsel__newtp(sys, name); + struct evsel *evsel = perf_evsel__newtp(sys, name); if (IS_ERR(evsel)) return -1; evsel->handler = handler; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -static int perf_evlist__nr_threads(struct perf_evlist *evlist, - struct perf_evsel *evsel) +static int perf_evlist__nr_threads(struct evlist *evlist, + struct evsel *evsel) { - if (evsel->system_wide) + if (evsel->core.system_wide) return 1; else - return thread_map__nr(evlist->threads); + return perf_thread_map__nr(evlist->core.threads); } -void perf_evlist__disable(struct perf_evlist *evlist) +void evlist__cpu_iter_start(struct evlist *evlist) { - struct perf_evsel *pos; + struct evsel *pos; + /* + * Reset the per evsel cpu_iter. This is needed because + * each evsel's cpumap may have a different index space, + * and some operations need the index to modify + * the FD xyarray (e.g. open, close) + */ + evlist__for_each_entry(evlist, pos) + pos->cpu_iter = 0; +} + +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu) +{ + if (ev->cpu_iter >= ev->core.cpus->nr) + return true; + if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu) + return true; + return false; +} + +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) +{ + if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) { + ev->cpu_iter++; + return false; + } + return true; +} + +void evlist__disable(struct evlist *evlist) +{ + struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__disable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { - if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd) + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - perf_evsel__disable(pos); + pos->disabled = true; } evlist->enabled = false; } -void perf_evlist__enable(struct perf_evlist *evlist) +void evlist__enable(struct evlist *evlist) { - struct perf_evsel *pos; + struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__enable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { - if (!perf_evsel__is_group_leader(pos) || !pos->fd) + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - perf_evsel__enable(pos); + pos->disabled = false; } evlist->enabled = true; } -void perf_evlist__toggle_enable(struct perf_evlist *evlist) +void perf_evlist__toggle_enable(struct evlist *evlist) { - (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist); + (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, - struct perf_evsel *evsel, int cpu) +static int perf_evlist__enable_event_cpu(struct evlist *evlist, + struct evsel *evsel, int cpu) { int thread; int nr_threads = perf_evlist__nr_threads(evlist, evsel); - if (!evsel->fd) + if (!evsel->core.fd) return -EINVAL; for (thread = 0; thread < nr_threads; thread++) { @@ -391,14 +457,14 @@ static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, return 0; } -static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, - struct perf_evsel *evsel, +static int perf_evlist__enable_event_thread(struct evlist *evlist, + struct evsel *evsel, int thread) { int cpu; - int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); - if (!evsel->fd) + if (!evsel->core.fd) return -EINVAL; for (cpu = 0; cpu < nr_cpus; cpu++) { @@ -409,10 +475,10 @@ static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, return 0; } -int perf_evlist__enable_event_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx) +int perf_evlist__enable_event_idx(struct evlist *evlist, + struct evsel *evsel, int idx) { - bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus); + bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); if (per_cpu_mmaps) return perf_evlist__enable_event_cpu(evlist, evsel, idx); @@ -420,154 +486,29 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist, return perf_evlist__enable_event_thread(evlist, evsel, idx); } -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) -{ - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); - int nfds = 0; - struct perf_evsel *evsel; - - evlist__for_each_entry(evlist, evsel) { - if (evsel->system_wide) - nfds += nr_cpus; - else - nfds += nr_cpus * nr_threads; - } - - if (fdarray__available_entries(&evlist->pollfd) < nfds && - fdarray__grow(&evlist->pollfd, nfds) < 0) - return -ENOMEM; - - return 0; -} - -static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, - struct perf_mmap *map, short revent) -{ - int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); - /* - * Save the idx so that when we filter out fds POLLHUP'ed we can - * close the associated evlist->mmap[] entry. - */ - if (pos >= 0) { - evlist->pollfd.priv[pos].ptr = map; - - fcntl(fd, F_SETFL, O_NONBLOCK); - } - - return pos; -} - -int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +int evlist__add_pollfd(struct evlist *evlist, int fd) { - return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN); + return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN); } -static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, - void *arg __maybe_unused) +int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) { - struct perf_mmap *map = fda->priv[fd].ptr; - - if (map) - perf_mmap__put(map); + return perf_evlist__filter_pollfd(&evlist->core, revents_and_mask); } -int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) +int evlist__poll(struct evlist *evlist, int timeout) { - return fdarray__filter(&evlist->pollfd, revents_and_mask, - perf_evlist__munmap_filtered, NULL); + return perf_evlist__poll(&evlist->core, timeout); } -int perf_evlist__poll(struct perf_evlist *evlist, int timeout) -{ - return fdarray__poll(&evlist->pollfd, timeout); -} - -static void perf_evlist__id_hash(struct perf_evlist *evlist, - struct perf_evsel *evsel, - int cpu, int thread, u64 id) -{ - int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); - - sid->id = id; - sid->evsel = evsel; - hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); - hlist_add_head(&sid->node, &evlist->heads[hash]); -} - -void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) -{ - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); - evsel->id[evsel->ids++] = id; -} - -int perf_evlist__id_add_fd(struct perf_evlist *evlist, - struct perf_evsel *evsel, - int cpu, int thread, int fd) -{ - u64 read_data[4] = { 0, }; - int id_idx = 1; /* The first entry is the counter value */ - u64 id; - int ret; - - ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); - if (!ret) - goto add; - - if (errno != ENOTTY) - return -1; - - /* Legacy way to get event id.. All hail to old kernels! */ - - /* - * This way does not work with group format read, so bail - * out in that case. - */ - if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) - return -1; - - if (!(evsel->attr.read_format & PERF_FORMAT_ID) || - read(fd, &read_data, sizeof(read_data)) == -1) - return -1; - - if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - ++id_idx; - if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - ++id_idx; - - id = read_data[id_idx]; - - add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); - return 0; -} - -static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx, int cpu, - int thread) -{ - struct perf_sample_id *sid = SID(evsel, cpu, thread); - sid->idx = idx; - if (evlist->cpus && cpu >= 0) - sid->cpu = evlist->cpus->map[cpu]; - else - sid->cpu = -1; - if (!evsel->system_wide && evlist->threads && thread >= 0) - sid->tid = thread_map__pid(evlist->threads, thread); - else - sid->tid = -1; -} - -struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) +struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; int hash; hash = hash_64(id, PERF_EVLIST__HLIST_BITS); - head = &evlist->heads[hash]; + head = &evlist->core.heads[hash]; hlist_for_each_entry(sid, head, node) if (sid->id == id) @@ -576,24 +517,24 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) return NULL; } -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; - if (evlist->nr_entries == 1 || !id) - return perf_evlist__first(evlist); + if (evlist->core.nr_entries == 1 || !id) + return evlist__first(evlist); sid = perf_evlist__id2sid(evlist, id); if (sid) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); if (!perf_evlist__sample_id_all(evlist)) - return perf_evlist__first(evlist); + return evlist__first(evlist); return NULL; } -struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, +struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; @@ -603,15 +544,15 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, sid = perf_evlist__id2sid(evlist, id); if (sid) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); return NULL; } -static int perf_evlist__event2id(struct perf_evlist *evlist, +static int perf_evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id) { - const u64 *array = event->sample.array; + const __u64 *array = event->sample.array; ssize_t n; n = (event->header.size - sizeof(event->header)) >> 3; @@ -629,19 +570,19 @@ static int perf_evlist__event2id(struct perf_evlist *evlist, return 0; } -struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, +struct evsel *perf_evlist__event2evsel(struct evlist *evlist, union perf_event *event) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); struct hlist_head *head; struct perf_sample_id *sid; int hash; u64 id; - if (evlist->nr_entries == 1) + if (evlist->core.nr_entries == 1) return first; - if (!first->attr.sample_id_all && + if (!first->core.attr.sample_id_all && event->header.type != PERF_RECORD_SAMPLE) return first; @@ -653,24 +594,24 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, return first; hash = hash_64(id, PERF_EVLIST__HLIST_BITS); - head = &evlist->heads[hash]; + head = &evlist->core.heads[hash]; hlist_for_each_entry(sid, head, node) { if (sid->id == id) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); } return NULL; } -static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) +static int perf_evlist__set_paused(struct evlist *evlist, bool value) { int i; if (!evlist->overwrite_mmap) return 0; - for (i = 0; i < evlist->nr_mmaps; i++) { - int fd = evlist->overwrite_mmap[i].fd; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + int fd = evlist->overwrite_mmap[i].core.fd; int err; if (fd < 0) @@ -682,52 +623,56 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) return 0; } -static int perf_evlist__pause(struct perf_evlist *evlist) +static int perf_evlist__pause(struct evlist *evlist) { return perf_evlist__set_paused(evlist, true); } -static int perf_evlist__resume(struct perf_evlist *evlist) +static int perf_evlist__resume(struct evlist *evlist) { return perf_evlist__set_paused(evlist, false); } -static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) +static void evlist__munmap_nofree(struct evlist *evlist) { int i; if (evlist->mmap) - for (i = 0; i < evlist->nr_mmaps; i++) - perf_mmap__munmap(&evlist->mmap[i]); + for (i = 0; i < evlist->core.nr_mmaps; i++) + perf_mmap__munmap(&evlist->mmap[i].core); if (evlist->overwrite_mmap) - for (i = 0; i < evlist->nr_mmaps; i++) - perf_mmap__munmap(&evlist->overwrite_mmap[i]); + for (i = 0; i < evlist->core.nr_mmaps; i++) + perf_mmap__munmap(&evlist->overwrite_mmap[i].core); } -void perf_evlist__munmap(struct perf_evlist *evlist) +void evlist__munmap(struct evlist *evlist) { - perf_evlist__munmap_nofree(evlist); + evlist__munmap_nofree(evlist); zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); } -static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, - bool overwrite) +static void perf_mmap__unmap_cb(struct perf_mmap *map) +{ + struct mmap *m = container_of(map, struct mmap, core); + + mmap__munmap(m); +} + +static struct mmap *evlist__alloc_mmap(struct evlist *evlist, + bool overwrite) { int i; - struct perf_mmap *map; + struct mmap *map; - evlist->nr_mmaps = cpu_map__nr(evlist->cpus); - if (cpu_map__empty(evlist->cpus)) - evlist->nr_mmaps = thread_map__nr(evlist->threads); - map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap)); if (!map) return NULL; - for (i = 0; i < evlist->nr_mmaps; i++) { - map[i].fd = -1; - map[i].overwrite = overwrite; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct perf_mmap *prev = i ? &map[i - 1].core : NULL; + /* * When the perf_mmap() call is made we grab one refcount, plus * one extra to let perf_mmap__consume() get the last @@ -737,151 +682,56 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and * thus does perf_mmap__get() on it. */ - refcount_set(&map[i].refcnt, 0); + perf_mmap__init(&map[i].core, prev, overwrite, perf_mmap__unmap_cb); } - return map; -} -static bool -perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, - struct perf_evsel *evsel) -{ - if (evsel->attr.write_backward) - return false; - return true; + return map; } -static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, - struct mmap_params *mp, int cpu_idx, - int thread, int *_output, int *_output_overwrite) +static void +perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist, + struct perf_mmap_param *_mp, + int idx, bool per_cpu) { - struct perf_evsel *evsel; - int revent; - int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx); - - evlist__for_each_entry(evlist, evsel) { - struct perf_mmap *maps = evlist->mmap; - int *output = _output; - int fd; - int cpu; - - mp->prot = PROT_READ | PROT_WRITE; - if (evsel->attr.write_backward) { - output = _output_overwrite; - maps = evlist->overwrite_mmap; - - if (!maps) { - maps = perf_evlist__alloc_mmap(evlist, true); - if (!maps) - return -1; - evlist->overwrite_mmap = maps; - if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); - } - mp->prot &= ~PROT_WRITE; - } - - if (evsel->system_wide && thread) - continue; - - cpu = cpu_map__idx(evsel->cpus, evlist_cpu); - if (cpu == -1) - continue; - - fd = FD(evsel, cpu, thread); - - if (*output == -1) { - *output = fd; - - if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0) - return -1; - } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) - return -1; - - perf_mmap__get(&maps[idx]); - } - - revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0; - - /* - * The system_wide flag causes a selected event to be opened - * always without a pid. Consequently it will never get a - * POLLHUP, but it is used for tracking in combination with - * other events, so it should not need to be polled anyway. - * Therefore don't add it for polling. - */ - if (!evsel->system_wide && - __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) { - perf_mmap__put(&maps[idx]); - return -1; - } - - if (evsel->attr.read_format & PERF_FORMAT_ID) { - if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, - fd) < 0) - return -1; - perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, - thread); - } - } + struct evlist *evlist = container_of(_evlist, struct evlist, core); + struct mmap_params *mp = container_of(_mp, struct mmap_params, core); - return 0; + auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, idx, per_cpu); } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, - struct mmap_params *mp) +static struct perf_mmap* +perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) { - int cpu, thread; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + struct evlist *evlist = container_of(_evlist, struct evlist, core); + struct mmap *maps; - pr_debug2("perf event ring buffer mmapped per cpu\n"); - for (cpu = 0; cpu < nr_cpus; cpu++) { - int output = -1; - int output_overwrite = -1; + maps = overwrite ? evlist->overwrite_mmap : evlist->mmap; - auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu, - true); + if (!maps) { + maps = evlist__alloc_mmap(evlist, overwrite); + if (!maps) + return NULL; - for (thread = 0; thread < nr_threads; thread++) { - if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, - thread, &output, &output_overwrite)) - goto out_unmap; + if (overwrite) { + evlist->overwrite_mmap = maps; + if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + } else { + evlist->mmap = maps; } } - return 0; - -out_unmap: - perf_evlist__munmap_nofree(evlist); - return -1; + return &maps[idx].core; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, - struct mmap_params *mp) +static int +perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp, + int output, int cpu) { - int thread; - int nr_threads = thread_map__nr(evlist->threads); + struct mmap *map = container_of(_map, struct mmap, core); + struct mmap_params *mp = container_of(_mp, struct mmap_params, core); - pr_debug2("perf event ring buffer mmapped per thread\n"); - for (thread = 0; thread < nr_threads; thread++) { - int output = -1; - int output_overwrite = -1; - - auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread, - false); - - if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, - &output, &output_overwrite)) - goto out_unmap; - } - - return 0; - -out_unmap: - perf_evlist__munmap_nofree(evlist); - return -1; + return mmap__mmap(map, mp, output, cpu); } unsigned long perf_event_mlock_kb_in_pages(void) @@ -907,7 +757,7 @@ unsigned long perf_event_mlock_kb_in_pages(void) return pages; } -size_t perf_evlist__mmap_size(unsigned long pages) +size_t evlist__mmap_size(unsigned long pages) { if (pages == UINT_MAX) pages = perf_event_mlock_kb_in_pages(); @@ -990,7 +840,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, } /** - * perf_evlist__mmap_ex - Create mmaps to receive events. + * evlist__mmap_ex - Create mmaps to receive events. * @evlist: list of events * @pages: map length in pages * @overwrite: overwrite older events? @@ -998,7 +848,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, * @auxtrace_overwrite - overwrite older auxtrace data? * * If @overwrite is %false the user needs to signal event consumption using - * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this + * perf_mmap__write_tail(). Using evlist__mmap_read() does this * automatically. * * Similarly, if @auxtrace_overwrite is %false the user needs to signal data @@ -1006,60 +856,47 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, * * Return: %0 on success, negative error code otherwise. */ -int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, +int evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level) { - struct perf_evsel *evsel; - const struct cpu_map *cpus = evlist->cpus; - const struct thread_map *threads = evlist->threads; /* * Delay setting mp.prot: set it before calling perf_mmap__mmap. * Its value is decided by evsel's write_backward. * So &mp should not be passed through const pointer. */ - struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush, - .comp_level = comp_level }; - - if (!evlist->mmap) - evlist->mmap = perf_evlist__alloc_mmap(evlist, false); - if (!evlist->mmap) - return -ENOMEM; - - if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) - return -ENOMEM; + struct mmap_params mp = { + .nr_cblocks = nr_cblocks, + .affinity = affinity, + .flush = flush, + .comp_level = comp_level + }; + struct perf_evlist_mmap_ops ops = { + .idx = perf_evlist__mmap_cb_idx, + .get = perf_evlist__mmap_cb_get, + .mmap = perf_evlist__mmap_cb_mmap, + }; - evlist->mmap_len = perf_evlist__mmap_size(pages); - pr_debug("mmap size %zuB\n", evlist->mmap_len); - mp.mask = evlist->mmap_len - page_size - 1; + evlist->core.mmap_len = evlist__mmap_size(pages); + pr_debug("mmap size %zuB\n", evlist->core.mmap_len); - auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len, + auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len, auxtrace_pages, auxtrace_overwrite); - evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0) - return -ENOMEM; - } - - if (cpu_map__empty(cpus)) - return perf_evlist__mmap_per_thread(evlist, &mp); - - return perf_evlist__mmap_per_cpu(evlist, &mp); + return perf_evlist__mmap_ops(&evlist->core, &ops, &mp.core); } -int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages) +int evlist__mmap(struct evlist *evlist, unsigned int pages) { - return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); + return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); } -int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) +int perf_evlist__create_maps(struct evlist *evlist, struct target *target) { bool all_threads = (target->per_thread && target->system_wide); - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; /* * If specify '-a' and '--per-thread' to perf record, perf record @@ -1086,68 +923,45 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) return -1; if (target__uses_dummy_map(target)) - cpus = cpu_map__dummy_new(); + cpus = perf_cpu_map__dummy_new(); else - cpus = cpu_map__new(target->cpu_list); + cpus = perf_cpu_map__new(target->cpu_list); if (!cpus) goto out_delete_threads; - evlist->has_user_cpus = !!target->cpu_list; + evlist->core.has_user_cpus = !!target->cpu_list; - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); return 0; out_delete_threads: - thread_map__put(threads); + perf_thread_map__put(threads); return -1; } -void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads) -{ - /* - * Allow for the possibility that one or another of the maps isn't being - * changed i.e. don't put it. Note we are assuming the maps that are - * being applied are brand new and evlist is taking ownership of the - * original reference count of 1. If that is not the case it is up to - * the caller to increase the reference count. - */ - if (cpus != evlist->cpus) { - cpu_map__put(evlist->cpus); - evlist->cpus = cpu_map__get(cpus); - } - - if (threads != evlist->threads) { - thread_map__put(evlist->threads); - evlist->threads = thread_map__get(threads); - } - - perf_evlist__propagate_maps(evlist); -} - -void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__set_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) __perf_evsel__set_sample_bit(evsel, bit); } -void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__reset_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) __perf_evsel__reset_sample_bit(evsel, bit); } -int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) +int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) { - struct perf_evsel *evsel; + struct evsel *evsel; int err = 0; evlist__for_each_entry(evlist, evsel) { @@ -1158,7 +972,7 @@ 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, evsel->filter); + err = perf_evsel__apply_filter(&evsel->core, evsel->filter); if (err) { *err_evsel = evsel; break; @@ -1168,13 +982,16 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e return err; } -int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter) +int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) { - struct perf_evsel *evsel; + struct evsel *evsel; int err = 0; + if (filter == NULL) + return -1; + evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; err = perf_evsel__set_filter(evsel, filter); @@ -1185,16 +1002,35 @@ int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter) return err; } -int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids) +int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter) +{ + struct evsel *evsel; + int err = 0; + + if (filter == NULL) + return -1; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) + continue; + + err = perf_evsel__append_tp_filter(evsel, filter); + if (err) + break; + } + + return err; +} + +char *asprintf__tp_filter_pids(size_t npids, pid_t *pids) { char *filter; - int ret = -1; size_t i; for (i = 0; i < npids; ++i) { if (i == 0) { if (asprintf(&filter, "common_pid != %d", pids[i]) < 0) - return -1; + return NULL; } else { char *tmp; @@ -1206,22 +1042,45 @@ int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pi } } - ret = perf_evlist__set_tp_filter(evlist, filter); + return filter; out_free: free(filter); + return NULL; +} + +int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +{ + char *filter = asprintf__tp_filter_pids(npids, pids); + int ret = perf_evlist__set_tp_filter(evlist, filter); + + free(filter); return ret; } -int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid) +int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) { return perf_evlist__set_tp_filter_pids(evlist, 1, &pid); } -bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) +int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { - struct perf_evsel *pos; + char *filter = asprintf__tp_filter_pids(npids, pids); + int ret = perf_evlist__append_tp_filter(evlist, filter); - if (evlist->nr_entries == 1) + free(filter); + return ret; +} + +int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) +{ + return perf_evlist__append_tp_filter_pids(evlist, 1, &pid); +} + +bool perf_evlist__valid_sample_type(struct evlist *evlist) +{ + struct evsel *pos; + + if (evlist->core.nr_entries == 1) return true; if (evlist->id_pos < 0 || evlist->is_pos < 0) @@ -1236,43 +1095,43 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) return true; } -u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) +u64 __perf_evlist__combined_sample_type(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; if (evlist->combined_sample_type) return evlist->combined_sample_type; evlist__for_each_entry(evlist, evsel) - evlist->combined_sample_type |= evsel->attr.sample_type; + evlist->combined_sample_type |= evsel->core.attr.sample_type; return evlist->combined_sample_type; } -u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) +u64 perf_evlist__combined_sample_type(struct evlist *evlist) { evlist->combined_sample_type = 0; return __perf_evlist__combined_sample_type(evlist); } -u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist) +u64 perf_evlist__combined_branch_type(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 branch_type = 0; evlist__for_each_entry(evlist, evsel) - branch_type |= evsel->attr.branch_sample_type; + branch_type |= evsel->core.attr.branch_sample_type; return branch_type; } -bool perf_evlist__valid_read_format(struct perf_evlist *evlist) +bool perf_evlist__valid_read_format(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; - u64 read_format = first->attr.read_format; - u64 sample_type = first->attr.sample_type; + struct evsel *first = evlist__first(evlist), *pos = first; + u64 read_format = first->core.attr.read_format; + u64 sample_type = first->core.attr.sample_type; evlist__for_each_entry(evlist, pos) { - if (read_format != pos->attr.read_format) + if (read_format != pos->core.attr.read_format) return false; } @@ -1285,23 +1144,17 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist) return true; } -u64 perf_evlist__read_format(struct perf_evlist *evlist) +u16 perf_evlist__id_hdr_size(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.read_format; -} - -u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) -{ - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); struct perf_sample *data; u64 sample_type; u16 size = 0; - if (!first->attr.sample_id_all) + if (!first->core.attr.sample_id_all) goto out; - sample_type = first->attr.sample_type; + sample_type = first->core.attr.sample_type; if (sample_type & PERF_SAMPLE_TID) size += sizeof(data->tid) * 2; @@ -1324,42 +1177,68 @@ out: return size; } -bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist) +bool perf_evlist__valid_sample_id_all(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + struct evsel *first = evlist__first(evlist), *pos = first; evlist__for_each_entry_continue(evlist, pos) { - if (first->attr.sample_id_all != pos->attr.sample_id_all) + if (first->core.attr.sample_id_all != pos->core.attr.sample_id_all) return false; } return true; } -bool perf_evlist__sample_id_all(struct perf_evlist *evlist) +bool perf_evlist__sample_id_all(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.sample_id_all; + struct evsel *first = evlist__first(evlist); + return first->core.attr.sample_id_all; } -void perf_evlist__set_selected(struct perf_evlist *evlist, - struct perf_evsel *evsel) +void perf_evlist__set_selected(struct evlist *evlist, + struct evsel *evsel) { evlist->selected = evsel; } -void perf_evlist__close(struct perf_evlist *evlist) +void evlist__close(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; + struct affinity affinity; + int cpu, i; + + /* + * With perf record core.cpus is usually NULL. + * Use the old method to handle this for now. + */ + if (!evlist->core.cpus) { + evlist__for_each_entry_reverse(evlist, evsel) + evsel__close(evsel); + return; + } - evlist__for_each_entry_reverse(evlist, evsel) - perf_evsel__close(evsel); + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry_reverse(evlist, evsel) { + if (evsel__cpu_iter_skip(evsel, cpu)) + continue; + perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); + evlist__for_each_entry_reverse(evlist, evsel) { + perf_evsel__free_fd(&evsel->core); + perf_evsel__free_id(&evsel->core); + } } -static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) +static int perf_evlist__create_syswide_maps(struct evlist *evlist) { - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; int err = -ENOMEM; /* @@ -1371,32 +1250,32 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) * error, and we may not want to do that fallback to a * default cpu identity map :-\ */ - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) goto out; - threads = thread_map__new_dummy(); + threads = perf_thread_map__new_dummy(); if (!threads) goto out_put; - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); out: return err; out_put: - cpu_map__put(cpus); + perf_cpu_map__put(cpus); goto out; } -int perf_evlist__open(struct perf_evlist *evlist) +int evlist__open(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; int err; /* * Default: one fd per CPU, all threads, aka systemwide * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ - if (evlist->threads == NULL && evlist->cpus == NULL) { + if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { err = perf_evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; @@ -1405,19 +1284,19 @@ int perf_evlist__open(struct perf_evlist *evlist) perf_evlist__update_id_pos(evlist); evlist__for_each_entry(evlist, evsel) { - err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); + err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads); if (err < 0) goto out_err; } return 0; out_err: - perf_evlist__close(evlist); + evlist__close(evlist); errno = -err; return err; } -int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target, +int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) { @@ -1499,12 +1378,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar } if (target__none(target)) { - if (evlist->threads == NULL) { + if (evlist->core.threads == NULL) { fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n", __func__, __LINE__); goto out_close_pipes; } - thread_map__set_pid(evlist->threads, 0, evlist->workload.pid); + perf_thread_map__set_pid(evlist->core.threads, 0, evlist->workload.pid); } close(child_ready_pipe[1]); @@ -1531,7 +1410,7 @@ out_close_ready_pipe: return -1; } -int perf_evlist__start_workload(struct perf_evlist *evlist) +int perf_evlist__start_workload(struct evlist *evlist) { if (evlist->workload.cork_fd > 0) { char bf = 0; @@ -1550,41 +1429,28 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) return 0; } -int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, +int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return perf_evsel__parse_sample(evsel, event, sample); } -int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist, +int perf_evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return perf_evsel__parse_sample_timestamp(evsel, event, timestamp); } -size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) -{ - struct perf_evsel *evsel; - size_t printed = 0; - - evlist__for_each_entry(evlist, evsel) { - printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "", - perf_evsel__name(evsel)); - } - - return printed + fprintf(fp, "\n"); -} - -int perf_evlist__strerror_open(struct perf_evlist *evlist, +int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size) { int printed, value; @@ -1613,20 +1479,20 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist, "Hint:\tThe current value is %d.", value); break; case EINVAL: { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); int max_freq; if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0) goto out_default; - if (first->attr.sample_freq < (u64)max_freq) + if (first->core.attr.sample_freq < (u64)max_freq) goto out_default; printed = scnprintf(buf, size, "Error:\t%s.\n" "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n" "Hint:\tThe current value is %d and %" PRIu64 " is being requested.", - emsg, max_freq, first->attr.sample_freq); + emsg, max_freq, first->core.attr.sample_freq); break; } default: @@ -1638,10 +1504,10 @@ out_default: return 0; } -int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size) +int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) { char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); - int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; + int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0; switch (err) { case EPERM: @@ -1669,27 +1535,27 @@ int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, s return 0; } -void perf_evlist__to_front(struct perf_evlist *evlist, - struct perf_evsel *move_evsel) +void perf_evlist__to_front(struct evlist *evlist, + struct evsel *move_evsel) { - struct perf_evsel *evsel, *n; + struct evsel *evsel, *n; LIST_HEAD(move); - if (move_evsel == perf_evlist__first(evlist)) + if (move_evsel == evlist__first(evlist)) return; evlist__for_each_entry_safe(evlist, n, evsel) { if (evsel->leader == move_evsel->leader) - list_move_tail(&evsel->node, &move); + list_move_tail(&evsel->core.node, &move); } - list_splice(&move, &evlist->entries); + list_splice(&move, &evlist->core.entries); } -void perf_evlist__set_tracking_event(struct perf_evlist *evlist, - struct perf_evsel *tracking_evsel) +void perf_evlist__set_tracking_event(struct evlist *evlist, + struct evsel *tracking_evsel) { - struct perf_evsel *evsel; + struct evsel *evsel; if (tracking_evsel->tracking) return; @@ -1702,11 +1568,11 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist, tracking_evsel->tracking = true; } -struct perf_evsel * -perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, +struct evsel * +perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (!evsel->name) @@ -1718,7 +1584,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, return NULL; } -void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, +void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state) { enum bkw_mmap_state old_state = evlist->bkw_mmap_state; @@ -1776,12 +1642,12 @@ state_err: return; } -bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) +bool perf_evlist__exclude_kernel(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (!evsel->attr.exclude_kernel) + if (!evsel->core.attr.exclude_kernel) return false; } @@ -1793,25 +1659,26 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) * the group display. Set the artificial group and set the leader's * forced_leader flag to notify the display code. */ -void perf_evlist__force_leader(struct perf_evlist *evlist) +void perf_evlist__force_leader(struct evlist *evlist) { if (!evlist->nr_groups) { - struct perf_evsel *leader = perf_evlist__first(evlist); + struct evsel *leader = evlist__first(evlist); perf_evlist__set_leader(evlist); leader->forced_leader = true; } } -struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, - struct perf_evsel *evsel) +struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, + struct evsel *evsel, + bool close) { - struct perf_evsel *c2, *leader; + struct evsel *c2, *leader; bool is_open = true; leader = evsel->leader; pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); + leader->name, leader->core.nr_members); /* * for_each_group_member doesn't work here because it doesn't @@ -1821,25 +1688,30 @@ struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, if (c2 == evsel) is_open = false; if (c2->leader == leader) { - if (is_open) - perf_evsel__close(c2); + if (is_open && close) + perf_evsel__close(&c2->core); c2->leader = c2; - c2->nr_members = 0; + c2->core.nr_members = 0; + /* + * Set this for all former members of the group + * to indicate they get reopened. + */ + c2->reset_group = true; } } return leader; } -int perf_evlist__add_sb_event(struct perf_evlist **evlist, +int perf_evlist__add_sb_event(struct evlist **evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data) { - struct perf_evsel *evsel; + struct evsel *evsel; bool new_evlist = (*evlist) == NULL; if (*evlist == NULL) - *evlist = perf_evlist__new(); + *evlist = evlist__new(); if (*evlist == NULL) return -1; @@ -1848,18 +1720,18 @@ int perf_evlist__add_sb_event(struct perf_evlist **evlist, attr->sample_id_all = 1; } - evsel = perf_evsel__new_idx(attr, (*evlist)->nr_entries); + evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries); if (!evsel) goto out_err; evsel->side_band.cb = cb; evsel->side_band.data = data; - perf_evlist__add(*evlist, evsel); + evlist__add(*evlist, evsel); return 0; out_err: if (new_evlist) { - perf_evlist__delete(*evlist); + evlist__delete(*evlist); *evlist = NULL; } return -1; @@ -1867,9 +1739,17 @@ out_err: static void *perf_evlist__poll_thread(void *arg) { - struct perf_evlist *evlist = arg; + struct evlist *evlist = arg; bool draining = false; int i, done = 0; + /* + * In order to read symbols from other namespaces perf to needs to call + * setns(2). This isn't permitted if the struct_fs has multiple users. + * unshare(2) the fs so that we may continue to setns into namespaces + * that we're observing when, for instance, reading the build-ids at + * the end of a 'perf record' session. + */ + unshare(CLONE_FS); while (!done) { bool got_data = false; @@ -1878,26 +1758,26 @@ static void *perf_evlist__poll_thread(void *arg) draining = true; if (!draining) - perf_evlist__poll(evlist, 1000); + evlist__poll(evlist, 1000); - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *map = &evlist->mmap[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *map = &evlist->mmap[i]; union perf_event *event; - if (perf_mmap__read_init(map)) + if (perf_mmap__read_init(&map->core)) continue; - while ((event = perf_mmap__read_event(map)) != NULL) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + while ((event = perf_mmap__read_event(&map->core)) != NULL) { + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (evsel && evsel->side_band.cb) evsel->side_band.cb(event, evsel->side_band.data); else pr_warning("cannot locate proper evsel for the side band event\n"); - perf_mmap__consume(map); + perf_mmap__consume(&map->core); got_data = true; } - perf_mmap__read_done(map); + perf_mmap__read_done(&map->core); } if (draining && !got_data) @@ -1906,10 +1786,10 @@ static void *perf_evlist__poll_thread(void *arg) return NULL; } -int perf_evlist__start_sb_thread(struct perf_evlist *evlist, +int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) { - struct perf_evsel *counter; + struct evsel *counter; if (!evlist) return 0; @@ -1918,16 +1798,16 @@ int perf_evlist__start_sb_thread(struct perf_evlist *evlist, goto out_delete_evlist; evlist__for_each_entry(evlist, counter) { - if (perf_evsel__open(counter, evlist->cpus, - evlist->threads) < 0) + if (evsel__open(counter, evlist->core.cpus, + evlist->core.threads) < 0) goto out_delete_evlist; } - if (perf_evlist__mmap(evlist, UINT_MAX)) + if (evlist__mmap(evlist, UINT_MAX)) goto out_delete_evlist; evlist__for_each_entry(evlist, counter) { - if (perf_evsel__enable(counter)) + if (evsel__enable(counter)) goto out_delete_evlist; } @@ -1938,16 +1818,16 @@ int perf_evlist__start_sb_thread(struct perf_evlist *evlist, return 0; out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; return -1; } -void perf_evlist__stop_sb_thread(struct perf_evlist *evlist) +void perf_evlist__stop_sb_thread(struct evlist *evlist) { if (!evlist) return; evlist->thread.done = 1; pthread_join(evlist->thread.th, NULL); - perf_evlist__delete(evlist); + evlist__delete(evlist); } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 49354fe24d5f..f5bd5c386df1 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -7,32 +7,51 @@ #include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> -#include <stdio.h> -#include "../perf.h" -#include "event.h" +#include <internal/evlist.h> +#include <internal/evsel.h> +#include "events_stats.h" #include "evsel.h" -#include "mmap.h" -#include "util.h" +#include <pthread.h> #include <signal.h> #include <unistd.h> struct pollfd; struct thread_map; -struct cpu_map; +struct perf_cpu_map; struct record_opts; -#define PERF_EVLIST__HLIST_BITS 8 -#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +/* + * 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]; - int nr_entries; +struct evlist { + struct perf_evlist core; int nr_groups; - int nr_mmaps; bool enabled; - bool has_user_cpus; - size_t mmap_len; int id_pos; int is_pos; u64 combined_sample_type; @@ -41,15 +60,12 @@ struct perf_evlist { int cork_fd; pid_t pid; } workload; - struct fdarray pollfd; - struct perf_mmap *mmap; - struct perf_mmap *overwrite_mmap; - struct thread_map *threads; - struct cpu_map *cpus; - struct perf_evsel *selected; + struct mmap *mmap; + struct mmap *overwrite_mmap; + struct evsel *selected; struct events_stats stats; struct perf_env *env; - void (*trace_event_sample_raw)(struct perf_evlist *evlist, + void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); u64 first_sample_time; @@ -60,51 +76,58 @@ struct perf_evlist { } thread; }; -struct perf_evsel_str_handler { +struct evsel_str_handler { const char *name; void *handler; }; -struct perf_evlist *perf_evlist__new(void); -struct perf_evlist *perf_evlist__new_default(void); -struct perf_evlist *perf_evlist__new_dummy(void); -void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads); -void perf_evlist__exit(struct perf_evlist *evlist); -void perf_evlist__delete(struct perf_evlist *evlist); +struct evlist *evlist__new(void); +struct evlist *perf_evlist__new_default(void); +struct evlist *perf_evlist__new_dummy(void); +void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +void evlist__exit(struct evlist *evlist); +void evlist__delete(struct 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); +void evlist__add(struct evlist *evlist, struct evsel *entry); +void evlist__remove(struct evlist *evlist, struct evsel *evsel); -int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise); +int __perf_evlist__add_default(struct evlist *evlist, bool precise); -static inline int perf_evlist__add_default(struct perf_evlist *evlist) +static inline int perf_evlist__add_default(struct evlist *evlist) { return __perf_evlist__add_default(evlist, true); } -int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, +int __perf_evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); #define perf_evlist__add_default_attrs(evlist, array) \ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) -int perf_evlist__add_dummy(struct perf_evlist *evlist); +int perf_evlist__add_dummy(struct evlist *evlist); -int perf_evlist__add_sb_event(struct perf_evlist **evlist, +int perf_evlist__add_sb_event(struct evlist **evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data); -int perf_evlist__start_sb_thread(struct perf_evlist *evlist, +int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target); -void perf_evlist__stop_sb_thread(struct perf_evlist *evlist); +void perf_evlist__stop_sb_thread(struct evlist *evlist); -int perf_evlist__add_newtp(struct perf_evlist *evlist, +int perf_evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); -void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, +int __evlist__set_tracepoints_handlers(struct evlist *evlist, + const struct evsel_str_handler *assocs, + size_t nr_assocs); + +#define evlist__set_tracepoints_handlers(evlist, array) \ + __evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) + +void __perf_evlist__set_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit); -void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__reset_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit); #define perf_evlist__set_sample_bit(evlist, bit) \ @@ -113,58 +136,57 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, #define perf_evlist__reset_sample_bit(evlist, bit) \ __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) -int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter); -int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid); -int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); +int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter); +int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); +int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -struct perf_evsel * -perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); +int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter); -struct perf_evsel * -perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, - const char *name); +int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); +int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); + +struct evsel * +perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id); -void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id); -int perf_evlist__id_add_fd(struct perf_evlist *evlist, - struct perf_evsel *evsel, - int cpu, int thread, int fd); +struct evsel * +perf_evlist__find_tracepoint_by_name(struct evlist *evlist, + const char *name); -int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); -int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask); +int evlist__add_pollfd(struct evlist *evlist, int fd); +int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); -int perf_evlist__poll(struct perf_evlist *evlist, int timeout); +int evlist__poll(struct evlist *evlist, int timeout); -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); -struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, +struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id); +struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, u64 id); -struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); +struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id); -void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state); +void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); -void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); +void evlist__mmap_consume(struct evlist *evlist, int idx); -int perf_evlist__open(struct perf_evlist *evlist); -void perf_evlist__close(struct perf_evlist *evlist); +int evlist__open(struct evlist *evlist); +void evlist__close(struct evlist *evlist); struct callchain_param; -void perf_evlist__set_id_pos(struct perf_evlist *evlist); +void perf_evlist__set_id_pos(struct evlist *evlist); bool perf_can_sample_identifier(void); bool perf_can_record_switch_events(void); bool perf_can_record_cpu_wide(void); -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, +bool perf_can_aux_sample(void); +void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); -int perf_evlist__prepare_workload(struct perf_evlist *evlist, +int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)); -int perf_evlist__start_workload(struct perf_evlist *evlist); +int perf_evlist__start_workload(struct evlist *evlist); struct option; @@ -175,77 +197,76 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, unsigned long perf_event_mlock_kb_in_pages(void); -int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, +int evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level); -int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages); -void perf_evlist__munmap(struct perf_evlist *evlist); +int evlist__mmap(struct evlist *evlist, unsigned int pages); +void evlist__munmap(struct evlist *evlist); -size_t perf_evlist__mmap_size(unsigned long pages); +size_t evlist__mmap_size(unsigned long pages); -void perf_evlist__disable(struct perf_evlist *evlist); -void perf_evlist__enable(struct perf_evlist *evlist); -void perf_evlist__toggle_enable(struct perf_evlist *evlist); +void evlist__disable(struct evlist *evlist); +void evlist__enable(struct evlist *evlist); +void perf_evlist__toggle_enable(struct evlist *evlist); -int perf_evlist__enable_event_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx); +int perf_evlist__enable_event_idx(struct evlist *evlist, + struct evsel *evsel, int idx); -void perf_evlist__set_selected(struct perf_evlist *evlist, - struct perf_evsel *evsel); +void perf_evlist__set_selected(struct evlist *evlist, + struct evsel *evsel); -void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads); -int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); +int perf_evlist__create_maps(struct evlist *evlist, struct target *target); +int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); -void perf_evlist__set_leader(struct perf_evlist *evlist); +void perf_evlist__set_leader(struct evlist *evlist); -u64 perf_evlist__read_format(struct perf_evlist *evlist); -u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist); -u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist); -u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist); -bool perf_evlist__sample_id_all(struct perf_evlist *evlist); -u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); +u64 __perf_evlist__combined_sample_type(struct evlist *evlist); +u64 perf_evlist__combined_sample_type(struct evlist *evlist); +u64 perf_evlist__combined_branch_type(struct evlist *evlist); +bool perf_evlist__sample_id_all(struct evlist *evlist); +u16 perf_evlist__id_hdr_size(struct evlist *evlist); -int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, +int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); -int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist, +int perf_evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp); -bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); -bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); -bool perf_evlist__valid_read_format(struct perf_evlist *evlist); +bool perf_evlist__valid_sample_type(struct evlist *evlist); +bool perf_evlist__valid_sample_id_all(struct evlist *evlist); +bool perf_evlist__valid_read_format(struct evlist *evlist); -void perf_evlist__splice_list_tail(struct perf_evlist *evlist, +void perf_evlist__splice_list_tail(struct evlist *evlist, struct list_head *list); -static inline bool perf_evlist__empty(struct perf_evlist *evlist) +static inline bool perf_evlist__empty(struct evlist *evlist) { - return list_empty(&evlist->entries); + return list_empty(&evlist->core.entries); } -static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +static inline struct evsel *evlist__first(struct evlist *evlist) { - return list_entry(evlist->entries.next, struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(&evlist->core); + + return container_of(evsel, struct evsel, core); } -static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +static inline struct evsel *evlist__last(struct evlist *evlist) { - return list_entry(evlist->entries.prev, struct perf_evsel, node); -} + struct perf_evsel *evsel = perf_evlist__last(&evlist->core); -size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); + return container_of(evsel, struct evsel, core); +} -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); +int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); -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); +bool perf_evlist__can_select_event(struct evlist *evlist, const char *str); +void perf_evlist__to_front(struct evlist *evlist, + struct evsel *move_evsel); /** * __evlist__for_each_entry - iterate thru all the evsels @@ -253,7 +274,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry(list, evsel) \ - list_for_each_entry(evsel, list, node) + list_for_each_entry(evsel, list, core.node) /** * evlist__for_each_entry - iterate thru all the evsels @@ -261,7 +282,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry(evlist, evsel) \ - __evlist__for_each_entry(&(evlist)->entries, evsel) + __evlist__for_each_entry(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_continue - continue iteration thru all the evsels @@ -269,7 +290,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_continue(list, evsel) \ - list_for_each_entry_continue(evsel, list, node) + list_for_each_entry_continue(evsel, list, core.node) /** * evlist__for_each_entry_continue - continue iteration thru all the evsels @@ -277,7 +298,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry_continue(evlist, evsel) \ - __evlist__for_each_entry_continue(&(evlist)->entries, evsel) + __evlist__for_each_entry_continue(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order @@ -285,7 +306,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_reverse(list, evsel) \ - list_for_each_entry_reverse(evsel, list, node) + list_for_each_entry_reverse(evsel, list, core.node) /** * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order @@ -293,7 +314,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry_reverse(evlist, evsel) \ - __evlist__for_each_entry_reverse(&(evlist)->entries, evsel) + __evlist__for_each_entry_reverse(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_safe - safely iterate thru all the evsels @@ -302,7 +323,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_safe(list, tmp, evsel) \ - list_for_each_entry_safe(evsel, tmp, list, node) + list_for_each_entry_safe(evsel, tmp, list, core.node) /** * evlist__for_each_entry_safe - safely iterate thru all the evsels @@ -311,21 +332,30 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @tmp: struct evsel temp iterator */ #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ - __evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel) + __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) + +#define evlist__for_each_cpu(evlist, index, cpu) \ + evlist__cpu_iter_start(evlist); \ + perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) + +void perf_evlist__set_tracking_event(struct evlist *evlist, + struct evsel *tracking_evsel); -void perf_evlist__set_tracking_event(struct perf_evlist *evlist, - struct perf_evsel *tracking_evsel); +void evlist__cpu_iter_start(struct evlist *evlist); +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); -struct perf_evsel * -perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); +struct evsel * +perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); -struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, +struct evsel *perf_evlist__event2evsel(struct evlist *evlist, union perf_event *event); -bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); +bool perf_evlist__exclude_kernel(struct evlist *evlist); -void perf_evlist__force_leader(struct perf_evlist *evlist); +void perf_evlist__force_leader(struct evlist *evlist); -struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, - struct perf_evsel *evsel); +struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, + struct evsel *evsel, + bool close); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 52459dd5ad0c..c8dc4450884c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -22,22 +22,33 @@ #include <sys/resource.h> #include <sys/types.h> #include <dirent.h> +#include <stdlib.h> +#include <perf/evsel.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" +#include "counts.h" #include "event.h" #include "evsel.h" +#include "util/env.h" +#include "util/evsel_config.h" +#include "util/evsel_fprintf.h" #include "evlist.h" -#include "cpumap.h" +#include <perf/cpumap.h> #include "thread_map.h" #include "target.h" #include "perf_regs.h" +#include "record.h" #include "debug.h" #include "trace-event.h" #include "stat.h" #include "string2.h" #include "memswap.h" +#include "util.h" +#include "../perf-sys.h" #include "util/parse-branch-options.h" +#include <internal/xyarray.h> +#include <internal/lib.h> #include <linux/ctype.h> @@ -45,30 +56,30 @@ struct perf_missing_features perf_missing_features; static clockid_t clockid; -static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) +static int perf_evsel__no_extra_init(struct 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) +static void perf_evsel__no_extra_fini(struct evsel *evsel __maybe_unused) { } static struct { size_t size; - int (*init)(struct perf_evsel *evsel); - void (*fini)(struct perf_evsel *evsel); + int (*init)(struct evsel *evsel); + void (*fini)(struct evsel *evsel); } perf_evsel__object = { - .size = sizeof(struct perf_evsel), + .size = sizeof(struct evsel), .init = perf_evsel__no_extra_init, .fini = perf_evsel__no_extra_fini, }; int perf_evsel__object_config(size_t object_size, - int (*init)(struct perf_evsel *evsel), - void (*fini)(struct perf_evsel *evsel)) + int (*init)(struct evsel *evsel), + void (*fini)(struct evsel *evsel)) { if (object_size == 0) @@ -89,7 +100,7 @@ set_methods: return 0; } -#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __perf_evsel__sample_size(u64 sample_type) { @@ -113,7 +124,7 @@ int __perf_evsel__sample_size(u64 sample_type) * * This function returns the position of the event id (PERF_SAMPLE_ID or * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct - * sample_event. + * perf_record_sample. */ static int __perf_evsel__calc_id_pos(u64 sample_type) { @@ -167,33 +178,33 @@ static int __perf_evsel__calc_is_pos(u64 sample_type) return idx; } -void perf_evsel__calc_id_pos(struct perf_evsel *evsel) +void perf_evsel__calc_id_pos(struct evsel *evsel) { - evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type); - evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); + evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type); + evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type); } -void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { - if (!(evsel->attr.sample_type & bit)) { - evsel->attr.sample_type |= bit; + if (!(evsel->core.attr.sample_type & bit)) { + evsel->core.attr.sample_type |= bit; evsel->sample_size += sizeof(u64); perf_evsel__calc_id_pos(evsel); } } -void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { - if (evsel->attr.sample_type & bit) { - evsel->attr.sample_type &= ~bit; + if (evsel->core.attr.sample_type & bit) { + evsel->core.attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); perf_evsel__calc_id_pos(evsel); } } -void perf_evsel__set_sample_id(struct perf_evsel *evsel, +void perf_evsel__set_sample_id(struct evsel *evsel, bool can_sample_identifier) { if (can_sample_identifier) { @@ -202,7 +213,7 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, } else { perf_evsel__set_sample_bit(evsel, ID); } - evsel->attr.read_format |= PERF_FORMAT_ID; + evsel->core.attr.read_format |= PERF_FORMAT_ID; } /** @@ -213,7 +224,7 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, * * Return %true if event is function trace event */ -bool perf_evsel__is_function_event(struct perf_evsel *evsel) +bool perf_evsel__is_function_event(struct evsel *evsel) { #define FUNCTION_EVENT "ftrace:function" @@ -223,19 +234,19 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel) #undef FUNCTION_EVENT } -void perf_evsel__init(struct perf_evsel *evsel, - struct perf_event_attr *attr, int idx) +void evsel__init(struct evsel *evsel, + struct perf_event_attr *attr, int idx) { + perf_evsel__init(&evsel->core, attr); evsel->idx = idx; evsel->tracking = !idx; - evsel->attr = *attr; evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; + evsel->bpf_obj = NULL; evsel->bpf_fd = -1; - INIT_LIST_HEAD(&evsel->node); INIT_LIST_HEAD(&evsel->config_terms); perf_evsel__object.init(evsel); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); @@ -248,18 +259,18 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->pmu_name = NULL; } -struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) +struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { - struct perf_evsel *evsel = zalloc(perf_evsel__object.size); + struct evsel *evsel = zalloc(perf_evsel__object.size); if (!evsel) return NULL; - perf_evsel__init(evsel, attr, idx); + evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { - evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), - evsel->attr.sample_period = 1; + evsel->core.attr.sample_period = 1; } if (perf_evsel__is_clock(evsel)) { @@ -278,17 +289,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) static bool perf_event_can_profile_kernel(void) { - return geteuid() == 0 || perf_event_paranoid() == -1; + return perf_event_paranoid_check(1); } -struct perf_evsel *perf_evsel__new_cycles(bool precise) +struct evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, .exclude_kernel = !perf_event_can_profile_kernel(), }; - struct perf_evsel *evsel; + struct evsel *evsel; event_attr_init(&attr); @@ -300,7 +311,7 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise) * to kick in when we return and before perf_evsel__open() is called. */ new_event: - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel == NULL) goto out; @@ -315,7 +326,7 @@ new_event: out: return evsel; error_free: - perf_evsel__delete(evsel); + evsel__delete(evsel); evsel = NULL; goto out; } @@ -323,9 +334,9 @@ error_free: /* * Returns pointer with encoded error via <linux/err.h> interface. */ -struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) +struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) { - struct perf_evsel *evsel = zalloc(perf_evsel__object.size); + struct evsel *evsel = zalloc(perf_evsel__object.size); int err = -ENOMEM; if (evsel == NULL) { @@ -349,7 +360,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int event_attr_init(&attr); attr.config = evsel->tp_format->id; attr.sample_period = 1; - perf_evsel__init(evsel, &attr, idx); + evsel__init(evsel, &attr, idx); } return evsel; @@ -382,10 +393,10 @@ static const char *__perf_evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) { int colon = 0, r = 0; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; bool exclude_guest_default = false; #define MOD_PRINT(context, mod) do { \ @@ -418,9 +429,9 @@ static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t return r; } -static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { - int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config)); + int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config)); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -444,9 +455,9 @@ static const char *__perf_evsel__sw_name(u64 config) return "unknown-software"; } -static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size) { - int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config)); + int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config)); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -468,9 +479,9 @@ static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) return r; } -static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -568,15 +579,15 @@ out_err: return scnprintf(bf, size, "%s", err); } -static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size) { - int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size); + int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size); return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } -static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size) { - int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config); return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } @@ -586,7 +597,7 @@ static int perf_evsel__tool_name(char *bf, size_t size) return ret; } -const char *perf_evsel__name(struct perf_evsel *evsel) +const char *perf_evsel__name(struct evsel *evsel) { char bf[128]; @@ -596,7 +607,7 @@ const char *perf_evsel__name(struct perf_evsel *evsel) if (evsel->name) return evsel->name; - switch (evsel->attr.type) { + switch (evsel->core.attr.type) { case PERF_TYPE_RAW: perf_evsel__raw_name(evsel, bf, sizeof(bf)); break; @@ -626,7 +637,7 @@ const char *perf_evsel__name(struct perf_evsel *evsel) default: scnprintf(bf, sizeof(bf), "unknown attr type: %d", - evsel->attr.type); + evsel->core.attr.type); break; } @@ -638,7 +649,7 @@ out_unknown: return "unknown"; } -const char *perf_evsel__group_name(struct perf_evsel *evsel) +const char *perf_evsel__group_name(struct evsel *evsel) { return evsel->group_name ?: "anon group"; } @@ -653,10 +664,10 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel) * For record -e 'cycles,instructions' and report --group * 'cycles:u, instructions:u' */ -int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) +int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size) { int ret = 0; - struct perf_evsel *pos; + struct evsel *pos; const char *group_name = perf_evsel__group_name(evsel); if (!evsel->forced_leader) @@ -675,12 +686,12 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } -static void __perf_evsel__config_callchain(struct perf_evsel *evsel, +static void __perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { bool function = perf_evsel__is_function_event(evsel); - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); @@ -734,7 +745,7 @@ static void __perf_evsel__config_callchain(struct perf_evsel *evsel, } } -void perf_evsel__config_callchain(struct perf_evsel *evsel, +void perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { @@ -743,10 +754,10 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel, } static void -perf_evsel__reset_callgraph(struct perf_evsel *evsel, +perf_evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); if (param->record_mode == CALLCHAIN_LBR) { @@ -760,12 +771,12 @@ perf_evsel__reset_callgraph(struct perf_evsel *evsel, } } -static void apply_config_terms(struct perf_evsel *evsel, +static void apply_config_terms(struct evsel *evsel, struct record_opts *opts, bool track) { struct perf_evsel_config_term *term; struct list_head *config_terms = &evsel->config_terms; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; /* callgraph default */ struct callchain_param param = { .record_mode = callchain_param.record_mode, @@ -797,12 +808,12 @@ static void apply_config_terms(struct perf_evsel *evsel, perf_evsel__reset_sample_bit(evsel, TIME); break; case PERF_EVSEL__CONFIG_TERM_CALLGRAPH: - callgraph_buf = term->val.callgraph; + callgraph_buf = term->val.str; break; case PERF_EVSEL__CONFIG_TERM_BRANCH: - if (term->val.branch && strcmp(term->val.branch, "no")) { + if (term->val.str && strcmp(term->val.str, "no")) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); - parse_branch_str(term->val.branch, + parse_branch_str(term->val.str, &attr->branch_sample_type); } else perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); @@ -832,6 +843,14 @@ static void apply_config_terms(struct perf_evsel *evsel, break; case PERF_EVSEL__CONFIG_TERM_PERCORE: break; + case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT: + attr->aux_output = term->val.aux_output ? 1 : 0; + break; + case PERF_EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: + /* Already applied by auxtrace */ + break; + case PERF_EVSEL__CONFIG_TERM_CFG_CHG: + break; default: break; } @@ -878,17 +897,30 @@ static void apply_config_terms(struct perf_evsel *evsel, if (sample_address) { perf_evsel__set_sample_bit(evsel, ADDR); perf_evsel__set_sample_bit(evsel, DATA_SRC); - evsel->attr.mmap_data = track; + evsel->core.attr.mmap_data = track; } perf_evsel__config_callchain(evsel, opts, ¶m); } } } -static bool is_dummy_event(struct perf_evsel *evsel) +static bool is_dummy_event(struct evsel *evsel) +{ + return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && + (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); +} + +struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel, + enum evsel_term_type type) { - return (evsel->attr.type == PERF_TYPE_SOFTWARE) && - (evsel->attr.config == PERF_COUNT_SW_DUMMY); + struct perf_evsel_config_term *term, *found_term = NULL; + + list_for_each_entry(term, &evsel->config_terms, list) { + if (term->type == type) + found_term = term; + } + + return found_term; } /* @@ -919,11 +951,11 @@ static bool is_dummy_event(struct perf_evsel *evsel) * enable/disable events specifically, as there's no * initial traced exec call. */ -void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, +void perf_evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain) { - struct perf_evsel *leader = evsel->leader; - struct perf_event_attr *attr = &evsel->attr; + struct evsel *leader = evsel->leader; + struct perf_event_attr *attr = &evsel->core.attr; int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; @@ -947,7 +979,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * Apply group format only if we belong to group * with more than one members. */ - if (leader->nr_members > 1) { + if (leader->core.nr_members > 1) { attr->read_format |= PERF_FORMAT_GROUP; attr->inherit = 0; } @@ -984,14 +1016,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * event to follow the master sample_type to ease up * report. */ - attr->sample_type = leader->attr.sample_type; + attr->sample_type = leader->core.attr.sample_type; } if (opts->no_samples) attr->sample_freq = 0; if (opts->inherit_stat) { - evsel->attr.read_format |= + evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | PERF_FORMAT_ID; @@ -1009,7 +1041,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * fault handler and its overall trickiness nature. */ if (perf_evsel__is_function_event(evsel)) - evsel->attr.exclude_callchain_user = 1; + evsel->core.attr.exclude_callchain_user = 1; if (callchain && callchain->enabled && !evsel->no_aux_samples) perf_evsel__config_callchain(evsel, opts, callchain); @@ -1065,8 +1097,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; attr->ksymbol = track && !perf_missing_features.ksymbol; - attr->bpf_event = track && !opts->no_bpf_event && - !perf_missing_features.bpf_event; + attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf; if (opts->record_namespaces) attr->namespaces = track; @@ -1078,7 +1109,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__set_sample_bit(evsel, TRANSACTION); if (opts->running_time) { - evsel->attr.read_format |= + evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; } @@ -1124,8 +1155,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } - if (evsel->own_cpus || evsel->unit) - evsel->attr.read_format |= PERF_FORMAT_ID; + if (evsel->core.own_cpus || evsel->unit) + evsel->core.attr.read_format |= PERF_FORMAT_ID; /* * Apply event specific term settings, @@ -1152,48 +1183,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } -static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) -{ - evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); - - if (evsel->fd) { - int cpu, thread; - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { - FD(evsel, cpu, thread) = -1; - } - } - } - - return evsel->fd != NULL ? 0 : -ENOMEM; -} - -static int perf_evsel__run_ioctl(struct perf_evsel *evsel, - int ioc, void *arg) -{ - int cpu, 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); - - if (err) - return err; - } - } - - return 0; -} - -int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) -{ - return perf_evsel__run_ioctl(evsel, - PERF_EVENT_IOC_SET_FILTER, - (void *)filter); -} - -int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__set_filter(struct evsel *evsel, const char *filter) { char *new_filter = strdup(filter); @@ -1206,7 +1196,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) return -1; } -static int perf_evsel__append_filter(struct perf_evsel *evsel, +static int perf_evsel__append_filter(struct evsel *evsel, const char *fmt, const char *filter) { char *new_filter; @@ -1223,29 +1213,40 @@ static int perf_evsel__append_filter(struct perf_evsel *evsel, return -1; } -int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter) { return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter); } -int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter) { return perf_evsel__append_filter(evsel, "%s,%s", filter); } -int perf_evsel__enable(struct perf_evsel *evsel) +/* Caller has to clear disabled after going through all CPUs. */ +int evsel__enable_cpu(struct evsel *evsel, int cpu) { - int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); + return perf_evsel__enable_cpu(&evsel->core, cpu); +} + +int evsel__enable(struct evsel *evsel) +{ + int err = perf_evsel__enable(&evsel->core); if (!err) evsel->disabled = false; - return err; } -int perf_evsel__disable(struct perf_evsel *evsel) +/* Caller has to set disabled after going through all CPUs. */ +int evsel__disable_cpu(struct evsel *evsel, int cpu) { - int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); + return perf_evsel__disable_cpu(&evsel->core, cpu); +} + +int evsel__disable(struct evsel *evsel) +{ + int err = perf_evsel__disable(&evsel->core); /* * We mark it disabled here so that tools that disable a event can * ignore events after they disable it. I.e. the ring buffer may have @@ -1258,87 +1259,42 @@ int perf_evsel__disable(struct perf_evsel *evsel) return err; } -int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) -{ - if (ncpus == 0 || nthreads == 0) - return 0; - - if (evsel->system_wide) - nthreads = 1; - - evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); - if (evsel->sample_id == NULL) - return -ENOMEM; - - evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); - if (evsel->id == NULL) { - xyarray__delete(evsel->sample_id); - evsel->sample_id = NULL; - return -ENOMEM; - } - - return 0; -} - -static void perf_evsel__free_fd(struct perf_evsel *evsel) -{ - xyarray__delete(evsel->fd); - evsel->fd = NULL; -} - -static void perf_evsel__free_id(struct perf_evsel *evsel) -{ - xyarray__delete(evsel->sample_id); - evsel->sample_id = NULL; - zfree(&evsel->id); - evsel->ids = 0; -} - -static void perf_evsel__free_config_terms(struct perf_evsel *evsel) +static void perf_evsel__free_config_terms(struct evsel *evsel) { struct perf_evsel_config_term *term, *h; list_for_each_entry_safe(term, h, &evsel->config_terms, list) { list_del_init(&term->list); + if (term->free_str) + zfree(&term->val.str); free(term); } } -void perf_evsel__close_fd(struct perf_evsel *evsel) +void perf_evsel__exit(struct evsel *evsel) { - int cpu, 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; - } -} - -void perf_evsel__exit(struct perf_evsel *evsel) -{ - assert(list_empty(&evsel->node)); + assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); perf_evsel__free_counts(evsel); - perf_evsel__free_fd(evsel); - perf_evsel__free_id(evsel); + perf_evsel__free_fd(&evsel->core); + perf_evsel__free_id(&evsel->core); perf_evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); - cpu_map__put(evsel->cpus); - cpu_map__put(evsel->own_cpus); - thread_map__put(evsel->threads); + perf_cpu_map__put(evsel->core.cpus); + perf_cpu_map__put(evsel->core.own_cpus); + perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); perf_evsel__object.fini(evsel); } -void perf_evsel__delete(struct perf_evsel *evsel) +void evsel__delete(struct evsel *evsel) { perf_evsel__exit(evsel); free(evsel); } -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, +void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -1378,57 +1334,16 @@ 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->values, size) <= 0) - return -errno; - - return 0; -} - static int -perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread) +perf_evsel__read_one(struct 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); + return perf_evsel__read(&evsel->core, cpu, thread, count); } static void -perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, +perf_evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) { struct perf_counts_values *count; @@ -1438,20 +1353,21 @@ perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, count->val = val; count->ena = ena; count->run = run; - count->loaded = true; + + perf_counts__set_loaded(counter->counts, cpu, thread, true); } static int -perf_evsel__process_group_data(struct perf_evsel *leader, +perf_evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) { - u64 read_format = leader->attr.read_format; + u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; u64 nr, ena = 0, run = 0, i; nr = *data++; - if (nr != (u64) leader->nr_members) + if (nr != (u64) leader->core.nr_members) return -EINVAL; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -1466,7 +1382,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader, v[0].value, ena, run); for (i = 1; i < nr; i++) { - struct perf_evsel *counter; + struct evsel *counter; counter = perf_evlist__id2evsel(leader->evlist, v[i].id); if (!counter) @@ -1480,11 +1396,11 @@ perf_evsel__process_group_data(struct perf_evsel *leader, } static int -perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) +perf_evsel__read_group(struct evsel *leader, int cpu, int thread) { struct perf_stat_evsel *ps = leader->stats; - u64 read_format = leader->attr.read_format; - int size = perf_evsel__read_size(leader); + u64 read_format = leader->core.attr.read_format; + int size = perf_evsel__read_size(&leader->core); u64 *data = ps->group_data; if (!(read_format & PERF_FORMAT_ID)) @@ -1510,9 +1426,9 @@ perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) return perf_evsel__process_group_data(leader, cpu, thread, data); } -int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) +int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_GROUP) return perf_evsel__read_group(evsel, cpu, thread); @@ -1520,7 +1436,7 @@ int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) return perf_evsel__read_one(evsel, cpu, thread); } -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, +int __perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale) { struct perf_counts_values count; @@ -1541,9 +1457,9 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, return 0; } -static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) +static int get_group_fd(struct evsel *evsel, int cpu, int thread) { - struct perf_evsel *leader = evsel->leader; + struct evsel *leader = evsel->leader; int fd; if (perf_evsel__is_group_leader(evsel)) @@ -1553,7 +1469,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) * Leader must be already processed/open, * if not it's a bug. */ - BUG_ON(!leader->fd); + BUG_ON(!leader->core.fd); fd = FD(leader, cpu, thread); BUG_ON(fd == -1); @@ -1561,152 +1477,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) return fd; } -struct bit_names { - int bit; - const char *name; -}; - -static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) -{ - bool first_bit = true; - int i = 0; - - do { - if (value & bits[i].bit) { - buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); - first_bit = false; - } - } while (bits[++i].name != NULL); -} - -static void __p_sample_type(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_SAMPLE_##n, #n } - struct bit_names bits[] = { - bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), - bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), - bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), - bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), - bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), - bit_name(WEIGHT), bit_name(PHYS_ADDR), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -static void __p_branch_sample_type(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n } - struct bit_names bits[] = { - bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY), - bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL), - bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), - bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), - bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -static void __p_read_format(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_FORMAT_##n, #n } - struct bit_names bits[] = { - bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), - bit_name(ID), bit_name(GROUP), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -#define BUF_SIZE 1024 - -#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val)) -#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) -#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) -#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) -#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) -#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) - -#define PRINT_ATTRn(_n, _f, _p) \ -do { \ - if (attr->_f) { \ - _p(attr->_f); \ - ret += attr__fprintf(fp, _n, buf, priv);\ - } \ -} while (0) - -#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) - -int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, - attr__fprintf_f attr__fprintf, void *priv) -{ - char buf[BUF_SIZE]; - int ret = 0; - - PRINT_ATTRf(type, p_unsigned); - PRINT_ATTRf(size, p_unsigned); - PRINT_ATTRf(config, p_hex); - PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); - PRINT_ATTRf(sample_type, p_sample_type); - PRINT_ATTRf(read_format, p_read_format); - - PRINT_ATTRf(disabled, p_unsigned); - PRINT_ATTRf(inherit, p_unsigned); - PRINT_ATTRf(pinned, p_unsigned); - PRINT_ATTRf(exclusive, p_unsigned); - PRINT_ATTRf(exclude_user, p_unsigned); - PRINT_ATTRf(exclude_kernel, p_unsigned); - PRINT_ATTRf(exclude_hv, p_unsigned); - PRINT_ATTRf(exclude_idle, p_unsigned); - PRINT_ATTRf(mmap, p_unsigned); - PRINT_ATTRf(comm, p_unsigned); - PRINT_ATTRf(freq, p_unsigned); - PRINT_ATTRf(inherit_stat, p_unsigned); - PRINT_ATTRf(enable_on_exec, p_unsigned); - PRINT_ATTRf(task, p_unsigned); - PRINT_ATTRf(watermark, p_unsigned); - PRINT_ATTRf(precise_ip, p_unsigned); - PRINT_ATTRf(mmap_data, p_unsigned); - PRINT_ATTRf(sample_id_all, p_unsigned); - PRINT_ATTRf(exclude_host, p_unsigned); - PRINT_ATTRf(exclude_guest, p_unsigned); - PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); - PRINT_ATTRf(exclude_callchain_user, p_unsigned); - PRINT_ATTRf(mmap2, p_unsigned); - PRINT_ATTRf(comm_exec, p_unsigned); - PRINT_ATTRf(use_clockid, p_unsigned); - PRINT_ATTRf(context_switch, p_unsigned); - PRINT_ATTRf(write_backward, p_unsigned); - PRINT_ATTRf(namespaces, p_unsigned); - PRINT_ATTRf(ksymbol, p_unsigned); - PRINT_ATTRf(bpf_event, p_unsigned); - - PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); - PRINT_ATTRf(bp_type, p_unsigned); - PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); - PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); - PRINT_ATTRf(branch_sample_type, p_branch_sample_type); - PRINT_ATTRf(sample_regs_user, p_hex); - PRINT_ATTRf(sample_stack_user, p_unsigned); - PRINT_ATTRf(clockid, p_signed); - PRINT_ATTRf(sample_regs_intr, p_hex); - PRINT_ATTRf(aux_watermark, p_unsigned); - PRINT_ATTRf(sample_max_stack, p_unsigned); - - return ret; -} - -static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __maybe_unused) -{ - return fprintf(fp, " %-32s %s\n", name, val); -} - -static void perf_evsel__remove_fd(struct perf_evsel *pos, +static void perf_evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) { @@ -1715,11 +1486,11 @@ static void perf_evsel__remove_fd(struct perf_evsel *pos, FD(pos, cpu, thread) = FD(pos, cpu, thread + 1); } -static int update_fds(struct perf_evsel *evsel, +static int update_fds(struct evsel *evsel, int nr_cpus, int cpu_idx, int nr_threads, int thread_idx) { - struct perf_evsel *pos; + struct evsel *pos; if (cpu_idx >= nr_cpus || thread_idx >= nr_threads) return -EINVAL; @@ -1739,18 +1510,18 @@ static int update_fds(struct perf_evsel *evsel, return 0; } -static bool ignore_missing_thread(struct perf_evsel *evsel, +static bool ignore_missing_thread(struct evsel *evsel, int nr_cpus, int cpu, - struct thread_map *threads, + struct perf_thread_map *threads, int thread, int err) { - pid_t ignore_pid = thread_map__pid(threads, thread); + pid_t ignore_pid = perf_thread_map__pid(threads, thread); if (!evsel->ignore_missing_thread) return false; /* The system wide setup does not work with threads. */ - if (evsel->system_wide) + if (evsel->core.system_wide) return false; /* The -ESRCH is perf event syscall errno for pid's not found. */ @@ -1776,9 +1547,15 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } +static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __maybe_unused) +{ + return fprintf(fp, " %-32s %s\n", name, val); +} + static void display_attr(struct perf_event_attr *attr) { - if (verbose >= 2) { + if (verbose >= 2 || debug_peo_args) { fprintf(stderr, "%.60s\n", graph_dotted_line); fprintf(stderr, "perf_event_attr:\n"); perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); @@ -1786,18 +1563,18 @@ static void display_attr(struct perf_event_attr *attr) } } -static int perf_event_open(struct perf_evsel *evsel, +static int perf_event_open(struct evsel *evsel, pid_t pid, int cpu, int group_fd, unsigned long flags) { - int precise_ip = evsel->attr.precise_ip; + int precise_ip = evsel->core.attr.precise_ip; int fd; while (1) { - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", + pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpu, group_fd, flags); - fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, group_fd, flags); if (fd >= 0) break; @@ -1809,36 +1586,38 @@ static int perf_event_open(struct perf_evsel *evsel, * We tried all the precise_ip values, and it's * still failing, so leave it to standard fallback. */ - if (!evsel->attr.precise_ip) { - evsel->attr.precise_ip = precise_ip; + if (!evsel->core.attr.precise_ip) { + evsel->core.attr.precise_ip = precise_ip; break; } - pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); - evsel->attr.precise_ip--; - pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip); - display_attr(&evsel->attr); + pr_debug2_peo("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); + evsel->core.attr.precise_ip--; + pr_debug2_peo("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip); + display_attr(&evsel->core.attr); } return fd; } -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) +static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads, + int start_cpu, int end_cpu) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; - int pid = -1, err; + int pid = -1, err, old_errno; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; - if (perf_missing_features.write_backward && evsel->attr.write_backward) + if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) || + (perf_missing_features.aux_output && evsel->core.attr.aux_output)) return -EINVAL; if (cpus == NULL) { - static struct cpu_map *empty_cpu_map; + static struct perf_cpu_map *empty_cpu_map; if (empty_cpu_map == NULL) { - empty_cpu_map = cpu_map__dummy_new(); + empty_cpu_map = perf_cpu_map__dummy_new(); if (empty_cpu_map == NULL) return -ENOMEM; } @@ -1847,7 +1626,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } if (threads == NULL) { - static struct thread_map *empty_thread_map; + static struct perf_thread_map *empty_thread_map; if (empty_thread_map == NULL) { empty_thread_map = thread_map__new_by_tid(-1); @@ -1858,13 +1637,13 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, threads = empty_thread_map; } - if (evsel->system_wide) + if (evsel->core.system_wide) nthreads = 1; else nthreads = threads->nr; - if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0) + if (evsel->core.fd == NULL && + perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0) return -ENOMEM; if (evsel->cgrp) { @@ -1874,39 +1653,39 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, fallback_missing_features: if (perf_missing_features.clockid_wrong) - evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */ + evsel->core.attr.clockid = CLOCK_MONOTONIC; /* should always work */ if (perf_missing_features.clockid) { - evsel->attr.use_clockid = 0; - evsel->attr.clockid = 0; + evsel->core.attr.use_clockid = 0; + evsel->core.attr.clockid = 0; } if (perf_missing_features.cloexec) flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) - evsel->attr.mmap2 = 0; + evsel->core.attr.mmap2 = 0; if (perf_missing_features.exclude_guest) - evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; + evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0; if (perf_missing_features.lbr_flags) - evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | + evsel->core.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); + if (perf_missing_features.group_read && evsel->core.attr.inherit) + evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); if (perf_missing_features.ksymbol) - evsel->attr.ksymbol = 0; - if (perf_missing_features.bpf_event) - evsel->attr.bpf_event = 0; + evsel->core.attr.ksymbol = 0; + if (perf_missing_features.bpf) + evsel->core.attr.bpf_event = 0; retry_sample_id: if (perf_missing_features.sample_id_all) - evsel->attr.sample_id_all = 0; + evsel->core.attr.sample_id_all = 0; - display_attr(&evsel->attr); + display_attr(&evsel->core.attr); - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = start_cpu; cpu < end_cpu; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; - if (!evsel->cgrp && !evsel->system_wide) - pid = thread_map__pid(threads, thread); + if (!evsel->cgrp && !evsel->core.system_wide) + pid = perf_thread_map__pid(threads, thread); group_fd = get_group_fd(evsel, cpu, thread); retry_open: @@ -1934,12 +1713,12 @@ retry_open: continue; } - pr_debug2("\nsys_perf_event_open failed, error %d\n", + pr_debug2_peo("\nsys_perf_event_open failed, error %d\n", err); goto try_fallback; } - pr_debug2(" = %d\n", fd); + pr_debug2_peo(" = %d\n", fd); if (evsel->bpf_fd >= 0) { int evt_fd = fd; @@ -1980,8 +1759,8 @@ try_fallback: */ if (err == -EMFILE && set_rlimit < INCREASED_MAX) { struct rlimit l; - int old_errno = errno; + old_errno = errno; if (getrlimit(RLIMIT_NOFILE, &l) == 0) { if (set_rlimit == NO_CHANGE) l.rlim_cur = l.rlim_max; @@ -2005,100 +1784,114 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) { - perf_missing_features.bpf_event = true; - pr_debug2("switching off bpf_event\n"); + if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { + perf_missing_features.aux_output = true; + pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) { + perf_missing_features.bpf = true; + pr_debug2_peo("switching off bpf_event\n"); goto fallback_missing_features; - } else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) { + } else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { perf_missing_features.ksymbol = true; - pr_debug2("switching off ksymbol\n"); + pr_debug2_peo("switching off ksymbol\n"); goto fallback_missing_features; - } else if (!perf_missing_features.write_backward && evsel->attr.write_backward) { + } else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { perf_missing_features.write_backward = true; - pr_debug2("switching off write_backward\n"); + pr_debug2_peo("switching off write_backward\n"); goto out_close; - } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { + } else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { perf_missing_features.clockid_wrong = true; - pr_debug2("switching off clockid\n"); + pr_debug2_peo("switching off clockid\n"); goto fallback_missing_features; - } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { + } else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { perf_missing_features.clockid = true; - pr_debug2("switching off use_clockid\n"); + pr_debug2_peo("switching off use_clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { perf_missing_features.cloexec = true; - pr_debug2("switching off cloexec flag\n"); + pr_debug2_peo("switching off cloexec flag\n"); goto fallback_missing_features; - } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + } else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { perf_missing_features.mmap2 = true; - pr_debug2("switching off mmap2\n"); + pr_debug2_peo("switching off mmap2\n"); goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) { perf_missing_features.exclude_guest = true; - pr_debug2("switching off exclude_guest, exclude_host\n"); + pr_debug2_peo("switching off exclude_guest, exclude_host\n"); goto fallback_missing_features; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; - pr_debug2("switching off sample_id_all\n"); + pr_debug2_peo("switching off sample_id_all\n"); goto retry_sample_id; } else if (!perf_missing_features.lbr_flags && - (evsel->attr.branch_sample_type & + (evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; - pr_debug2("switching off branch sample type no (cycles/flags)\n"); + pr_debug2_peo("switching off branch sample type no (cycles/flags)\n"); goto fallback_missing_features; } else if (!perf_missing_features.group_read && - evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP) && + evsel->core.attr.inherit && + (evsel->core.attr.read_format & PERF_FORMAT_GROUP) && perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; - pr_debug2("switching off group read\n"); + pr_debug2_peo("switching off group read\n"); goto fallback_missing_features; } out_close: if (err) threads->err_thread = thread; + old_errno = errno; do { while (--thread >= 0) { - close(FD(evsel, cpu, thread)); + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } thread = nthreads; } while (--cpu >= 0); + errno = old_errno; return err; } -void perf_evsel__close(struct perf_evsel *evsel) +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) { - if (evsel->fd == NULL) - return; + return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1); +} - perf_evsel__close_fd(evsel); - perf_evsel__free_fd(evsel); - perf_evsel__free_id(evsel); +void evsel__close(struct evsel *evsel) +{ + perf_evsel__close(&evsel->core); + perf_evsel__free_id(&evsel->core); } -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus) +int perf_evsel__open_per_cpu(struct evsel *evsel, + struct perf_cpu_map *cpus, + int cpu) { - return perf_evsel__open(evsel, cpus, NULL); + if (cpu == -1) + return evsel__open_cpu(evsel, cpus, NULL, 0, + cpus ? cpus->nr : 1); + + return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); } -int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads) +int perf_evsel__open_per_thread(struct evsel *evsel, + struct perf_thread_map *threads) { - return perf_evsel__open(evsel, NULL, threads); + return evsel__open(evsel, NULL, threads); } -static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, +static int perf_evsel__parse_id_sample(const struct evsel *evsel, const union perf_event *event, struct perf_sample *sample) { - u64 type = evsel->attr.sample_type; - const u64 *array = event->sample.array; + u64 type = evsel->core.attr.sample_type; + const __u64 *array = event->sample.array; bool swapped = evsel->needs_swap; union u64_swap u; @@ -2183,12 +1976,12 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size) return 0; } -int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, +int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; bool swapped = evsel->needs_swap; - const u64 *array; + const __u64 *array; u16 max_size = event->header.size; const void *endp = (void *)event + max_size; u64 sz; @@ -2202,14 +1995,14 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; - data->period = evsel->attr.sample_period; + data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; if (event->header.type != PERF_RECORD_SAMPLE) { - if (!evsel->attr.sample_id_all) + if (!evsel->core.attr.sample_id_all) return 0; return perf_evsel__parse_id_sample(evsel, event, data); } @@ -2282,7 +2075,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_READ) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; OVERFLOW_CHECK_u64(array); if (read_format & PERF_FORMAT_GROUP) @@ -2387,7 +2180,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->user_regs.abi) { - u64 mask = evsel->attr.sample_regs_user; + u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); @@ -2443,7 +2236,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { - u64 mask = evsel->attr.sample_regs_intr; + u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); @@ -2459,15 +2252,28 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } + if (type & PERF_SAMPLE_AUX) { + OVERFLOW_CHECK_u64(array); + sz = *array++; + + OVERFLOW_CHECK(array, sz, max_size); + /* Undo swap of data */ + if (swapped) + mem_bswap_64((char *)array, sz); + data->aux_sample.size = sz; + data->aux_sample.data = (char *)array; + array = (void *)array + sz; + } + return 0; } -int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, +int perf_evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, u64 *timestamp) { - u64 type = evsel->attr.sample_type; - const u64 *array; + u64 type = evsel->core.attr.sample_type; + const __u64 *array; if (!(type & PERF_SAMPLE_TIME)) return -1; @@ -2477,7 +2283,7 @@ int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, .time = -1ULL, }; - if (!evsel->attr.sample_id_all) + if (!evsel->core.attr.sample_id_all) return -1; if (perf_evsel__parse_id_sample(evsel, event, &data)) return -1; @@ -2506,289 +2312,12 @@ int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, return 0; } -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 read_format) -{ - size_t sz, result = sizeof(struct sample_event); - - if (type & PERF_SAMPLE_IDENTIFIER) - result += sizeof(u64); - - if (type & PERF_SAMPLE_IP) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TIME) - result += sizeof(u64); - - if (type & PERF_SAMPLE_ADDR) - result += sizeof(u64); - - if (type & PERF_SAMPLE_ID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_STREAM_ID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_CPU) - result += sizeof(u64); - - if (type & PERF_SAMPLE_PERIOD) - result += sizeof(u64); - - if (type & PERF_SAMPLE_READ) { - result += sizeof(u64); - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - result += sizeof(u64); - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - result += sizeof(u64); - /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ - if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_CALLCHAIN) { - sz = (sample->callchain->nr + 1) * sizeof(u64); - result += sz; - } - - if (type & PERF_SAMPLE_RAW) { - result += sizeof(u32); - result += sample->raw_size; - } - - if (type & PERF_SAMPLE_BRANCH_STACK) { - sz = sample->branch_stack->nr * sizeof(struct branch_entry); - sz += sizeof(u64); - result += sz; - } - - if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - result += sizeof(u64); - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_STACK_USER) { - sz = sample->user_stack.size; - result += sizeof(u64); - if (sz) { - result += sz; - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_WEIGHT) - result += sizeof(u64); - - if (type & PERF_SAMPLE_DATA_SRC) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TRANSACTION) - result += sizeof(u64); - - if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - result += sizeof(u64); - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_PHYS_ADDR) - result += sizeof(u64); - - return result; -} - -int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 read_format, - const struct perf_sample *sample) -{ - u64 *array; - size_t sz; - /* - * used for cross-endian analysis. See git commit 65014ab3 - * for why this goofiness is needed. - */ - union u64_swap u; - - array = event->sample.array; - - if (type & PERF_SAMPLE_IDENTIFIER) { - *array = sample->id; - array++; - } - - if (type & PERF_SAMPLE_IP) { - *array = sample->ip; - array++; - } - - if (type & PERF_SAMPLE_TID) { - u.val32[0] = sample->pid; - u.val32[1] = sample->tid; - *array = u.val64; - array++; - } - - if (type & PERF_SAMPLE_TIME) { - *array = sample->time; - array++; - } - - if (type & PERF_SAMPLE_ADDR) { - *array = sample->addr; - array++; - } - - if (type & PERF_SAMPLE_ID) { - *array = sample->id; - array++; - } - - if (type & PERF_SAMPLE_STREAM_ID) { - *array = sample->stream_id; - array++; - } - - if (type & PERF_SAMPLE_CPU) { - u.val32[0] = sample->cpu; - u.val32[1] = 0; - *array = u.val64; - array++; - } - - if (type & PERF_SAMPLE_PERIOD) { - *array = sample->period; - array++; - } - - if (type & PERF_SAMPLE_READ) { - if (read_format & PERF_FORMAT_GROUP) - *array = sample->read.group.nr; - else - *array = sample->read.one.value; - array++; - - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - *array = sample->read.time_enabled; - array++; - } - - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - *array = sample->read.time_running; - array++; - } - - /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ - if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - memcpy(array, sample->read.group.values, sz); - array = (void *)array + sz; - } else { - *array = sample->read.one.id; - array++; - } - } - - if (type & PERF_SAMPLE_CALLCHAIN) { - sz = (sample->callchain->nr + 1) * sizeof(u64); - memcpy(array, sample->callchain, sz); - array = (void *)array + sz; - } - - if (type & PERF_SAMPLE_RAW) { - u.val32[0] = sample->raw_size; - *array = u.val64; - array = (void *)array + sizeof(u32); - - memcpy(array, sample->raw_data, sample->raw_size); - array = (void *)array + sample->raw_size; - } - - if (type & PERF_SAMPLE_BRANCH_STACK) { - sz = sample->branch_stack->nr * sizeof(struct branch_entry); - sz += sizeof(u64); - memcpy(array, sample->branch_stack, sz); - array = (void *)array + sz; - } - - if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - *array++ = sample->user_regs.abi; - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - memcpy(array, sample->user_regs.regs, sz); - array = (void *)array + sz; - } else { - *array++ = 0; - } - } - - if (type & PERF_SAMPLE_STACK_USER) { - sz = sample->user_stack.size; - *array++ = sz; - if (sz) { - memcpy(array, sample->user_stack.data, sz); - array = (void *)array + sz; - *array++ = sz; - } - } - - if (type & PERF_SAMPLE_WEIGHT) { - *array = sample->weight; - array++; - } - - if (type & PERF_SAMPLE_DATA_SRC) { - *array = sample->data_src; - array++; - } - - if (type & PERF_SAMPLE_TRANSACTION) { - *array = sample->transaction; - array++; - } - - if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - *array++ = sample->intr_regs.abi; - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - memcpy(array, sample->intr_regs.regs, sz); - array = (void *)array + sz; - } else { - *array++ = 0; - } - } - - if (type & PERF_SAMPLE_PHYS_ADDR) { - *array = sample->phys_addr; - array++; - } - - return 0; -} - -struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) +struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name) { return tep_find_field(evsel->tp_format, name); } -void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, +void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = perf_evsel__field(evsel, name); @@ -2846,7 +2375,7 @@ u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sam return 0; } -u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, +u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = perf_evsel__field(evsel, name); @@ -2857,14 +2386,14 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } -bool perf_evsel__fallback(struct perf_evsel *evsel, int err, +bool perf_evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) { int paranoid; if ((err == ENOENT || err == ENXIO || err == ENODEV) && - evsel->attr.type == PERF_TYPE_HARDWARE && - evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + evsel->core.attr.type == PERF_TYPE_HARDWARE && + evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* * If it's cycles then fall back to hrtimer based * cpu-clock-tick sw counter, which is always available even if @@ -2876,12 +2405,12 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, scnprintf(msg, msgsize, "%s", "The cycles event is not supported, trying to fall back to cpu-clock-ticks"); - evsel->attr.type = PERF_TYPE_SOFTWARE; - evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK; + evsel->core.attr.type = PERF_TYPE_SOFTWARE; + evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK; zfree(&evsel->name); return true; - } else if (err == EACCES && !evsel->attr.exclude_kernel && + } else if (err == EACCES && !evsel->core.attr.exclude_kernel && (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; @@ -2898,9 +2427,11 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, if (evsel->name) free(evsel->name); evsel->name = new_name; - scnprintf(msg, msgsize, -"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid); - evsel->attr.exclude_kernel = 1; + scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying " + "to fall back to excluding kernel and hypervisor " + " samples", paranoid); + evsel->core.attr.exclude_kernel = 1; + evsel->core.attr.exclude_hv = 1; return true; } @@ -2944,7 +2475,7 @@ static bool find_process(const char *name) return ret ? false : true; } -int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, +int perf_evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size) { char sbuf[STRERR_BUFSIZE]; @@ -2997,15 +2528,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: - if (evsel->attr.sample_period != 0) + if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", perf_evsel__name(evsel)); - if (evsel->attr.precise_ip) + if (evsel->core.attr.precise_ip) return scnprintf(msg, size, "%s", "\'precise\' request may not be supported. Try removing 'p' modifier."); #if defined(__i386__) || defined(__x86_64__) - if (evsel->attr.type == PERF_TYPE_HARDWARE) + if (evsel->core.attr.type == PERF_TYPE_HARDWARE) return scnprintf(msg, size, "%s", "No hardware sampling interrupt available.\n"); #endif @@ -3017,12 +2548,14 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: - if (evsel->attr.write_backward && perf_missing_features.write_backward) + if (evsel->core.attr.write_backward && perf_missing_features.write_backward) return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) return scnprintf(msg, size, "wrong clockid (%d).", clockid); + if (perf_missing_features.aux_output) + return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); break; default: break; @@ -3035,23 +2568,23 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, perf_evsel__name(evsel)); } -struct perf_env *perf_evsel__env(struct perf_evsel *evsel) +struct perf_env *perf_evsel__env(struct evsel *evsel) { if (evsel && evsel->evlist) return evsel->evlist->env; - return NULL; + return &perf_env; } -static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) { int cpu, thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(evsel->fd); + for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { int fd = FD(evsel, cpu, thread); - if (perf_evlist__id_add_fd(evlist, evsel, + if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread, fd) < 0) return -1; } @@ -3060,12 +2593,12 @@ static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) return 0; } -int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist) { - struct cpu_map *cpus = evsel->cpus; - struct thread_map *threads = evsel->threads; + struct perf_cpu_map *cpus = evsel->core.cpus; + struct perf_thread_map *threads = evsel->core.threads; - if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr)) + if (perf_evsel__alloc_id(&evsel->core, cpus->nr, threads->nr)) return -ENOMEM; return store_evsel_ids(evsel, evlist); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index cad54e8ba522..dc14f4a823cd 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -4,76 +4,19 @@ #include <linux/list.h> #include <stdbool.h> -#include <stddef.h> +#include <sys/types.h> #include <linux/perf_event.h> #include <linux/types.h> -#include "xyarray.h" +#include <internal/evsel.h> +#include <perf/evsel.h> #include "symbol_conf.h" -#include "cpumap.h" -#include "counts.h" - -struct perf_evsel; - -/* - * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are - * more than one entry in the evlist. - */ -struct perf_sample_id { - struct hlist_node node; - u64 id; - struct perf_evsel *evsel; - int idx; - int cpu; - pid_t tid; - - /* Holds total ID period value for PERF_SAMPLE_READ processing. */ - u64 period; -}; +#include <internal/cpumap.h> +struct bpf_object; struct cgroup; - -/* - * The 'struct perf_evsel_config_term' is used to pass event - * specific configuration data to perf_evsel__config routine. - * It is allocated within event parsing and attached to - * perf_evsel::config_terms list head. -*/ -enum term_type { - PERF_EVSEL__CONFIG_TERM_PERIOD, - PERF_EVSEL__CONFIG_TERM_FREQ, - PERF_EVSEL__CONFIG_TERM_TIME, - PERF_EVSEL__CONFIG_TERM_CALLGRAPH, - PERF_EVSEL__CONFIG_TERM_STACK_USER, - PERF_EVSEL__CONFIG_TERM_INHERIT, - PERF_EVSEL__CONFIG_TERM_MAX_STACK, - PERF_EVSEL__CONFIG_TERM_MAX_EVENTS, - PERF_EVSEL__CONFIG_TERM_OVERWRITE, - PERF_EVSEL__CONFIG_TERM_DRV_CFG, - PERF_EVSEL__CONFIG_TERM_BRANCH, - PERF_EVSEL__CONFIG_TERM_PERCORE, -}; - -struct perf_evsel_config_term { - struct list_head list; - enum term_type type; - union { - u64 period; - u64 freq; - bool time; - char *callgraph; - char *drv_cfg; - u64 stack_user; - int max_stack; - bool inherit; - bool overwrite; - char *branch; - unsigned long max_events; - bool percore; - } val; - bool weak; -}; - +struct perf_counts; struct perf_stat_evsel; +union perf_event; typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data); @@ -82,34 +25,28 @@ enum perf_tool_event { PERF_TOOL_DURATION_TIME = 1, }; -/** struct perf_evsel - event selector +/** struct evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. - * @node - To insert it into evlist->entries or in other list_heads, say in - * the event parsing routines. + * @core - libperf evsel object * @name - Can be set to retain the original event name passed by the user, * so that when showing results in tools such as 'perf stat', we * show the name used, not some alias. * @id_pos: the position of the event id (PERF_SAMPLE_ID or * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of - * struct sample_event + * struct perf_record_sample * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or * PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all * is used there is an id sample appended to non-sample events * @priv: And what is in its containing unnamed union are tool specific */ -struct perf_evsel { - struct list_head node; - struct perf_evlist *evlist; - struct perf_event_attr attr; +struct evsel { + struct perf_evsel core; + struct evlist *evlist; char *filter; - struct xyarray *fd; - struct xyarray *sample_id; - u64 *id; struct perf_counts *counts; struct perf_counts *prev_raw_counts; int idx; - u32 ids; unsigned long max_events; unsigned long nr_events_printed; char *name; @@ -122,9 +59,6 @@ struct perf_evsel { u64 db_id; struct cgroup *cgrp; void *handler; - struct cpu_map *cpus; - struct cpu_map *own_cpus; - struct thread_map *threads; unsigned int sample_size; int id_pos; int is_pos; @@ -136,7 +70,6 @@ struct perf_evsel { bool disabled; bool no_aux_samples; bool immediate; - bool system_wide; bool tracking; bool per_pkg; bool precise_max; @@ -145,22 +78,27 @@ struct perf_evsel { bool use_uncore_alias; /* parse modifier helper */ int exclude_GH; - int nr_members; int sample_read; unsigned long *per_pkg_mask; - struct perf_evsel *leader; + struct evsel *leader; char *group_name; bool cmdline_group_boundary; struct list_head config_terms; + struct bpf_object *bpf_obj; int bpf_fd; + int err; bool auto_merge_stats; bool merged_stat; const char * metric_expr; const char * metric_name; - struct perf_evsel **metric_events; + struct evsel **metric_events; + struct evsel *metric_leader; bool collect_stat; bool weak_group; + bool reset_group; + bool errored; bool percore; + int cpu_iter; const char *pmu_name; struct { perf_evsel__sb_cb_t *cb; @@ -168,11 +106,6 @@ struct perf_evsel { } side_band; }; -union u64_swap { - u64 val64; - u32 val32[2]; -}; - struct perf_missing_features { bool sample_id_all; bool exclude_guest; @@ -184,73 +117,73 @@ struct perf_missing_features { bool write_backward; bool group_read; bool ksymbol; - bool bpf_event; + bool bpf; + bool aux_output; }; extern struct perf_missing_features perf_missing_features; -struct cpu_map; +struct perf_cpu_map; struct target; struct thread_map; struct record_opts; -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel) { - return evsel->cpus; + return perf_evsel__cpus(&evsel->core); } -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +static inline int perf_evsel__nr_cpus(struct evsel *evsel) { - return perf_evsel__cpus(evsel)->nr; + return evsel__cpus(evsel)->nr; } void perf_counts_values__scale(struct perf_counts_values *count, bool scale, s8 *pscaled); -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, +void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count); int perf_evsel__object_config(size_t object_size, - int (*init)(struct perf_evsel *evsel), - void (*fini)(struct perf_evsel *evsel)); + int (*init)(struct evsel *evsel), + void (*fini)(struct evsel *evsel)); -struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); +struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); -static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) +static inline struct evsel *evsel__new(struct perf_event_attr *attr) { return perf_evsel__new_idx(attr, 0); } -struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx); +struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx); /* * Returns pointer with encoded error via <linux/err.h> interface. */ -static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name) +static inline struct evsel *perf_evsel__newtp(const char *sys, const char *name) { return perf_evsel__newtp_idx(sys, name, 0); } -struct perf_evsel *perf_evsel__new_cycles(bool precise); +struct evsel *perf_evsel__new_cycles(bool precise); struct tep_event *event_format__new(const char *sys, const char *name); -void perf_evsel__init(struct perf_evsel *evsel, - struct perf_event_attr *attr, int idx); -void perf_evsel__exit(struct perf_evsel *evsel); -void perf_evsel__delete(struct perf_evsel *evsel); +void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); +void perf_evsel__exit(struct evsel *evsel); +void evsel__delete(struct evsel *evsel); struct callchain_param; -void perf_evsel__config(struct perf_evsel *evsel, +void perf_evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain); -void perf_evsel__config_callchain(struct perf_evsel *evsel, +void perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain); int __perf_evsel__sample_size(u64 sample_type); -void perf_evsel__calc_id_pos(struct perf_evsel *evsel); +void perf_evsel__calc_id_pos(struct evsel *evsel); bool perf_evsel__is_cache_op_valid(u8 type, u8 op); @@ -266,17 +199,14 @@ extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX]; extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); -const char *perf_evsel__name(struct perf_evsel *evsel); +const char *perf_evsel__name(struct evsel *evsel); -const char *perf_evsel__group_name(struct perf_evsel *evsel); -int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); +const char *perf_evsel__group_name(struct evsel *evsel); +int perf_evsel__group_desc(struct 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); - -void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit); -void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit); #define perf_evsel__set_sample_bit(evsel, bit) \ @@ -285,33 +215,35 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, #define perf_evsel__reset_sample_bit(evsel, bit) \ __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) -void perf_evsel__set_sample_id(struct perf_evsel *evsel, +void perf_evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier); -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, +int perf_evsel__set_filter(struct evsel *evsel, const char *filter); +int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter); +int perf_evsel__append_addr_filter(struct evsel *evsel, 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); - -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus); -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 evsel__enable_cpu(struct evsel *evsel, int cpu); +int evsel__enable(struct evsel *evsel); +int evsel__disable(struct evsel *evsel); +int evsel__disable_cpu(struct evsel *evsel, int cpu); + +int perf_evsel__open_per_cpu(struct evsel *evsel, + struct perf_cpu_map *cpus, + int cpu); +int perf_evsel__open_per_thread(struct evsel *evsel, + struct perf_thread_map *threads); +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +void evsel__close(struct evsel *evsel); struct perf_sample; -void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, +void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name); -u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, +u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name); -static inline char *perf_evsel__strval(struct perf_evsel *evsel, +static inline char *perf_evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name) { @@ -322,31 +254,28 @@ struct tep_format_field; u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap); -struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); +struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name); #define perf_evsel__match(evsel, t, c) \ - (evsel->attr.type == PERF_TYPE_##t && \ - evsel->attr.config == PERF_COUNT_##c) + (evsel->core.attr.type == PERF_TYPE_##t && \ + evsel->core.attr.config == PERF_COUNT_##c) -static inline bool perf_evsel__match2(struct perf_evsel *e1, - struct perf_evsel *e2) +static inline bool perf_evsel__match2(struct evsel *e1, + struct evsel *e2) { - return (e1->attr.type == e2->attr.type) && - (e1->attr.config == e2->attr.config); + return (e1->core.attr.type == e2->core.attr.type) && + (e1->core.attr.config == e2->core.attr.config); } #define perf_evsel__cmp(a, b) \ ((a) && \ (b) && \ - (a)->attr.type == (b)->attr.type && \ - (a)->attr.config == (b)->attr.config) - -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, - struct perf_counts_values *count); + (a)->core.attr.type == (b)->core.attr.type && \ + (a)->core.attr.config == (b)->core.attr.config) -int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread); +int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread); -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, +int __perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale); /** @@ -356,7 +285,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, * @cpu - CPU of interest * @thread - thread of interest */ -static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, +static inline int perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread) { return __perf_evsel__read_on_cpu(evsel, cpu, thread, false); @@ -369,27 +298,27 @@ static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, * @cpu - CPU of interest * @thread - thread of interest */ -static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel, +static inline int perf_evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread) { return __perf_evsel__read_on_cpu(evsel, cpu, thread, true); } -int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, +int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample); -int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, +int perf_evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, u64 *timestamp); -static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) +static inline struct evsel *perf_evsel__next(struct evsel *evsel) { - return list_entry(evsel->node.next, struct perf_evsel, node); + return list_entry(evsel->core.node.next, struct evsel, core.node); } -static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel) +static inline struct evsel *perf_evsel__prev(struct evsel *evsel) { - return list_entry(evsel->node.prev, struct perf_evsel, node); + return list_entry(evsel->core.node.prev, struct evsel, core.node); } /** @@ -399,7 +328,7 @@ static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel) * * Return %true if @evsel is a group leader or a stand-alone event */ -static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) +static inline bool perf_evsel__is_group_leader(const struct evsel *evsel) { return evsel->leader == evsel; } @@ -412,96 +341,60 @@ static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) * Return %true iff event group view is enabled and @evsel is a actual group * leader which has other members in the group */ -static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) +static inline bool perf_evsel__is_group_event(struct evsel *evsel) { if (!symbol_conf.event_group) return false; - return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; + return perf_evsel__is_group_leader(evsel) && evsel->core.nr_members > 1; } -bool perf_evsel__is_function_event(struct perf_evsel *evsel); +bool perf_evsel__is_function_event(struct evsel *evsel); -static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) +static inline bool perf_evsel__is_bpf_output(struct evsel *evsel) { return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); } -static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +static inline bool perf_evsel__is_clock(struct evsel *evsel) { return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } -struct perf_attr_details { - bool freq; - bool verbose; - bool event_group; - bool force; - bool trace_fields; -}; - -int perf_evsel__fprintf(struct perf_evsel *evsel, - struct perf_attr_details *details, FILE *fp); - -#define EVSEL__PRINT_IP (1<<0) -#define EVSEL__PRINT_SYM (1<<1) -#define EVSEL__PRINT_DSO (1<<2) -#define EVSEL__PRINT_SYMOFFSET (1<<3) -#define EVSEL__PRINT_ONELINE (1<<4) -#define EVSEL__PRINT_SRCLINE (1<<5) -#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) -#define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) -#define EVSEL__PRINT_SKIP_IGNORED (1<<8) - -struct callchain_cursor; - -int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, - unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp); - -int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, - int left_alignment, unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp); - -bool perf_evsel__fallback(struct perf_evsel *evsel, int err, +bool perf_evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize); -int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, +int perf_evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size); -static inline int perf_evsel__group_idx(struct perf_evsel *evsel) +static inline int perf_evsel__group_idx(struct evsel *evsel) { return evsel->idx - evsel->leader->idx; } /* Iterates group WITHOUT the leader. */ #define for_each_group_member(_evsel, _leader) \ -for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ +for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \ (_evsel) && (_evsel)->leader == (_leader); \ - (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) /* Iterates group WITH the leader. */ #define for_each_group_evsel(_evsel, _leader) \ for ((_evsel) = _leader; \ (_evsel) && (_evsel)->leader == (_leader); \ - (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) -static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel) +static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel) { - return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; + return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } -static inline bool evsel__has_callchain(const struct perf_evsel *evsel) +static inline bool evsel__has_callchain(const struct evsel *evsel) { - return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; + return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; } -typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); - -int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, - attr__fprintf_f attr__fprintf, void *priv); - -struct perf_env *perf_evsel__env(struct perf_evsel *evsel); +struct perf_env *perf_evsel__env(struct evsel *evsel); -int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist); +int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h new file mode 100644 index 000000000000..e026ab67b008 --- /dev/null +++ b/tools/perf/util/evsel_config.h @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __PERF_EVSEL_CONFIG_H +#define __PERF_EVSEL_CONFIG_H 1 + +#include <linux/types.h> +#include <stdbool.h> + +/* + * The 'struct perf_evsel_config_term' is used to pass event + * specific configuration data to perf_evsel__config routine. + * It is allocated within event parsing and attached to + * perf_evsel::config_terms list head. +*/ +enum evsel_term_type { + PERF_EVSEL__CONFIG_TERM_PERIOD, + PERF_EVSEL__CONFIG_TERM_FREQ, + PERF_EVSEL__CONFIG_TERM_TIME, + PERF_EVSEL__CONFIG_TERM_CALLGRAPH, + PERF_EVSEL__CONFIG_TERM_STACK_USER, + PERF_EVSEL__CONFIG_TERM_INHERIT, + PERF_EVSEL__CONFIG_TERM_MAX_STACK, + PERF_EVSEL__CONFIG_TERM_MAX_EVENTS, + PERF_EVSEL__CONFIG_TERM_OVERWRITE, + PERF_EVSEL__CONFIG_TERM_DRV_CFG, + PERF_EVSEL__CONFIG_TERM_BRANCH, + PERF_EVSEL__CONFIG_TERM_PERCORE, + PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT, + PERF_EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, + PERF_EVSEL__CONFIG_TERM_CFG_CHG, +}; + +struct perf_evsel_config_term { + struct list_head list; + enum evsel_term_type type; + bool free_str; + union { + u64 period; + u64 freq; + bool time; + u64 stack_user; + int max_stack; + bool inherit; + bool overwrite; + unsigned long max_events; + bool percore; + bool aux_output; + u32 aux_sample_size; + u64 cfg_chg; + char *str; + } val; + bool weak; +}; + +struct evsel; + +struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel, + enum evsel_term_type type); + +#define perf_evsel__get_config_term(evsel, type) \ + __perf_evsel__get_config_term(evsel, PERF_EVSEL__CONFIG_TERM_ ## type) + +#endif // __PERF_EVSEL_CONFIG_H diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 95ea147f9e18..3b4842840db0 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -4,6 +4,8 @@ #include <stdbool.h> #include <traceevent/event-parse.h> #include "evsel.h" +#include "util/evsel_fprintf.h" +#include "util/event.h" #include "callchain.h" #include "map.h" #include "strlist.h" @@ -33,26 +35,26 @@ static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, vo return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); } -int perf_evsel__fprintf(struct perf_evsel *evsel, +int perf_evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE *fp) { bool first = true; int printed = 0; if (details->event_group) { - struct perf_evsel *pos; + struct evsel *pos; if (!perf_evsel__is_group_leader(evsel)) return 0; - if (evsel->nr_members > 1) + if (evsel->core.nr_members > 1) printed += fprintf(fp, "%s{", evsel->group_name ?: ""); printed += fprintf(fp, "%s", perf_evsel__name(evsel)); for_each_group_member(pos, evsel) printed += fprintf(fp, ",%s", perf_evsel__name(pos)); - if (evsel->nr_members > 1) + if (evsel->core.nr_members > 1) printed += fprintf(fp, "}"); goto out; } @@ -60,22 +62,22 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += fprintf(fp, "%s", perf_evsel__name(evsel)); if (details->verbose) { - printed += perf_event_attr__fprintf(fp, &evsel->attr, + printed += perf_event_attr__fprintf(fp, &evsel->core.attr, __print_attr__fprintf, &first); } else if (details->freq) { const char *term = "sample_freq"; - if (!evsel->attr.freq) + if (!evsel->core.attr.freq) term = "sample_period"; printed += comma_fprintf(fp, &first, " %s=%" PRIu64, - term, (u64)evsel->attr.sample_freq); + term, (u64)evsel->core.attr.sample_freq); } if (details->trace_fields) { struct tep_format_field *field; - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { printed += comma_fprintf(fp, &first, " (not a tracepoint)"); goto out; } @@ -101,7 +103,7 @@ out: int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, unsigned int print_opts, struct callchain_cursor *cursor, - FILE *fp) + struct strlist *bt_stop_list, FILE *fp) { int printed = 0; struct callchain_cursor_node *node; @@ -123,13 +125,18 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, callchain_cursor_commit(cursor); while (1) { + struct symbol *sym; + struct map *map; u64 addr = 0; node = callchain_cursor_current(cursor); if (!node) break; - if (node->sym && node->sym->ignore && print_skip_ignored) + sym = node->ms.sym; + map = node->ms.map; + + if (sym && sym->ignore && print_skip_ignored) goto next; printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); @@ -140,44 +147,42 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_ip) printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); - if (node->map) - addr = node->map->map_ip(node->map, node->ip); + if (map) + addr = map->map_ip(map, node->ip); if (print_sym) { printed += fprintf(fp, " "); node_al.addr = addr; - node_al.map = node->map; + node_al.map = map; if (print_symoffset) { - printed += __symbol__fprintf_symname_offs(node->sym, &node_al, + printed += __symbol__fprintf_symname_offs(sym, &node_al, print_unknown_as_addr, true, fp); } else { - printed += __symbol__fprintf_symname(node->sym, &node_al, + printed += __symbol__fprintf_symname(sym, &node_al, print_unknown_as_addr, fp); } } - if (print_dso && (!node->sym || !node->sym->inlined)) { + if (print_dso && (!sym || !sym->inlined)) { printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(node->map, fp); + printed += map__fprintf_dsoname(map, fp); printed += fprintf(fp, ")"); } if (print_srcline) - printed += map__fprintf_srcline(node->map, addr, "\n ", fp); + printed += map__fprintf_srcline(map, addr, "\n ", fp); - if (node->sym && node->sym->inlined) + if (sym && sym->inlined) printed += fprintf(fp, " (inlined)"); if (!print_oneline) printed += fprintf(fp, "\n"); /* Add srccode here too? */ - if (symbol_conf.bt_stop_list && - node->sym && - strlist__has_entry(symbol_conf.bt_stop_list, - node->sym->name)) { + if (bt_stop_list && sym && + strlist__has_entry(bt_stop_list, sym->name)) { break; } @@ -192,7 +197,7 @@ next: int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int left_alignment, unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp) + struct callchain_cursor *cursor, struct strlist *bt_stop_list, FILE *fp) { int printed = 0; int print_ip = print_opts & EVSEL__PRINT_IP; @@ -203,8 +208,8 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; if (cursor != NULL) { - printed += sample__fprintf_callchain(sample, left_alignment, - print_opts, cursor, fp); + printed += sample__fprintf_callchain(sample, left_alignment, print_opts, + cursor, bt_stop_list, fp); } else { printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); diff --git a/tools/perf/util/evsel_fprintf.h b/tools/perf/util/evsel_fprintf.h new file mode 100644 index 000000000000..47e6c8456bb1 --- /dev/null +++ b/tools/perf/util/evsel_fprintf.h @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __PERF_EVSEL_FPRINTF_H +#define __PERF_EVSEL_FPRINTF_H 1 + +#include <stdio.h> +#include <stdbool.h> + +struct evsel; + +struct perf_attr_details { + bool freq; + bool verbose; + bool event_group; + bool force; + bool trace_fields; +}; + +int perf_evsel__fprintf(struct evsel *evsel, + struct perf_attr_details *details, FILE *fp); + +#define EVSEL__PRINT_IP (1<<0) +#define EVSEL__PRINT_SYM (1<<1) +#define EVSEL__PRINT_DSO (1<<2) +#define EVSEL__PRINT_SYMOFFSET (1<<3) +#define EVSEL__PRINT_ONELINE (1<<4) +#define EVSEL__PRINT_SRCLINE (1<<5) +#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) +#define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) +#define EVSEL__PRINT_SKIP_IGNORED (1<<8) + +struct addr_location; +struct perf_event_attr; +struct perf_sample; +struct callchain_cursor; +struct strlist; + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, struct callchain_cursor *cursor, + struct strlist *bt_stop_list, FILE *fp); + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, + struct strlist *bt_stop_list, FILE *fp); + +typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv); +#endif // __PERF_EVSEL_H diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c new file mode 100644 index 000000000000..3ba72f743d3c --- /dev/null +++ b/tools/perf/util/evswitch.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + +#include "evswitch.h" +#include "evlist.h" + +bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel) +{ + if (evswitch->on && evswitch->discarding) { + if (evswitch->on != evsel) + return true; + + evswitch->discarding = false; + + if (!evswitch->show_on_off_events) + return true; + + return false; + } + + if (evswitch->off && !evswitch->discarding) { + if (evswitch->off != evsel) + return false; + + evswitch->discarding = true; + + if (!evswitch->show_on_off_events) + return true; + } + + return false; +} + +static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *evname) +{ + int printed = fprintf(fp, "ERROR: switch-%s event not found (%s)\n", evtype, evname); + + return printed += fprintf(fp, "HINT: use 'perf evlist' to see the available event names\n"); +} + +int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) +{ + if (evswitch->on_name) { + evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name); + if (evswitch->on == NULL) { + evswitch__fprintf_enoent(fp, "on", evswitch->on_name); + return -ENOENT; + } + evswitch->discarding = true; + } + + if (evswitch->off_name) { + evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name); + if (evswitch->off == NULL) { + evswitch__fprintf_enoent(fp, "off", evswitch->off_name); + return -ENOENT; + } + } + + return 0; +} diff --git a/tools/perf/util/evswitch.h b/tools/perf/util/evswitch.h new file mode 100644 index 000000000000..fd30460b6218 --- /dev/null +++ b/tools/perf/util/evswitch.h @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> +#ifndef __PERF_EVSWITCH_H +#define __PERF_EVSWITCH_H 1 + +#include <stdbool.h> +#include <stdio.h> + +struct evsel; +struct evlist; + +struct evswitch { + struct evsel *on, *off; + const char *on_name, *off_name; + bool discarding; + bool show_on_off_events; +}; + +int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp); + +bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel); + +#define OPTS_EVSWITCH(evswitch) \ + OPT_STRING(0, "switch-on", &(evswitch)->on_name, \ + "event", "Consider events after the ocurrence of this event"), \ + OPT_STRING(0, "switch-off", &(evswitch)->off_name, \ + "event", "Stop considering events after the ocurrence of this event"), \ + OPT_BOOLEAN(0, "show-on-off-events", &(evswitch)->show_on_off_events, \ + "Show the on/off switch events, used with --switch-on and --switch-off") + +#endif /* __PERF_EVSWITCH_H */ diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 432b8560cf51..7d226241f1d7 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -2,15 +2,18 @@ %{ #include "util.h" #include "util/debug.h" +#include <stdlib.h> // strtod() #define IN_EXPR_Y 1 #include "expr.h" #include "smt.h" +#include <assert.h> #include <string.h> #define MAXIDLEN 256 %} -%pure-parser +%define api.pure full + %parse-param { double *final_val } %parse-param { struct parse_ctx *ctx } %parse-param { const char **pp } diff --git a/tools/perf/util/fncache.c b/tools/perf/util/fncache.c new file mode 100644 index 000000000000..6225cbc52310 --- /dev/null +++ b/tools/perf/util/fncache.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Manage a cache of file names' existence */ +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <linux/list.h> +#include "fncache.h" + +struct fncache { + struct hlist_node nd; + bool res; + char name[]; +}; + +#define FNHSIZE 61 + +static struct hlist_head fncache_hash[FNHSIZE]; + +unsigned shash(const unsigned char *s) +{ + unsigned h = 0; + while (*s) + h = 65599 * h + *s++; + return h ^ (h >> 16); +} + +static bool lookup_fncache(const char *name, bool *res) +{ + int h = shash((const unsigned char *)name) % FNHSIZE; + struct fncache *n; + + hlist_for_each_entry(n, &fncache_hash[h], nd) { + if (!strcmp(n->name, name)) { + *res = n->res; + return true; + } + } + return false; +} + +static void update_fncache(const char *name, bool res) +{ + struct fncache *n = malloc(sizeof(struct fncache) + strlen(name) + 1); + int h = shash((const unsigned char *)name) % FNHSIZE; + + if (!n) + return; + strcpy(n->name, name); + n->res = res; + hlist_add_head(&n->nd, &fncache_hash[h]); +} + +/* No LRU, only use when bounded in some other way. */ +bool file_available(const char *name) +{ + bool res; + + if (lookup_fncache(name, &res)) + return res; + res = access(name, R_OK) == 0; + update_fncache(name, res); + return res; +} diff --git a/tools/perf/util/fncache.h b/tools/perf/util/fncache.h new file mode 100644 index 000000000000..fe020beaefb1 --- /dev/null +++ b/tools/perf/util/fncache.h @@ -0,0 +1,7 @@ +#ifndef _FCACHE_H +#define _FCACHE_H 1 + +unsigned shash(const unsigned char *s); +bool file_available(const char *name); + +#endif diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index 7001247ebbd6..aed49806a09b 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -8,30 +8,26 @@ */ #include <sys/types.h> -#include <stdio.h> -#include <getopt.h> #include <stddef.h> #include <libelf.h> #include <string.h> #include <stdlib.h> +#include <unistd.h> #include <inttypes.h> -#include <limits.h> #include <fcntl.h> #include <err.h> #ifdef HAVE_DWARF_SUPPORT #include <dwarf.h> #endif -#include "perf.h" #include "genelf.h" #include "../util/jitdump.h" +#include <linux/compiler.h> #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif -#define JVMTI - #define BUILD_ID_URANDOM /* different uuid for each run */ #ifdef HAVE_LIBCRYPTO @@ -510,44 +506,3 @@ error: return retval; } - -#ifndef JVMTI - -static unsigned char x86_code[] = { - 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ - 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ - 0xCD, 0x80 /* int $0x80 */ -}; - -static struct options options; - -int main(int argc, char **argv) -{ - int c, fd, ret; - - while ((c = getopt(argc, argv, "o:h")) != -1) { - switch (c) { - case 'o': - options.output = optarg; - break; - case 'h': - printf("Usage: genelf -o output_file [-h]\n"); - return 0; - default: - errx(1, "unknown option"); - } - } - - fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666); - if (fd == -1) - err(1, "cannot create file %s", options.output); - - ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code)); - close(fd); - - if (ret != 0) - unlink(options.output); - - return ret; -} -#endif diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index b72440bf9a79..d4137559be05 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -35,6 +35,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #elif defined(__sparc__) #define GEN_ELF_ARCH EM_SPARC #define GEN_ELF_CLASS ELFCLASS32 +#elif defined(__s390x__) +#define GEN_ELF_ARCH EM_S390 +#define GEN_ELF_CLASS ELFCLASS64 #else #error "unsupported architecture" #endif diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index 995e490c17fa..30e9f618f6cd 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -24,7 +24,6 @@ #include <err.h> #include <dwarf.h> -#include "perf.h" #include "genelf.h" #include "../util/jitdump.h" diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c index 01f32f26552d..b205d929245f 100644 --- a/tools/perf/util/get_current_dir_name.c +++ b/tools/perf/util/get_current_dir_name.c @@ -5,7 +5,6 @@ #include "get_current_dir_name.h" #include <unistd.h> #include <stdlib.h> -#include <stdlib.h> /* Android's 'bionic' library, for one, doesn't have this */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1903d7ec9797..4246e7447e54 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -20,12 +20,14 @@ #include <linux/time64.h> #include <dirent.h> #include <bpf/libbpf.h> +#include <perf/cpumap.h> +#include "dso.h" #include "evlist.h" #include "evsel.h" +#include "util/evsel_fprintf.h" #include "header.h" #include "memswap.h" -#include "../perf.h" #include "trace-event.h" #include "session.h" #include "symbol.h" @@ -41,10 +43,12 @@ #include "tool.h" #include "time-utils.h" #include "units.h" +#include "util/util.h" // perf_exe() #include "cputopo.h" #include "bpf-event.h" #include <linux/ctype.h> +#include <internal/lib.h> /* * magic2 = "PERFILE2" @@ -68,15 +72,6 @@ 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); @@ -299,16 +294,16 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) } static int write_tracing_data(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) return -1; - return read_tracing_data(ff->fd, &evlist->entries); + return read_tracing_data(ff->fd, &evlist->core.entries); } static int write_build_id(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; int err; @@ -332,7 +327,7 @@ static int write_build_id(struct feat_fd *ff, } static int write_hostname(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -345,7 +340,7 @@ static int write_hostname(struct feat_fd *ff, } static int write_osrelease(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -358,7 +353,7 @@ static int write_osrelease(struct feat_fd *ff, } static int write_arch(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -371,7 +366,7 @@ static int write_arch(struct feat_fd *ff, } static int write_version(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return do_write_string(ff, perf_version_string); } @@ -432,9 +427,27 @@ done: } static int write_cpudesc(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) -{ + struct evlist *evlist __maybe_unused) +{ +#if defined(__powerpc__) || defined(__hppa__) || defined(__sparc__) +#define CPUINFO_PROC { "cpu", } +#elif defined(__s390__) +#define CPUINFO_PROC { "vendor_id", } +#elif defined(__sh__) +#define CPUINFO_PROC { "cpu type", } +#elif defined(__alpha__) || defined(__mips__) +#define CPUINFO_PROC { "cpu model", } +#elif defined(__arm__) +#define CPUINFO_PROC { "model name", "Processor", } +#elif defined(__arc__) +#define CPUINFO_PROC { "Processor", } +#elif defined(__xtensa__) +#define CPUINFO_PROC { "core ID", } +#else +#define CPUINFO_PROC { "model name", } +#endif const char *cpuinfo_procs[] = CPUINFO_PROC; +#undef CPUINFO_PROC unsigned int i; for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { @@ -448,7 +461,7 @@ static int write_cpudesc(struct feat_fd *ff, static int write_nrcpus(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { long nr; u32 nrc, nra; @@ -470,13 +483,13 @@ static int write_nrcpus(struct feat_fd *ff, } static int write_event_desc(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; u32 nre, nri, sz; int ret; - nre = evlist->nr_entries; + nre = evlist->core.nr_entries; /* * write number of events @@ -488,13 +501,13 @@ static int write_event_desc(struct feat_fd *ff, /* * size of perf_event_attr struct */ - sz = (u32)sizeof(evsel->attr); + sz = (u32)sizeof(evsel->core.attr); ret = do_write(ff, &sz, sizeof(sz)); if (ret < 0) return ret; evlist__for_each_entry(evlist, evsel) { - ret = do_write(ff, &evsel->attr, sz); + ret = do_write(ff, &evsel->core.attr, sz); if (ret < 0) return ret; /* @@ -504,7 +517,7 @@ static int write_event_desc(struct feat_fd *ff, * copy into an nri to be independent of the * type of ids, */ - nri = evsel->ids; + nri = evsel->core.ids; ret = do_write(ff, &nri, sizeof(nri)); if (ret < 0) return ret; @@ -518,7 +531,7 @@ static int write_event_desc(struct feat_fd *ff, /* * write unique ids for this event */ - ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64)); + ret = do_write(ff, evsel->core.id, evsel->core.ids * sizeof(u64)); if (ret < 0) return ret; } @@ -526,7 +539,7 @@ static int write_event_desc(struct feat_fd *ff, } static int write_cmdline(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char pbuf[MAXPATHLEN], *buf; int i, ret, n; @@ -555,7 +568,7 @@ static int write_cmdline(struct feat_fd *ff, static int write_cpu_topology(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct cpu_topology *tp; u32 i; @@ -627,7 +640,7 @@ done: static int write_total_mem(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -656,7 +669,7 @@ static int write_total_mem(struct feat_fd *ff, } static int write_numa_topology(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct numa_topology *tp; int ret = -1; @@ -710,7 +723,7 @@ err: */ static int write_pmu_mappings(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_pmu *pmu = NULL; u32 pmu_num = 0; @@ -759,10 +772,10 @@ static int write_pmu_mappings(struct feat_fd *ff, * }; */ static int write_group_desc(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { u32 nr_groups = evlist->nr_groups; - struct perf_evsel *evsel; + struct evsel *evsel; int ret; ret = do_write(ff, &nr_groups, sizeof(nr_groups)); @@ -771,10 +784,10 @@ static int write_group_desc(struct feat_fd *ff, evlist__for_each_entry(evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { + evsel->core.nr_members > 1) { const char *name = evsel->group_name ?: "{anon_group}"; u32 leader_idx = evsel->idx; - u32 nr_members = evsel->nr_members; + u32 nr_members = evsel->core.nr_members; ret = do_write_string(ff, name); if (ret < 0) @@ -837,11 +850,11 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { - return -1; + return ENOSYS; /* Not implemented */ } static int write_cpuid(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char buffer[64]; int ret; @@ -854,13 +867,13 @@ static int write_cpuid(struct feat_fd *ff, } static int write_branch_stack(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } static int write_auxtrace(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; int err; @@ -877,14 +890,14 @@ static int write_auxtrace(struct feat_fd *ff, } static int write_clockid(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return do_write(ff, &ff->ph->env.clockid_res_ns, sizeof(ff->ph->env.clockid_res_ns)); } static int write_dir_format(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; struct perf_data *data; @@ -900,7 +913,7 @@ static int write_dir_format(struct feat_fd *ff, #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_env *env = &ff->ph->env; struct rb_root *root; @@ -942,14 +955,14 @@ out: } #else // HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } #endif // HAVE_LIBBPF_SUPPORT static int write_bpf_btf(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_env *env = &ff->ph->env; struct rb_root *root; @@ -1061,7 +1074,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path); if (sysfs__read_str(file, &cache->map, &len)) { - zfree(&cache->map); + zfree(&cache->size); zfree(&cache->type); return -1; } @@ -1076,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) +#define MAX_CACHE_LVL 4 + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) { u32 i, cnt = 0; - long ncpus; u32 nr, cpu; u16 level; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) - return -1; - - nr = (u32)(ncpus & UINT_MAX); + nr = cpu__max_cpu(); for (cpu = 0; cpu < nr; cpu++) { - for (level = 0; level < 10; level++) { + for (level = 0; level < MAX_CACHE_LVL; level++) { struct cpu_cache_level c; int err; @@ -1110,26 +1120,21 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) caches[cnt++] = c; else cpu_cache_level__free(&c); - - if (WARN_ONCE(cnt == size, "way too many cpu caches..")) - goto out; } } - out: *cntp = cnt; return 0; } -#define MAX_CACHES (MAX_NR_CPUS * 4) - static int write_cache(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { - struct cpu_cache_level caches[MAX_CACHES]; + u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL; + struct cpu_cache_level caches[max_caches]; u32 cnt = 0, i, version = 1; int ret; - ret = build_caches(caches, MAX_CACHES, &cnt); + ret = build_caches(caches, &cnt); if (ret) goto out; @@ -1175,13 +1180,13 @@ out: } static int write_stat(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } static int write_sample_time(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { int ret; @@ -1282,8 +1287,10 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) continue; if (WARN_ONCE(cnt >= size, - "failed to write MEM_TOPOLOGY, way too many nodes\n")) + "failed to write MEM_TOPOLOGY, way too many nodes\n")) { + closedir(dir); return -1; + } ret = memory_node__read(&nodes[cnt++], idx); } @@ -1315,7 +1322,7 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) * 48 - bitmap | bitmap of memory indexes that belongs to node */ static int write_mem_topology(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { static struct memory_node nodes[MAX_MEMORY_NODES]; u64 bsize, version = 1, i, nr; @@ -1365,7 +1372,7 @@ out: } static int write_compressed(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { int ret; @@ -1568,24 +1575,24 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) up_read(&env->bpf_progs.lock); } -static void free_event_desc(struct perf_evsel *events) +static void free_event_desc(struct evsel *events) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!events) return; - for (evsel = events; evsel->attr.size; evsel++) { + for (evsel = events; evsel->core.attr.size; evsel++) { zfree(&evsel->name); - zfree(&evsel->id); + zfree(&evsel->core.id); } free(events); } -static struct perf_evsel *read_event_desc(struct feat_fd *ff) +static struct evsel *read_event_desc(struct feat_fd *ff) { - struct perf_evsel *evsel, *events = NULL; + struct evsel *evsel, *events = NULL; u64 *id; void *buf = NULL; u32 nre, sz, nr, i, j; @@ -1603,12 +1610,12 @@ static struct perf_evsel *read_event_desc(struct feat_fd *ff) if (!buf) goto error; - /* the last event terminates with evsel->attr.size == 0: */ + /* the last event terminates with evsel->core.attr.size == 0: */ events = calloc(nre + 1, sizeof(*events)); if (!events) goto error; - msz = sizeof(evsel->attr); + msz = sizeof(evsel->core.attr); if (sz < msz) msz = sz; @@ -1625,7 +1632,7 @@ static struct perf_evsel *read_event_desc(struct feat_fd *ff) if (ff->ph->needs_swap) perf_event__attr_swap(buf); - memcpy(&evsel->attr, buf, msz); + memcpy(&evsel->core.attr, buf, msz); if (do_read_u32(ff, &nr)) goto error; @@ -1643,8 +1650,8 @@ static struct perf_evsel *read_event_desc(struct feat_fd *ff) id = calloc(nr, sizeof(*id)); if (!id) goto error; - evsel->ids = nr; - evsel->id = id; + evsel->core.ids = nr; + evsel->core.id = id; for (j = 0 ; j < nr; j++) { if (do_read_u64(ff, id)) @@ -1669,7 +1676,7 @@ static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, static void print_event_desc(struct feat_fd *ff, FILE *fp) { - struct perf_evsel *evsel, *events; + struct evsel *evsel, *events; u32 j; u64 *id; @@ -1683,12 +1690,12 @@ static void print_event_desc(struct feat_fd *ff, FILE *fp) return; } - for (evsel = events; evsel->attr.size; evsel++) { + for (evsel = events; evsel->core.attr.size; evsel++) { fprintf(fp, "# event : name = %s, ", evsel->name); - if (evsel->ids) { + if (evsel->core.ids) { fprintf(fp, ", id = {"); - for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { + for (j = 0, id = evsel->core.id; j < evsel->core.ids; j++, id++) { if (j) fputc(',', fp); fprintf(fp, " %"PRIu64, *id); @@ -1696,7 +1703,7 @@ static void print_event_desc(struct feat_fd *ff, FILE *fp) fprintf(fp, " }"); } - perf_event_attr__fprintf(fp, &evsel->attr, __desc_attr__fprintf, NULL); + perf_event_attr__fprintf(fp, &evsel->core.attr, __desc_attr__fprintf, NULL); fputc('\n', fp); } @@ -1804,18 +1811,18 @@ error: static void print_group_desc(struct feat_fd *ff, FILE *fp) { struct perf_session *session; - struct perf_evsel *evsel; + struct evsel *evsel; u32 nr = 0; session = container_of(ff->ph, struct perf_session, header); evlist__for_each_entry(session->evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { + evsel->core.nr_members > 1) { fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", perf_evsel__name(evsel)); - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; } else if (nr) { fprintf(fp, ",%s", perf_evsel__name(evsel)); @@ -1876,7 +1883,7 @@ static void print_mem_topology(struct feat_fd *ff, FILE *fp) } } -static int __event_process_build_id(struct build_id_event *bev, +static int __event_process_build_id(struct perf_record_header_build_id *bev, char *filename, struct perf_session *session) { @@ -1945,7 +1952,7 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[0]; } old_bev; - struct build_id_event bev; + struct perf_record_header_build_id bev; char filename[PATH_MAX]; u64 limit = offset + size; @@ -1986,7 +1993,7 @@ static int perf_header__read_build_ids(struct perf_header *header, int input, u64 offset, u64 size) { struct perf_session *session = container_of(header, struct perf_session, header); - struct build_id_event bev; + struct perf_record_header_build_id bev; char filename[PATH_MAX]; u64 limit = offset + size, orig_offset = offset; int err = -1; @@ -2008,7 +2015,7 @@ static int perf_header__read_build_ids(struct perf_header *header, * * "perf: 'perf kvm' tool for monitoring guest performance from host" * - * Added a field to struct build_id_event that broke the file + * Added a field to struct perf_record_header_build_id that broke the file * format. * * Since the kernel build-id is the first entry, process the @@ -2089,10 +2096,10 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) return 0; } -static struct perf_evsel * -perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) +static struct evsel * +perf_evlist__find_by_index(struct evlist *evlist, int idx) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (evsel->idx == idx) @@ -2103,10 +2110,10 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) } static void -perf_evlist__set_event_name(struct perf_evlist *evlist, - struct perf_evsel *event) +perf_evlist__set_event_name(struct evlist *evlist, + struct evsel *event) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!event->name) return; @@ -2125,7 +2132,7 @@ static int process_event_desc(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; - struct perf_evsel *evsel, *events = read_event_desc(ff); + struct evsel *evsel, *events = read_event_desc(ff); if (!events) return 0; @@ -2138,7 +2145,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused) ff->events = events; } - for (evsel = events; evsel->attr.size; evsel++) + for (evsel = events; evsel->core.attr.size; evsel++) perf_evlist__set_event_name(session->evlist, evsel); if (!session->data->is_pipe) @@ -2251,8 +2258,10 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) /* On s390 the socket_id number is not related to the numbers of cpus. * The socket_id number might be higher than the numbers of cpus. * This depends on the configuration. + * AArch64 is the same. */ - if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4)) + if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4) + || !strncmp(ph->env.arch, "aarch64", 7))) do_core_id_test = false; for (i = 0; i < (u32)cpu_nr; i++) { @@ -2348,7 +2357,7 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) if (!str) goto error; - n->map = cpu_map__new(str); + n->map = perf_cpu_map__new(str); if (!n->map) goto error; @@ -2415,7 +2424,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) size_t ret = -1; u32 i, nr, nr_groups; struct perf_session *session; - struct perf_evsel *evsel, *leader = NULL; + struct evsel *evsel, *leader = NULL; struct group_desc { char *name; u32 leader_idx; @@ -2462,7 +2471,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) evsel->group_name = desc[i].name; desc[i].name = NULL; } - evsel->nr_members = desc[i].nr_members; + evsel->core.nr_members = desc[i].nr_members; if (i >= nr_groups || nr > 0) { pr_debug("invalid group desc\n"); @@ -2470,7 +2479,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) } leader = evsel; - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; i++; } else if (nr) { /* This is a group member */ @@ -2800,15 +2809,6 @@ static int process_compressed(struct feat_fd *ff, return 0; } -struct feature_ops { - 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_OPR(n, func, __full_only) \ [HEADER_##n] = { \ .name = __stringify(n), \ @@ -2835,8 +2835,10 @@ struct feature_ops { #define process_branch_stack NULL #define process_stat NULL +// Only used in util/synthetic-events.c +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; -static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(TRACING_DATA, tracing_data, false), FEAT_OPN(BUILD_ID, build_id, false), FEAT_OPR(HOSTNAME, hostname, false), @@ -2920,7 +2922,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - stctime = st.st_ctime; + stctime = st.st_mtime; fprintf(fp, "# captured on : %s", ctime(&stctime)); fprintf(fp, "# header version : %u\n", header->version); @@ -2946,7 +2948,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) static int do_write_feat(struct feat_fd *ff, int type, struct perf_file_section **p, - struct perf_evlist *evlist) + struct evlist *evlist) { int err; int ret = 0; @@ -2976,7 +2978,7 @@ static int do_write_feat(struct feat_fd *ff, int type, } static int perf_header__adds_write(struct perf_header *header, - struct perf_evlist *evlist, int fd) + struct evlist *evlist, int fd) { int nr_sections; struct feat_fd ff; @@ -3044,13 +3046,13 @@ int perf_header__write_pipe(int fd) } int perf_session__write_header(struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, int fd, bool at_exit) { struct perf_file_header f_header; struct perf_file_attr f_attr; struct perf_header *header = &session->header; - struct perf_evsel *evsel; + struct evsel *evsel; struct feat_fd ff; u64 attr_offset; int err; @@ -3060,7 +3062,7 @@ int perf_session__write_header(struct perf_session *session, evlist__for_each_entry(session->evlist, evsel) { evsel->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64)); + err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; @@ -3071,10 +3073,10 @@ int perf_session__write_header(struct perf_session *session, evlist__for_each_entry(evlist, evsel) { f_attr = (struct perf_file_attr){ - .attr = evsel->attr, + .attr = evsel->core.attr, .ids = { .offset = evsel->id_offset, - .size = evsel->ids * sizeof(u64), + .size = evsel->core.ids * sizeof(u64), } }; err = do_write(&ff, &f_attr, sizeof(f_attr)); @@ -3100,7 +3102,7 @@ int perf_session__write_header(struct perf_session *session, .attr_size = sizeof(f_attr), .attrs = { .offset = attr_offset, - .size = evlist->nr_entries * sizeof(f_attr), + .size = evlist->core.nr_entries * sizeof(f_attr), }, .data = { .offset = header->data_offset, @@ -3479,7 +3481,7 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, +static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) { struct tep_event *event; @@ -3494,9 +3496,9 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return -1; } - event = tep_find_event(pevent, evsel->attr.config); + event = tep_find_event(pevent, evsel->core.attr.config); if (event == NULL) { - pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); + pr_debug("cannot find event format for %d\n", (int)evsel->core.attr.config); return -1; } @@ -3511,13 +3513,13 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return 0; } -static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, +static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(evlist, pos) { - if (pos->attr.type == PERF_TYPE_TRACEPOINT && + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT && perf_evsel__prepare_tracepoint_event(pos, pevent)) return -1; } @@ -3535,7 +3537,7 @@ int perf_session__read_header(struct perf_session *session) int nr_attrs, nr_ids, i, j; int fd = perf_data__fd(data); - session->evlist = perf_evlist__new(); + session->evlist = evlist__new(); if (session->evlist == NULL) return -ENOMEM; @@ -3570,7 +3572,7 @@ int perf_session__read_header(struct perf_session *session) lseek(fd, f_header.attrs.offset, SEEK_SET); for (i = 0; i < nr_attrs; i++) { - struct perf_evsel *evsel; + struct evsel *evsel; off_t tmp; if (read_attr(fd, header, &f_attr) < 0) @@ -3583,7 +3585,7 @@ int perf_session__read_header(struct perf_session *session) } tmp = lseek(fd, 0, SEEK_CUR); - evsel = perf_evsel__new(&f_attr.attr); + evsel = evsel__new(&f_attr.attr); if (evsel == NULL) goto out_delete_evlist; @@ -3591,9 +3593,9 @@ int perf_session__read_header(struct perf_session *session) evsel->needs_swap = header->needs_swap; /* * Do it before so that if perf_evsel__alloc_id fails, this - * entry gets purged too at perf_evlist__delete(). + * entry gets purged too at evlist__delete(). */ - perf_evlist__add(session->evlist, evsel); + evlist__add(session->evlist, evsel); nr_ids = f_attr.ids.size / sizeof(u64); /* @@ -3601,7 +3603,7 @@ int perf_session__read_header(struct perf_session *session) * for allocating the perf_sample_id table we fake 1 cpu and * hattr->ids threads. */ - if (perf_evsel__alloc_id(evsel, 1, nr_ids)) + if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids)) goto out_delete_evlist; lseek(fd, f_attr.ids.offset, SEEK_SET); @@ -3610,7 +3612,7 @@ int perf_session__read_header(struct perf_session *session) if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id))) goto out_errno; - perf_evlist__id_add(session->evlist, evsel, 0, j, f_id); + perf_evlist__id_add(&session->evlist->core, &evsel->core, 0, j, f_id); } lseek(fd, tmp, SEEK_SET); @@ -3628,116 +3630,17 @@ out_errno: return -errno; out_delete_evlist: - perf_evlist__delete(session->evlist); + evlist__delete(session->evlist); session->evlist = NULL; return -ENOMEM; } -int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u32 ids, u64 *id, - perf_event__handler_t process) -{ - union perf_event *ev; - size_t size; - int err; - - size = sizeof(struct perf_event_attr); - size = PERF_ALIGN(size, sizeof(u64)); - size += sizeof(struct perf_event_header); - size += ids * sizeof(u64); - - ev = zalloc(size); - - if (ev == NULL) - return -ENOMEM; - - ev->attr.attr = *attr; - memcpy(ev->attr.id, id, ids * sizeof(u64)); - - ev->attr.header.type = PERF_RECORD_HEADER_ATTR; - ev->attr.header.size = (u16)size; - - if (ev->attr.header.size == size) - err = process(tool, ev, NULL, NULL); - else - err = -E2BIG; - - free(ev); - - 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; - ff.ph = &session->header; - - 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; - } - } - - /* Send HEADER_LAST_FEATURE mark. */ - fe = ff.buf; - fe->feat_id = HEADER_LAST_FEATURE; - fe->header.type = PERF_RECORD_HEADER_FEATURE; - fe->header.size = sizeof(*fe); - - ret = process(tool, ff.buf, NULL, NULL); - - free(ff.buf); - return ret; -} - int perf_event__process_feature(struct perf_session *session, union perf_event *event) { struct perf_tool *tool = session->tool; struct feat_fd ff = { .fd = 0 }; - struct feature_event *fe = (struct feature_event *)event; + struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; @@ -3774,126 +3677,19 @@ int perf_event__process_feature(struct perf_session *session, return 0; } -static struct event_update_event * -event_update_event__new(size_t size, u64 type, u64 id) -{ - struct event_update_event *ev; - - size += sizeof(*ev); - size = PERF_ALIGN(size, sizeof(u64)); - - ev = zalloc(size); - if (ev) { - ev->header.type = PERF_RECORD_EVENT_UPDATE; - ev->header.size = (u16)size; - ev->type = type; - ev->id = id; - } - return ev; -} - -int -perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process) -{ - struct event_update_event *ev; - size_t size = strlen(evsel->unit); - int err; - - ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - strlcpy(ev->data, evsel->unit, size + 1); - err = process(tool, (union perf_event *)ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process) -{ - struct event_update_event *ev; - struct event_update_event_scale *ev_data; - int err; - - ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - ev_data = (struct event_update_event_scale *) ev->data; - ev_data->scale = evsel->scale; - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process) -{ - struct event_update_event *ev; - size_t len = strlen(evsel->name); - int err; - - ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - strlcpy(ev->data, evsel->name, len + 1); - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process) -{ - size_t size = sizeof(struct event_update_event); - struct event_update_event *ev; - int max, err; - u16 type; - - if (!evsel->own_cpus) - return 0; - - ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max); - if (!ev) - return -ENOMEM; - - ev->header.type = PERF_RECORD_EVENT_UPDATE; - ev->header.size = (u16)size; - ev->type = PERF_EVENT_UPDATE__CPUS; - ev->id = evsel->id[0]; - - cpu_map_data__synthesize((struct cpu_map_data *) ev->data, - evsel->own_cpus, - type, max); - - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) { - struct event_update_event *ev = &event->event_update; - struct event_update_event_scale *ev_scale; - struct event_update_event_cpus *ev_cpus; - struct cpu_map *map; + struct perf_record_event_update *ev = &event->event_update; + struct perf_record_event_update_scale *ev_scale; + struct perf_record_event_update_cpus *ev_cpus; + struct perf_cpu_map *map; size_t ret; - ret = fprintf(fp, "\n... id: %" PRIu64 "\n", ev->id); + ret = fprintf(fp, "\n... id: %" PRI_lu64 "\n", ev->id); switch (ev->type) { case PERF_EVENT_UPDATE__SCALE: - ev_scale = (struct event_update_event_scale *) ev->data; + ev_scale = (struct perf_record_event_update_scale *)ev->data; ret += fprintf(fp, "... scale: %f\n", ev_scale->scale); break; case PERF_EVENT_UPDATE__UNIT: @@ -3903,7 +3699,7 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) ret += fprintf(fp, "... name: %s\n", ev->data); break; case PERF_EVENT_UPDATE__CPUS: - ev_cpus = (struct event_update_event_cpus *) ev->data; + ev_cpus = (struct perf_record_event_update_cpus *)ev->data; ret += fprintf(fp, "... "); map = cpu_map__new_data(&ev_cpus->cpus); @@ -3920,112 +3716,25 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) return ret; } -int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_evlist *evlist, - perf_event__handler_t process) -{ - struct perf_evsel *evsel; - int err = 0; - - evlist__for_each_entry(evlist, evsel) { - err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, - evsel->id, process); - if (err) { - pr_debug("failed to create perf header attribute\n"); - return err; - } - } - - return err; -} - -static bool has_unit(struct perf_evsel *counter) -{ - return counter->unit && *counter->unit; -} - -static bool has_scale(struct perf_evsel *counter) -{ - return counter->scale != 1; -} - -int perf_event__synthesize_extra_attr(struct perf_tool *tool, - struct perf_evlist *evsel_list, - perf_event__handler_t process, - bool is_pipe) -{ - struct perf_evsel *counter; - int err; - - /* - * Synthesize other events stuff not carried within - * attr event - unit, scale, name - */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->supported) - continue; - - /* - * Synthesize unit and scale only if it's defined. - */ - if (has_unit(counter)) { - err = perf_event__synthesize_event_update_unit(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel unit.\n"); - return err; - } - } - - if (has_scale(counter)) { - err = perf_event__synthesize_event_update_scale(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel counter.\n"); - return err; - } - } - - if (counter->own_cpus) { - err = perf_event__synthesize_event_update_cpus(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel cpus.\n"); - return err; - } - } - - /* - * Name is needed only for pipe output, - * perf.data carries event names. - */ - if (is_pipe) { - err = perf_event__synthesize_event_update_name(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel name.\n"); - return err; - } - } - } - return 0; -} - int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { u32 i, ids, n_ids; - struct perf_evsel *evsel; - struct perf_evlist *evlist = *pevlist; + struct evsel *evsel; + struct evlist *evlist = *pevlist; if (evlist == NULL) { - *pevlist = evlist = perf_evlist__new(); + *pevlist = evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; } - evsel = perf_evsel__new(&event->attr.attr); + evsel = evsel__new(&event->attr.attr); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); ids = event->header.size; ids -= (void *)&event->attr.id - (void *)event; @@ -4035,11 +3744,11 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, * for allocating the perf_sample_id table we fake 1 cpu and * hattr->ids threads. */ - if (perf_evsel__alloc_id(evsel, 1, n_ids)) + if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]); } return 0; @@ -4047,14 +3756,14 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { - struct event_update_event *ev = &event->event_update; - struct event_update_event_scale *ev_scale; - struct event_update_event_cpus *ev_cpus; - struct perf_evlist *evlist; - struct perf_evsel *evsel; - struct cpu_map *map; + struct perf_record_event_update *ev = &event->event_update; + struct perf_record_event_update_scale *ev_scale; + struct perf_record_event_update_cpus *ev_cpus; + struct evlist *evlist; + struct evsel *evsel; + struct perf_cpu_map *map; if (!pevlist || *pevlist == NULL) return -EINVAL; @@ -4073,15 +3782,15 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, evsel->name = strdup(ev->data); break; case PERF_EVENT_UPDATE__SCALE: - ev_scale = (struct event_update_event_scale *) ev->data; + ev_scale = (struct perf_record_event_update_scale *)ev->data; evsel->scale = ev_scale->scale; break; case PERF_EVENT_UPDATE__CPUS: - ev_cpus = (struct event_update_event_cpus *) ev->data; + ev_cpus = (struct perf_record_event_update_cpus *)ev->data; map = cpu_map__new_data(&ev_cpus->cpus); if (map) - evsel->own_cpus = map; + evsel->core.own_cpus = map; else pr_err("failed to get event_update cpus\n"); default: @@ -4091,55 +3800,6 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, return 0; } -int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, - struct perf_evlist *evlist, - perf_event__handler_t process) -{ - 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; - - /* - * We are going to store the size of the data followed - * by the data contents. Since the fd descriptor is a pipe, - * we cannot seek back to store the size of the data once - * we know it. Instead we: - * - * - write the tracing data to the temp file - * - get/write the data size to pipe - * - write the tracing data from the temp file - * to the pipe - */ - tdata = tracing_data_get(&evlist->entries, fd, true); - if (!tdata) - return -1; - - memset(&ev, 0, sizeof(ev)); - - ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; - size = tdata->size; - aligned_size = PERF_ALIGN(size, sizeof(u64)); - padding = aligned_size - size; - ev.tracing_data.header.size = sizeof(ev.tracing_data); - ev.tracing_data.size = aligned_size; - - process(tool, &ev, NULL, NULL); - - /* - * The put function will copy all the tracing data - * stored in temp file to the pipe. - */ - tracing_data_put(tdata); - - ff = (struct feat_fd){ .fd = fd }; - if (write_padded(&ff, NULL, 0, padding)) - return -1; - - return aligned_size; -} - int perf_event__process_tracing_data(struct perf_session *session, union perf_event *event) { @@ -4149,7 +3809,7 @@ int perf_event__process_tracing_data(struct perf_session *session, char buf[BUFSIZ]; /* setup for reading amidst mmap */ - lseek(fd, offset + sizeof(struct tracing_data_event), + lseek(fd, offset + sizeof(struct perf_record_header_tracing_data), SEEK_SET); size_read = trace_report(fd, &session->tevent, @@ -4179,34 +3839,6 @@ int perf_event__process_tracing_data(struct perf_session *session, return size_read + padding; } -int perf_event__synthesize_build_id(struct perf_tool *tool, - struct dso *pos, u16 misc, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t len; - int err = 0; - - if (!pos->hit) - return err; - - memset(&ev, 0, sizeof(ev)); - - len = pos->long_name_len + 1; - len = PERF_ALIGN(len, NAME_ALIGN); - memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); - ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; - ev.build_id.header.misc = misc; - ev.build_id.pid = machine->pid; - ev.build_id.header.size = sizeof(ev.build_id) + len; - memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); - - err = process(tool, &ev, NULL, machine); - - return err; -} - int perf_event__process_build_id(struct perf_session *session, union perf_event *event) { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 5b3abe4172e2..840f95cee349 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -5,10 +5,10 @@ #include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> +#include <stdio.h> // FILE #include <stdbool.h> #include <linux/bitmap.h> #include <linux/types.h> -#include "event.h" #include "env.h" #include "pmu.h" @@ -52,10 +52,6 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; -enum perf_dir_version { - PERF_DIR_VERSION = 1, -}; - struct perf_file_section { u64 offset; u64 size; @@ -92,12 +88,32 @@ struct perf_header { struct perf_env env; }; -struct perf_evlist; +struct feat_fd { + struct perf_header *ph; + int fd; + void *buf; /* Either buf != NULL or fd >= 0 */ + ssize_t offset; + size_t size; + struct evsel *events; +}; + +struct perf_header_feature_ops { + int (*write)(struct feat_fd *ff, struct 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; +}; + +struct evlist; struct perf_session; +struct perf_tool; +union perf_event; int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, int fd, bool at_exit); int perf_header__write_pipe(int fd); @@ -115,54 +131,16 @@ 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__synthesize_extra_attr(struct perf_tool *tool, - struct perf_evlist *evsel_list, - perf_event__handler_t process, - bool is_pipe); - int perf_event__process_feature(struct perf_session *session, union perf_event *event); - -int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u32 ids, u64 *id, - perf_event__handler_t process); -int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_evlist *evlist, - perf_event__handler_t process); -int perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct perf_evsel *evsel, - perf_event__handler_t process); int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); int perf_event__process_event_update(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); - -int perf_event__synthesize_tracing_data(struct perf_tool *tool, - int fd, struct perf_evlist *evlist, - perf_event__handler_t process); int perf_event__process_tracing_data(struct perf_session *session, union perf_event *event); - -int perf_event__synthesize_build_id(struct perf_tool *tool, - struct dso *pos, u16 misc, - perf_event__handler_t process, - struct machine *machine); int perf_event__process_build_id(struct perf_session *session, union perf_event *event); bool is_perf_magic(u64 magic); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f24fd1954f6c..ca5a8f4d007e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1,8 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include "callchain.h" +#include "debug.h" +#include "dso.h" #include "build-id.h" #include "hist.h" #include "map.h" +#include "map_symbol.h" +#include "branch.h" +#include "mem-events.h" #include "session.h" #include "namespaces.h" #include "sort.h" @@ -13,11 +18,14 @@ #include "srcline.h" #include "symbol.h" #include "thread.h" +#include "block-info.h" #include "ui/progress.h" #include <errno.h> #include <math.h> #include <inttypes.h> #include <sys/param.h> +#include <linux/rbtree.h> +#include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> @@ -73,6 +81,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) int symlen; u16 len; + if (h->block_info) + return; /* * +4 accounts for '[x] ' priv level info * +2 accounts for 0x prefix on raw addresses @@ -102,13 +112,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); if (h->branch_info) { - if (h->branch_info->from.sym) { - symlen = (int)h->branch_info->from.sym->namelen + 4; + if (h->branch_info->from.ms.sym) { + symlen = (int)h->branch_info->from.ms.sym->namelen + 4; if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); - symlen = dso__name_len(h->branch_info->from.map->dso); + symlen = dso__name_len(h->branch_info->from.ms.map->dso); hists__new_col_len(hists, HISTC_DSO_FROM, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -116,13 +126,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM); } - if (h->branch_info->to.sym) { - symlen = (int)h->branch_info->to.sym->namelen + 4; + if (h->branch_info->to.ms.sym) { + symlen = (int)h->branch_info->to.ms.sym->namelen + 4; if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); - symlen = dso__name_len(h->branch_info->to.map->dso); + symlen = dso__name_len(h->branch_info->to.ms.map->dso); hists__new_col_len(hists, HISTC_DSO_TO, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -139,8 +149,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) } if (h->mem_info) { - if (h->mem_info->daddr.sym) { - symlen = (int)h->mem_info->daddr.sym->namelen + 4 + if (h->mem_info->daddr.ms.sym) { + symlen = (int)h->mem_info->daddr.ms.sym->namelen + 4 + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -154,8 +164,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen); } - if (h->mem_info->iaddr.sym) { - symlen = (int)h->mem_info->iaddr.sym->namelen + 4 + if (h->mem_info->iaddr.ms.sym) { + symlen = (int)h->mem_info->iaddr.ms.sym->namelen + 4 + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL, symlen); @@ -165,8 +175,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen); } - if (h->mem_info->daddr.map) { - symlen = dso__name_len(h->mem_info->daddr.map->dso); + if (h->mem_info->daddr.ms.map) { + symlen = dso__name_len(h->mem_info->daddr.ms.map->dso); hists__new_col_len(hists, HISTC_MEM_DADDR_DSO, symlen); } else { @@ -193,7 +203,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); - hists__new_col_len(hists, HISTC_TIME, 12); + if (symbol_conf.nanosecs) + hists__new_col_len(hists, HISTC_TIME, 16); + else + hists__new_col_len(hists, HISTC_TIME, 12); if (h->srcline) { len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header)); @@ -430,13 +443,13 @@ static int hist_entry__init(struct hist_entry *he, memcpy(he->branch_info, template->branch_info, sizeof(*he->branch_info)); - map__get(he->branch_info->from.map); - map__get(he->branch_info->to.map); + map__get(he->branch_info->from.ms.map); + map__get(he->branch_info->to.ms.map); } if (he->mem_info) { - map__get(he->mem_info->iaddr.map); - map__get(he->mem_info->daddr.map); + map__get(he->mem_info->iaddr.ms.map); + map__get(he->mem_info->daddr.ms.map); } if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) @@ -479,13 +492,13 @@ err_rawdata: err_infos: if (he->branch_info) { - map__put(he->branch_info->from.map); - map__put(he->branch_info->to.map); + map__put(he->branch_info->from.ms.map); + map__put(he->branch_info->to.ms.map); zfree(&he->branch_info); } if (he->mem_info) { - map__put(he->mem_info->iaddr.map); - map__put(he->mem_info->daddr.map); + map__put(he->mem_info->iaddr.ms.map); + map__put(he->mem_info->daddr.ms.map); } err: map__zput(he->ms.map); @@ -679,6 +692,7 @@ __hists__add_entry(struct hists *hists, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, .ms = { + .maps = al->maps, .map = al->map, .sym = al->sym, }, @@ -745,6 +759,11 @@ struct hist_entry *hists__add_entry_block(struct hists *hists, struct hist_entry entry = { .block_info = block_info, .hists = hists, + .ms = { + .maps = al->maps, + .map = al->map, + .sym = al->sym, + }, }, *he = hists__findnew_entry(hists, &entry, al, false); return he; @@ -816,7 +835,7 @@ static int iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct hist_entry *he = iter->he; int err = -EINVAL; @@ -876,8 +895,9 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) if (iter->curr >= iter->total) return 0; - al->map = bi[i].to.map; - al->sym = bi[i].to.sym; + al->maps = bi[i].to.ms.maps; + al->map = bi[i].to.ms.map; + al->sym = bi[i].to.ms.sym; al->addr = bi[i].to.addr; return 1; } @@ -886,7 +906,7 @@ static int iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { struct branch_info *bi; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry *he = NULL; @@ -895,7 +915,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a bi = iter->priv; - if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + if (iter->hide_unresolved && !(bi[i].from.ms.sym && bi[i].to.ms.sym)) goto out; /* @@ -938,7 +958,7 @@ iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused, static int iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; struct hist_entry *he; @@ -956,7 +976,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { struct hist_entry *he = iter->he; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; if (he == NULL) @@ -996,7 +1016,7 @@ static int iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; @@ -1041,7 +1061,7 @@ static int iter_add_next_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; struct hist_entry *he; @@ -1052,6 +1072,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .comm = thread__comm(al->thread), .ip = al->addr, .ms = { + .maps = al->maps, .map = al->map, .sym = al->sym, }, @@ -1234,16 +1255,16 @@ void hist_entry__delete(struct hist_entry *he) map__zput(he->ms.map); if (he->branch_info) { - map__zput(he->branch_info->from.map); - map__zput(he->branch_info->to.map); + map__zput(he->branch_info->from.ms.map); + map__zput(he->branch_info->to.ms.map); free_srcline(he->branch_info->srcline_from); free_srcline(he->branch_info->srcline_to); zfree(&he->branch_info); } if (he->mem_info) { - map__zput(he->mem_info->iaddr.map); - map__zput(he->mem_info->daddr.map); + map__zput(he->mem_info->iaddr.ms.map); + map__zput(he->mem_info->daddr.ms.map); mem_info__zput(he->mem_info); } @@ -1615,7 +1636,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; @@ -1873,7 +1894,7 @@ static void output_resort(struct hists *hists, struct ui_progress *prog, } } -void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog, +void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog, hists__resort_cb_t cb, void *cb_arg) { bool use_callchain; @@ -1888,7 +1909,7 @@ void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress * output_resort(evsel__hists(evsel), prog, use_callchain, cb, cb_arg); } -void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog) +void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog) { return perf_evsel__output_resort_cb(evsel, prog, NULL, NULL); } @@ -2539,8 +2560,28 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } +int hists__unlink(struct hists *hists) +{ + struct rb_root_cached *root; + struct rb_node *nd; + struct hist_entry *pos; + + if (hists__has(hists, need_collapse)) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + list_del_init(&pos->pairs.node); + } + + return 0; +} + void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, - struct perf_sample *sample, bool nonany_branch_mode) + struct perf_sample *sample, bool nonany_branch_mode, + u64 *total_cycles) { struct branch_info *bi; @@ -2567,15 +2608,18 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, nonany_branch_mode ? NULL : prev, bi[i].flags.cycles); prev = &bi[i].to; + + if (total_cycles) + *total_cycles += bi[i].flags.cycles; } free(bi); } } } -size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) +size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) { - struct perf_evsel *pos; + struct evsel *pos; size_t ret = 0; evlist__for_each_entry(evlist, pos) { @@ -2602,7 +2646,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh int socket_id = hists->socket_filter; unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = hists->stats.total_period; - struct perf_evsel *evsel = hists_to_evsel(hists); + struct evsel *evsel = hists_to_evsel(hists); const char *ev_name = perf_evsel__name(evsel); char buf[512], sample_freq_str[64] = ""; size_t buflen = sizeof(buf); @@ -2615,7 +2659,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh } if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; + struct evsel *pos; perf_evsel__group_desc(evsel, buf, buflen); ev_name = buf; @@ -2638,12 +2682,12 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh enable_ref = true; if (show_freq) - scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); + scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->core.attr.sample_freq); nr_samples = convert_unit(nr_samples, &unit); printed = scnprintf(bf, size, "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, - nr_samples, unit, evsel->nr_members > 1 ? "s" : "", + nr_samples, unit, evsel->core.nr_members > 1 ? "s" : "", ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); @@ -2731,7 +2775,7 @@ static void hists__delete_all_entries(struct hists *hists) hists__delete_remaining_entries(&hists->entries_collapsed); } -static void hists_evsel__exit(struct perf_evsel *evsel) +static void hists_evsel__exit(struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); struct perf_hpp_fmt *fmt, *pos; @@ -2749,7 +2793,7 @@ static void hists_evsel__exit(struct perf_evsel *evsel) } } -static int hists_evsel__init(struct perf_evsel *evsel) +static int hists_evsel__init(struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 24635f36148d..0aa63aeb58ec 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -6,9 +6,8 @@ #include <linux/types.h> #include <pthread.h> #include "evsel.h" -#include "header.h" #include "color.h" -#include "ui/progress.h" +#include "events_stats.h" struct hist_entry; struct hist_entry_ops; @@ -16,8 +15,10 @@ struct addr_location; struct map_symbol; struct mem_info; struct branch_info; +struct branch_stack; struct block_info; struct symbol; +struct ui_progress; enum hist_filter { HIST_FILTER__DSO, @@ -116,7 +117,7 @@ struct hist_entry_iter { bool hide_unresolved; - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_sample *sample; struct hist_entry *he; struct symbol *parent; @@ -171,9 +172,9 @@ void hist_entry__delete(struct hist_entry *he); typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg); -void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog, +void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog, hists__resort_cb_t cb, void *cb_arg); -void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog); +void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog); void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog, hists__resort_cb_t cb); @@ -190,13 +191,11 @@ void hists__reset_stats(struct hists *hists); void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists, u32 type); void hists__inc_nr_samples(struct hists *hists, bool filtered); -void events_stats__inc(struct events_stats *stats, u32 type); -size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); +size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -217,19 +216,20 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he); void hists__match(struct hists *leader, struct hists *other); int hists__link(struct hists *leader, struct hists *other); +int hists__unlink(struct hists *hists); struct hists_evsel { - struct perf_evsel evsel; + struct evsel evsel; struct hists hists; }; -static inline struct perf_evsel *hists_to_evsel(struct hists *hists) +static inline struct evsel *hists_to_evsel(struct hists *hists) { struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists); return &hevsel->evsel; } -static inline struct hists *evsel__hists(struct perf_evsel *evsel) +static inline struct hists *evsel__hists(struct evsel *evsel) { struct hists_evsel *hevsel = (struct hists_evsel *)evsel; return &hevsel->hists; @@ -339,10 +339,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format) list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list) #define hists__for_each_format(hists, format) \ - perf_hpp_list__for_each_format((hists)->hpp_list, fmt) + perf_hpp_list__for_each_format((hists)->hpp_list, format) #define hists__for_each_sort_list(hists, format) \ - perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt) + perf_hpp_list__for_each_sort_list((hists)->hpp_list, format) extern struct perf_hpp_fmt perf_hpp__format[]; @@ -367,7 +367,7 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); void perf_hpp__append_sort_keys(struct perf_hpp_list *list); int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, - struct perf_evlist *evlist); + struct evlist *evlist); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); @@ -432,7 +432,7 @@ static inline size_t perf_hpp__color_overhead(void) : 0; } -struct perf_evlist; +struct evlist; struct hist_browser_timer { void (*timer)(void *arg); @@ -449,34 +449,40 @@ enum rstype { A_SOURCE }; +struct block_hist; + #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" void attr_to_script(char *buf, struct perf_event_attr *attr); -int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, +int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, +int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_options); -int script_browse(const char *script_opt, struct perf_evsel *evsel); +int script_browse(const char *script_opt, struct evsel *evsel); void run_script(char *cmd); int res_sample_browse(struct res_sample *res_samples, int num_res, - struct perf_evsel *evsel, enum rstype rstype); + struct evsel *evsel, enum rstype rstype); void res_sample_init(void); + +int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, + float min_percent, struct perf_env *env, + struct annotation_options *annotation_opts); #else static inline -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, +int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, @@ -487,7 +493,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, return 0; } static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *annotation_options __maybe_unused) { @@ -495,7 +501,7 @@ static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *annotation_opts __maybe_unused) { @@ -503,14 +509,14 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, } static inline int script_browse(const char *script_opt __maybe_unused, - struct perf_evsel *evsel __maybe_unused) + struct evsel *evsel __maybe_unused) { return 0; } static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused, int num_res __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, enum rstype rstype __maybe_unused) { return 0; @@ -518,6 +524,15 @@ static inline int res_sample_browse(struct res_sample *res_samples __maybe_unuse static inline void res_sample_init(void) {} +static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused, + struct evsel *evsel __maybe_unused, + float min_percent __maybe_unused, + struct perf_env *env __maybe_unused, + struct annotation_options *annotation_opts __maybe_unused) +{ + return 0; +} + #define K_LEFT -1000 #define K_RIGHT -2000 #define K_SWITCH_INPUT_DATA -3000 @@ -527,7 +542,8 @@ unsigned int hists__sort_list_width(struct hists *hists); unsigned int hists__overhead_width(struct hists *hists); void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, - struct perf_sample *sample, bool nonany_branch_mode); + struct perf_sample *sample, bool nonany_branch_mode, + u64 *total_cycles); struct option; int parse_filter_percentage(const struct option *opt, const char *arg, int unset); diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index f01d48a8d707..b8a5159361b4 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -5,10 +5,93 @@ /* linkage.h ... for including arch/x86/lib/memcpy_64.S */ -#define ENTRY(name) \ - .globl name; \ +/* Some toolchains use other characters (e.g. '`') to mark new line in macro */ +#ifndef ASM_NL +#define ASM_NL ; +#endif + +#ifndef __ALIGN +#define __ALIGN .align 4,0x90 +#define __ALIGN_STR ".align 4,0x90" +#endif + +/* SYM_T_FUNC -- type used by assembler to mark functions */ +#ifndef SYM_T_FUNC +#define SYM_T_FUNC STT_FUNC +#endif + +/* SYM_A_* -- align the symbol? */ +#define SYM_A_ALIGN ALIGN + +/* SYM_L_* -- linkage of symbols */ +#define SYM_L_GLOBAL(name) .globl name +#define SYM_L_LOCAL(name) /* nothing */ + +#define ALIGN __ALIGN + +/* === generic annotations === */ + +/* SYM_ENTRY -- use only if you have to for non-paired symbols */ +#ifndef SYM_ENTRY +#define SYM_ENTRY(name, linkage, align...) \ + linkage(name) ASM_NL \ + align ASM_NL \ name: +#endif + +/* SYM_START -- use only if you have to */ +#ifndef SYM_START +#define SYM_START(name, linkage, align...) \ + SYM_ENTRY(name, linkage, align) +#endif + +/* SYM_END -- use only if you have to */ +#ifndef SYM_END +#define SYM_END(name, sym_type) \ + .type name sym_type ASM_NL \ + .size name, .-name +#endif + +/* + * SYM_FUNC_START_ALIAS -- use where there are two global names for one + * function + */ +#ifndef SYM_FUNC_START_ALIAS +#define SYM_FUNC_START_ALIAS(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START -- use for global functions */ +#ifndef SYM_FUNC_START +/* + * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two + * later. + */ +#define SYM_FUNC_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START_LOCAL -- use for local functions */ +#ifndef SYM_FUNC_START_LOCAL +/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ +#ifndef SYM_FUNC_END_ALIAS +#define SYM_FUNC_END_ALIAS(name) \ + SYM_END(name, SYM_T_FUNC) +#endif -#define ENDPROC(name) +/* + * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, + * SYM_FUNC_START_WEAK, ... + */ +#ifndef SYM_FUNC_END +/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_END(name) \ + SYM_END(name, SYM_T_FUNC) +#endif #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 5560e95afdda..34cb380d19a3 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -14,14 +14,13 @@ #include <linux/log2.h> #include <linux/zalloc.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" #include "evlist.h" #include "machine.h" -#include "map.h" #include "symbol.h" #include "session.h" +#include "tool.h" #include "thread.h" #include "thread-stack.h" #include "debug.h" @@ -29,6 +28,7 @@ #include "auxtrace.h" #include "intel-pt-decoder/intel-pt-insn-decoder.h" #include "intel-bts.h" +#include "util/synthetic-events.h" #define MAX_TIMESTAMP (~0ULL) @@ -760,15 +760,15 @@ static int intel_bts_synth_event(struct perf_session *session, static int intel_bts_synth_events(struct intel_bts *bts, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; struct perf_event_attr attr; bool found = false; u64 id; int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == bts->pmu_type && evsel->ids) { + if (evsel->core.attr.type == bts->pmu_type && evsel->core.ids) { found = true; break; } @@ -782,20 +782,20 @@ static int intel_bts_synth_events(struct intel_bts *bts, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; attr.sample_type &= ~(u64)PERF_SAMPLE_CPU; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; - - id = evsel->id[0] + 1000000000; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; + + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; @@ -818,7 +818,7 @@ static int intel_bts_synth_events(struct intel_bts *bts, * We only use sample types from PERF_SAMPLE_MASK so we can use * __perf_evsel__sample_size() here. */ - bts->branches_event_size = sizeof(struct sample_event) + + bts->branches_event_size = sizeof(struct perf_record_sample) + __perf_evsel__sample_size(attr.sample_type); } @@ -834,7 +834,7 @@ static const char * const intel_bts_info_fmts[] = { [INTEL_BTS_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n", }; -static void intel_bts_print_info(u64 *arr, int start, int finish) +static void intel_bts_print_info(__u64 *arr, int start, int finish) { int i; @@ -848,12 +848,12 @@ static void intel_bts_print_info(u64 *arr, int start, int finish) int intel_bts_process_auxtrace_info(union perf_event *event, struct perf_session *session) { - struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; size_t min_sz = sizeof(u64) * INTEL_BTS_SNAPSHOT_MODE; struct intel_bts *bts; int err; - if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) + + if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) + min_sz) return -EINVAL; diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 23bf788f84b9..bc629359826f 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -1,7 +1,7 @@ perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o -inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk -inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt +inat_tables_script = $(srctree)/tools/arch/x86/tools/gen-insn-attr-x86.awk +inat_tables_maps = $(srctree)/tools/arch/x86/lib/x86-opcode-map.txt $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps) $(call rule_mkdir) @@ -9,23 +9,7 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table # Busybox's diff doesn't have -I, avoid warning in the case -$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c - @(diff -I 2>&1 | grep -q 'option requires an argument' && \ - test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - ((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \ - ((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \ - ((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \ - ((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \ - ((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \ - ((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \ - ((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \ - (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true +$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk deleted file mode 100644 index ddd5c4c21129..000000000000 --- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk +++ /dev/null @@ -1,392 +0,0 @@ -#!/bin/awk -f -# SPDX-License-Identifier: GPL-2.0 -# gen-insn-attr-x86.awk: Instruction attribute table generator -# Written by Masami Hiramatsu <mhiramat@redhat.com> -# -# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c - -# Awk implementation sanity check -function check_awk_implement() { - if (sprintf("%x", 0) != "0") - return "Your awk has a printf-format problem." - return "" -} - -# Clear working vars -function clear_vars() { - delete table - delete lptable2 - delete lptable1 - delete lptable3 - eid = -1 # escape id - gid = -1 # group id - aid = -1 # AVX id - tname = "" -} - -BEGIN { - # Implementation error checking - awkchecked = check_awk_implement() - if (awkchecked != "") { - print "Error: " awkchecked > "/dev/stderr" - print "Please try to use gawk." > "/dev/stderr" - exit 1 - } - - # Setup generating tables - print "/* x86 opcode map generated from x86-opcode-map.txt */" - print "/* Do not change this code. */\n" - ggid = 1 - geid = 1 - gaid = 0 - delete etable - delete gtable - delete atable - - opnd_expr = "^[A-Za-z/]" - ext_expr = "^\\(" - sep_expr = "^\\|$" - group_expr = "^Grp[0-9A-Za-z]+" - - imm_expr = "^[IJAOL][a-z]" - imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" - imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" - imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)" - imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)" - imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)" - imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)" - imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" - imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" - imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)" - imm_flag["Ob"] = "INAT_MOFFSET" - imm_flag["Ov"] = "INAT_MOFFSET" - imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" - - modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])" - force64_expr = "\\([df]64\\)" - rex_expr = "^REX(\\.[XRWB]+)*" - fpu_expr = "^ESC" # TODO - - lprefix1_expr = "\\((66|!F3)\\)" - lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" - lprefix_expr = "\\((66|F2|F3)\\)" - max_lprefix = 4 - - # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript - # accepts VEX prefix - vexok_opcode_expr = "^[vk].*" - vexok_expr = "\\(v1\\)" - # All opcodes with (v) superscript supports *only* VEX prefix - vexonly_expr = "\\(v\\)" - # All opcodes with (ev) superscript supports *only* EVEX prefix - evexonly_expr = "\\(ev\\)" - - prefix_expr = "\\(Prefix\\)" - prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" - prefix_num["REPNE"] = "INAT_PFX_REPNE" - prefix_num["REP/REPE"] = "INAT_PFX_REPE" - prefix_num["XACQUIRE"] = "INAT_PFX_REPNE" - prefix_num["XRELEASE"] = "INAT_PFX_REPE" - prefix_num["LOCK"] = "INAT_PFX_LOCK" - prefix_num["SEG=CS"] = "INAT_PFX_CS" - prefix_num["SEG=DS"] = "INAT_PFX_DS" - prefix_num["SEG=ES"] = "INAT_PFX_ES" - prefix_num["SEG=FS"] = "INAT_PFX_FS" - prefix_num["SEG=GS"] = "INAT_PFX_GS" - prefix_num["SEG=SS"] = "INAT_PFX_SS" - prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" - prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" - prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" - prefix_num["EVEX"] = "INAT_PFX_EVEX" - - clear_vars() -} - -function semantic_error(msg) { - print "Semantic error at " NR ": " msg > "/dev/stderr" - exit 1 -} - -function debug(msg) { - print "DEBUG: " msg -} - -function array_size(arr, i,c) { - c = 0 - for (i in arr) - c++ - return c -} - -/^Table:/ { - print "/* " $0 " */" - if (tname != "") - semantic_error("Hit Table: before EndTable:."); -} - -/^Referrer:/ { - if (NF != 1) { - # escape opcode table - ref = "" - for (i = 2; i <= NF; i++) - ref = ref $i - eid = escape[ref] - tname = sprintf("inat_escape_table_%d", eid) - } -} - -/^AVXcode:/ { - if (NF != 1) { - # AVX/escape opcode table - aid = $2 - if (gaid <= aid) - gaid = aid + 1 - if (tname == "") # AVX only opcode table - tname = sprintf("inat_avx_table_%d", $2) - } - if (aid == -1 && eid == -1) # primary opcode table - tname = "inat_primary_table" -} - -/^GrpTable:/ { - print "/* " $0 " */" - if (!($2 in group)) - semantic_error("No group: " $2 ) - gid = group[$2] - tname = "inat_group_table_" gid -} - -function print_table(tbl,name,fmt,n) -{ - print "const insn_attr_t " name " = {" - for (i = 0; i < n; i++) { - id = sprintf(fmt, i) - if (tbl[id]) - print " [" id "] = " tbl[id] "," - } - print "};" -} - -/^EndTable/ { - if (gid != -1) { - # print group tables - if (array_size(table) != 0) { - print_table(table, tname "[INAT_GROUP_TABLE_SIZE]", - "0x%x", 8) - gtable[gid,0] = tname - } - if (array_size(lptable1) != 0) { - print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]", - "0x%x", 8) - gtable[gid,1] = tname "_1" - } - if (array_size(lptable2) != 0) { - print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]", - "0x%x", 8) - gtable[gid,2] = tname "_2" - } - if (array_size(lptable3) != 0) { - print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]", - "0x%x", 8) - gtable[gid,3] = tname "_3" - } - } else { - # print primary/escaped tables - if (array_size(table) != 0) { - print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]", - "0x%02x", 256) - etable[eid,0] = tname - if (aid >= 0) - atable[aid,0] = tname - } - if (array_size(lptable1) != 0) { - print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]", - "0x%02x", 256) - etable[eid,1] = tname "_1" - if (aid >= 0) - atable[aid,1] = tname "_1" - } - if (array_size(lptable2) != 0) { - print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]", - "0x%02x", 256) - etable[eid,2] = tname "_2" - if (aid >= 0) - atable[aid,2] = tname "_2" - } - if (array_size(lptable3) != 0) { - print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]", - "0x%02x", 256) - etable[eid,3] = tname "_3" - if (aid >= 0) - atable[aid,3] = tname "_3" - } - } - print "" - clear_vars() -} - -function add_flags(old,new) { - if (old && new) - return old " | " new - else if (old) - return old - else - return new -} - -# convert operands to flags. -function convert_operands(count,opnd, i,j,imm,mod) -{ - imm = null - mod = null - for (j = 1; j <= count; j++) { - i = opnd[j] - if (match(i, imm_expr) == 1) { - if (!imm_flag[i]) - semantic_error("Unknown imm opnd: " i) - if (imm) { - if (i != "Ib") - semantic_error("Second IMM error") - imm = add_flags(imm, "INAT_SCNDIMM") - } else - imm = imm_flag[i] - } else if (match(i, modrm_expr)) - mod = "INAT_MODRM" - } - return add_flags(imm, mod) -} - -/^[0-9a-f]+\:/ { - if (NR == 1) - next - # get index - idx = "0x" substr($1, 1, index($1,":") - 1) - if (idx in table) - semantic_error("Redefine " idx " in " tname) - - # check if escaped opcode - if ("escape" == $2) { - if ($3 != "#") - semantic_error("No escaped name") - ref = "" - for (i = 4; i <= NF; i++) - ref = ref $i - if (ref in escape) - semantic_error("Redefine escape (" ref ")") - escape[ref] = geid - geid++ - table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")" - next - } - - variant = null - # converts - i = 2 - while (i <= NF) { - opcode = $(i++) - delete opnds - ext = null - flags = null - opnd = null - # parse one opcode - if (match($i, opnd_expr)) { - opnd = $i - count = split($(i++), opnds, ",") - flags = convert_operands(count, opnds) - } - if (match($i, ext_expr)) - ext = $(i++) - if (match($i, sep_expr)) - i++ - else if (i < NF) - semantic_error($i " is not a separator") - - # check if group opcode - if (match(opcode, group_expr)) { - if (!(opcode in group)) { - group[opcode] = ggid - ggid++ - } - flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")") - } - # check force(or default) 64bit - if (match(ext, force64_expr)) - flags = add_flags(flags, "INAT_FORCE64") - - # check REX prefix - if (match(opcode, rex_expr)) - flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)") - - # check coprocessor escape : TODO - if (match(opcode, fpu_expr)) - flags = add_flags(flags, "INAT_MODRM") - - # check VEX codes - if (match(ext, evexonly_expr)) - flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") - else if (match(ext, vexonly_expr)) - flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") - else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) - flags = add_flags(flags, "INAT_VEXOK") - - # check prefixes - if (match(ext, prefix_expr)) { - if (!prefix_num[opcode]) - semantic_error("Unknown prefix: " opcode) - flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")") - } - if (length(flags) == 0) - continue - # check if last prefix - if (match(ext, lprefix1_expr)) { - lptable1[idx] = add_flags(lptable1[idx],flags) - variant = "INAT_VARIANT" - } - if (match(ext, lprefix2_expr)) { - lptable2[idx] = add_flags(lptable2[idx],flags) - variant = "INAT_VARIANT" - } - if (match(ext, lprefix3_expr)) { - lptable3[idx] = add_flags(lptable3[idx],flags) - variant = "INAT_VARIANT" - } - if (!match(ext, lprefix_expr)){ - table[idx] = add_flags(table[idx],flags) - } - } - if (variant) - table[idx] = add_flags(table[idx],variant) -} - -END { - if (awkchecked != "") - exit 1 - # print escape opcode map's array - print "/* Escape opcode map array */" - print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ - "[INAT_LSTPFX_MAX + 1] = {" - for (i = 0; i < geid; i++) - for (j = 0; j < max_lprefix; j++) - if (etable[i,j]) - print " ["i"]["j"] = "etable[i,j]"," - print "};\n" - # print group opcode map's array - print "/* Group opcode map array */" - print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\ - "[INAT_LSTPFX_MAX + 1] = {" - for (i = 0; i < ggid; i++) - for (j = 0; j < max_lprefix; j++) - if (gtable[i,j]) - print " ["i"]["j"] = "gtable[i,j]"," - print "};\n" - # print AVX opcode map's array - print "/* AVX opcode map array */" - print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\ - "[INAT_LSTPFX_MAX + 1] = {" - for (i = 0; i < gaid; i++) - for (j = 0; j < max_lprefix; j++) - if (atable[i,j]) - print " ["i"]["j"] = "atable[i,j]"," - print "};" -} diff --git a/tools/perf/util/intel-pt-decoder/inat.c b/tools/perf/util/intel-pt-decoder/inat.c deleted file mode 100644 index 446c0413a27c..000000000000 --- a/tools/perf/util/intel-pt-decoder/inat.c +++ /dev/null @@ -1,82 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * x86 instruction attribute tables - * - * Written by Masami Hiramatsu <mhiramat@redhat.com> - */ -#include "insn.h" - -/* Attribute tables are generated from opcode map */ -#include "inat-tables.c" - -/* Attribute search APIs */ -insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode) -{ - return inat_primary_table[opcode]; -} - -int inat_get_last_prefix_id(insn_byte_t last_pfx) -{ - insn_attr_t lpfx_attr; - - lpfx_attr = inat_get_opcode_attribute(last_pfx); - return inat_last_prefix_id(lpfx_attr); -} - -insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id, - insn_attr_t esc_attr) -{ - const insn_attr_t *table; - int n; - - n = inat_escape_id(esc_attr); - - table = inat_escape_tables[n][0]; - if (!table) - return 0; - if (inat_has_variant(table[opcode]) && lpfx_id) { - table = inat_escape_tables[n][lpfx_id]; - if (!table) - return 0; - } - return table[opcode]; -} - -insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id, - insn_attr_t grp_attr) -{ - const insn_attr_t *table; - int n; - - n = inat_group_id(grp_attr); - - table = inat_group_tables[n][0]; - if (!table) - return inat_group_common_attribute(grp_attr); - if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) { - table = inat_group_tables[n][lpfx_id]; - if (!table) - return inat_group_common_attribute(grp_attr); - } - return table[X86_MODRM_REG(modrm)] | - inat_group_common_attribute(grp_attr); -} - -insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, - insn_byte_t vex_p) -{ - const insn_attr_t *table; - if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX) - return 0; - /* At first, this checks the master table */ - table = inat_avx_tables[vex_m][0]; - if (!table) - return 0; - if (!inat_is_group(table[opcode]) && vex_p) { - /* If this is not a group, get attribute directly */ - table = inat_avx_tables[vex_m][vex_p]; - if (!table) - return 0; - } - return table[opcode]; -} diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h deleted file mode 100644 index 877827b7c2c3..000000000000 --- a/tools/perf/util/intel-pt-decoder/inat.h +++ /dev/null @@ -1,230 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_X86_INAT_H -#define _ASM_X86_INAT_H -/* - * x86 instruction attributes - * - * Written by Masami Hiramatsu <mhiramat@redhat.com> - */ -#include "inat_types.h" - -/* - * Internal bits. Don't use bitmasks directly, because these bits are - * unstable. You should use checking functions. - */ - -#define INAT_OPCODE_TABLE_SIZE 256 -#define INAT_GROUP_TABLE_SIZE 8 - -/* Legacy last prefixes */ -#define INAT_PFX_OPNDSZ 1 /* 0x66 */ /* LPFX1 */ -#define INAT_PFX_REPE 2 /* 0xF3 */ /* LPFX2 */ -#define INAT_PFX_REPNE 3 /* 0xF2 */ /* LPFX3 */ -/* Other Legacy prefixes */ -#define INAT_PFX_LOCK 4 /* 0xF0 */ -#define INAT_PFX_CS 5 /* 0x2E */ -#define INAT_PFX_DS 6 /* 0x3E */ -#define INAT_PFX_ES 7 /* 0x26 */ -#define INAT_PFX_FS 8 /* 0x64 */ -#define INAT_PFX_GS 9 /* 0x65 */ -#define INAT_PFX_SS 10 /* 0x36 */ -#define INAT_PFX_ADDRSZ 11 /* 0x67 */ -/* x86-64 REX prefix */ -#define INAT_PFX_REX 12 /* 0x4X */ -/* AVX VEX prefixes */ -#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ -#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ -#define INAT_PFX_EVEX 15 /* EVEX prefix */ - -#define INAT_LSTPFX_MAX 3 -#define INAT_LGCPFX_MAX 11 - -/* Immediate size */ -#define INAT_IMM_BYTE 1 -#define INAT_IMM_WORD 2 -#define INAT_IMM_DWORD 3 -#define INAT_IMM_QWORD 4 -#define INAT_IMM_PTR 5 -#define INAT_IMM_VWORD32 6 -#define INAT_IMM_VWORD 7 - -/* Legacy prefix */ -#define INAT_PFX_OFFS 0 -#define INAT_PFX_BITS 4 -#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) -#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) -/* Escape opcodes */ -#define INAT_ESC_OFFS (INAT_PFX_OFFS + INAT_PFX_BITS) -#define INAT_ESC_BITS 2 -#define INAT_ESC_MAX ((1 << INAT_ESC_BITS) - 1) -#define INAT_ESC_MASK (INAT_ESC_MAX << INAT_ESC_OFFS) -/* Group opcodes (1-16) */ -#define INAT_GRP_OFFS (INAT_ESC_OFFS + INAT_ESC_BITS) -#define INAT_GRP_BITS 5 -#define INAT_GRP_MAX ((1 << INAT_GRP_BITS) - 1) -#define INAT_GRP_MASK (INAT_GRP_MAX << INAT_GRP_OFFS) -/* Immediates */ -#define INAT_IMM_OFFS (INAT_GRP_OFFS + INAT_GRP_BITS) -#define INAT_IMM_BITS 3 -#define INAT_IMM_MASK (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS) -/* Flags */ -#define INAT_FLAG_OFFS (INAT_IMM_OFFS + INAT_IMM_BITS) -#define INAT_MODRM (1 << (INAT_FLAG_OFFS)) -#define INAT_FORCE64 (1 << (INAT_FLAG_OFFS + 1)) -#define INAT_SCNDIMM (1 << (INAT_FLAG_OFFS + 2)) -#define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 3)) -#define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) -#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) -#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) -#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) -/* Attribute making macros for attribute tables */ -#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) -#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) -#define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) -#define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) - -/* Identifiers for segment registers */ -#define INAT_SEG_REG_IGNORE 0 -#define INAT_SEG_REG_DEFAULT 1 -#define INAT_SEG_REG_CS 2 -#define INAT_SEG_REG_SS 3 -#define INAT_SEG_REG_DS 4 -#define INAT_SEG_REG_ES 5 -#define INAT_SEG_REG_FS 6 -#define INAT_SEG_REG_GS 7 - -/* Attribute search APIs */ -extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); -extern int inat_get_last_prefix_id(insn_byte_t last_pfx); -extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, - int lpfx_id, - insn_attr_t esc_attr); -extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, - int lpfx_id, - insn_attr_t esc_attr); -extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, - insn_byte_t vex_m, - insn_byte_t vex_pp); - -/* Attribute checking functions */ -static inline int inat_is_legacy_prefix(insn_attr_t attr) -{ - attr &= INAT_PFX_MASK; - return attr && attr <= INAT_LGCPFX_MAX; -} - -static inline int inat_is_address_size_prefix(insn_attr_t attr) -{ - return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ; -} - -static inline int inat_is_operand_size_prefix(insn_attr_t attr) -{ - return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ; -} - -static inline int inat_is_rex_prefix(insn_attr_t attr) -{ - return (attr & INAT_PFX_MASK) == INAT_PFX_REX; -} - -static inline int inat_last_prefix_id(insn_attr_t attr) -{ - if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX) - return 0; - else - return attr & INAT_PFX_MASK; -} - -static inline int inat_is_vex_prefix(insn_attr_t attr) -{ - attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || - attr == INAT_PFX_EVEX; -} - -static inline int inat_is_evex_prefix(insn_attr_t attr) -{ - return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; -} - -static inline int inat_is_vex3_prefix(insn_attr_t attr) -{ - return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3; -} - -static inline int inat_is_escape(insn_attr_t attr) -{ - return attr & INAT_ESC_MASK; -} - -static inline int inat_escape_id(insn_attr_t attr) -{ - return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS; -} - -static inline int inat_is_group(insn_attr_t attr) -{ - return attr & INAT_GRP_MASK; -} - -static inline int inat_group_id(insn_attr_t attr) -{ - return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS; -} - -static inline int inat_group_common_attribute(insn_attr_t attr) -{ - return attr & ~INAT_GRP_MASK; -} - -static inline int inat_has_immediate(insn_attr_t attr) -{ - return attr & INAT_IMM_MASK; -} - -static inline int inat_immediate_size(insn_attr_t attr) -{ - return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS; -} - -static inline int inat_has_modrm(insn_attr_t attr) -{ - return attr & INAT_MODRM; -} - -static inline int inat_is_force64(insn_attr_t attr) -{ - return attr & INAT_FORCE64; -} - -static inline int inat_has_second_immediate(insn_attr_t attr) -{ - return attr & INAT_SCNDIMM; -} - -static inline int inat_has_moffset(insn_attr_t attr) -{ - return attr & INAT_MOFFSET; -} - -static inline int inat_has_variant(insn_attr_t attr) -{ - return attr & INAT_VARIANT; -} - -static inline int inat_accept_vex(insn_attr_t attr) -{ - return attr & INAT_VEXOK; -} - -static inline int inat_must_vex(insn_attr_t attr) -{ - return attr & (INAT_VEXONLY | INAT_EVEXONLY); -} - -static inline int inat_must_evex(insn_attr_t attr) -{ - return attr & INAT_EVEXONLY; -} -#endif diff --git a/tools/perf/util/intel-pt-decoder/inat_types.h b/tools/perf/util/intel-pt-decoder/inat_types.h deleted file mode 100644 index b047efa9ddc2..000000000000 --- a/tools/perf/util/intel-pt-decoder/inat_types.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_X86_INAT_TYPES_H -#define _ASM_X86_INAT_TYPES_H -/* - * x86 instruction attributes - * - * Written by Masami Hiramatsu <mhiramat@redhat.com> - */ - -/* Instruction attributes */ -typedef unsigned int insn_attr_t; -typedef unsigned char insn_byte_t; -typedef signed int insn_value_t; - -#endif diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c deleted file mode 100644 index 82783bf43b74..000000000000 --- a/tools/perf/util/intel-pt-decoder/insn.c +++ /dev/null @@ -1,593 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * x86 instruction analysis - * - * Copyright (C) IBM Corporation, 2002, 2004, 2009 - */ - -#ifdef __KERNEL__ -#include <linux/string.h> -#else -#include <string.h> -#endif -#include "inat.h" -#include "insn.h" - -/* Verify next sizeof(t) bytes can be on the same instruction */ -#define validate_next(t, insn, n) \ - ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) - -#define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) - -#define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); r; }) - -#define get_next(t, insn) \ - ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) - -#define peek_nbyte_next(t, insn, n) \ - ({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); }) - -#define peek_next(t, insn) peek_nbyte_next(t, insn, 0) - -/** - * insn_init() - initialize struct insn - * @insn: &struct insn to be initialized - * @kaddr: address (in kernel memory) of instruction (or copy thereof) - * @x86_64: !0 for 64-bit kernel or 64-bit app - */ -void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) -{ - /* - * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid - * even if the input buffer is long enough to hold them. - */ - if (buf_len > MAX_INSN_SIZE) - buf_len = MAX_INSN_SIZE; - - memset(insn, 0, sizeof(*insn)); - insn->kaddr = kaddr; - insn->end_kaddr = kaddr + buf_len; - insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; - insn->opnd_bytes = 4; - if (x86_64) - insn->addr_bytes = 8; - else - insn->addr_bytes = 4; -} - -/** - * insn_get_prefixes - scan x86 instruction prefix bytes - * @insn: &struct insn containing instruction - * - * Populates the @insn->prefixes bitmap, and updates @insn->next_byte - * to point to the (first) opcode. No effect if @insn->prefixes.got - * is already set. - */ -void insn_get_prefixes(struct insn *insn) -{ - struct insn_field *prefixes = &insn->prefixes; - insn_attr_t attr; - insn_byte_t b, lb; - int i, nb; - - if (prefixes->got) - return; - - nb = 0; - lb = 0; - b = peek_next(insn_byte_t, insn); - attr = inat_get_opcode_attribute(b); - while (inat_is_legacy_prefix(attr)) { - /* Skip if same prefix */ - for (i = 0; i < nb; i++) - if (prefixes->bytes[i] == b) - goto found; - if (nb == 4) - /* Invalid instruction */ - break; - prefixes->bytes[nb++] = b; - if (inat_is_address_size_prefix(attr)) { - /* address size switches 2/4 or 4/8 */ - if (insn->x86_64) - insn->addr_bytes ^= 12; - else - insn->addr_bytes ^= 6; - } else if (inat_is_operand_size_prefix(attr)) { - /* oprand size switches 2/4 */ - insn->opnd_bytes ^= 6; - } -found: - prefixes->nbytes++; - insn->next_byte++; - lb = b; - b = peek_next(insn_byte_t, insn); - attr = inat_get_opcode_attribute(b); - } - /* Set the last prefix */ - if (lb && lb != insn->prefixes.bytes[3]) { - if (unlikely(insn->prefixes.bytes[3])) { - /* Swap the last prefix */ - b = insn->prefixes.bytes[3]; - for (i = 0; i < nb; i++) - if (prefixes->bytes[i] == lb) - prefixes->bytes[i] = b; - } - insn->prefixes.bytes[3] = lb; - } - - /* Decode REX prefix */ - if (insn->x86_64) { - b = peek_next(insn_byte_t, insn); - attr = inat_get_opcode_attribute(b); - if (inat_is_rex_prefix(attr)) { - insn->rex_prefix.value = b; - insn->rex_prefix.nbytes = 1; - insn->next_byte++; - if (X86_REX_W(b)) - /* REX.W overrides opnd_size */ - insn->opnd_bytes = 8; - } - } - insn->rex_prefix.got = 1; - - /* Decode VEX prefix */ - b = peek_next(insn_byte_t, insn); - attr = inat_get_opcode_attribute(b); - if (inat_is_vex_prefix(attr)) { - insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1); - if (!insn->x86_64) { - /* - * In 32-bits mode, if the [7:6] bits (mod bits of - * ModRM) on the second byte are not 11b, it is - * LDS or LES or BOUND. - */ - if (X86_MODRM_MOD(b2) != 3) - goto vex_end; - } - insn->vex_prefix.bytes[0] = b; - insn->vex_prefix.bytes[1] = b2; - if (inat_is_evex_prefix(attr)) { - b2 = peek_nbyte_next(insn_byte_t, insn, 2); - insn->vex_prefix.bytes[2] = b2; - b2 = peek_nbyte_next(insn_byte_t, insn, 3); - insn->vex_prefix.bytes[3] = b2; - insn->vex_prefix.nbytes = 4; - insn->next_byte += 4; - if (insn->x86_64 && X86_VEX_W(b2)) - /* VEX.W overrides opnd_size */ - insn->opnd_bytes = 8; - } else if (inat_is_vex3_prefix(attr)) { - b2 = peek_nbyte_next(insn_byte_t, insn, 2); - insn->vex_prefix.bytes[2] = b2; - insn->vex_prefix.nbytes = 3; - insn->next_byte += 3; - if (insn->x86_64 && X86_VEX_W(b2)) - /* VEX.W overrides opnd_size */ - insn->opnd_bytes = 8; - } else { - /* - * For VEX2, fake VEX3-like byte#2. - * Makes it easier to decode vex.W, vex.vvvv, - * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0. - */ - insn->vex_prefix.bytes[2] = b2 & 0x7f; - insn->vex_prefix.nbytes = 2; - insn->next_byte += 2; - } - } -vex_end: - insn->vex_prefix.got = 1; - - prefixes->got = 1; - -err_out: - return; -} - -/** - * insn_get_opcode - collect opcode(s) - * @insn: &struct insn containing instruction - * - * Populates @insn->opcode, updates @insn->next_byte to point past the - * opcode byte(s), and set @insn->attr (except for groups). - * If necessary, first collects any preceding (prefix) bytes. - * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got - * is already 1. - */ -void insn_get_opcode(struct insn *insn) -{ - struct insn_field *opcode = &insn->opcode; - insn_byte_t op; - int pfx_id; - if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); - - /* Get first opcode */ - op = get_next(insn_byte_t, insn); - opcode->bytes[0] = op; - opcode->nbytes = 1; - - /* Check if there is VEX prefix or not */ - if (insn_is_avx(insn)) { - insn_byte_t m, p; - m = insn_vex_m_bits(insn); - p = insn_vex_p_bits(insn); - insn->attr = inat_get_avx_attribute(op, m, p); - if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || - (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ - } - - insn->attr = inat_get_opcode_attribute(op); - while (inat_is_escape(insn->attr)) { - /* Get escaped opcode */ - op = get_next(insn_byte_t, insn); - opcode->bytes[opcode->nbytes++] = op; - pfx_id = insn_last_prefix_id(insn); - insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); - } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ -end: - opcode->got = 1; - -err_out: - return; -} - -/** - * insn_get_modrm - collect ModRM byte, if any - * @insn: &struct insn containing instruction - * - * Populates @insn->modrm and updates @insn->next_byte to point past the - * ModRM byte, if any. If necessary, first collects the preceding bytes - * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. - */ -void insn_get_modrm(struct insn *insn) -{ - struct insn_field *modrm = &insn->modrm; - insn_byte_t pfx_id, mod; - if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); - - if (inat_has_modrm(insn->attr)) { - mod = get_next(insn_byte_t, insn); - modrm->value = mod; - modrm->nbytes = 1; - if (inat_is_group(insn->attr)) { - pfx_id = insn_last_prefix_id(insn); - insn->attr = inat_get_group_attribute(mod, pfx_id, - insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ - } - } - - if (insn->x86_64 && inat_is_force64(insn->attr)) - insn->opnd_bytes = 8; - modrm->got = 1; - -err_out: - return; -} - - -/** - * insn_rip_relative() - Does instruction use RIP-relative addressing mode? - * @insn: &struct insn containing instruction - * - * If necessary, first collects the instruction up to and including the - * ModRM byte. No effect if @insn->x86_64 is 0. - */ -int insn_rip_relative(struct insn *insn) -{ - struct insn_field *modrm = &insn->modrm; - - if (!insn->x86_64) - return 0; - if (!modrm->got) - insn_get_modrm(insn); - /* - * For rip-relative instructions, the mod field (top 2 bits) - * is zero and the r/m field (bottom 3 bits) is 0x5. - */ - return (modrm->nbytes && (modrm->value & 0xc7) == 0x5); -} - -/** - * insn_get_sib() - Get the SIB byte of instruction - * @insn: &struct insn containing instruction - * - * If necessary, first collects the instruction up to and including the - * ModRM byte. - */ -void insn_get_sib(struct insn *insn) -{ - insn_byte_t modrm; - - if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); - if (insn->modrm.nbytes) { - modrm = (insn_byte_t)insn->modrm.value; - if (insn->addr_bytes != 2 && - X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) { - insn->sib.value = get_next(insn_byte_t, insn); - insn->sib.nbytes = 1; - } - } - insn->sib.got = 1; - -err_out: - return; -} - - -/** - * insn_get_displacement() - Get the displacement of instruction - * @insn: &struct insn containing instruction - * - * If necessary, first collects the instruction up to and including the - * SIB byte. - * Displacement value is sign-expanded. - */ -void insn_get_displacement(struct insn *insn) -{ - insn_byte_t mod, rm, base; - - if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); - if (insn->modrm.nbytes) { - /* - * Interpreting the modrm byte: - * mod = 00 - no displacement fields (exceptions below) - * mod = 01 - 1-byte displacement field - * mod = 10 - displacement field is 4 bytes, or 2 bytes if - * address size = 2 (0x67 prefix in 32-bit mode) - * mod = 11 - no memory operand - * - * If address size = 2... - * mod = 00, r/m = 110 - displacement field is 2 bytes - * - * If address size != 2... - * mod != 11, r/m = 100 - SIB byte exists - * mod = 00, SIB base = 101 - displacement field is 4 bytes - * mod = 00, r/m = 101 - rip-relative addressing, displacement - * field is 4 bytes - */ - mod = X86_MODRM_MOD(insn->modrm.value); - rm = X86_MODRM_RM(insn->modrm.value); - base = X86_SIB_BASE(insn->sib.value); - if (mod == 3) - goto out; - if (mod == 1) { - insn->displacement.value = get_next(signed char, insn); - insn->displacement.nbytes = 1; - } else if (insn->addr_bytes == 2) { - if ((mod == 0 && rm == 6) || mod == 2) { - insn->displacement.value = - get_next(short, insn); - insn->displacement.nbytes = 2; - } - } else { - if ((mod == 0 && rm == 5) || mod == 2 || - (mod == 0 && base == 5)) { - insn->displacement.value = get_next(int, insn); - insn->displacement.nbytes = 4; - } - } - } -out: - insn->displacement.got = 1; - -err_out: - return; -} - -/* Decode moffset16/32/64. Return 0 if failed */ -static int __get_moffset(struct insn *insn) -{ - switch (insn->addr_bytes) { - case 2: - insn->moffset1.value = get_next(short, insn); - insn->moffset1.nbytes = 2; - break; - case 4: - insn->moffset1.value = get_next(int, insn); - insn->moffset1.nbytes = 4; - break; - case 8: - insn->moffset1.value = get_next(int, insn); - insn->moffset1.nbytes = 4; - insn->moffset2.value = get_next(int, insn); - insn->moffset2.nbytes = 4; - break; - default: /* opnd_bytes must be modified manually */ - goto err_out; - } - insn->moffset1.got = insn->moffset2.got = 1; - - return 1; - -err_out: - return 0; -} - -/* Decode imm v32(Iz). Return 0 if failed */ -static int __get_immv32(struct insn *insn) -{ - switch (insn->opnd_bytes) { - case 2: - insn->immediate.value = get_next(short, insn); - insn->immediate.nbytes = 2; - break; - case 4: - case 8: - insn->immediate.value = get_next(int, insn); - insn->immediate.nbytes = 4; - break; - default: /* opnd_bytes must be modified manually */ - goto err_out; - } - - return 1; - -err_out: - return 0; -} - -/* Decode imm v64(Iv/Ov), Return 0 if failed */ -static int __get_immv(struct insn *insn) -{ - switch (insn->opnd_bytes) { - case 2: - insn->immediate1.value = get_next(short, insn); - insn->immediate1.nbytes = 2; - break; - case 4: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - break; - case 8: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - insn->immediate2.value = get_next(int, insn); - insn->immediate2.nbytes = 4; - break; - default: /* opnd_bytes must be modified manually */ - goto err_out; - } - insn->immediate1.got = insn->immediate2.got = 1; - - return 1; -err_out: - return 0; -} - -/* Decode ptr16:16/32(Ap) */ -static int __get_immptr(struct insn *insn) -{ - switch (insn->opnd_bytes) { - case 2: - insn->immediate1.value = get_next(short, insn); - insn->immediate1.nbytes = 2; - break; - case 4: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - break; - case 8: - /* ptr16:64 is not exist (no segment) */ - return 0; - default: /* opnd_bytes must be modified manually */ - goto err_out; - } - insn->immediate2.value = get_next(unsigned short, insn); - insn->immediate2.nbytes = 2; - insn->immediate1.got = insn->immediate2.got = 1; - - return 1; -err_out: - return 0; -} - -/** - * insn_get_immediate() - Get the immediates of instruction - * @insn: &struct insn containing instruction - * - * If necessary, first collects the instruction up to and including the - * displacement bytes. - * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) - */ -void insn_get_immediate(struct insn *insn) -{ - if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); - - if (inat_has_moffset(insn->attr)) { - if (!__get_moffset(insn)) - goto err_out; - goto done; - } - - if (!inat_has_immediate(insn->attr)) - /* no immediates */ - goto done; - - switch (inat_immediate_size(insn->attr)) { - case INAT_IMM_BYTE: - insn->immediate.value = get_next(signed char, insn); - insn->immediate.nbytes = 1; - break; - case INAT_IMM_WORD: - insn->immediate.value = get_next(short, insn); - insn->immediate.nbytes = 2; - break; - case INAT_IMM_DWORD: - insn->immediate.value = get_next(int, insn); - insn->immediate.nbytes = 4; - break; - case INAT_IMM_QWORD: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - insn->immediate2.value = get_next(int, insn); - insn->immediate2.nbytes = 4; - break; - case INAT_IMM_PTR: - if (!__get_immptr(insn)) - goto err_out; - break; - case INAT_IMM_VWORD32: - if (!__get_immv32(insn)) - goto err_out; - break; - case INAT_IMM_VWORD: - if (!__get_immv(insn)) - goto err_out; - break; - default: - /* Here, insn must have an immediate, but failed */ - goto err_out; - } - if (inat_has_second_immediate(insn->attr)) { - insn->immediate2.value = get_next(signed char, insn); - insn->immediate2.nbytes = 1; - } -done: - insn->immediate.got = 1; - -err_out: - return; -} - -/** - * insn_get_length() - Get the length of instruction - * @insn: &struct insn containing instruction - * - * If necessary, first collects the instruction up to and including the - * immediates bytes. - */ -void insn_get_length(struct insn *insn) -{ - if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); - insn->length = (unsigned char)((unsigned long)insn->next_byte - - (unsigned long)insn->kaddr); -} diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h deleted file mode 100644 index 37a4c390750b..000000000000 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ /dev/null @@ -1,216 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_X86_INSN_H -#define _ASM_X86_INSN_H -/* - * x86 instruction analysis - * - * Copyright (C) IBM Corporation, 2009 - */ - -/* insn_attr_t is defined in inat.h */ -#include "inat.h" - -struct insn_field { - union { - insn_value_t value; - insn_byte_t bytes[4]; - }; - /* !0 if we've run insn_get_xxx() for this field */ - unsigned char got; - unsigned char nbytes; -}; - -struct insn { - struct insn_field prefixes; /* - * Prefixes - * prefixes.bytes[3]: last prefix - */ - struct insn_field rex_prefix; /* REX prefix */ - struct insn_field vex_prefix; /* VEX prefix */ - struct insn_field opcode; /* - * opcode.bytes[0]: opcode1 - * opcode.bytes[1]: opcode2 - * opcode.bytes[2]: opcode3 - */ - struct insn_field modrm; - struct insn_field sib; - struct insn_field displacement; - union { - struct insn_field immediate; - struct insn_field moffset1; /* for 64bit MOV */ - struct insn_field immediate1; /* for 64bit imm or off16/32 */ - }; - union { - struct insn_field moffset2; /* for 64bit MOV */ - struct insn_field immediate2; /* for 64bit imm or seg16 */ - }; - - insn_attr_t attr; - unsigned char opnd_bytes; - unsigned char addr_bytes; - unsigned char length; - unsigned char x86_64; - - const insn_byte_t *kaddr; /* kernel address of insn to analyze */ - const insn_byte_t *end_kaddr; /* kernel address of last insn in buffer */ - const insn_byte_t *next_byte; -}; - -#define MAX_INSN_SIZE 15 - -#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) -#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) -#define X86_MODRM_RM(modrm) ((modrm) & 0x07) - -#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6) -#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3) -#define X86_SIB_BASE(sib) ((sib) & 0x07) - -#define X86_REX_W(rex) ((rex) & 8) -#define X86_REX_R(rex) ((rex) & 4) -#define X86_REX_X(rex) ((rex) & 2) -#define X86_REX_B(rex) ((rex) & 1) - -/* VEX bit flags */ -#define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */ -#define X86_VEX_R(vex) ((vex) & 0x80) /* VEX2/3 Byte1 */ -#define X86_VEX_X(vex) ((vex) & 0x40) /* VEX3 Byte1 */ -#define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ -#define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ -/* VEX bit fields */ -#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ -#define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ -#define X86_VEX2_M 1 /* VEX2.M always 1 */ -#define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ -#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */ -#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ - -extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); - -/* Attribute will be determined after getting ModRM (for opcode groups) */ -static inline void insn_get_attribute(struct insn *insn) -{ - insn_get_modrm(insn); -} - -/* Instruction uses RIP-relative addressing */ -extern int insn_rip_relative(struct insn *insn); - -/* Init insn for kernel text */ -static inline void kernel_insn_init(struct insn *insn, - const void *kaddr, int buf_len) -{ -#ifdef CONFIG_X86_64 - insn_init(insn, kaddr, buf_len, 1); -#else /* CONFIG_X86_32 */ - insn_init(insn, kaddr, buf_len, 0); -#endif -} - -static inline int insn_is_avx(struct insn *insn) -{ - if (!insn->prefixes.got) - insn_get_prefixes(insn); - return (insn->vex_prefix.value != 0); -} - -static inline int insn_is_evex(struct insn *insn) -{ - if (!insn->prefixes.got) - insn_get_prefixes(insn); - return (insn->vex_prefix.nbytes == 4); -} - -/* Ensure this instruction is decoded completely */ -static inline int insn_complete(struct insn *insn) -{ - return insn->opcode.got && insn->modrm.got && insn->sib.got && - insn->displacement.got && insn->immediate.got; -} - -static inline insn_byte_t insn_vex_m_bits(struct insn *insn) -{ - if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ - return X86_VEX2_M; - else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ - return X86_VEX3_M(insn->vex_prefix.bytes[1]); - else /* EVEX */ - return X86_EVEX_M(insn->vex_prefix.bytes[1]); -} - -static inline insn_byte_t insn_vex_p_bits(struct insn *insn) -{ - if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ - return X86_VEX_P(insn->vex_prefix.bytes[1]); - else - return X86_VEX_P(insn->vex_prefix.bytes[2]); -} - -/* Get the last prefix id from last prefix or VEX prefix */ -static inline int insn_last_prefix_id(struct insn *insn) -{ - if (insn_is_avx(insn)) - return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */ - - if (insn->prefixes.bytes[3]) - return inat_get_last_prefix_id(insn->prefixes.bytes[3]); - - return 0; -} - -/* Offset of each field from kaddr */ -static inline int insn_offset_rex_prefix(struct insn *insn) -{ - return insn->prefixes.nbytes; -} -static inline int insn_offset_vex_prefix(struct insn *insn) -{ - return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes; -} -static inline int insn_offset_opcode(struct insn *insn) -{ - return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes; -} -static inline int insn_offset_modrm(struct insn *insn) -{ - return insn_offset_opcode(insn) + insn->opcode.nbytes; -} -static inline int insn_offset_sib(struct insn *insn) -{ - return insn_offset_modrm(insn) + insn->modrm.nbytes; -} -static inline int insn_offset_displacement(struct insn *insn) -{ - return insn_offset_sib(insn) + insn->sib.nbytes; -} -static inline int insn_offset_immediate(struct insn *insn) -{ - return insn_offset_displacement(insn) + insn->displacement.nbytes; -} - -#define POP_SS_OPCODE 0x1f -#define MOV_SREG_OPCODE 0x8e - -/* - * Intel SDM Vol.3A 6.8.3 states; - * "Any single-step trap that would be delivered following the MOV to SS - * instruction or POP to SS instruction (because EFLAGS.TF is 1) is - * suppressed." - * This function returns true if @insn is MOV SS or POP SS. On these - * instructions, single stepping is suppressed. - */ -static inline int insn_masking_exception(struct insn *insn) -{ - return insn->opcode.bytes[0] == POP_SS_OPCODE || - (insn->opcode.bytes[0] == MOV_SREG_OPCODE && - X86_MODRM_REG(insn->modrm.bytes[0]) == 2); -} - -#endif /* _ASM_X86_INSN_H */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 3bfdf2b7a96a..f8ccfd6be0ee 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -14,9 +14,9 @@ #include <stdint.h> #include <inttypes.h> #include <linux/compiler.h> +#include <linux/string.h> #include <linux/zalloc.h> -#include "../cache.h" #include "../auxtrace.h" #include "intel-pt-insn-decoder.h" diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 598f56be9f17..fb8a3558d3d5 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -4,17 +4,17 @@ * Copyright (c) 2013-2014, Intel Corporation. */ +#include <linux/kernel.h> #include <stdio.h> #include <string.h> #include <endian.h> #include <byteswap.h> +#include "../../../arch/x86/include/asm/insn.h" -#include "event.h" - -#include "insn.h" +#include "../../../arch/x86/lib/inat.c" +#include "../../../arch/x86/lib/insn.c" -#include "inat.c" -#include "insn.c" +#include "event.h" #include "intel-pt-insn-decoder.h" #include "dump-insn.h" diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt deleted file mode 100644 index e0b85930dd77..000000000000 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ /dev/null @@ -1,1072 +0,0 @@ -# x86 Opcode Maps -# -# This is (mostly) based on following documentations. -# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C -# (#326018-047US, June 2013) -# -#<Opcode maps> -# Table: table-name -# Referrer: escaped-name -# AVXcode: avx-code -# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] -# (or) -# opcode: escape # escaped-name -# EndTable -# -# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix -# mnemonics that begin with lowercase 'k' accept a VEX prefix -# -#<group maps> -# GrpTable: GrpXXX -# reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] -# EndTable -# -# AVX Superscripts -# (ev): this opcode requires EVEX prefix. -# (evo): this opcode is changed by EVEX prefix (EVEX opcode) -# (v): this opcode requires VEX prefix. -# (v1): this opcode only supports 128bit VEX. -# -# Last Prefix Superscripts -# - (66): the last prefix is 0x66 -# - (F3): the last prefix is 0xF3 -# - (F2): the last prefix is 0xF2 -# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case) -# - (66&F2): Both 0x66 and 0xF2 prefixes are specified. - -Table: one byte opcode -Referrer: -AVXcode: -# 0x00 - 0x0f -00: ADD Eb,Gb -01: ADD Ev,Gv -02: ADD Gb,Eb -03: ADD Gv,Ev -04: ADD AL,Ib -05: ADD rAX,Iz -06: PUSH ES (i64) -07: POP ES (i64) -08: OR Eb,Gb -09: OR Ev,Gv -0a: OR Gb,Eb -0b: OR Gv,Ev -0c: OR AL,Ib -0d: OR rAX,Iz -0e: PUSH CS (i64) -0f: escape # 2-byte escape -# 0x10 - 0x1f -10: ADC Eb,Gb -11: ADC Ev,Gv -12: ADC Gb,Eb -13: ADC Gv,Ev -14: ADC AL,Ib -15: ADC rAX,Iz -16: PUSH SS (i64) -17: POP SS (i64) -18: SBB Eb,Gb -19: SBB Ev,Gv -1a: SBB Gb,Eb -1b: SBB Gv,Ev -1c: SBB AL,Ib -1d: SBB rAX,Iz -1e: PUSH DS (i64) -1f: POP DS (i64) -# 0x20 - 0x2f -20: AND Eb,Gb -21: AND Ev,Gv -22: AND Gb,Eb -23: AND Gv,Ev -24: AND AL,Ib -25: AND rAx,Iz -26: SEG=ES (Prefix) -27: DAA (i64) -28: SUB Eb,Gb -29: SUB Ev,Gv -2a: SUB Gb,Eb -2b: SUB Gv,Ev -2c: SUB AL,Ib -2d: SUB rAX,Iz -2e: SEG=CS (Prefix) -2f: DAS (i64) -# 0x30 - 0x3f -30: XOR Eb,Gb -31: XOR Ev,Gv -32: XOR Gb,Eb -33: XOR Gv,Ev -34: XOR AL,Ib -35: XOR rAX,Iz -36: SEG=SS (Prefix) -37: AAA (i64) -38: CMP Eb,Gb -39: CMP Ev,Gv -3a: CMP Gb,Eb -3b: CMP Gv,Ev -3c: CMP AL,Ib -3d: CMP rAX,Iz -3e: SEG=DS (Prefix) -3f: AAS (i64) -# 0x40 - 0x4f -40: INC eAX (i64) | REX (o64) -41: INC eCX (i64) | REX.B (o64) -42: INC eDX (i64) | REX.X (o64) -43: INC eBX (i64) | REX.XB (o64) -44: INC eSP (i64) | REX.R (o64) -45: INC eBP (i64) | REX.RB (o64) -46: INC eSI (i64) | REX.RX (o64) -47: INC eDI (i64) | REX.RXB (o64) -48: DEC eAX (i64) | REX.W (o64) -49: DEC eCX (i64) | REX.WB (o64) -4a: DEC eDX (i64) | REX.WX (o64) -4b: DEC eBX (i64) | REX.WXB (o64) -4c: DEC eSP (i64) | REX.WR (o64) -4d: DEC eBP (i64) | REX.WRB (o64) -4e: DEC eSI (i64) | REX.WRX (o64) -4f: DEC eDI (i64) | REX.WRXB (o64) -# 0x50 - 0x5f -50: PUSH rAX/r8 (d64) -51: PUSH rCX/r9 (d64) -52: PUSH rDX/r10 (d64) -53: PUSH rBX/r11 (d64) -54: PUSH rSP/r12 (d64) -55: PUSH rBP/r13 (d64) -56: PUSH rSI/r14 (d64) -57: PUSH rDI/r15 (d64) -58: POP rAX/r8 (d64) -59: POP rCX/r9 (d64) -5a: POP rDX/r10 (d64) -5b: POP rBX/r11 (d64) -5c: POP rSP/r12 (d64) -5d: POP rBP/r13 (d64) -5e: POP rSI/r14 (d64) -5f: POP rDI/r15 (d64) -# 0x60 - 0x6f -60: PUSHA/PUSHAD (i64) -61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) | EVEX (Prefix) -63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) -64: SEG=FS (Prefix) -65: SEG=GS (Prefix) -66: Operand-Size (Prefix) -67: Address-Size (Prefix) -68: PUSH Iz (d64) -69: IMUL Gv,Ev,Iz -6a: PUSH Ib (d64) -6b: IMUL Gv,Ev,Ib -6c: INS/INSB Yb,DX -6d: INS/INSW/INSD Yz,DX -6e: OUTS/OUTSB DX,Xb -6f: OUTS/OUTSW/OUTSD DX,Xz -# 0x70 - 0x7f -70: JO Jb -71: JNO Jb -72: JB/JNAE/JC Jb -73: JNB/JAE/JNC Jb -74: JZ/JE Jb -75: JNZ/JNE Jb -76: JBE/JNA Jb -77: JNBE/JA Jb -78: JS Jb -79: JNS Jb -7a: JP/JPE Jb -7b: JNP/JPO Jb -7c: JL/JNGE Jb -7d: JNL/JGE Jb -7e: JLE/JNG Jb -7f: JNLE/JG Jb -# 0x80 - 0x8f -80: Grp1 Eb,Ib (1A) -81: Grp1 Ev,Iz (1A) -82: Grp1 Eb,Ib (1A),(i64) -83: Grp1 Ev,Ib (1A) -84: TEST Eb,Gb -85: TEST Ev,Gv -86: XCHG Eb,Gb -87: XCHG Ev,Gv -88: MOV Eb,Gb -89: MOV Ev,Gv -8a: MOV Gb,Eb -8b: MOV Gv,Ev -8c: MOV Ev,Sw -8d: LEA Gv,M -8e: MOV Sw,Ew -8f: Grp1A (1A) | POP Ev (d64) -# 0x90 - 0x9f -90: NOP | PAUSE (F3) | XCHG r8,rAX -91: XCHG rCX/r9,rAX -92: XCHG rDX/r10,rAX -93: XCHG rBX/r11,rAX -94: XCHG rSP/r12,rAX -95: XCHG rBP/r13,rAX -96: XCHG rSI/r14,rAX -97: XCHG rDI/r15,rAX -98: CBW/CWDE/CDQE -99: CWD/CDQ/CQO -9a: CALLF Ap (i64) -9b: FWAIT/WAIT -9c: PUSHF/D/Q Fv (d64) -9d: POPF/D/Q Fv (d64) -9e: SAHF -9f: LAHF -# 0xa0 - 0xaf -a0: MOV AL,Ob -a1: MOV rAX,Ov -a2: MOV Ob,AL -a3: MOV Ov,rAX -a4: MOVS/B Yb,Xb -a5: MOVS/W/D/Q Yv,Xv -a6: CMPS/B Xb,Yb -a7: CMPS/W/D Xv,Yv -a8: TEST AL,Ib -a9: TEST rAX,Iz -aa: STOS/B Yb,AL -ab: STOS/W/D/Q Yv,rAX -ac: LODS/B AL,Xb -ad: LODS/W/D/Q rAX,Xv -ae: SCAS/B AL,Yb -# Note: The May 2011 Intel manual shows Xv for the second parameter of the -# next instruction but Yv is correct -af: SCAS/W/D/Q rAX,Yv -# 0xb0 - 0xbf -b0: MOV AL/R8L,Ib -b1: MOV CL/R9L,Ib -b2: MOV DL/R10L,Ib -b3: MOV BL/R11L,Ib -b4: MOV AH/R12L,Ib -b5: MOV CH/R13L,Ib -b6: MOV DH/R14L,Ib -b7: MOV BH/R15L,Ib -b8: MOV rAX/r8,Iv -b9: MOV rCX/r9,Iv -ba: MOV rDX/r10,Iv -bb: MOV rBX/r11,Iv -bc: MOV rSP/r12,Iv -bd: MOV rBP/r13,Iv -be: MOV rSI/r14,Iv -bf: MOV rDI/r15,Iv -# 0xc0 - 0xcf -c0: Grp2 Eb,Ib (1A) -c1: Grp2 Ev,Ib (1A) -c2: RETN Iw (f64) -c3: RETN -c4: LES Gz,Mp (i64) | VEX+2byte (Prefix) -c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix) -c6: Grp11A Eb,Ib (1A) -c7: Grp11B Ev,Iz (1A) -c8: ENTER Iw,Ib -c9: LEAVE (d64) -ca: RETF Iw -cb: RETF -cc: INT3 -cd: INT Ib -ce: INTO (i64) -cf: IRET/D/Q -# 0xd0 - 0xdf -d0: Grp2 Eb,1 (1A) -d1: Grp2 Ev,1 (1A) -d2: Grp2 Eb,CL (1A) -d3: Grp2 Ev,CL (1A) -d4: AAM Ib (i64) -d5: AAD Ib (i64) -d6: -d7: XLAT/XLATB -d8: ESC -d9: ESC -da: ESC -db: ESC -dc: ESC -dd: ESC -de: ESC -df: ESC -# 0xe0 - 0xef -# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix -# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation -# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD. -e0: LOOPNE/LOOPNZ Jb (f64) -e1: LOOPE/LOOPZ Jb (f64) -e2: LOOP Jb (f64) -e3: JrCXZ Jb (f64) -e4: IN AL,Ib -e5: IN eAX,Ib -e6: OUT Ib,AL -e7: OUT Ib,eAX -# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset -# in "near" jumps and calls is 16-bit. For CALL, -# push of return address is 16-bit wide, RSP is decremented by 2 -# but is not truncated to 16 bits, unlike RIP. -e8: CALL Jz (f64) -e9: JMP-near Jz (f64) -ea: JMP-far Ap (i64) -eb: JMP-short Jb (f64) -ec: IN AL,DX -ed: IN eAX,DX -ee: OUT DX,AL -ef: OUT DX,eAX -# 0xf0 - 0xff -f0: LOCK (Prefix) -f1: -f2: REPNE (Prefix) | XACQUIRE (Prefix) -f3: REP/REPE (Prefix) | XRELEASE (Prefix) -f4: HLT -f5: CMC -f6: Grp3_1 Eb (1A) -f7: Grp3_2 Ev (1A) -f8: CLC -f9: STC -fa: CLI -fb: STI -fc: CLD -fd: STD -fe: Grp4 (1A) -ff: Grp5 (1A) -EndTable - -Table: 2-byte opcode (0x0f) -Referrer: 2-byte escape -AVXcode: 1 -# 0x0f 0x00-0x0f -00: Grp6 (1A) -01: Grp7 (1A) -02: LAR Gv,Ew -03: LSL Gv,Ew -04: -05: SYSCALL (o64) -06: CLTS -07: SYSRET (o64) -08: INVD -09: WBINVD -0a: -0b: UD2 (1B) -0c: -# AMD's prefetch group. Intel supports prefetchw(/1) only. -0d: GrpP -0e: FEMMS -# 3DNow! uses the last imm byte as opcode extension. -0f: 3DNow! Pq,Qq,Ib -# 0x0f 0x10-0x1f -# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands -# but it actually has operands. And also, vmovss and vmovsd only accept 128bit. -# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form. -# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming -# Reference A.1 -10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1) -11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1) -12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2) -13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1) -14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66) -15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66) -16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3) -17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1) -18: Grp16 (1A) -19: -# Intel SDM opcode map does not list MPX instructions. For now using Gv for -# bnd registers and Ev for everything else is OK because the instruction -# decoder does not use the information except as an indication that there is -# a ModR/M byte. -1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev -1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv -1c: -1d: -1e: -1f: NOP Ev -# 0x0f 0x20-0x2f -20: MOV Rd,Cd -21: MOV Rd,Dd -22: MOV Cd,Rd -23: MOV Dd,Rd -24: -25: -26: -27: -28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66) -29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66) -2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1) -2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66) -2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1) -2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1) -2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1) -2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1) -# 0x0f 0x30-0x3f -30: WRMSR -31: RDTSC -32: RDMSR -33: RDPMC -34: SYSENTER -35: SYSEXIT -36: -37: GETSEC -38: escape # 3-byte escape 1 -39: -3a: escape # 3-byte escape 2 -3b: -3c: -3d: -3e: -3f: -# 0x0f 0x40-0x4f -40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) -42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) -43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) -45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) -46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) -47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) -48: CMOVS Gv,Ev -49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) -4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk -4c: CMOVL/NGE Gv,Ev -4d: CMOVNL/GE Gv,Ev -4e: CMOVLE/NG Gv,Ev -4f: CMOVNLE/G Gv,Ev -# 0x0f 0x50-0x5f -50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66) -51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1) -52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1) -53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1) -54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66) -55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66) -56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66) -57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66) -58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) -59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) -5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) -5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) -5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) -5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) -5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1) -# 0x0f 0x60-0x6f -60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1) -61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1) -62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1) -63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1) -64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1) -65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1) -66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1) -67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1) -68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1) -69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1) -6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1) -6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1) -6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) -6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) -6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) -# 0x0f 0x70-0x7f -70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) -71: Grp12 (1A) -72: Grp13 (1A) -73: Grp14 (1A) -74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1) -75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1) -76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) -# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. -77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) -79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) -7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) -7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) -7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) -7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) -7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) -# 0x0f 0x80-0x8f -# Note: "forced64" is Intel CPU behavior (see comment about CALL insn). -80: JO Jz (f64) -81: JNO Jz (f64) -82: JB/JC/JNAE Jz (f64) -83: JAE/JNB/JNC Jz (f64) -84: JE/JZ Jz (f64) -85: JNE/JNZ Jz (f64) -86: JBE/JNA Jz (f64) -87: JA/JNBE Jz (f64) -88: JS Jz (f64) -89: JNS Jz (f64) -8a: JP/JPE Jz (f64) -8b: JNP/JPO Jz (f64) -8c: JL/JNGE Jz (f64) -8d: JNL/JGE Jz (f64) -8e: JLE/JNG Jz (f64) -8f: JNLE/JG Jz (f64) -# 0x0f 0x90-0x9f -90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) -91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) -92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) -93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) -94: SETE/Z Eb -95: SETNE/NZ Eb -96: SETBE/NA Eb -97: SETA/NBE Eb -98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) -99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) -9a: SETP/PE Eb -9b: SETNP/PO Eb -9c: SETL/NGE Eb -9d: SETNL/GE Eb -9e: SETLE/NG Eb -9f: SETNLE/G Eb -# 0x0f 0xa0-0xaf -a0: PUSH FS (d64) -a1: POP FS (d64) -a2: CPUID -a3: BT Ev,Gv -a4: SHLD Ev,Gv,Ib -a5: SHLD Ev,Gv,CL -a6: GrpPDLK -a7: GrpRNG -a8: PUSH GS (d64) -a9: POP GS (d64) -aa: RSM -ab: BTS Ev,Gv -ac: SHRD Ev,Gv,Ib -ad: SHRD Ev,Gv,CL -ae: Grp15 (1A),(1C) -af: IMUL Gv,Ev -# 0x0f 0xb0-0xbf -b0: CMPXCHG Eb,Gb -b1: CMPXCHG Ev,Gv -b2: LSS Gv,Mp -b3: BTR Ev,Gv -b4: LFS Gv,Mp -b5: LGS Gv,Mp -b6: MOVZX Gv,Eb -b7: MOVZX Gv,Ew -b8: JMPE (!F3) | POPCNT Gv,Ev (F3) -b9: Grp10 (1A) -ba: Grp8 Ev,Ib (1A) -bb: BTC Ev,Gv -bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3) -bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3) -be: MOVSX Gv,Eb -bf: MOVSX Gv,Ew -# 0x0f 0xc0-0xcf -c0: XADD Eb,Gb -c1: XADD Ev,Gv -c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1) -c3: movnti My,Gy -c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1) -c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1) -c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66) -c7: Grp9 (1A) -c8: BSWAP RAX/EAX/R8/R8D -c9: BSWAP RCX/ECX/R9/R9D -ca: BSWAP RDX/EDX/R10/R10D -cb: BSWAP RBX/EBX/R11/R11D -cc: BSWAP RSP/ESP/R12/R12D -cd: BSWAP RBP/EBP/R13/R13D -ce: BSWAP RSI/ESI/R14/R14D -cf: BSWAP RDI/EDI/R15/R15D -# 0x0f 0xd0-0xdf -d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2) -d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1) -d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1) -d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1) -d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1) -d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1) -d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2) -d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) -d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) -d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) -da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) -dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) -dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) -de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) -# 0x0f 0xe0-0xef -e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) -e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) -e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) -e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) -e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) -e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) -e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) -e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) -e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) -ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) -ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) -ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) -ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) -# 0x0f 0xf0-0xff -f0: vlddqu Vx,Mx (F2) -f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) -f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1) -f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1) -f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1) -f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1) -f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1) -f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1) -f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1) -f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1) -fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1) -fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) -fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) -fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) -fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: UD0 -EndTable - -Table: 3-byte opcode 1 (0x0f 0x38) -Referrer: 3-byte escape 1 -AVXcode: 2 -# 0x0f 0x38 0x00-0x0f -00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1) -01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1) -02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1) -03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1) -04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1) -05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1) -06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1) -07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1) -08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1) -09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1) -0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1) -0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1) -0c: vpermilps Vx,Hx,Wx (66),(v) -0d: vpermilpd Vx,Hx,Wx (66),(v) -0e: vtestps Vx,Wx (66),(v) -0f: vtestpd Vx,Wx (66),(v) -# 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) -11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) -12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) -13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) -14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) -15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) -16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) -17: vptest Vx,Wx (66) -18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) -1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) -1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) -1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) -1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) -1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: vpabsq Vx,Wx (66),(ev) -# 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) -21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) -24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) -26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) -27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) -28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) -2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) -2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) -2e: vmaskmovps Mx,Hx,Vx (66),(v) -2f: vmaskmovpd Mx,Hx,Vx (66),(v) -# 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) -31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) -34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) -36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) -37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) -39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) -3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) -3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) -3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) -3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) -# 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) -41: vphminposuw Vdq,Wdq (66),(v1) -42: vgetexpps/d Vx,Wx (66),(ev) -43: vgetexpss/d Vx,Hx,Wx (66),(ev) -44: vplzcntd/q Vx,Wx (66),(ev) -45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) -47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x4b -4c: vrcp14ps/d Vpd,Wpd (66),(ev) -4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) -4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) -4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -# Skip 0x50-0x57 -58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) -5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) -5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) -# Skip 0x5c-0x63 -64: vpblendmd/q Vx,Hx,Wx (66),(ev) -65: vblendmps/d Vx,Hx,Wx (66),(ev) -66: vpblendmb/w Vx,Hx,Wx (66),(ev) -# Skip 0x67-0x74 -75: vpermi2b/w Vx,Hx,Wx (66),(ev) -76: vpermi2d/q Vx,Hx,Wx (66),(ev) -77: vpermi2ps/d Vx,Hx,Wx (66),(ev) -78: vpbroadcastb Vx,Wx (66),(v) -79: vpbroadcastw Vx,Wx (66),(v) -7a: vpbroadcastb Vx,Rv (66),(ev) -7b: vpbroadcastw Vx,Rv (66),(ev) -7c: vpbroadcastd/q Vx,Rv (66),(ev) -7d: vpermt2b/w Vx,Hx,Wx (66),(ev) -7e: vpermt2d/q Vx,Hx,Wx (66),(ev) -7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) -80: INVEPT Gy,Mdq (66) -81: INVVPID Gy,Mdq (66) -82: INVPCID Gy,Mdq (66) -83: vpmultishiftqb Vx,Hx,Wx (66),(ev) -88: vexpandps/d Vpd,Wpd (66),(ev) -89: vpexpandd/q Vx,Wx (66),(ev) -8a: vcompressps/d Wx,Vx (66),(ev) -8b: vpcompressd/q Wx,Vx (66),(ev) -8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) -8d: vpermb/w Vx,Hx,Wx (66),(ev) -8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) -# 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) -91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) -92: vgatherdps/d Vx,Hx,Wx (66),(v) -93: vgatherqps/d Vx,Hx,Wx (66),(v) -94: -95: -96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v) -97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v) -98: vfmadd132ps/d Vx,Hx,Wx (66),(v) -99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1) -9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) -9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) -9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v) -9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) -9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) -9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) -a0: vpscatterdd/q Wx,Vx (66),(ev) -a1: vpscatterqd/q Wx,Vx (66),(ev) -a2: vscatterdps/d Wx,Vx (66),(ev) -a3: vscatterqps/d Wx,Vx (66),(ev) -a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) -a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) -a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) -a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1) -aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) -ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) -ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) -ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) -ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) -af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) -b4: vpmadd52luq Vx,Hx,Wx (66),(ev) -b5: vpmadd52huq Vx,Hx,Wx (66),(ev) -b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) -b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) -b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) -b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1) -ba: vfmsub231ps/d Vx,Hx,Wx (66),(v) -bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1) -bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v) -bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) -be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) -bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) -# 0x0f 0x38 0xc0-0xff -c4: vpconflictd/q Vx,Wx (66),(ev) -c6: Grp18 (1A) -c7: Grp19 (1A) -c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) -c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) -cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) -cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) -cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) -db: VAESIMC Vdq,Wdq (66),(v1) -dc: VAESENC Vdq,Hdq,Wdq (66),(v1) -dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) -de: VAESDEC Vdq,Hdq,Wdq (66),(v1) -df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) -f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) -f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) -f2: ANDN Gy,By,Ey (v) -f3: Grp17 (1A) -f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) -f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) -f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) -EndTable - -Table: 3-byte opcode 2 (0x0f 0x3a) -Referrer: 3-byte escape 2 -AVXcode: 3 -# 0x0f 0x3a 0x00-0xff -00: vpermq Vqq,Wqq,Ib (66),(v) -01: vpermpd Vqq,Wqq,Ib (66),(v) -02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: valignd/q Vx,Hx,Wx,Ib (66),(ev) -04: vpermilps Vx,Wx,Ib (66),(v) -05: vpermilpd Vx,Wx,Ib (66),(v) -06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) -07: -08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) -09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) -0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) -0c: vblendps Vx,Hx,Wx,Ib (66) -0d: vblendpd Vx,Hx,Wx,Ib (66) -0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) -0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1) -14: vpextrb Rd/Mb,Vdq,Ib (66),(v1) -15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) -16: vpextrd/q Ey,Vdq,Ib (66),(v1) -17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) -19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) -1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) -1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) -1d: vcvtps2ph Wx,Vx,Ib (66),(v) -1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) -1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) -20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) -21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) -22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) -25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) -26: vgetmantps/d Vx,Wx,Ib (66),(ev) -27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) -30: kshiftrb/w Vk,Uk,Ib (66),(v) -31: kshiftrd/q Vk,Uk,Ib (66),(v) -32: kshiftlb/w Vk,Uk,Ib (66),(v) -33: kshiftld/q Vk,Uk,Ib (66),(v) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) -39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) -3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) -3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) -3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) -3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) -40: vdpps Vx,Hx,Wx,Ib (66) -41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) -43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) -44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) -46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) -4a: vblendvps Vx,Hx,Wx,Lx (66),(v) -4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) -4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) -50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) -51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) -54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) -55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) -56: vreduceps/d Vx,Wx,Ib (66),(ev) -57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) -60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) -61: vpcmpestri Vdq,Wdq,Ib (66),(v1) -62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) -63: vpcmpistri Vdq,Wdq,Ib (66),(v1) -66: vfpclassps/d Vk,Wx,Ib (66),(ev) -67: vfpclassss/d Vk,Wx,Ib (66),(ev) -cc: sha1rnds4 Vdq,Wdq,Ib -df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) -f0: RORX Gy,Ey,Ib (F2),(v) -EndTable - -GrpTable: Grp1 -0: ADD -1: OR -2: ADC -3: SBB -4: AND -5: SUB -6: XOR -7: CMP -EndTable - -GrpTable: Grp1A -0: POP -EndTable - -GrpTable: Grp2 -0: ROL -1: ROR -2: RCL -3: RCR -4: SHL/SAL -5: SHR -6: -7: SAR -EndTable - -GrpTable: Grp3_1 -0: TEST Eb,Ib -1: TEST Eb,Ib -2: NOT Eb -3: NEG Eb -4: MUL AL,Eb -5: IMUL AL,Eb -6: DIV AL,Eb -7: IDIV AL,Eb -EndTable - -GrpTable: Grp3_2 -0: TEST Ev,Iz -1: -2: NOT Ev -3: NEG Ev -4: MUL rAX,Ev -5: IMUL rAX,Ev -6: DIV rAX,Ev -7: IDIV rAX,Ev -EndTable - -GrpTable: Grp4 -0: INC Eb -1: DEC Eb -EndTable - -GrpTable: Grp5 -0: INC Ev -1: DEC Ev -# Note: "forced64" is Intel CPU behavior (see comment about CALL insn). -2: CALLN Ev (f64) -3: CALLF Ep -4: JMPN Ev (f64) -5: JMPF Mp -6: PUSH Ev (d64) -7: -EndTable - -GrpTable: Grp6 -0: SLDT Rv/Mw -1: STR Rv/Mw -2: LLDT Ew -3: LTR Ew -4: VERR Ew -5: VERW Ew -EndTable - -GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) -3: LIDT Ms -4: SMSW Mw/Rv -5: rdpkru (110),(11B) | wrpkru (111),(11B) -6: LMSW Ew -7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) -EndTable - -GrpTable: Grp8 -4: BT -5: BTS -6: BTR -7: BTC -EndTable - -GrpTable: Grp9 -1: CMPXCHG8B/16B Mq/Mdq -3: xrstors -4: xsavec -5: xsaves -6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) -7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) -EndTable - -GrpTable: Grp10 -# all are UD1 -0: UD1 -1: UD1 -2: UD1 -3: UD1 -4: UD1 -5: UD1 -6: UD1 -7: UD1 -EndTable - -# Grp11A and Grp11B are expressed as Grp11 in Intel SDM -GrpTable: Grp11A -0: MOV Eb,Ib -7: XABORT Ib (000),(11B) -EndTable - -GrpTable: Grp11B -0: MOV Eb,Iz -7: XBEGIN Jz (000),(11B) -EndTable - -GrpTable: Grp12 -2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1) -4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1) -6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1) -EndTable - -GrpTable: Grp13 -0: vprord/q Hx,Wx,Ib (66),(ev) -1: vprold/q Hx,Wx,Ib (66),(ev) -2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) -6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) -EndTable - -GrpTable: Grp14 -2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1) -3: vpsrldq Hx,Ux,Ib (66),(11B),(v1) -6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1) -7: vpslldq Hx,Ux,Ib (66),(11B),(v1) -EndTable - -GrpTable: Grp15 -0: fxsave | RDFSBASE Ry (F3),(11B) -1: fxstor | RDGSBASE Ry (F3),(11B) -2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) -3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE | ptwrite Ey (F3),(11B) -5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) -EndTable - -GrpTable: Grp16 -0: prefetch NTA -1: prefetch T0 -2: prefetch T1 -3: prefetch T2 -EndTable - -GrpTable: Grp17 -1: BLSR By,Ey (v) -2: BLSMSK By,Ey (v) -3: BLSI By,Ey (v) -EndTable - -GrpTable: Grp18 -1: vgatherpf0dps/d Wx (66),(ev) -2: vgatherpf1dps/d Wx (66),(ev) -5: vscatterpf0dps/d Wx (66),(ev) -6: vscatterpf1dps/d Wx (66),(ev) -EndTable - -GrpTable: Grp19 -1: vgatherpf0qps/d Wx (66),(ev) -2: vgatherpf1qps/d Wx (66),(ev) -5: vscatterpf0qps/d Wx (66),(ev) -6: vscatterpf1qps/d Wx (66),(ev) -EndTable - -# AMD's Prefetch Group -GrpTable: GrpP -0: PREFETCH -1: PREFETCHW -EndTable - -GrpTable: GrpPDLK -0: MONTMUL -1: XSHA1 -2: XSHA2 -EndTable - -GrpTable: GrpRNG -0: xstore-rng -1: xcrypt-ecb -2: xcrypt-cbc -4: xcrypt-cfb -5: xcrypt-ofb -EndTable diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index df061599fef4..33cf8928cf05 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -9,10 +9,10 @@ #include <stdbool.h> #include <errno.h> #include <linux/kernel.h> +#include <linux/string.h> #include <linux/types.h> #include <linux/zalloc.h> -#include "../perf.h" #include "session.h" #include "machine.h" #include "memswap.h" @@ -33,6 +33,7 @@ #include "tsc.h" #include "intel-pt.h" #include "config.h" +#include "util/synthetic-events.h" #include "time-utils.h" #include "../arch/x86/include/uapi/asm/perf_regs.h" @@ -56,7 +57,7 @@ struct intel_pt { u32 auxtrace_type; struct perf_session *session; struct machine *machine; - struct perf_evsel *switch_evsel; + struct evsel *switch_evsel; struct thread *unknown_thread; bool timeless_decoding; bool sampling_mode; @@ -104,7 +105,7 @@ struct intel_pt { u64 cbr_id; bool sample_pebs; - struct perf_evsel *pebs_evsel; + struct evsel *pebs_evsel; u64 tsc_bit; u64 mtc_bit; @@ -232,6 +233,16 @@ static void intel_pt_log_event(union perf_event *event) perf_event__fprintf(event, f); } +static void intel_pt_dump_sample(struct perf_session *session, + struct perf_sample *sample) +{ + struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, + auxtrace); + + printf("\n"); + intel_pt_dump(pt, sample->aux_sample.data, sample->aux_sample.size); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -723,11 +734,11 @@ static bool intel_pt_get_config(struct intel_pt *pt, static bool intel_pt_exclude_kernel(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, NULL) && - !evsel->attr.exclude_kernel) + if (intel_pt_get_config(pt, &evsel->core.attr, NULL) && + !evsel->core.attr.exclude_kernel) return false; } return true; @@ -735,14 +746,14 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt) static bool intel_pt_return_compression(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 config; if (!pt->noretcomp_bit) return true; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config) && + if (intel_pt_get_config(pt, &evsel->core.attr, &config) && (config & pt->noretcomp_bit)) return false; } @@ -751,11 +762,11 @@ static bool intel_pt_return_compression(struct intel_pt *pt) static bool intel_pt_branch_enable(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 config; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config) && + if (intel_pt_get_config(pt, &evsel->core.attr, &config) && (config & 1) && !(config & 0x2000)) return false; } @@ -764,7 +775,7 @@ static bool intel_pt_branch_enable(struct intel_pt *pt) static unsigned int intel_pt_mtc_period(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; unsigned int shift; u64 config; @@ -775,7 +786,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt) config >>= 1; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config)) + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) return (config & pt->mtc_freq_bits) >> shift; } return 0; @@ -783,7 +794,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt) static bool intel_pt_timeless_decoding(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; bool timeless_decoding = true; u64 config; @@ -791,9 +802,9 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt) return true; evlist__for_each_entry(pt->session->evlist, evsel) { - if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME)) + if (!(evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) return true; - if (intel_pt_get_config(pt, &evsel->attr, &config)) { + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) { if (config & pt->tsc_bit) timeless_decoding = false; else @@ -805,11 +816,11 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt) static bool intel_pt_tracing_kernel(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, NULL) && - !evsel->attr.exclude_kernel) + if (intel_pt_get_config(pt, &evsel->core.attr, NULL) && + !evsel->core.attr.exclude_kernel) return true; } return false; @@ -817,7 +828,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt) static bool intel_pt_have_tsc(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; bool have_tsc = false; u64 config; @@ -825,7 +836,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt) return false; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config)) { + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) { if (config & pt->tsc_bit) have_tsc = true; else @@ -835,6 +846,18 @@ static bool intel_pt_have_tsc(struct intel_pt *pt) return have_tsc; } +static bool intel_pt_sampling_mode(struct intel_pt *pt) +{ + struct evsel *evsel; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if ((evsel->core.attr.sample_type & PERF_SAMPLE_AUX) && + evsel->core.attr.aux_sample_size) + return true; + } + return false; +} + static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns) { u64 quot, rem; @@ -1702,9 +1725,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) struct perf_sample sample = { .ip = 0, }; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; - struct perf_evsel *evsel = pt->pebs_evsel; - u64 sample_type = evsel->attr.sample_type; - u64 id = evsel->id[0]; + struct evsel *evsel = pt->pebs_evsel; + u64 sample_type = evsel->core.attr.sample_type; + u64 id = evsel->core.id[0]; u8 cpumode; if (intel_pt_skip_event(pt)) @@ -1715,8 +1738,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) sample.id = id; sample.stream_id = id; - if (!evsel->attr.freq) - sample.period = evsel->attr.sample_period; + if (!evsel->core.attr.freq) + sample.period = evsel->core.attr.sample_period; /* No support for non-zero CS base */ if (items->has_ip) @@ -1757,7 +1780,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) if (sample_type & PERF_SAMPLE_REGS_INTR && items->mask[INTEL_PT_GP_REGS_POS]) { u64 regs[sizeof(sample.intr_regs.mask)]; - u64 regs_mask = evsel->attr.sample_regs_intr; + u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; sample.intr_regs.abi = items->is_32_bit ? @@ -2319,6 +2342,56 @@ static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid, return 0; } +static void intel_pt_sample_set_pid_tid_cpu(struct intel_pt_queue *ptq, + struct auxtrace_queue *queue, + struct perf_sample *sample) +{ + struct machine *m = ptq->pt->machine; + + ptq->pid = sample->pid; + ptq->tid = sample->tid; + ptq->cpu = queue->cpu; + + intel_pt_log("queue %u cpu %d pid %d tid %d\n", + ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid); + + thread__zput(ptq->thread); + + if (ptq->tid == -1) + return; + + if (ptq->pid == -1) { + ptq->thread = machine__find_thread(m, -1, ptq->tid); + if (ptq->thread) + ptq->pid = ptq->thread->pid_; + return; + } + + ptq->thread = machine__findnew_thread(m, ptq->pid, ptq->tid); +} + +static int intel_pt_process_timeless_sample(struct intel_pt *pt, + struct perf_sample *sample) +{ + struct auxtrace_queue *queue; + struct intel_pt_queue *ptq; + u64 ts = 0; + + queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session); + if (!queue) + return -EINVAL; + + ptq = queue->priv; + if (!ptq) + return 0; + + ptq->stop = false; + ptq->time = sample->time; + intel_pt_sample_set_pid_tid_cpu(ptq, queue, sample); + intel_pt_run_decoder(ptq, &ts); + return 0; +} + static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample) { return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu, @@ -2401,7 +2474,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, static int intel_pt_process_switch(struct intel_pt *pt, struct perf_sample *sample) { - struct perf_evsel *evsel; + struct evsel *evsel; pid_t tid; int cpu, ret; @@ -2549,7 +2622,11 @@ static int intel_pt_process_event(struct perf_session *session, } if (pt->timeless_decoding) { - if (event->header.type == PERF_RECORD_EXIT) { + if (pt->sampling_mode) { + if (sample->aux_sample.size) + err = intel_pt_process_timeless_sample(pt, + sample); + } else if (event->header.type == PERF_RECORD_EXIT) { err = intel_pt_process_timeless_queues(pt, event->fork.tid, sample->time); @@ -2675,6 +2752,28 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session, return 0; } +static int intel_pt_queue_data(struct perf_session *session, + struct perf_sample *sample, + union perf_event *event, u64 data_offset) +{ + struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, + auxtrace); + u64 timestamp; + + if (event) { + return auxtrace_queues__add_event(&pt->queues, session, event, + data_offset, NULL); + } + + if (sample->time && sample->time != (u64)-1) + timestamp = perf_time_to_tsc(sample->time, &pt->tc); + else + timestamp = 0; + + return auxtrace_queues__add_sample(&pt->queues, session, sample, + data_offset, timestamp); +} + struct intel_pt_synth { struct perf_tool dummy_tool; struct perf_session *session; @@ -2713,13 +2812,13 @@ static int intel_pt_synth_event(struct perf_session *session, const char *name, return err; } -static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, +static void intel_pt_set_event_name(struct evlist *evlist, u64 id, const char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->id && evsel->id[0] == id) { + if (evsel->core.id && evsel->core.id[0] == id) { if (evsel->name) zfree(&evsel->name); evsel->name = strdup(name); @@ -2728,13 +2827,13 @@ static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, } } -static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, - struct perf_evlist *evlist) +static struct evsel *intel_pt_evsel(struct intel_pt *pt, + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == pt->pmu_type && evsel->ids) + if (evsel->core.attr.type == pt->pmu_type && evsel->core.ids) return evsel; } @@ -2744,8 +2843,8 @@ static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, static int intel_pt_synth_events(struct intel_pt *pt, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel = intel_pt_evsel(pt, evlist); + struct evlist *evlist = session->evlist; + struct evsel *evsel = intel_pt_evsel(pt, evlist); struct perf_event_attr attr; u64 id; int err; @@ -2758,7 +2857,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; if (pt->timeless_decoding) @@ -2767,15 +2866,15 @@ static int intel_pt_synth_events(struct intel_pt *pt, attr.sample_type |= PERF_SAMPLE_TIME; if (!pt->per_cpu_mmaps) attr.sample_type &= ~(u64)PERF_SAMPLE_CPU; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; - - id = evsel->id[0] + 1000000000; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; + + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; @@ -2857,7 +2956,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, id += 1; } - if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) { + if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) { attr.config = PERF_SYNTH_INTEL_MWAIT; err = intel_pt_synth_event(session, "mwait", &attr, id); if (err) @@ -2894,9 +2993,25 @@ static int intel_pt_synth_events(struct intel_pt *pt, return 0; } -static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist) +static void intel_pt_setup_pebs_events(struct intel_pt *pt) +{ + struct evsel *evsel; + + if (!pt->synth_opts.other_events) + return; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if (evsel->core.attr.aux_output && evsel->core.id) { + pt->sample_pebs = true; + pt->pebs_evsel = evsel; + return; + } + } +} + +static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry_reverse(evlist, evsel) { const char *name = perf_evsel__name(evsel); @@ -2908,12 +3023,12 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist) return NULL; } -static bool intel_pt_find_switch(struct perf_evlist *evlist) +static bool intel_pt_find_switch(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.context_switch) + if (evsel->core.attr.context_switch) return true; } @@ -3028,7 +3143,7 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_FILTER_STR_LEN] = " Filter string len. %"PRIu64"\n", }; -static void intel_pt_print_info(u64 *arr, int start, int finish) +static void intel_pt_print_info(__u64 *arr, int start, int finish) { int i; @@ -3047,23 +3162,23 @@ static void intel_pt_print_info_str(const char *name, const char *str) fprintf(stdout, " %-20s%s\n", name, str ? str : ""); } -static bool intel_pt_has(struct auxtrace_info_event *auxtrace_info, int pos) +static bool intel_pt_has(struct perf_record_auxtrace_info *auxtrace_info, int pos) { return auxtrace_info->header.size >= - sizeof(struct auxtrace_info_event) + (sizeof(u64) * (pos + 1)); + sizeof(struct perf_record_auxtrace_info) + (sizeof(u64) * (pos + 1)); } int intel_pt_process_auxtrace_info(union perf_event *event, struct perf_session *session) { - struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS; struct intel_pt *pt; void *info_end; - u64 *info; + __u64 *info; int err; - if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) + + if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) + min_sz) return -EINVAL; @@ -3161,7 +3276,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (pt->timeless_decoding && !pt->tc.time_mult) pt->tc.time_mult = 1; pt->have_tsc = intel_pt_have_tsc(pt); - pt->sampling_mode = false; + pt->sampling_mode = intel_pt_sampling_mode(pt); pt->est_tsc = !pt->timeless_decoding; pt->unknown_thread = thread__new(999999999, 999999999); @@ -3181,13 +3296,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event, err = thread__set_comm(pt->unknown_thread, "unknown", 0); if (err) goto err_delete_thread; - if (thread__init_map_groups(pt->unknown_thread, pt->machine)) { + if (thread__init_maps(pt->unknown_thread, pt->machine)) { err = -ENOMEM; goto err_delete_thread; } pt->auxtrace.process_event = intel_pt_process_event; pt->auxtrace.process_auxtrace_event = intel_pt_process_auxtrace_event; + pt->auxtrace.queue_data = intel_pt_queue_data; + pt->auxtrace.dump_auxtrace_sample = intel_pt_dump_sample; pt->auxtrace.flush_events = intel_pt_flush; pt->auxtrace.free_events = intel_pt_free_events; pt->auxtrace.free = intel_pt_free; @@ -3263,7 +3380,12 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - err = auxtrace_queues__process_index(&pt->queues, session); + intel_pt_setup_pebs_events(pt); + + if (pt->sampling_mode || list_empty(&session->auxtrace_index)) + err = auxtrace_queue_data(session, true, true); + else + err = auxtrace_queues__process_index(&pt->queues, session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 18c34f0c1966..e3ccb0ce1938 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -14,7 +14,7 @@ #include <sys/mman.h> #include <linux/stringify.h> -#include "util.h" +#include "build-id.h" #include "event.h" #include "debug.h" #include "evlist.h" @@ -26,7 +26,6 @@ #include "jit.h" #include "jitdump.h" #include "genelf.h" -#include "../builtin.h" #include <linux/ctype.h> #include <linux/zalloc.h> @@ -118,13 +117,13 @@ jit_close(struct jit_buf_desc *jd) static int jit_validate_events(struct perf_session *session) { - struct perf_evsel *evsel; + struct evsel *evsel; /* * check that all events use CLOCK_MONOTONIC */ evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC) + if (evsel->core.attr.use_clockid == 0 || evsel->core.attr.clockid != CLOCK_MONOTONIC) return -1; } return 0; @@ -396,7 +395,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) size_t size; u16 idr_size; const char *sym; - uint32_t count; + uint64_t count; int ret, csize, usize; pid_t pid, tid; struct { @@ -419,7 +418,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) return -1; filename = event->mmap2.filename; - size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so", + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, pid, count); @@ -530,7 +529,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) return -1; filename = event->mmap2.filename; - size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64, + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, pid, jr->move.code_index); @@ -758,7 +757,7 @@ jit_process(struct perf_session *session, pid_t pid, u64 *nbytes) { - struct perf_evsel *first; + struct evsel *first; struct jit_buf_desc jd; int ret; @@ -778,8 +777,8 @@ jit_process(struct perf_session *session, * track sample_type to compute id_all layout * perf sets the same sample type to all events as of now */ - first = perf_evlist__first(session->evlist); - jd.sample_type = first->attr.sample_type; + first = evlist__first(session->evlist); + jd.sample_type = first->core.attr.sample_type; *nbytes = 0; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 1403dec189b4..6f0fa05b62b6 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -2,12 +2,14 @@ #ifndef __PERF_KVM_STAT_H #define __PERF_KVM_STAT_H -#include "../perf.h" +#ifdef HAVE_KVM_STAT_SUPPORT + #include "tool.h" #include "stat.h" +#include "record.h" -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct perf_session; struct event_key { @@ -45,17 +47,17 @@ struct kvm_event_key { struct perf_kvm_stat; struct child_event_ops { - void (*get_key)(struct perf_evsel *evsel, + void (*get_key)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); const char *name; }; struct kvm_events_ops { - bool (*is_begin_event)(struct perf_evsel *evsel, + bool (*is_begin_event)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); - bool (*is_end_event)(struct perf_evsel *evsel, + bool (*is_end_event)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); struct child_event_ops *child_ops; void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, @@ -74,7 +76,7 @@ struct exit_reasons_table { struct perf_kvm_stat { struct perf_tool tool; struct record_opts opts; - struct perf_evlist *evlist; + struct evlist *evlist; struct perf_session *session; const char *file_name; @@ -109,21 +111,21 @@ struct kvm_reg_events_ops { struct kvm_events_ops *ops; }; -void exit_event_get_key(struct perf_evsel *evsel, +void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); -bool exit_event_begin(struct perf_evsel *evsel, +bool exit_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); -bool exit_event_end(struct perf_evsel *evsel, +bool exit_event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); -bool kvm_exit_event(struct perf_evsel *evsel); -bool kvm_entry_event(struct perf_evsel *evsel); +bool kvm_exit_event(struct evsel *evsel); +bool kvm_entry_event(struct evsel *evsel); int setup_kvm_events_tp(struct perf_kvm_stat *kvm); #define define_exit_reasons_table(name, symbols) \ @@ -144,5 +146,7 @@ extern const int decode_str_len; extern const char *kvm_exit_reason; extern const char *kvm_entry_trace; extern const char *kvm_exit_trace; +#endif /* HAVE_KVM_STAT_SUPPORT */ +extern int kvm_add_default_arch_event(int *argc, const char **argv); #endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index 66756e6be111..6b4e5a0892f8 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -22,7 +22,6 @@ #define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP #include "unwind.h" -#include "debug.h" #include "libunwind-aarch64.h" #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h> #include "../../arch/arm64/util/unwind-libunwind.c" diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index c5e568188e19..21c216c40a3b 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -22,7 +22,6 @@ #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP #include "unwind.h" -#include "debug.h" #include "libunwind-x86.h" #include <../../../../arch/x86/include/uapi/asm/perf_regs.h> diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 9f0470ecbca9..b5af680fc667 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -8,7 +8,9 @@ #include <limits.h> #include <stdio.h> #include <stdlib.h> +#include <unistd.h> #include <linux/err.h> +#include <linux/string.h> #include <linux/zalloc.h> #include "debug.h" #include "llvm-utils.h" @@ -231,14 +233,14 @@ static int detect_kbuild_dir(char **kbuild_dir) const char *prefix_dir = ""; const char *suffix_dir = ""; + /* _UTSNAME_LENGTH is 65 */ + char release[128]; + char *autoconf_path; int err; if (!test_dir) { - /* _UTSNAME_LENGTH is 65 */ - char release[128]; - err = fetch_kernel_version(NULL, release, sizeof(release)); if (err) @@ -286,6 +288,7 @@ static const char *kinc_fetch_script = "obj-y := dummy.o\n" "\\$(obj)/%.o: \\$(src)/%.c\n" "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" +"\t\\$(CC) -c -o \\$@ \\$<\n" "EOF\n" "touch $TMPDIR/dummy.c\n" "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" @@ -416,10 +419,9 @@ void llvm__dump_obj(const char *path, void *obj_buf, size_t size) goto out; } - pr_info("LLVM: dumping %s\n", obj_path); + pr_debug("LLVM: dumping %s\n", obj_path); if (fwrite(obj_buf, size, 1, fp) != 1) - pr_warning("WARNING: failed to write to file '%s': %s, skip object dumping\n", - obj_path, strerror(errno)); + pr_debug("WARNING: failed to write to file '%s': %s, skip object dumping\n", obj_path, strerror(errno)); fclose(fp); out: free(obj_path); diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h index bf3f3f4c4fe2..7878a0e3fa98 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -6,7 +6,7 @@ #ifndef __LLVM_UTILS_H #define __LLVM_UTILS_H -#include "debug.h" +#include <stdbool.h> struct llvm_param { /* Path of clang executable */ diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index b1dd29a9d915..39062df02629 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -7,9 +7,10 @@ #include <sys/stat.h> #include <fcntl.h> #include "compress.h" -#include "util.h" #include "debug.h" +#include <string.h> #include <unistd.h> +#include <internal/lib.h> #define BUFSIZE 8192 diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 83b2fbbeeb90..fb5c2cd44d30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -3,17 +3,26 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> +#include <stdlib.h> #include "callchain.h" #include "debug.h" +#include "dso.h" +#include "env.h" #include "event.h" #include "evsel.h" #include "hist.h" #include "machine.h" #include "map.h" +#include "map_symbol.h" +#include "branch.h" +#include "mem-events.h" +#include "srcline.h" #include "symbol.h" #include "sort.h" #include "strlist.h" +#include "target.h" #include "thread.h" +#include "util.h" #include "vdso.h" #include <stdbool.h> #include <sys/types.h> @@ -23,14 +32,21 @@ #include "linux/hash.h" #include "asm/bug.h" #include "bpf-event.h" +#include <internal/lib.h> // page_size #include <linux/ctype.h> #include <symbol/kallsyms.h> #include <linux/mman.h> +#include <linux/string.h> #include <linux/zalloc.h> static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); +static struct dso *machine__kernel_dso(struct machine *machine) +{ + return machine->vmlinux_map->dso; +} + static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -70,7 +86,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) int err = -ENOMEM; memset(machine, 0, sizeof(*machine)); - map_groups__init(&machine->kmaps, machine); + maps__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->dsos); @@ -201,7 +217,7 @@ void machine__exit(struct machine *machine) return; machine__destroy_kernel_maps(machine); - map_groups__exit(&machine->kmaps); + maps__exit(&machine->kmaps); dsos__exit(&machine->dsos); machine__exit_vdso(machine); zfree(&machine->root_dir); @@ -396,28 +412,28 @@ static void machine__update_thread_pid(struct machine *machine, if (!leader) goto out_err; - if (!leader->mg) - leader->mg = map_groups__new(machine); + if (!leader->maps) + leader->maps = maps__new(machine); - if (!leader->mg) + if (!leader->maps) goto out_err; - if (th->mg == leader->mg) + if (th->maps == leader->maps) return; - if (th->mg) { + if (th->maps) { /* * Maps are created from MMAP events which provide the pid and * tid. Consequently there never should be any maps on a thread * with an unknown pid. Just print an error if there are. */ - if (!map_groups__empty(th->mg)) + if (!maps__empty(th->maps)) pr_err("Discarding thread maps for %d:%d\n", th->pid_, th->tid); - map_groups__put(th->mg); + maps__put(th->maps); } - th->mg = map_groups__get(leader->mg); + th->maps = maps__get(leader->maps); out_put: thread__put(leader); return; @@ -520,14 +536,13 @@ static struct thread *____machine__findnew_thread(struct machine *machine, rb_insert_color_cached(&th->rb_node, &threads->entries, leftmost); /* - * We have to initialize map_groups separately - * after rb tree is updated. + * We have to initialize maps separately after rb tree is updated. * * The reason is that we call machine__findnew_thread - * within thread__init_map_groups to find the thread + * within thread__init_maps to find the thread * leader and that would screwed the rb tree. */ - if (thread__init_map_groups(th, machine)) { + if (thread__init_maps(th, machine)) { rb_erase_cached(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); thread__put(th); @@ -642,7 +657,7 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused, int machine__process_lost_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { - dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", + dump_printf(": id:%" PRI_lu64 ": lost:%" PRI_lu64 "\n", event->lost.id, event->lost.lost); return 0; } @@ -650,7 +665,7 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, int machine__process_lost_samples_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample) { - dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n", + dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n", sample->id, event->lost_samples.lost); return 0; } @@ -671,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); + dso->kernel = DSO_TYPE_KERNEL; } dso__get(dso); @@ -708,22 +724,29 @@ static int machine__process_ksymbol_register(struct machine *machine, struct perf_sample *sample __maybe_unused) { struct symbol *sym; - struct map *map; + struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr); - map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr); if (!map) { - map = dso__new_map(event->ksymbol_event.name); - if (!map) + struct dso *dso = dso__new(event->ksymbol.name); + + if (dso) { + dso->kernel = DSO_TYPE_KERNEL; + map = map__new2(0, dso); + } + + if (!dso || !map) { + dso__put(dso); return -ENOMEM; + } - map->start = event->ksymbol_event.addr; - map->end = map->start + event->ksymbol_event.len; - map_groups__insert(&machine->kmaps, map); + map->start = event->ksymbol.addr; + map->end = map->start + event->ksymbol.len; + maps__insert(&machine->kmaps, map); } sym = symbol__new(map->map_ip(map, map->start), - event->ksymbol_event.len, - 0, 0, event->ksymbol_event.name); + event->ksymbol.len, + 0, 0, event->ksymbol.name); if (!sym) return -ENOMEM; dso__insert_symbol(map->dso, sym); @@ -736,9 +759,9 @@ static int machine__process_ksymbol_unregister(struct machine *machine, { struct map *map; - map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr); + map = maps__find(&machine->kmaps, event->ksymbol.addr); if (map) - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); return 0; } @@ -750,51 +773,22 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, if (dump_trace) perf_event__fprintf_ksymbol(event, stdout); - if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER) + if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER) return machine__process_ksymbol_unregister(machine, event, sample); return machine__process_ksymbol_register(machine, event, sample); } -static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename) -{ - const char *dup_filename; - - if (!filename || !dso || !dso->long_name) - return; - if (dso->long_name[0] != '[') - return; - if (!strchr(filename, '/')) - return; - - dup_filename = strdup(filename); - if (!dup_filename) - return; - - dso__set_long_name(dso, dup_filename, true); -} - -struct map *machine__findnew_module_map(struct machine *machine, u64 start, - const char *filename) +static struct map *machine__addnew_module_map(struct machine *machine, u64 start, + const char *filename) { struct map *map = NULL; - struct dso *dso = NULL; struct kmod_path m; + struct dso *dso; if (kmod_path__parse_name(&m, filename)) return NULL; - map = map_groups__find_by_name(&machine->kmaps, m.name); - if (map) { - /* - * If the map's dso is an offline module, give dso__load() - * a chance to find the file path of that module by fixing - * long_name. - */ - dso__adjust_kmod_long_name(map->dso, filename); - goto out; - } - dso = machine__findnew_module_dso(machine, &m, filename); if (dso == NULL) goto out; @@ -803,9 +797,9 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, if (map == NULL) goto out; - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); - /* Put the map here because map_groups__insert alread got it */ + /* Put the map here because maps__insert alread got it */ map__put(map); out: /* put the dso here, corresponding to machine__findnew_module_dso */ @@ -850,7 +844,7 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) { int i; size_t printed = 0; - struct dso *kdso = machine__kernel_map(machine)->dso; + struct dso *kdso = machine__kernel_dso(machine); if (kdso->has_build_id) { char filename[PATH_MAX]; @@ -987,10 +981,9 @@ int machine__create_extra_kernel_map(struct machine *machine, kmap = map__kmap(map); - kmap->kmaps = &machine->kmaps; strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", kmap->name, map->start, map->end); @@ -1035,8 +1028,7 @@ static u64 find_entry_trampoline(struct dso *dso) int machine__map_x86_64_entry_trampolines(struct machine *machine, struct dso *kernel) { - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps; + struct maps *kmaps = &machine->kmaps; int nr_cpus_avail, cpu; bool found = false; struct map *map; @@ -1046,14 +1038,14 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, * In the vmlinux case, pgoff is a virtual address which must now be * mapped to a vmlinux offset. */ - for (map = maps__first(maps); map; map = map__next(map)) { + maps__for_each_entry(kmaps, map) { struct kmap *kmap = __map__kmap(map); struct map *dest_map; if (!kmap || !is_entry_trampoline(kmap->name)) continue; - dest_map = map_groups__find(kmaps, map->pgoff); + dest_map = maps__find(kmaps, map->pgoff); if (dest_map != map) map->pgoff = dest_map->map_ip(dest_map, map->pgoff); found = true; @@ -1098,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu static int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - struct kmap *kmap; - struct map *map; - /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -1109,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) return -1; machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; - map = machine__kernel_map(machine); - kmap = map__kmap(map); - if (!kmap) - return -1; - - kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, map); - + maps__insert(&machine->kmaps, machine->vmlinux_map); return 0; } @@ -1129,7 +1111,7 @@ void machine__destroy_kernel_maps(struct machine *machine) return; kmap = map__kmap(map); - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); if (kmap && kmap->ref_reloc_sym) { zfree((char **)&kmap->ref_reloc_sym->name); zfree(&kmap->ref_reloc_sym); @@ -1224,7 +1206,7 @@ int machine__load_kallsyms(struct machine *machine, const char *filename) * kernel, with modules between them, fixup the end of all * sections. */ - map_groups__fixup_end(&machine->kmaps); + maps__fixup_end(&machine->kmaps); } return ret; @@ -1275,11 +1257,10 @@ static bool is_kmod_dso(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; } -static int map_groups__set_module_path(struct map_groups *mg, const char *path, - struct kmod_path *m) +static int maps__set_module_path(struct maps *maps, const char *path, struct kmod_path *m) { char *long_name; - struct map *map = map_groups__find_by_name(mg, m->name); + struct map *map = maps__find_by_name(maps, m->name); if (map == NULL) return 0; @@ -1303,8 +1284,7 @@ static int map_groups__set_module_path(struct map_groups *mg, const char *path, return 0; } -static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name, int depth) +static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, int depth) { struct dirent *dent; DIR *dir = opendir(dir_name); @@ -1336,8 +1316,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, continue; } - ret = map_groups__set_modules_path_dir(mg, path, - depth + 1); + ret = maps__set_modules_path_dir(maps, path, depth + 1); if (ret < 0) goto out; } else { @@ -1348,7 +1327,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, goto out; if (m.kmod) - ret = map_groups__set_module_path(mg, path, &m); + ret = maps__set_module_path(maps, path, &m); zfree(&m.name); @@ -1375,7 +1354,7 @@ static int machine__set_modules_path(struct machine *machine) machine->root_dir, version); free(version); - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); + return maps__set_modules_path_dir(&machine->kmaps, modules_path, 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, u64 *size __maybe_unused, @@ -1393,7 +1372,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, if (arch__fix_module_text_start(&start, &size, name) < 0) return -1; - map = machine__findnew_module_map(machine, start, name); + map = machine__addnew_module_map(machine, start, name); if (map == NULL) return -1; map->end = start + size; @@ -1448,11 +1427,11 @@ static void machine__update_kernel_mmap(struct machine *machine, struct map *map = machine__kernel_map(machine); map__get(map); - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); machine__set_kernel_mmap(machine, start, end); - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); map__put(map); } @@ -1532,8 +1511,7 @@ static bool perf_event__is_extra_kernel_mmap(struct machine *machine, static int machine__process_extra_kernel_map(struct machine *machine, union perf_event *event) { - struct map *kernel_map = machine__kernel_map(machine); - struct dso *kernel = kernel_map ? kernel_map->dso : NULL; + struct dso *kernel = machine__kernel_dso(machine); struct extra_kernel_map xm = { .start = event->mmap.start, .end = event->mmap.start + event->mmap.len, @@ -1569,8 +1547,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, strlen(machine->mmap_name) - 1) == 0; if (event->mmap.filename[0] == '/' || (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - map = machine__findnew_module_map(machine, event->mmap.start, - event->mmap.filename); + map = machine__addnew_module_map(machine, event->mmap.start, + event->mmap.filename); if (map == NULL) goto out_problem; @@ -1665,6 +1643,12 @@ int machine__process_mmap2_event(struct machine *machine, { struct thread *thread; struct map *map; + struct dso_id dso_id = { + .maj = event->mmap2.maj, + .min = event->mmap2.min, + .ino = event->mmap2.ino, + .ino_generation = event->mmap2.ino_generation, + }; int ret = 0; if (dump_trace) @@ -1685,10 +1669,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, - event->mmap2.maj, - event->mmap2.min, event->mmap2.ino, - event->mmap2.ino_generation, - event->mmap2.prot, + &dso_id, event->mmap2.prot, event->mmap2.flags, event->mmap2.filename, thread); @@ -1741,9 +1722,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - 0, 0, 0, 0, prot, 0, - event->mmap.filename, - thread); + NULL, prot, 0, event->mmap.filename, thread); if (map == NULL) goto out_problem_map; @@ -1919,7 +1898,7 @@ int machine__process_event(struct machine *machine, union perf_event *event, case PERF_RECORD_KSYMBOL: ret = machine__process_ksymbol(machine, event, sample); break; case PERF_RECORD_BPF_EVENT: - ret = machine__process_bpf_event(machine, event, sample); break; + ret = machine__process_bpf(machine, event, sample); break; default: ret = -1; break; @@ -1953,8 +1932,9 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; + ams->ms.maps = al.maps; + ams->ms.sym = al.sym; + ams->ms.map = al.map; ams->phys_addr = 0; } @@ -1970,8 +1950,9 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; + ams->ms.maps = al.maps; + ams->ms.sym = al.sym; + ams->ms.map = al.map; ams->phys_addr = phys_addr; } @@ -1991,8 +1972,9 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return mi; } -static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip) +static char *callchain_srcline(struct map_symbol *ms, u64 ip) { + struct map *map = ms->map; char *srcline = NULL; if (!map || callchain_param.key == CCKEY_FUNCTION) @@ -2004,7 +1986,7 @@ static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip) bool show_addr = callchain_param.key == CCKEY_ADDRESS; srcline = get_srcline(map->dso, map__rip_2objdump(map, ip), - sym, show_sym, show_addr, ip); + ms->sym, show_sym, show_addr, ip); srcline__tree_insert(&map->dso->srclines, ip, srcline); } @@ -2027,6 +2009,7 @@ static int add_callchain_ip(struct thread *thread, struct iterations *iter, u64 branch_from) { + struct map_symbol ms; struct addr_location al; int nr_loop_iter = 0; u64 iter_cycles = 0; @@ -2084,8 +2067,11 @@ static int add_callchain_ip(struct thread *thread, iter_cycles = iter->cycles; } - srcline = callchain_srcline(al.map, al.sym, al.addr); - return callchain_cursor_append(cursor, ip, al.map, al.sym, + ms.maps = al.maps; + ms.map = al.map; + ms.sym = al.sym; + srcline = callchain_srcline(&ms, al.addr); + return callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, iter_cycles, branch_from, srcline); } @@ -2288,7 +2274,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, static int thread__resolve_callchain_sample(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -2392,7 +2378,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (callchain_param.order != ORDER_CALLEE) { + if (chain && callchain_param.order != ORDER_CALLEE) { err = find_prev_cpumode(chain, thread, cursor, parent, root_al, &cpumode, chain->nr - first_call); if (err) @@ -2433,9 +2419,10 @@ check_calls: return 0; } -static int append_inlines(struct callchain_cursor *cursor, - struct map *map, struct symbol *sym, u64 ip) +static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip) { + struct symbol *sym = ms->sym; + struct map *map = ms->map; struct inline_node *inline_node; struct inline_list *ilist; u64 addr; @@ -2456,8 +2443,12 @@ static int append_inlines(struct callchain_cursor *cursor, } list_for_each_entry(ilist, &inline_node->val, list) { - ret = callchain_cursor_append(cursor, ip, map, - ilist->symbol, false, + struct map_symbol ilist_ms = { + .maps = ms->maps, + .map = map, + .sym = ilist->symbol, + }; + ret = callchain_cursor_append(cursor, ip, &ilist_ms, false, NULL, 0, 0, 0, ilist->srcline); if (ret != 0) @@ -2473,34 +2464,33 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) const char *srcline = NULL; u64 addr = entry->ip; - if (symbol_conf.hide_unresolved && entry->sym == NULL) + if (symbol_conf.hide_unresolved && entry->ms.sym == NULL) return 0; - if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) + if (append_inlines(cursor, &entry->ms, entry->ip) == 0) return 0; /* * Convert entry->ip from a virtual address to an offset in * its corresponding binary. */ - if (entry->map) - addr = map__map_ip(entry->map, entry->ip); + if (entry->ms.map) + addr = map__map_ip(entry->ms.map, entry->ip); - srcline = callchain_srcline(entry->map, entry->sym, addr); - return callchain_cursor_append(cursor, entry->ip, - entry->map, entry->sym, + srcline = callchain_srcline(&entry->ms, addr); + return callchain_cursor_append(cursor, entry->ip, &entry->ms, false, NULL, 0, 0, 0, srcline); } static int thread__resolve_callchain_unwind(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, int max_stack) { /* Can we do dwarf post unwind? */ - if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && - (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + if (!((evsel->core.attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->core.attr.sample_type & PERF_SAMPLE_STACK_USER))) return 0; /* Bail out if nothing was captured. */ @@ -2514,7 +2504,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, int thread__resolve_callchain(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -2599,24 +2589,11 @@ int machines__for_each_thread(struct machines *machines, return rc; } -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 nr_threads_synthesize) -{ - if (target__has_task(target)) - return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); - else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, - nr_threads_synthesize); - /* command specified */ - return 0; -} - pid_t machine__get_current_tid(struct machine *machine, int cpu) { - if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid) + int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS); + + if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid) return -1; return machine->current_tid[cpu]; @@ -2626,6 +2603,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid) { struct thread *thread; + int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS); if (cpu < 0) return -EINVAL; @@ -2633,14 +2611,14 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, if (!machine->current_tid) { int i; - machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t)); + machine->current_tid = calloc(nr_cpus, sizeof(pid_t)); if (!machine->current_tid) return -ENOMEM; - for (i = 0; i < MAX_NR_CPUS; i++) + for (i = 0; i < nr_cpus; i++) machine->current_tid[i] = -1; } - if (cpu >= MAX_NR_CPUS) { + if (cpu >= nr_cpus) { pr_err("Requested CPU %d too large. ", cpu); pr_err("Consider raising MAX_NR_CPUS\n"); return -EINVAL; @@ -2726,9 +2704,14 @@ out: return addr_cpumode; } +struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id) +{ + return dsos__findnew_id(&machine->dsos, filename, id); +} + struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { - return dsos__findnew(&machine->dsos, filename); + return machine__findnew_dso_id(machine, filename, NULL); } char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 7aa38da26427..be0a930eca89 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -4,16 +4,18 @@ #include <sys/types.h> #include <linux/rbtree.h> -#include "map_groups.h" -#include "dso.h" -#include "event.h" +#include "maps.h" +#include "dsos.h" #include "rwsem.h" struct addr_location; struct branch_stack; -struct perf_evsel; +struct dso; +struct dso_id; +struct evsel; struct perf_sample; struct symbol; +struct target; struct thread; union perf_event; @@ -49,7 +51,7 @@ struct machine { struct vdso_info *vdso_info; struct perf_env *env; struct dsos dsos; - struct map_groups kmaps; + struct maps kmaps; struct map *vmlinux_map; u64 kernel_start; pid_t *current_tid; @@ -81,7 +83,7 @@ struct map *machine__kernel_map(struct machine *machine) static inline struct maps *machine__kernel_maps(struct machine *machine) { - return &machine->kmaps.maps; + return &machine->kmaps; } int machine__get_kernel_start(struct machine *machine); @@ -175,7 +177,7 @@ struct callchain_cursor; int thread__resolve_callchain(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -201,6 +203,7 @@ int machine__nr_cpus_avail(struct machine *machine); struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); +struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id); struct dso *machine__findnew_dso(struct machine *machine, const char *filename); size_t machine__fprintf(struct machine *machine, FILE *fp); @@ -209,7 +212,7 @@ static inline struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr, struct map **mapp) { - return map_groups__find_symbol(&machine->kmaps, addr, mapp); + return maps__find_symbol(&machine->kmaps, addr, mapp); } static inline @@ -217,11 +220,9 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, const char *name, struct map **mapp) { - return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp); + return maps__find_symbol_by_name(&machine->kmaps, name, mapp); } -struct map *machine__findnew_module_map(struct machine *machine, u64 start, - const char *filename); int arch__fix_module_text_start(u64 *start, u64 *size, const char *name); int machine__load_kallsyms(struct machine *machine, const char *filename); @@ -250,20 +251,6 @@ int machines__for_each_thread(struct machines *machines, int (*fn)(struct thread *thread, void *p), void *priv); -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 nr_threads_synthesize); -static inline -int machine__synthesize_threads(struct machine *machine, struct target *target, - struct thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) -{ - return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); -} - pid_t machine__get_current_tid(struct machine *machine, int cpu); int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 668410b1d426..a08ca276098e 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "symbol.h" +#include <assert.h> #include <errno.h> #include <inttypes.h> #include <limits.h> @@ -8,7 +9,9 @@ #include <stdio.h> #include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ +#include "dso.h" #include "map.h" +#include "map_symbol.h" #include "thread.h" #include "vdso.h" #include "build-id.h" @@ -20,9 +23,9 @@ #include "namespaces.h" #include "unwind.h" #include "srccode.h" +#include "ui/ui.h" static void __maps__insert(struct maps *maps, struct map *map); -static void __maps__insert_name(struct maps *maps, struct map *map); static inline int is_anon_memory(const char *filename, u32 flags) { @@ -136,14 +139,13 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; RB_CLEAR_NODE(&map->rb_node); - map->groups = NULL; map->erange_warned = false; refcount_set(&map->refcnt, 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, u32 prot, u32 flags, char *filename, + u64 pgoff, struct dso_id *id, + u32 prot, u32 flags, char *filename, struct thread *thread) { struct map *map = malloc(sizeof(*map)); @@ -159,11 +161,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, anon = is_anon_memory(filename, flags); vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); - - map->maj = d_maj; - map->min = d_min; - map->ino = ino; - map->ino_generation = ino_gen; map->prot = prot; map->flags = flags; nsi = nsinfo__get(thread->nsinfo); @@ -193,7 +190,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, pgoff = 0; dso = machine__findnew_vdso(machine, thread); } else - dso = machine__findnew_dso(machine, filename); + dso = machine__findnew_dso_id(machine, filename, id); if (dso == NULL) goto out_delete; @@ -240,18 +237,11 @@ struct map *map__new2(u64 start, struct dso *dso) return map; } -/* - * Use this and __map__is_kmodule() for map instances that are in - * machine->kmaps, and thus have map->groups->machine all properly set, to - * disambiguate between the kernel and modules. - * - * When the need arises, introduce map__is_{kernel,kmodule)() that - * checks (map->groups != NULL && map->groups->machine != NULL && - * map->dso->kernel) before calling __map__is_{kernel,kmodule}()) - */ bool __map__is_kernel(const struct map *map) { - return machine__kernel_map(map->groups->machine) == map; + if (!map->dso->kernel) + return false; + return machine__kernel_map(map__kmaps((struct map *)map)->machine) == map; } bool __map__is_extra_kernel_map(const struct map *map) @@ -284,7 +274,7 @@ bool map__has_symbols(const struct map *map) static void map__exit(struct map *map) { - BUG_ON(!RB_EMPTY_NODE(&map->rb_node)); + BUG_ON(refcount_read(&map->refcnt) != 0); dso__zput(map->dso); } @@ -385,13 +375,17 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) struct map *map__clone(struct map *from) { - struct map *map = memdup(from, sizeof(*map)); + size_t size = sizeof(struct map); + struct map *map; + if (from->dso && from->dso->kernel) + size += sizeof(struct kmap); + + map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); - map->groups = NULL; } return map; @@ -444,51 +438,6 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, return ret; } -int map__fprintf_srccode(struct map *map, u64 addr, - FILE *fp, - struct srccode_state *state) -{ - char *srcfile; - int ret = 0; - unsigned line; - int len; - char *srccode; - - if (!map || !map->dso) - return 0; - srcfile = get_srcline_split(map->dso, - map__rip_2objdump(map, addr), - &line); - if (!srcfile) - return 0; - - /* Avoid redundant printing */ - if (state && - state->srcfile && - !strcmp(state->srcfile, srcfile) && - state->line == line) { - free(srcfile); - return 0; - } - - srccode = find_sourceline(srcfile, line, &len); - if (!srccode) - goto out_free_line; - - ret = fprintf(fp, "|%-8d %.*s", line, len, srccode); - - if (state) { - state->srcfile = srcfile; - state->line = line; - } - return ret; - -out_free_line: - free(srcfile); - return ret; -} - - void srccode_state_free(struct srccode_state *state) { zfree(&state->srcfile); @@ -568,98 +517,133 @@ u64 map__objdump_2mem(struct map *map, u64 ip) return ip + map->reloc; } -static void maps__init(struct maps *maps) +void maps__init(struct maps *maps, struct machine *machine) { maps->entries = RB_ROOT; - maps->names = RB_ROOT; init_rwsem(&maps->lock); + maps->machine = machine; + maps->last_search_by_name = NULL; + maps->nr_maps = 0; + maps->maps_by_name = NULL; + refcount_set(&maps->refcnt, 1); } -void map_groups__init(struct map_groups *mg, struct machine *machine) +static void __maps__free_maps_by_name(struct maps *maps) { - maps__init(&mg->maps); - mg->machine = machine; - refcount_set(&mg->refcnt, 1); + /* + * Free everything to try to do it from the rbtree in the next search + */ + zfree(&maps->maps_by_name); + maps->nr_maps_allocated = 0; } -void map_groups__insert(struct map_groups *mg, struct map *map) +void maps__insert(struct maps *maps, struct map *map) { - maps__insert(&mg->maps, map); - map->groups = mg; -} + down_write(&maps->lock); + __maps__insert(maps, map); + ++maps->nr_maps; -static void __maps__purge(struct maps *maps) -{ - struct rb_root *root = &maps->entries; - struct rb_node *next = rb_first(root); + if (map->dso && map->dso->kernel) { + struct kmap *kmap = map__kmap(map); - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); + if (kmap) + kmap->kmaps = maps; + else + pr_err("Internal error: kernel dso with non kernel map\n"); + } - next = rb_next(&pos->rb_node); - rb_erase_init(&pos->rb_node, root); - map__put(pos); + + /* + * If we already performed some search by name, then we need to add the just + * inserted map and resort. + */ + if (maps->maps_by_name) { + if (maps->nr_maps > maps->nr_maps_allocated) { + int nr_allocate = maps->nr_maps * 2; + struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map)); + + if (maps_by_name == NULL) { + __maps__free_maps_by_name(maps); + up_write(&maps->lock); + return; + } + + maps->maps_by_name = maps_by_name; + maps->nr_maps_allocated = nr_allocate; + } + maps->maps_by_name[maps->nr_maps - 1] = map; + __maps__sort_by_name(maps); } + up_write(&maps->lock); } -static void __maps__purge_names(struct maps *maps) +static void __maps__remove(struct maps *maps, struct map *map) { - struct rb_root *root = &maps->names; - struct rb_node *next = rb_first(root); + rb_erase_init(&map->rb_node, &maps->entries); + map__put(map); +} - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node_name); +void maps__remove(struct maps *maps, struct map *map) +{ + down_write(&maps->lock); + if (maps->last_search_by_name == map) + maps->last_search_by_name = NULL; + + __maps__remove(maps, map); + --maps->nr_maps; + if (maps->maps_by_name) + __maps__free_maps_by_name(maps); + up_write(&maps->lock); +} + +static void __maps__purge(struct maps *maps) +{ + struct map *pos, *next; - next = rb_next(&pos->rb_node_name); - rb_erase_init(&pos->rb_node_name, root); + maps__for_each_entry_safe(maps, pos, next) { + rb_erase_init(&pos->rb_node, &maps->entries); map__put(pos); } } -static void maps__exit(struct maps *maps) +void maps__exit(struct maps *maps) { down_write(&maps->lock); __maps__purge(maps); - __maps__purge_names(maps); up_write(&maps->lock); } -void map_groups__exit(struct map_groups *mg) -{ - maps__exit(&mg->maps); -} - -bool map_groups__empty(struct map_groups *mg) +bool maps__empty(struct maps *maps) { - return !maps__first(&mg->maps); + return !maps__first(maps); } -struct map_groups *map_groups__new(struct machine *machine) +struct maps *maps__new(struct machine *machine) { - struct map_groups *mg = malloc(sizeof(*mg)); + struct maps *maps = zalloc(sizeof(*maps)); - if (mg != NULL) - map_groups__init(mg, machine); + if (maps != NULL) + maps__init(maps, machine); - return mg; + return maps; } -void map_groups__delete(struct map_groups *mg) +void maps__delete(struct maps *maps) { - map_groups__exit(mg); - free(mg); + maps__exit(maps); + unwind__finish_access(maps); + free(maps); } -void map_groups__put(struct map_groups *mg) +void maps__put(struct maps *maps) { - if (mg && refcount_dec_and_test(&mg->refcnt)) - map_groups__delete(mg); + if (maps && refcount_dec_and_test(&maps->refcnt)) + maps__delete(maps); } -struct symbol *map_groups__find_symbol(struct map_groups *mg, - u64 addr, struct map **mapp) +struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) { - struct map *map = map_groups__find(mg, addr); + struct map *map = maps__find(maps, addr); /* Ensure map is loaded before using map->map_ip */ if (map != NULL && map__load(map) >= 0) { @@ -678,17 +662,14 @@ static bool map__contains_symbol(struct map *map, struct symbol *sym) return ip >= map->start && ip < map->end; } -struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, - struct map **mapp) +struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { struct symbol *sym; - struct rb_node *nd; + struct map *pos; down_read(&maps->lock); - for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); - + maps__for_each_entry(maps, pos) { sym = map__find_symbol_by_name(pos, name); if (sym == NULL) @@ -708,38 +689,30 @@ out: return sym; } -struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - const char *name, - struct map **mapp) +int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) { - return maps__find_symbol_by_name(&mg->maps, name, mapp); -} - -int map_groups__find_ams(struct addr_map_symbol *ams) -{ - if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { - if (ams->map->groups == NULL) + if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) { + if (maps == NULL) return -1; - ams->map = map_groups__find(ams->map->groups, ams->addr); - if (ams->map == NULL) + ams->ms.map = maps__find(maps, ams->addr); + if (ams->ms.map == NULL) return -1; } - ams->al_addr = ams->map->map_ip(ams->map, ams->addr); - ams->sym = map__find_symbol(ams->map, ams->al_addr); + ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr); + ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr); - return ams->sym ? 0 : -1; + return ams->ms.sym ? 0 : -1; } -static size_t maps__fprintf(struct maps *maps, FILE *fp) +size_t maps__fprintf(struct maps *maps, FILE *fp) { size_t printed = 0; - struct rb_node *nd; + struct map *pos; down_read(&maps->lock); - for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); + maps__for_each_entry(maps, pos) { printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 2) { @@ -753,19 +726,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) return printed; } -size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) -{ - return maps__fprintf(&mg->maps, fp); -} - -static void __map_groups__insert(struct map_groups *mg, struct map *map) -{ - __maps__insert(&mg->maps, map); - __maps__insert_name(&mg->maps, map); - map->groups = mg; -} - -static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) +int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) { struct rb_root *root; struct rb_node *next, *first; @@ -831,7 +792,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp } before->end = map->start; - __map_groups__insert(pos->groups, before); + __maps__insert(maps, before); if (verbose >= 2 && !use_browser) map__fprintf(before, fp); map__put(before); @@ -846,7 +807,9 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp } after->start = map->end; - __map_groups__insert(pos->groups, after); + after->pgoff += map->end - pos->start; + assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end)); + __maps__insert(maps, after); if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); @@ -864,40 +827,33 @@ out: return err; } -int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - FILE *fp) -{ - return maps__fixup_overlappings(&mg->maps, map, fp); -} - /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct thread *thread, struct map_groups *parent) +int maps__clone(struct thread *thread, struct maps *parent) { - struct map_groups *mg = thread->mg; + struct maps *maps = thread->maps; int err = -ENOMEM; struct map *map; - struct maps *maps = &parent->maps; - down_read(&maps->lock); + down_read(&parent->lock); - for (map = maps__first(maps); map; map = map__next(map)) { + maps__for_each_entry(parent, map) { struct map *new = map__clone(map); if (new == NULL) goto out_unlock; - err = unwind__prepare_access(thread, new, NULL); + err = unwind__prepare_access(maps, new, NULL); if (err) goto out_unlock; - map_groups__insert(mg, new); + maps__insert(maps, new); map__put(new); } err = 0; out_unlock: - up_read(&maps->lock); + up_read(&parent->lock); return err; } @@ -922,51 +878,6 @@ static void __maps__insert(struct maps *maps, struct map *map) map__get(map); } -static void __maps__insert_name(struct maps *maps, struct map *map) -{ - struct rb_node **p = &maps->names.rb_node; - struct rb_node *parent = NULL; - struct map *m; - int rc; - - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct map, rb_node_name); - rc = strcmp(m->dso->short_name, map->dso->short_name); - if (rc < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&map->rb_node_name, parent, p); - rb_insert_color(&map->rb_node_name, &maps->names); - map__get(map); -} - -void maps__insert(struct maps *maps, struct map *map) -{ - down_write(&maps->lock); - __maps__insert(maps, map); - __maps__insert_name(maps, map); - up_write(&maps->lock); -} - -static void __maps__remove(struct maps *maps, struct map *map) -{ - rb_erase_init(&map->rb_node, &maps->entries); - map__put(map); - - rb_erase_init(&map->rb_node_name, &maps->names); - map__put(map); -} - -void maps__remove(struct maps *maps, struct map *map) -{ - down_write(&maps->lock); - __maps__remove(maps, map); - up_write(&maps->lock); -} - struct map *maps__find(struct maps *maps, u64 ip) { struct rb_node *p; @@ -1000,7 +911,7 @@ struct map *maps__first(struct maps *maps) return NULL; } -struct map *map__next(struct map *map) +static struct map *__map__next(struct map *map) { struct rb_node *next = rb_next(&map->rb_node); @@ -1009,6 +920,11 @@ struct map *map__next(struct map *map) return NULL; } +struct map *map__next(struct map *map) +{ + return map ? __map__next(map) : NULL; +} + struct kmap *__map__kmap(struct map *map) { if (!map->dso || !map->dso->kernel) @@ -1025,7 +941,7 @@ struct kmap *map__kmap(struct map *map) return kmap; } -struct map_groups *map__kmaps(struct map *map) +struct maps *map__kmaps(struct map *map) { struct kmap *kmap = map__kmap(map); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index dc93787c74f0..067036e8970c 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -12,29 +12,21 @@ #include <linux/types.h> struct dso; -struct ip_callchain; -struct ref_reloc_sym; -struct map_groups; +struct maps; struct machine; -struct perf_evsel; struct map { union { struct rb_node rb_node; struct list_head node; }; - struct rb_node rb_node_name; u64 start; u64 end; - bool erange_warned; - u32 priv; + bool erange_warned:1; + bool priv:1; u32 prot; - u32 flags; u64 pgoff; u64 reloc; - u32 maj, min; /* only valid for MMAP2 record */ - u64 ino; /* only valid for MMAP2 record */ - u64 ino_generation;/* only valid for MMAP2 record */ /* ip -> dso rip */ u64 (*map_ip)(struct map *, u64); @@ -42,15 +34,15 @@ struct map { u64 (*unmap_ip)(struct map *, u64); struct dso *dso; - struct map_groups *groups; refcount_t refcnt; + u32 flags; }; struct kmap; struct kmap *__map__kmap(struct map *map); struct kmap *map__kmap(struct map *map); -struct map_groups *map__kmaps(struct map *map); +struct maps *map__kmaps(struct map *map); static inline u64 map__map_ip(struct map *map, u64 ip) { @@ -110,9 +102,11 @@ struct thread; void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso); + +struct dso_id; + struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, u32 prot, u32 flags, + u64 pgoff, struct dso_id *id, u32 prot, u32 flags, char *filename, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); @@ -141,19 +135,12 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); -struct srccode_state; - -int map__fprintf_srccode(struct map *map, u64 addr, - FILE *fp, struct srccode_state *state); - int map__load(struct map *map); struct symbol *map__find_symbol(struct map *map, u64 addr); struct symbol *map__find_symbol_by_name(struct map *map, const char *name); void map__fixup_start(struct map *map); void map__fixup_end(struct map *map); -void map__reloc_vmlinux(struct map *map); - int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr); diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h deleted file mode 100644 index 5f25efa6d6bc..000000000000 --- a/tools/perf/util/map_groups.h +++ /dev/null @@ -1,93 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_MAP_GROUPS_H -#define __PERF_MAP_GROUPS_H - -#include <linux/refcount.h> -#include <linux/rbtree.h> -#include <stdio.h> -#include <stdbool.h> -#include <linux/types.h> -#include "rwsem.h" - -struct ref_reloc_sym; -struct machine; -struct map; -struct thread; - -struct maps { - struct rb_root entries; - struct rb_root names; - struct rw_semaphore lock; -}; - -void maps__insert(struct maps *maps, struct map *map); -void maps__remove(struct maps *maps, struct map *map); -struct map *maps__find(struct maps *maps, u64 addr); -struct map *maps__first(struct maps *maps); -struct map *map__next(struct map *map); -struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp); - -struct map_groups { - struct maps maps; - struct machine *machine; - refcount_t refcnt; -}; - -#define KMAP_NAME_LEN 256 - -struct kmap { - struct ref_reloc_sym *ref_reloc_sym; - struct map_groups *kmaps; - char name[KMAP_NAME_LEN]; -}; - -struct map_groups *map_groups__new(struct machine *machine); -void map_groups__delete(struct map_groups *mg); -bool map_groups__empty(struct map_groups *mg); - -static inline struct map_groups *map_groups__get(struct map_groups *mg) -{ - if (mg) - refcount_inc(&mg->refcnt); - return mg; -} - -void map_groups__put(struct map_groups *mg); -void map_groups__init(struct map_groups *mg, struct machine *machine); -void map_groups__exit(struct map_groups *mg); -int map_groups__clone(struct thread *thread, struct map_groups *parent); -size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); - -void map_groups__insert(struct map_groups *mg, struct map *map); - -static inline void map_groups__remove(struct map_groups *mg, struct map *map) -{ - maps__remove(&mg->maps, map); -} - -static inline struct map *map_groups__find(struct map_groups *mg, u64 addr) -{ - return maps__find(&mg->maps, addr); -} - -struct map *map_groups__first(struct map_groups *mg); - -static inline struct map *map_groups__next(struct map *map) -{ - return map__next(map); -} - -struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp); -struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp); - -struct addr_map_symbol; - -int map_groups__find_ams(struct addr_map_symbol *ams); - -int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp); - -struct map *map_groups__find_by_name(struct map_groups *mg, const char *name); - -int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map); - -#endif // __PERF_MAP_GROUPS_H diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 5a1aed9f6bb4..5b8ca93798e9 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -4,17 +4,18 @@ #include <linux/types.h> +struct maps; struct map; struct symbol; struct map_symbol { + struct maps *maps; struct map *map; struct symbol *sym; }; struct addr_map_symbol { - struct map *map; - struct symbol *sym; + struct map_symbol ms; u64 addr; u64 al_addr; u64 phys_addr; diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h new file mode 100644 index 000000000000..3dd000ddf925 --- /dev/null +++ b/tools/perf/util/maps.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_MAPS_H +#define __PERF_MAPS_H + +#include <linux/refcount.h> +#include <linux/rbtree.h> +#include <stdio.h> +#include <stdbool.h> +#include <linux/types.h> +#include "rwsem.h" + +struct ref_reloc_sym; +struct machine; +struct map; +struct maps; +struct thread; + +struct map *maps__find(struct maps *maps, u64 addr); +struct map *maps__first(struct maps *maps); +struct map *map__next(struct map *map); + +#define maps__for_each_entry(maps, map) \ + for (map = maps__first(maps); map; map = map__next(map)) + +#define maps__for_each_entry_safe(maps, map, next) \ + for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map)) + +struct maps { + struct rb_root entries; + struct rw_semaphore lock; + struct machine *machine; + struct map *last_search_by_name; + struct map **maps_by_name; + refcount_t refcnt; + unsigned int nr_maps; + unsigned int nr_maps_allocated; +#ifdef HAVE_LIBUNWIND_SUPPORT + void *addr_space; + struct unwind_libunwind_ops *unwind_libunwind_ops; +#endif +}; + +#define KMAP_NAME_LEN 256 + +struct kmap { + struct ref_reloc_sym *ref_reloc_sym; + struct maps *kmaps; + char name[KMAP_NAME_LEN]; +}; + +struct maps *maps__new(struct machine *machine); +void maps__delete(struct maps *maps); +bool maps__empty(struct maps *maps); + +static inline struct maps *maps__get(struct maps *maps) +{ + if (maps) + refcount_inc(&maps->refcnt); + return maps; +} + +void maps__put(struct maps *maps); +void maps__init(struct maps *maps, struct machine *machine); +void maps__exit(struct maps *maps); +int maps__clone(struct thread *thread, struct maps *parent); +size_t maps__fprintf(struct maps *maps, FILE *fp); + +void maps__insert(struct maps *maps, struct map *map); + +void maps__remove(struct maps *maps, struct map *map); + +struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp); +struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp); + +struct addr_map_symbol; + +int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams); + +int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp); + +struct map *maps__find_by_name(struct maps *maps, const char *name); + +int maps__merge_in(struct maps *kmaps, struct map *new_map); + +void __maps__sort_by_name(struct maps *maps); + +#endif // __PERF_MAPS_H diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 42c3e5a229d2..aa29589f6904 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -8,10 +8,10 @@ #include <unistd.h> #include <api/fs/fs.h> #include <linux/kernel.h> +#include "map_symbol.h" #include "mem-events.h" #include "debug.h" #include "symbol.h" -#include "sort.h" unsigned int perf_mem_events__loads_ldlat = 30; @@ -410,7 +410,7 @@ do { \ return -1; } - if (!mi->daddr.map || !mi->iaddr.map) { + if (!mi->daddr.ms.map || !mi->iaddr.ms.map) { stats->nomap++; return -1; } diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index a889ec2fa9f5..f1389bdae7bf 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -6,6 +6,8 @@ #include <stdint.h> #include <stdio.h> #include <linux/types.h> +#include <linux/refcount.h> +#include <linux/perf_event.h> #include "stat.h" struct perf_mem_event { @@ -16,6 +18,13 @@ struct perf_mem_event { const char *sysfs_name; }; +struct mem_info { + struct addr_map_symbol iaddr; + struct addr_map_symbol daddr; + union perf_mem_data_src data_src; + refcount_t refcnt; +}; + enum { PERF_MEM_EVENTS__LOAD, PERF_MEM_EVENTS__STORE, diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index cacc2fc4dcbd..797d86a1ab09 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -1,7 +1,10 @@ #include <errno.h> #include <inttypes.h> #include <linux/bitmap.h> +#include <linux/kernel.h> #include <linux/zalloc.h> +#include "debug.h" +#include "env.h" #include "mem2node.h" struct phys_entry { diff --git a/tools/perf/util/mem2node.h b/tools/perf/util/mem2node.h index 59c4752a2181..8dfa2b58d0cd 100644 --- a/tools/perf/util/mem2node.h +++ b/tools/perf/util/mem2node.h @@ -2,8 +2,9 @@ #define __MEM2NODE_H #include <linux/rbtree.h> -#include "env.h" +#include <linux/types.h> +struct perf_env; struct phys_entry; struct mem2node { diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h index 1e29ff903ca9..2c38e8c2d548 100644 --- a/tools/perf/util/memswap.h +++ b/tools/perf/util/memswap.h @@ -2,6 +2,13 @@ #ifndef PERF_MEMSWAP_H_ #define PERF_MEMSWAP_H_ +#include <linux/types.h> + +union u64_swap { + u64 val64; + u32 val32[2]; +}; + void mem_bswap_64(void *src, int byte_size); void mem_bswap_32(void *src, int byte_size); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 416a9015405e..02aee946b6c1 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -6,22 +6,25 @@ /* Manage metrics and groups of metrics from JSON files */ #include "metricgroup.h" +#include "debug.h" #include "evlist.h" +#include "evsel.h" #include "strbuf.h" #include "pmu.h" #include "expr.h" #include "rblist.h" #include <string.h> -#include <stdbool.h> #include <errno.h> #include "pmu-events/pmu-events.h" #include "strlist.h" #include <assert.h> #include <linux/ctype.h> +#include <linux/string.h> #include <linux/zalloc.h> +#include <subcmd/parse-options.h> struct metric_event *metricgroup__lookup(struct rblist *metric_events, - struct perf_evsel *evsel, + struct evsel *evsel, bool create) { struct rb_node *nd; @@ -84,63 +87,71 @@ struct egroup { const char **ids; const char *metric_name; const char *metric_expr; + const char *metric_unit; }; -static bool record_evsel(int *ind, struct perf_evsel **start, - int idnum, - struct perf_evsel **metric_events, - struct perf_evsel *ev) +static struct evsel *find_evsel_group(struct evlist *perf_evlist, + const char **ids, + int idnum, + struct evsel **metric_events) { - metric_events[*ind] = ev; - if (*ind == 0) - *start = ev; - if (++*ind == idnum) { - metric_events[*ind] = NULL; - return true; - } - return false; -} - -static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist, - const char **ids, - int idnum, - struct perf_evsel **metric_events) -{ - struct perf_evsel *ev, *start = NULL; - int ind = 0; + struct evsel *ev; + int i = 0; + bool leader_found; evlist__for_each_entry (perf_evlist, ev) { - if (ev->collect_stat) - continue; - if (!strcmp(ev->name, ids[ind])) { - if (record_evsel(&ind, &start, idnum, - metric_events, ev)) - return start; + if (!strcmp(ev->name, ids[i])) { + if (!metric_events[i]) + metric_events[i] = ev; + i++; + if (i == idnum) + break; } else { - /* - * We saw some other event that is not - * in our list of events. Discard - * the whole match and start again. - */ - ind = 0; - start = NULL; - if (!strcmp(ev->name, ids[ind])) { - if (record_evsel(&ind, &start, idnum, - metric_events, ev)) - return start; + if (i + 1 == idnum) { + /* Discard the whole match and start again */ + i = 0; + memset(metric_events, 0, + sizeof(struct evsel *) * idnum); + continue; + } + + if (!strcmp(ev->name, ids[i])) + metric_events[i] = ev; + else { + /* Discard the whole match and start again */ + i = 0; + memset(metric_events, 0, + sizeof(struct evsel *) * idnum); + continue; } } } - /* - * This can happen when an alias expands to multiple - * events, like for uncore events. - * We don't support this case for now. - */ - return NULL; + + if (i != idnum) { + /* Not whole match */ + return NULL; + } + + metric_events[idnum] = NULL; + + for (i = 0; i < idnum; i++) { + leader_found = false; + evlist__for_each_entry(perf_evlist, ev) { + if (!leader_found && (ev == metric_events[i])) + leader_found = true; + + if (leader_found && + !strcmp(ev->name, metric_events[i]->name)) { + ev->metric_leader = metric_events[i]; + } + } + } + + return metric_events[0]; } static int metricgroup__setup_events(struct list_head *groups, - struct perf_evlist *perf_evlist, + struct evlist *perf_evlist, struct rblist *metric_events_list) { struct metric_event *me; @@ -148,10 +159,10 @@ static int metricgroup__setup_events(struct list_head *groups, int i = 0; int ret = 0; struct egroup *eg; - struct perf_evsel *evsel; + struct evsel *evsel; list_for_each_entry (eg, groups, nd) { - struct perf_evsel **metric_events; + struct evsel **metric_events; metric_events = calloc(sizeof(void *), eg->idnum + 1); if (!metric_events) { @@ -179,6 +190,7 @@ static int metricgroup__setup_events(struct list_head *groups, } expr->metric_expr = eg->metric_expr; expr->metric_name = eg->metric_name; + expr->metric_unit = eg->metric_unit; expr->metric_events = metric_events; list_add(&expr->nd, &me->head); } @@ -450,6 +462,7 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events, eg->idnum = idnum; eg->metric_name = pe->metric_name; eg->metric_expr = pe->metric_expr; + eg->metric_unit = pe->unit; list_add_tail(&eg->nd, group_list); ret = 0; } @@ -502,7 +515,7 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events) { struct parse_events_error parse_error; - struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value; + struct evlist *perf_evlist = *(struct evlist **)opt->value; struct strbuf extra_events; LIST_HEAD(group_list); int ret; @@ -513,7 +526,7 @@ int metricgroup__parse_groups(const struct option *opt, if (ret) return ret; pr_debug("adding %s\n", extra_events.buf); - memset(&parse_error, 0, sizeof(struct parse_events_error)); + bzero(&parse_error, sizeof(parse_error)); ret = parse_events(perf_evlist, extra_events.buf, &parse_error); if (ret) { parse_events_print_error(&parse_error, extra_events.buf); diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 5c52097a5c63..475c7f912864 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -1,15 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only #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" +#include <linux/list.h> +#include <linux/rbtree.h> +#include <stdbool.h> + +struct evsel; +struct option; +struct rblist; struct metric_event { struct rb_node nd; - struct perf_evsel *evsel; + struct evsel *evsel; struct list_head head; /* list of metric_expr */ }; @@ -17,11 +20,12 @@ struct metric_expr { struct list_head nd; const char *metric_expr; const char *metric_name; - struct perf_evsel **metric_events; + const char *metric_unit; + struct evsel **metric_events; }; struct metric_event *metricgroup__lookup(struct rblist *metric_events, - struct perf_evsel *evsel, + struct evsel *evsel, bool create); int metricgroup__parse_groups(const struct option *opt, const char *str, diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 9f0b6391af33..3b664fa673a6 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -10,124 +10,35 @@ #include <inttypes.h> #include <asm/bug.h> #include <linux/zalloc.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> // sysconf() +#include <perf/mmap.h> #ifdef HAVE_LIBNUMA_SUPPORT #include <numaif.h> #endif +#include "cpumap.h" #include "debug.h" #include "event.h" #include "mmap.h" -#include "util.h" /* page_size */ +#include "../perf.h" +#include <internal/lib.h> /* page_size */ +#include <linux/bitmap.h> -size_t perf_mmap__mmap_len(struct perf_mmap *map) +#define MASK_SIZE 1023 +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag) { - 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, - u64 *startp, u64 end) -{ - unsigned char *data = map->base + page_size; - union perf_event *event = NULL; - int diff = end - *startp; - - if (diff >= (int)sizeof(event->header)) { - size_t size; - - event = (union perf_event *)&data[*startp & map->mask]; - size = event->header.size; - - if (size < sizeof(event->header) || diff < (int)size) - return NULL; - - /* - * Event straddles the mmap boundary -- header should always - * be inside due to u64 alignment of output. - */ - if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { - unsigned int offset = *startp; - 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; - } - - *startp += size; - } - - return event; -} - -/* - * Read event from ring buffer one by one. - * Return one event for each call. - * - * Usage: - * perf_mmap__read_init() - * while(event = perf_mmap__read_event()) { - * //process the event - * perf_mmap__consume() - * } - * perf_mmap__read_done() - */ -union perf_event *perf_mmap__read_event(struct perf_mmap *map) -{ - union perf_event *event; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->refcnt)) - return NULL; - - /* non-overwirte doesn't pause the ringbuffer */ - if (!map->overwrite) - map->end = perf_mmap__read_head(map); - - event = perf_mmap__read(map, &map->start, map->end); - - if (!map->overwrite) - map->prev = map->start; - - return event; -} + char buf[MASK_SIZE + 1]; + size_t len; -static bool perf_mmap__empty(struct perf_mmap *map) -{ - return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base; + len = bitmap_scnprintf(mask->bits, mask->nbits, buf, MASK_SIZE); + buf[len] = '\0'; + pr_debug("%p: %s mask[%zd]: %s\n", mask, tag, mask->nbits, buf); } -void perf_mmap__get(struct perf_mmap *map) +size_t mmap__mmap_len(struct 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) -{ - if (!map->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); + return perf_mmap__mmap_len(&map->core); } int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, @@ -150,22 +61,22 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_u } void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int idx __maybe_unused, bool per_cpu __maybe_unused) { } #ifdef HAVE_AIO_SUPPORT -static int perf_mmap__aio_enabled(struct perf_mmap *map) +static int perf_mmap__aio_enabled(struct mmap *map) { return map->aio.nr_cblocks > 0; } #ifdef HAVE_LIBNUMA_SUPPORT -static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) +static int perf_mmap__aio_alloc(struct mmap *map, int idx) { - map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, + map->aio.data[idx] = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); if (map->aio.data[idx] == MAP_FAILED) { map->aio.data[idx] = NULL; @@ -175,15 +86,15 @@ static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) return 0; } -static void perf_mmap__aio_free(struct perf_mmap *map, int idx) +static void perf_mmap__aio_free(struct mmap *map, int idx) { if (map->aio.data[idx]) { - munmap(map->aio.data[idx], perf_mmap__mmap_len(map)); + munmap(map->aio.data[idx], mmap__mmap_len(map)); map->aio.data[idx] = NULL; } } -static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affinity) +static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) { void *data; size_t mmap_len; @@ -191,7 +102,7 @@ static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affi if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) { data = map->aio.data[idx]; - mmap_len = perf_mmap__mmap_len(map); + mmap_len = mmap__mmap_len(map); node_mask = 1UL << cpu__get_node(cpu); if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) { pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n", @@ -203,28 +114,28 @@ static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affi return 0; } #else /* !HAVE_LIBNUMA_SUPPORT */ -static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) +static int perf_mmap__aio_alloc(struct mmap *map, int idx) { - map->aio.data[idx] = malloc(perf_mmap__mmap_len(map)); + map->aio.data[idx] = malloc(mmap__mmap_len(map)); if (map->aio.data[idx] == NULL) return -1; return 0; } -static void perf_mmap__aio_free(struct perf_mmap *map, int idx) +static void perf_mmap__aio_free(struct mmap *map, int idx) { zfree(&(map->aio.data[idx])); } -static int perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int idx __maybe_unused, +static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused, int cpu __maybe_unused, int affinity __maybe_unused) { return 0; } #endif -static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) +static int perf_mmap__aio_mmap(struct mmap *map, struct mmap_params *mp) { int delta_max, i, prio, ret; @@ -252,7 +163,7 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) pr_debug2("failed to allocate data buffer area, error %m"); return -1; } - ret = perf_mmap__aio_bind(map, i, map->cpu, mp->affinity); + ret = perf_mmap__aio_bind(map, i, map->core.cpu, mp->affinity); if (ret == -1) return -1; /* @@ -278,7 +189,7 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) return 0; } -static void perf_mmap__aio_munmap(struct perf_mmap *map) +static void perf_mmap__aio_munmap(struct mmap *map) { int i; @@ -290,101 +201,90 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map) zfree(&map->aio.aiocb); } #else /* !HAVE_AIO_SUPPORT */ -static int perf_mmap__aio_enabled(struct perf_mmap *map __maybe_unused) +static int perf_mmap__aio_enabled(struct mmap *map __maybe_unused) { return 0; } -static int perf_mmap__aio_mmap(struct perf_mmap *map __maybe_unused, +static int perf_mmap__aio_mmap(struct mmap *map __maybe_unused, struct mmap_params *mp __maybe_unused) { return 0; } -static void perf_mmap__aio_munmap(struct perf_mmap *map __maybe_unused) +static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) { } #endif -void perf_mmap__munmap(struct perf_mmap *map) +void mmap__munmap(struct mmap *map) { + bitmap_free(map->affinity_mask.bits); + perf_mmap__aio_munmap(map); if (map->data != NULL) { - munmap(map->data, perf_mmap__mmap_len(map)); + munmap(map->data, mmap__mmap_len(map)); map->data = NULL; } - if (map->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 build_node_mask(int node, cpu_set_t *mask) +static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int c, cpu, nr_cpus; - const struct cpu_map *cpu_map = NULL; + const struct perf_cpu_map *cpu_map = NULL; cpu_map = cpu_map__online(); if (!cpu_map) return; - nr_cpus = cpu_map__nr(cpu_map); + nr_cpus = perf_cpu_map__nr(cpu_map); for (c = 0; c < nr_cpus; c++) { cpu = cpu_map->map[c]; /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) - CPU_SET(cpu, mask); + set_bit(cpu, mask->bits); } } -static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp) +static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - CPU_ZERO(&map->affinity_mask); + map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits); + if (!map->affinity_mask.bits) + return -1; + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) - build_node_mask(cpu__get_node(map->cpu), &map->affinity_mask); + build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - CPU_SET(map->cpu, &map->affinity_mask); + set_bit(map->core.cpu, map->affinity_mask.bits); + + return 0; } -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu) +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) { - /* - * The last one will be done at perf_mmap__consume(), so that we - * make sure we don't prevent tools from consuming every last event in - * the ring buffer. - * - * I.e. we can get the POLLHUP meaning that the fd doesn't exist - * anymore, but the last events for it are still in the ring buffer, - * waiting to be consumed. - * - * Tools can chose to ignore this at their own discretion, but the - * evlist layer can't just drop it when filtering events in - * perf_evlist__filter_pollfd(). - */ - refcount_set(&map->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) { + if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", errno); - map->base = NULL; return -1; } - map->fd = fd; - map->cpu = cpu; - perf_mmap__setup_affinity_mask(map, mp); + if (mp->affinity != PERF_AFFINITY_SYS && + perf_mmap__setup_affinity_mask(map, mp)) { + pr_debug2("failed to alloc mmap affinity mask, error %d\n", + errno); + return -1; + } + + if (verbose == 2) + mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap"); - map->flush = mp->flush; + map->core.flush = mp->flush; map->comp_level = mp->comp_level; if (map->comp_level && !perf_mmap__aio_enabled(map)) { - map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, + map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); if (map->data == MAP_FAILED) { pr_debug2("failed to mmap data buffer, error %d\n", @@ -395,111 +295,31 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c } if (auxtrace_mmap__mmap(&map->auxtrace_mmap, - &mp->auxtrace_mp, map->base, fd)) + &mp->auxtrace_mp, map->core.base, fd)) return -1; return perf_mmap__aio_mmap(map, mp); } -static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end) +int perf_mmap__push(struct mmap *md, void *to, + int push(struct mmap *map, void *to, void *buf, size_t size)) { - struct perf_event_header *pheader; - u64 evt_head = *start; - int size = mask + 1; - - pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start); - pheader = (struct perf_event_header *)(buf + (*start & mask)); - while (true) { - if (evt_head - *start >= (unsigned int)size) { - pr_debug("Finished reading overwrite ring buffer: rewind\n"); - if (evt_head - *start > (unsigned int)size) - evt_head -= pheader->size; - *end = evt_head; - return 0; - } - - pheader = (struct perf_event_header *)(buf + (evt_head & mask)); - - if (pheader->size == 0) { - pr_debug("Finished reading overwrite ring buffer: get start\n"); - *end = evt_head; - return 0; - } - - evt_head += pheader->size; - pr_debug3("move evt_head: %"PRIx64"\n", evt_head); - } - WARN_ONCE(1, "Shouldn't get here\n"); - return -1; -} - -/* - * Report the start and end of the available data in ringbuffer - */ -static int __perf_mmap__read_init(struct perf_mmap *md) -{ - u64 head = perf_mmap__read_head(md); - u64 old = md->prev; - unsigned char *data = md->base + page_size; - unsigned long size; - - md->start = md->overwrite ? head : old; - md->end = md->overwrite ? old : head; - - if ((md->end - md->start) < md->flush) - return -EAGAIN; - - size = md->end - md->start; - if (size > (unsigned long)(md->mask) + 1) { - if (!md->overwrite) { - WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); - - md->prev = head; - perf_mmap__consume(md); - return -EAGAIN; - } - - /* - * Backward ring buffer is full. We still have a chance to read - * most of data from it. - */ - if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end)) - return -EINVAL; - } - - return 0; -} - -int perf_mmap__read_init(struct perf_mmap *map) -{ - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->refcnt)) - return -ENOENT; - - return __perf_mmap__read_init(map); -} - -int perf_mmap__push(struct perf_mmap *md, void *to, - int push(struct perf_mmap *map, void *to, void *buf, size_t size)) -{ - u64 head = perf_mmap__read_head(md); - unsigned char *data = md->base + page_size; + u64 head = perf_mmap__read_head(&md->core); + unsigned char *data = md->core.base + page_size; unsigned long size; void *buf; int rc = 0; - rc = perf_mmap__read_init(md); + rc = perf_mmap__read_init(&md->core); if (rc < 0) return (rc == -EAGAIN) ? 1 : -1; - size = md->end - md->start; + size = md->core.end - md->core.start; - if ((md->start & md->mask) + size != (md->end & md->mask)) { - buf = &data[md->start & md->mask]; - size = md->mask + 1 - (md->start & md->mask); - md->start += size; + if ((md->core.start & md->core.mask) + size != (md->core.end & md->core.mask)) { + buf = &data[md->core.start & md->core.mask]; + size = md->core.mask + 1 - (md->core.start & md->core.mask); + md->core.start += size; if (push(md, to, buf, size) < 0) { rc = -1; @@ -507,34 +327,17 @@ int perf_mmap__push(struct perf_mmap *md, void *to, } } - buf = &data[md->start & md->mask]; - size = md->end - md->start; - md->start += size; + buf = &data[md->core.start & md->core.mask]; + size = md->core.end - md->core.start; + md->core.start += size; if (push(md, to, buf, size) < 0) { rc = -1; goto out; } - md->prev = head; - perf_mmap__consume(md); + md->core.prev = head; + perf_mmap__consume(&md->core); out: return rc; } - -/* - * Mandatory for overwrite mode - * The direction of overwrite mode is backward. - * The last perf_mmap__read() will set tail to map->prev. - * Need to correct the map->prev to head which is the end of next read. - */ -void perf_mmap__read_done(struct perf_mmap *map) -{ - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->refcnt)) - return; - - map->prev = perf_mmap__read_head(map); -} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 274ce389cd84..9d5f589f02ae 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -1,11 +1,13 @@ #ifndef __PERF_MMAP_H #define __PERF_MMAP_H 1 +#include <internal/mmap.h> #include <linux/compiler.h> #include <linux/refcount.h> #include <linux/types.h> #include <linux/ring_buffer.h> #include <stdbool.h> +#include <pthread.h> // for cpu_set_t #ifdef HAVE_AIO_SUPPORT #include <aio.h> #endif @@ -13,23 +15,23 @@ #include "event.h" struct aiocb; + +struct mmap_cpu_mask { + unsigned long *bits; + size_t nbits; +}; + +#define MMAP_CPU_MASK_BYTES(m) \ + (BITS_TO_LONGS(((struct mmap_cpu_mask *)m)->nbits) * sizeof(unsigned long)) + /** - * struct perf_mmap - perf's ring buffer mmap details + * struct 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; - int cpu; - refcount_t refcnt; - u64 prev; - u64 start; - u64 end; - bool overwrite; +struct mmap { + struct perf_mmap core; struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); #ifdef HAVE_AIO_SUPPORT struct { void **data; @@ -38,72 +40,27 @@ struct perf_mmap { int nr_cblocks; } aio; #endif - cpu_set_t affinity_mask; - u64 flush; + struct mmap_cpu_mask affinity_mask; void *data; int comp_level; }; -/* - * 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, nr_cblocks, affinity, flush, comp_level; + struct perf_mmap_param core; + int nr_cblocks, affinity, flush, comp_level; struct auxtrace_mmap_params auxtrace_mp; }; -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu); -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); - -static inline u64 perf_mmap__read_head(struct perf_mmap *mm) -{ - return ring_buffer_read_head(mm->base); -} - -static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) -{ - ring_buffer_write_tail(md->base, tail); -} +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); +void mmap__munmap(struct mmap *map); -union perf_event *perf_mmap__read_forward(struct perf_mmap *map); +union perf_event *perf_mmap__read_forward(struct mmap *map); -union perf_event *perf_mmap__read_event(struct perf_mmap *map); +int perf_mmap__push(struct mmap *md, void *to, + int push(struct mmap *map, void *to, void *buf, size_t size)); -int perf_mmap__push(struct perf_mmap *md, void *to, - int push(struct perf_mmap *map, void *to, void *buf, size_t size)); +size_t mmap__mmap_len(struct mmap *map); -size_t perf_mmap__mmap_len(struct perf_mmap *map); +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); -int perf_mmap__read_init(struct perf_mmap *md); -void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 46d3a7754897..285d6f30d912 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -17,9 +17,27 @@ #include <string.h> #include <unistd.h> #include <asm/bug.h> +#include <linux/kernel.h> #include <linux/zalloc.h> -struct namespaces *namespaces__new(struct namespaces_event *event) +static const char *perf_ns__names[] = { + [NET_NS_INDEX] = "net", + [UTS_NS_INDEX] = "uts", + [IPC_NS_INDEX] = "ipc", + [PID_NS_INDEX] = "pid", + [USER_NS_INDEX] = "user", + [MNT_NS_INDEX] = "mnt", + [CGROUP_NS_INDEX] = "cgroup", +}; + +const char *perf_ns__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_ns__names)) + return "UNKNOWN"; + return perf_ns__names[id]; +} + +struct namespaces *namespaces__new(struct perf_record_namespaces *event) { struct namespaces *namespaces; u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) * diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 004430c0de93..4b33f684eddd 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -17,7 +17,7 @@ int setns(int fd, int nstype); #endif -struct namespaces_event; +struct perf_record_namespaces; struct namespaces { struct list_head list; @@ -25,7 +25,7 @@ struct namespaces { struct perf_ns_link_info link_info[]; }; -struct namespaces *namespaces__new(struct namespaces_event *event); +struct namespaces *namespaces__new(struct perf_record_namespaces *event); void namespaces__free(struct namespaces *namespaces); struct nsinfo { @@ -66,4 +66,6 @@ static inline void __nsinfo__zput(struct nsinfo **nsip) #define nsinfo__zput(nsi) __nsinfo__zput(&nsi) +const char *perf_ns__name(unsigned int id); + #endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index bb5f34b7ab44..359db2b1fcef 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -8,6 +8,7 @@ #include "session.h" #include "asm/bug.h" #include "debug.h" +#include "ui/progress.h" #define pr_N(n, fmt, ...) \ eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__) diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 726e8d9e8c54..bb4aa88c50a8 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -#include "perf.h" #include "util/debug.h" +#include "util/event.h" #include <subcmd/parse-options.h> #include "util/parse-branch-options.h" #include <stdlib.h> +#include <string.h> #define BRANCH_OPT(n, m) \ { .name = n, .mode = (m) } @@ -30,6 +31,7 @@ static const struct branch_mode branch_modes[] = { 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_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK), BRANCH_END }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 371ff3aee769..c01ba6f8fdad 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -10,30 +10,32 @@ #include <fcntl.h> #include <sys/param.h> #include "term.h" -#include "../perf.h" +#include "build-id.h" #include "evlist.h" #include "evsel.h" +#include <subcmd/pager.h> #include <subcmd/parse-options.h> #include "parse-events.h" #include <subcmd/exec-cmd.h> #include "string2.h" #include "strlist.h" #include "symbol.h" -#include "cache.h" #include "header.h" #include "bpf-loader.h" #include "debug.h" #include <api/fs/tracing_path.h> +#include <perf/cpumap.h> #include "parse-events-bison.h" #define YY_EXTRA_TYPE int #include "parse-events-flex.h" #include "pmu.h" #include "thread_map.h" -#include "cpumap.h" #include "probe-file.h" #include "asm/bug.h" #include "util/parse-branch-options.h" #include "metricgroup.h" +#include "util/evsel_config.h" +#include "util/event.h" #define MAX_NAME_LEN 100 @@ -180,6 +182,37 @@ static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir) #define MAX_EVENT_LENGTH 512 +void parse_events__handle_error(struct parse_events_error *err, int idx, + char *str, char *help) +{ + if (WARN(!str, "WARNING: failed to provide error string\n")) { + free(help); + return; + } + switch (err->num_errors) { + case 0: + err->idx = idx; + err->str = str; + err->help = help; + break; + case 1: + err->first_idx = err->idx; + err->idx = idx; + err->first_str = err->str; + err->str = str; + err->first_help = err->help; + err->help = help; + break; + default: + WARN_ONCE(1, "WARNING: multiple event parsing errors\n"); + free(err->str); + err->str = str; + free(err->help); + err->help = help; + break; + } + err->num_errors++; +} struct tracepoint_path *tracepoint_id_to_path(u64 config) { @@ -314,16 +347,16 @@ static char *get_config_name(struct list_head *head_terms) return NULL; } -static struct perf_evsel * +static struct evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct perf_pmu *pmu, struct list_head *config_terms, bool auto_merge_stats, const char *cpu_list) { - struct perf_evsel *evsel; - struct cpu_map *cpus = pmu ? pmu->cpus : - cpu_list ? cpu_map__new(cpu_list) : NULL; + struct evsel *evsel; + struct perf_cpu_map *cpus = pmu ? pmu->cpus : + cpu_list ? perf_cpu_map__new(cpu_list) : NULL; event_attr_init(attr); @@ -332,9 +365,9 @@ __add_event(struct list_head *list, int *idx, return NULL; (*idx)++; - evsel->cpus = cpu_map__get(cpus); - evsel->own_cpus = cpu_map__get(cpus); - evsel->system_wide = pmu ? pmu->is_uncore : false; + evsel->core.cpus = perf_cpu_map__get(cpus); + evsel->core.own_cpus = perf_cpu_map__get(cpus); + evsel->core.system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; if (name) @@ -343,7 +376,7 @@ __add_event(struct list_head *list, int *idx, if (config_terms) list_splice(config_terms, &evsel->config_terms); - list_add_tail(&evsel->node, list); + list_add_tail(&evsel->core.node, list); return evsel; } @@ -357,7 +390,7 @@ static int add_event(struct list_head *list, int *idx, static int add_event_tool(struct list_head *list, int *idx, enum perf_tool_event tool_event) { - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, @@ -478,6 +511,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, static void tracepoint_error(struct parse_events_error *e, int err, const char *sys, const char *name) { + const char *str; char help[BUFSIZ]; if (!e) @@ -491,18 +525,18 @@ static void tracepoint_error(struct parse_events_error *e, int err, switch (err) { case EACCES: - e->str = strdup("can't access trace events"); + str = "can't access trace events"; break; case ENOENT: - e->str = strdup("unknown tracepoint"); + str = "unknown tracepoint"; break; default: - e->str = strdup("failed to add tracepoint"); + str = "failed to add tracepoint"; break; } tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name); - e->help = strdup(help); + parse_events__handle_error(e, 0, strdup(str), strdup(help)); } static int add_tracepoint(struct list_head *list, int *idx, @@ -510,7 +544,7 @@ static int add_tracepoint(struct list_head *list, int *idx, struct parse_events_error *err, struct list_head *head_config) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++); if (IS_ERR(evsel)) { @@ -526,7 +560,7 @@ static int add_tracepoint(struct list_head *list, int *idx, list_splice(&config_terms, &evsel->config_terms); } - list_add_tail(&evsel->node, list); + list_add_tail(&evsel->core.node, list); return 0; } @@ -630,15 +664,24 @@ struct __add_bpf_event_param { struct list_head *head_config; }; -static int add_bpf_event(const char *group, const char *event, int fd, +static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj, void *_param) { LIST_HEAD(new_evsels); struct __add_bpf_event_param *param = _param; struct parse_events_state *parse_state = param->parse_state; struct list_head *list = param->list; - struct perf_evsel *pos; + struct evsel *pos; int err; + /* + * Check if we should add the event, i.e. if it is a TP but starts with a '!', + * then don't add the tracepoint, this will be used for something else, like + * adding to a BPF_MAP_TYPE_PROG_ARRAY. + * + * See tools/perf/examples/bpf/augmented_raw_syscalls.c + */ + if (group[0] == '!') + return 0; pr_debug("add bpf event %s:%s and attach bpf program %d\n", group, event, fd); @@ -647,22 +690,23 @@ static int add_bpf_event(const char *group, const char *event, int fd, event, parse_state->error, param->head_config); if (err) { - struct perf_evsel *evsel, *tmp; + struct evsel *evsel, *tmp; pr_debug("Failed to add BPF event %s:%s\n", group, event); - list_for_each_entry_safe(evsel, tmp, &new_evsels, node) { - list_del_init(&evsel->node); - perf_evsel__delete(evsel); + list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) { + list_del_init(&evsel->core.node); + evsel__delete(evsel); } return err; } pr_debug("adding %s:%s\n", group, event); - list_for_each_entry(pos, &new_evsels, node) { + list_for_each_entry(pos, &new_evsels, core.node) { pr_debug("adding %s:%s to %p\n", group, event, pos); pos->bpf_fd = fd; + pos->bpf_obj = obj; } list_splice(&new_evsels, list); return 0; @@ -920,11 +964,11 @@ static int check_type_val(struct parse_events_term *term, return 0; if (err) { - err->idx = term->err_val; - if (type == PARSE_EVENTS__TERM_TYPE_NUM) - err->str = strdup("expected numeric value"); - else - err->str = strdup("expected string value"); + parse_events__handle_error(err, term->err_val, + type == PARSE_EVENTS__TERM_TYPE_NUM + ? strdup("expected numeric value") + : strdup("expected string value"), + NULL); } return -EINVAL; } @@ -952,6 +996,8 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", + [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", }; static bool config_term_shrinked; @@ -959,8 +1005,11 @@ static bool config_term_shrinked; static bool config_term_avail(int term_type, struct parse_events_error *err) { + char *err_str; + if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) { - err->str = strdup("Invalid term_type"); + parse_events__handle_error(err, -1, + strdup("Invalid term_type"), NULL); return false; } if (!config_term_shrinked) @@ -979,9 +1028,9 @@ config_term_avail(int term_type, struct parse_events_error *err) return false; /* term_type is validated so indexing is safe */ - if (asprintf(&err->str, "'%s' is not usable in 'perf stat'", - config_term_names[term_type]) < 0) - err->str = NULL; + if (asprintf(&err_str, "'%s' is not usable in 'perf stat'", + config_term_names[term_type]) >= 0) + parse_events__handle_error(err, -1, err_str, NULL); return false; } } @@ -1023,17 +1072,20 @@ do { \ case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: CHECK_TYPE_VAL(STR); if (strcmp(term->val.str, "no") && - parse_branch_str(term->val.str, &attr->branch_sample_type)) { - err->str = strdup("invalid branch sample type"); - err->idx = term->err_val; + parse_branch_str(term->val.str, + &attr->branch_sample_type)) { + parse_events__handle_error(err, term->err_val, + strdup("invalid branch sample type"), + NULL); return -EINVAL; } break; case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); if (term->val.num > 1) { - err->str = strdup("expected 0 or 1"); - err->idx = term->err_val; + parse_events__handle_error(err, term->err_val, + strdup("expected 0 or 1"), + NULL); return -EINVAL; } break; @@ -1067,15 +1119,28 @@ do { \ case PARSE_EVENTS__TERM_TYPE_PERCORE: CHECK_TYPE_VAL(NUM); if ((unsigned int)term->val.num > 1) { - err->str = strdup("expected 0 or 1"); - err->idx = term->err_val; + parse_events__handle_error(err, term->err_val, + strdup("expected 0 or 1"), + NULL); + return -EINVAL; + } + break; + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + CHECK_TYPE_VAL(NUM); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + CHECK_TYPE_VAL(NUM); + if (term->val.num > UINT_MAX) { + parse_events__handle_error(err, term->err_val, + strdup("too big"), + NULL); return -EINVAL; } break; default: - err->str = strdup("unknown term"); - err->idx = term->err_term; - err->help = parse_events_formats_error_string(NULL); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + parse_events_formats_error_string(NULL)); return -EINVAL; } @@ -1122,12 +1187,14 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); default: if (err) { - err->idx = term->err_term; - err->str = strdup("unknown term"); - err->help = strdup("valid terms: call-graph,stack-size\n"); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + strdup("valid terms: call-graph,stack-size\n")); } return -EINVAL; } @@ -1152,8 +1219,7 @@ static int config_attr(struct perf_event_attr *attr, static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused) { -#define ADD_CONFIG_TERM(__type, __name, __val) \ -do { \ +#define ADD_CONFIG_TERM(__type) \ struct perf_evsel_config_term *__t; \ \ __t = zalloc(sizeof(*__t)); \ @@ -1162,9 +1228,24 @@ do { \ \ INIT_LIST_HEAD(&__t->list); \ __t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \ - __t->val.__name = __val; \ __t->weak = term->weak; \ - list_add_tail(&__t->list, head_terms); \ + list_add_tail(&__t->list, head_terms) + +#define ADD_CONFIG_TERM_VAL(__type, __name, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.__name = __val; \ +} while (0) + +#define ADD_CONFIG_TERM_STR(__type, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.str = strdup(__val); \ + if (!__t->val.str) { \ + zfree(&__t); \ + return -ENOMEM; \ + } \ + __t->free_str = true; \ } while (0) struct parse_events_term *term; @@ -1172,53 +1253,101 @@ do { \ list_for_each_entry(term, head_config, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - ADD_CONFIG_TERM(PERIOD, period, term->val.num); + ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: - ADD_CONFIG_TERM(FREQ, freq, term->val.num); + ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_TIME: - ADD_CONFIG_TERM(TIME, time, term->val.num); + ADD_CONFIG_TERM_VAL(TIME, time, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: - ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str); + ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - ADD_CONFIG_TERM(BRANCH, branch, term->val.str); + ADD_CONFIG_TERM_STR(BRANCH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_STACKSIZE: - ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num); + ADD_CONFIG_TERM_VAL(STACK_USER, stack_user, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_INHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOINHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: - ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: - ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_OVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_DRV_CFG: - ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str); + ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_PERCORE: - ADD_CONFIG_TERM(PERCORE, percore, - term->val.num ? true : false); + ADD_CONFIG_TERM_VAL(PERCORE, percore, + term->val.num ? true : false); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, + term->val.num ? 1 : 0); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, + term->val.num); break; default: break; } } -#undef ADD_EVSEL_CONFIG + return 0; +} + +/* + * Add PERF_EVSEL__CONFIG_TERM_CFG_CHG where cfg_chg will have a bit set for + * each bit of attr->config that the user has changed. + */ +static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, + struct list_head *head_terms) +{ + struct parse_events_term *term; + u64 bits = 0; + int type; + + list_for_each_entry(term, head_config, list) { + switch (term->type_term) { + case PARSE_EVENTS__TERM_TYPE_USER: + type = perf_pmu__format_type(&pmu->format, term->config); + if (type != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + bits |= perf_pmu__format_bits(&pmu->format, term->config); + break; + case PARSE_EVENTS__TERM_TYPE_CONFIG: + bits = ~(u64)0; + break; + default: + break; + } + } + + if (bits) + ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits); + +#undef ADD_CONFIG_TERM return 0; } @@ -1296,17 +1425,19 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; - struct perf_evsel *evsel; + struct evsel *evsel; struct parse_events_error *err = parse_state->error; bool use_uncore_alias; LIST_HEAD(config_terms); pmu = perf_pmu__find(name); if (!pmu) { - if (asprintf(&err->str, + char *err_str; + + if (asprintf(&err_str, "Cannot find PMU `%s'. Missing kernel support?", - name) < 0) - err->str = NULL; + name) >= 0) + parse_events__handle_error(err, 0, err_str, NULL); return -EINVAL; } @@ -1345,8 +1476,22 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) + /* + * When using default config, record which bits of attr->config were + * changed by the user. + */ + if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) + return -ENOMEM; + + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + struct perf_evsel_config_term *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &config_terms, list) { + list_del_init(&pos->list); + free(pos); + } return -EINVAL; + } evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, @@ -1369,7 +1514,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { - struct list_head *head; struct parse_events_term *term; struct list_head *list; struct perf_pmu *pmu = NULL; @@ -1386,19 +1530,30 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + struct list_head *head; + char *config; + head = malloc(sizeof(struct list_head)); if (!head) return -1; INIT_LIST_HEAD(head); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - str, 1, false, &str, NULL) < 0) + config = strdup(str); + if (!config) + return -1; + if (parse_events_term__num(&term, + PARSE_EVENTS__TERM_TYPE_USER, + config, 1, false, &config, + NULL) < 0) { + free(list); + free(config); return -1; + } list_add_tail(&term->list, head); if (!parse_events_add_pmu(parse_state, list, pmu->name, head, true, true)) { - pr_debug("%s -> %s/%s/\n", str, + pr_debug("%s -> %s/%s/\n", config, pmu->name, alias->str); ok++; } @@ -1407,8 +1562,10 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } } } - if (!ok) + if (!ok) { + free(list); return -1; + } *listp = list; return 0; } @@ -1443,13 +1600,13 @@ static int parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, struct parse_events_state *parse_state) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; uintptr_t *leaders; bool is_leader = true; int i, nr_pmu = 0, total_members, ret = 0; - leader = list_first_entry(list, struct perf_evsel, node); - evsel = list_last_entry(list, struct perf_evsel, node); + leader = list_first_entry(list, struct evsel, core.node); + evsel = list_last_entry(list, struct evsel, core.node); total_members = evsel->idx - leader->idx + 1; leaders = calloc(total_members, sizeof(uintptr_t)); @@ -1511,13 +1668,13 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, __evlist__for_each_entry(list, evsel) { if (i >= nr_pmu) i = 0; - evsel->leader = (struct perf_evsel *) leaders[i++]; + evsel->leader = (struct evsel *) leaders[i++]; } /* The number of members and group name are same for each group */ for (i = 0; i < nr_pmu; i++) { - evsel = (struct perf_evsel *) leaders[i]; - evsel->nr_members = total_members / nr_pmu; + evsel = (struct evsel *) leaders[i]; + evsel->core.nr_members = total_members / nr_pmu; evsel->group_name = name ? strdup(name) : NULL; } @@ -1534,7 +1691,7 @@ out: void parse_events__set_leader(char *name, struct list_head *list, struct parse_events_state *parse_state) { - struct perf_evsel *leader; + struct evsel *leader; if (list_empty(list)) { WARN_ONCE(true, "WARNING: failed to set leader: empty list"); @@ -1545,7 +1702,7 @@ void parse_events__set_leader(char *name, struct list_head *list, return; __perf_evlist__set_leader(list); - leader = list_entry(list->next, struct perf_evsel, node); + leader = list_entry(list->next, struct evsel, core.node); leader->group_name = name ? strdup(name) : NULL; } @@ -1578,18 +1735,18 @@ struct event_modifier { }; static int get_event_modifier(struct event_modifier *mod, char *str, - struct perf_evsel *evsel) -{ - int eu = evsel ? evsel->attr.exclude_user : 0; - int ek = evsel ? evsel->attr.exclude_kernel : 0; - int eh = evsel ? evsel->attr.exclude_hv : 0; - int eH = evsel ? evsel->attr.exclude_host : 0; - int eG = evsel ? evsel->attr.exclude_guest : 0; - int eI = evsel ? evsel->attr.exclude_idle : 0; - int precise = evsel ? evsel->attr.precise_ip : 0; + struct evsel *evsel) +{ + int eu = evsel ? evsel->core.attr.exclude_user : 0; + int ek = evsel ? evsel->core.attr.exclude_kernel : 0; + int eh = evsel ? evsel->core.attr.exclude_hv : 0; + int eH = evsel ? evsel->core.attr.exclude_host : 0; + int eG = evsel ? evsel->core.attr.exclude_guest : 0; + int eI = evsel ? evsel->core.attr.exclude_idle : 0; + int precise = evsel ? evsel->core.attr.precise_ip : 0; int precise_max = 0; int sample_read = 0; - int pinned = evsel ? evsel->attr.pinned : 0; + int pinned = evsel ? evsel->core.attr.pinned : 0; int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; @@ -1691,7 +1848,7 @@ static int check_modifier(char *str) int parse_events__modifier_event(struct list_head *list, char *str, bool add) { - struct perf_evsel *evsel; + struct evsel *evsel; struct event_modifier mod; if (str == NULL) @@ -1707,20 +1864,20 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) if (add && get_event_modifier(&mod, str, evsel)) return -EINVAL; - evsel->attr.exclude_user = mod.eu; - evsel->attr.exclude_kernel = mod.ek; - evsel->attr.exclude_hv = mod.eh; - evsel->attr.precise_ip = mod.precise; - evsel->attr.exclude_host = mod.eH; - evsel->attr.exclude_guest = mod.eG; - evsel->attr.exclude_idle = mod.eI; + evsel->core.attr.exclude_user = mod.eu; + evsel->core.attr.exclude_kernel = mod.ek; + evsel->core.attr.exclude_hv = mod.eh; + evsel->core.attr.precise_ip = mod.precise; + evsel->core.attr.exclude_host = mod.eH; + evsel->core.attr.exclude_guest = mod.eG; + evsel->core.attr.exclude_idle = mod.eI; 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; + evsel->core.attr.pinned = mod.pinned; } return 0; @@ -1728,7 +1885,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) int parse_events_name(struct list_head *list, char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; __evlist__for_each_entry(list, evsel) { if (!evsel->name) @@ -1894,12 +2051,12 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct perf_evlist *evlist, const char *str, +int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err) { struct parse_events_state parse_state = { .list = LIST_HEAD_INIT(parse_state.list), - .idx = evlist->nr_entries, + .idx = evlist->core.nr_entries, .error = err, .evlist = evlist, }; @@ -1907,17 +2064,22 @@ int parse_events(struct perf_evlist *evlist, const char *str, ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); - if (!ret) { - struct perf_evsel *last; - if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing\n"); - return -1; - } + if (!ret && list_empty(&parse_state.list)) { + WARN_ONCE(true, "WARNING: event parser found nothing\n"); + return -1; + } + + /* + * Add list to the evlist even with errors to allow callers to clean up. + */ + perf_evlist__splice_list_tail(evlist, &parse_state.list); + + if (!ret) { + struct evsel *last; - perf_evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups += parse_state.nr_groups; - last = perf_evlist__last(evlist); + last = evlist__last(evlist); last->cmdline_group_boundary = true; return 0; @@ -1925,7 +2087,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, /* * There are 2 users - builtin-record and builtin-test objects. - * Both call perf_evlist__delete in case of error, so we dont + * Both call evlist__delete in case of error, so we dont * need to bother. */ return ret; @@ -1940,15 +2102,14 @@ static int get_term_width(void) return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col; } -void parse_events_print_error(struct parse_events_error *err, - const char *event) +static void __parse_events_print_error(int err_idx, const char *err_str, + const char *err_help, const char *event) { const char *str = "invalid or unsupported event: "; char _buf[MAX_WIDTH]; char *buf = (char *) event; int idx = 0; - - if (err->str) { + if (err_str) { /* -2 for extra '' in the final fprintf */ int width = get_term_width() - 2; int len_event = strlen(event); @@ -1971,8 +2132,8 @@ void parse_events_print_error(struct parse_events_error *err, buf = _buf; /* We're cutting from the beginning. */ - if (err->idx > max_err_idx) - cut = err->idx - max_err_idx; + if (err_idx > max_err_idx) + cut = err_idx - max_err_idx; strncpy(buf, event + cut, max_len); @@ -1985,16 +2146,33 @@ void parse_events_print_error(struct parse_events_error *err, buf[max_len] = 0; } - idx = len_str + err->idx - cut; + idx = len_str + err_idx - cut; } fprintf(stderr, "%s'%s'\n", str, buf); if (idx) { - fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str); - if (err->help) - fprintf(stderr, "\n%s\n", err->help); - zfree(&err->str); - zfree(&err->help); + fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err_str); + if (err_help) + fprintf(stderr, "\n%s\n", err_help); + } +} + +void parse_events_print_error(struct parse_events_error *err, + const char *event) +{ + if (!err->num_errors) + return; + + __parse_events_print_error(err->idx, err->str, err->help, event); + zfree(&err->str); + zfree(&err->help); + + if (err->num_errors > 1) { + fputs("\nInitial error:\n", stderr); + __parse_events_print_error(err->first_idx, err->first_str, + err->first_help, event); + zfree(&err->first_str); + zfree(&err->first_help); } } @@ -2003,9 +2181,12 @@ void parse_events_print_error(struct parse_events_error *err, int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; - struct parse_events_error err = { .idx = 0, }; - int ret = parse_events(evlist, str, &err); + struct evlist *evlist = *(struct evlist **)opt->value; + struct parse_events_error err; + int ret; + + bzero(&err, sizeof(err)); + ret = parse_events(evlist, str, &err); if (ret) { parse_events_print_error(&err, str); @@ -2016,12 +2197,12 @@ int parse_events_option(const struct option *opt, const char *str, } static int -foreach_evsel_in_last_glob(struct perf_evlist *evlist, - int (*func)(struct perf_evsel *evsel, +foreach_evsel_in_last_glob(struct evlist *evlist, + int (*func)(struct evsel *evsel, const void *arg), const void *arg) { - struct perf_evsel *last = NULL; + struct evsel *last = NULL; int err; /* @@ -2030,8 +2211,8 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist, * * So no need to WARN here, let *func do this. */ - if (evlist->nr_entries > 0) - last = perf_evlist__last(evlist); + if (evlist->core.nr_entries > 0) + last = evlist__last(evlist); do { err = (*func)(last, arg); @@ -2040,15 +2221,15 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist, if (!last) return 0; - if (last->node.prev == &evlist->entries) + if (last->core.node.prev == &evlist->core.entries) return 0; - last = list_entry(last->node.prev, struct perf_evsel, node); + last = list_entry(last->core.node.prev, struct evsel, core.node); } while (!last->cmdline_group_boundary); return 0; } -static int set_filter(struct perf_evsel *evsel, const void *arg) +static int set_filter(struct evsel *evsel, const void *arg) { const char *str = arg; bool found = false; @@ -2061,7 +2242,7 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) return -1; } - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { if (perf_evsel__append_tp_filter(evsel, str) < 0) { fprintf(stderr, "not enough memory to hold filter string\n"); @@ -2072,7 +2253,7 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) } while ((pmu = perf_pmu__scan(pmu)) != NULL) - if (pmu->type == evsel->attr.type) { + if (pmu->type == evsel->core.attr.type) { found = true; break; } @@ -2099,18 +2280,18 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) int parse_filter(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct evlist *evlist = *(struct evlist **)opt->value; return foreach_evsel_in_last_glob(evlist, set_filter, (const void *)str); } -static int add_exclude_perf_filter(struct perf_evsel *evsel, +static int add_exclude_perf_filter(struct evsel *evsel, const void *arg __maybe_unused) { char new_filter[64]; - if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel == NULL || evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, "--exclude-perf option should follow a -e tracepoint option\n"); return -1; @@ -2131,7 +2312,7 @@ int exclude_perf(const struct option *opt, const char *arg __maybe_unused, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct evlist *evlist = *(struct evlist **)opt->value; return foreach_evsel_in_last_glob(evlist, add_exclude_perf_filter, NULL); @@ -2297,20 +2478,20 @@ static bool is_event_supported(u8 type, unsigned config) { bool ret = true; int open_return; - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_event_attr attr = { .type = type, .config = config, .disabled = 1, }; - struct thread_map *tmap = thread_map__new_by_tid(0); + struct perf_thread_map *tmap = thread_map__new_by_tid(0); if (tmap == NULL) return false; - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel) { - open_return = perf_evsel__open(evsel, NULL, tmap); + open_return = evsel__open(evsel, NULL, tmap); ret = open_return >= 0; if (open_return == -EACCES) { @@ -2321,13 +2502,13 @@ static bool is_event_supported(u8 type, unsigned config) * by default as some ARM machines do not support it. * */ - evsel->attr.exclude_kernel = 1; - ret = perf_evsel__open(evsel, NULL, tmap) >= 0; + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; } - perf_evsel__delete(evsel); + evsel__delete(evsel); } - thread_map__put(tmap); + perf_thread_map__put(tmap); return ret; } @@ -2580,7 +2761,7 @@ out_enomem: * Print the help text for the event symbols: */ void print_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag) + bool long_desc, bool details_flag, bool deprecated) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2592,7 +2773,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_hwcache_events(event_glob, name_only); print_pmu_events(event_glob, name_only, quiet_flag, long_desc, - details_flag); + details_flag, deprecated); if (event_glob != NULL) return; @@ -2698,30 +2879,63 @@ int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx) { struct event_symbol *sym; + char *str; struct parse_events_term temp = { .type_val = PARSE_EVENTS__TERM_TYPE_STR, .type_term = PARSE_EVENTS__TERM_TYPE_USER, - .config = config ?: (char *) "event", + .config = config, }; + if (!temp.config) { + temp.config = strdup("event"); + if (!temp.config) + return -ENOMEM; + } BUG_ON(idx >= PERF_COUNT_HW_MAX); sym = &event_symbols_hw[idx]; - return new_term(term, &temp, (char *) sym->symbol, 0); + str = strdup(sym->symbol); + if (!str) + return -ENOMEM; + return new_term(term, &temp, str, 0); } int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term) { + char *str; struct parse_events_term temp = { .type_val = term->type_val, .type_term = term->type_term, - .config = term->config, + .config = NULL, .err_term = term->err_term, .err_val = term->err_val, }; - return new_term(new, &temp, term->val.str, term->val.num); + if (term->config) { + temp.config = strdup(term->config); + if (!temp.config) + return -ENOMEM; + } + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + return new_term(new, &temp, NULL, term->val.num); + + str = strdup(term->val.str); + if (!str) + return -ENOMEM; + return new_term(new, &temp, str, 0); +} + +void parse_events_term__delete(struct parse_events_term *term) +{ + if (term->array.nr_ranges) + zfree(&term->array.ranges); + + if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) + zfree(&term->val.str); + + zfree(&term->config); + free(term); } int parse_events_copy_term_list(struct list_head *old, @@ -2754,10 +2968,8 @@ void parse_events_terms__purge(struct list_head *terms) struct parse_events_term *term, *h; list_for_each_entry_safe(term, h, terms, list) { - if (term->array.nr_ranges) - zfree(&term->array.ranges); list_del_init(&term->list); - free(term); + parse_events_term__delete(term); } } @@ -2777,13 +2989,10 @@ void parse_events__clear_array(struct parse_events_array *a) void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str) { - struct parse_events_error *err = parse_state->error; - - if (!err) + if (!parse_state->error) return; - err->idx = idx; - err->str = strdup(str); - WARN_ONCE(!err->str, "WARNING: failed to allocate error string"); + + parse_events__handle_error(parse_state->error, idx, strdup(str), NULL); } static void config_terms_list(char *buf, size_t buf_sz) diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f7139e1a2fd3..27596cbd0ba0 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -12,8 +12,8 @@ #include <string.h> struct list_head; -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct parse_events_error; struct option; @@ -31,7 +31,7 @@ bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); int parse_events_option(const struct option *opt, const char *str, int unset); -int parse_events(struct perf_evlist *evlist, const char *str, +int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *error); int parse_events_terms(struct list_head *terms, const char *str); int parse_filter(const struct option *opt, const char *str, int unset); @@ -76,6 +76,8 @@ enum { PARSE_EVENTS__TERM_TYPE_OVERWRITE, PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, + PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, + PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -109,9 +111,13 @@ struct parse_events_term { }; struct parse_events_error { + int num_errors; /* number of errors encountered */ int idx; /* index in the parsed string */ char *str; /* string to display at the index */ char *help; /* optional help string */ + int first_idx;/* as above, but for the first encountered error */ + char *first_str; + char *first_help; }; struct parse_events_state { @@ -119,10 +125,12 @@ struct parse_events_state { int idx; int nr_groups; struct parse_events_error *error; - struct perf_evlist *evlist; + struct evlist *evlist; struct list_head *terms; }; +void parse_events__handle_error(struct parse_events_error *err, int idx, + char *str, char *help); void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, @@ -136,6 +144,7 @@ int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx); int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); +void parse_events_term__delete(struct parse_events_term *term); void parse_events_terms__delete(struct list_head *terms); void parse_events_terms__purge(struct list_head *terms); void parse_events__clear_array(struct parse_events_array *a); @@ -194,7 +203,7 @@ void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc, bool details_flag); + bool long_desc, bool details_flag, bool deprecated); struct event_symbol { const char *symbol; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index ca6098874fe2..7b1c8ee537cf 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -284,6 +284,8 @@ no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); } overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } +aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } +aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index f1c36ed1cf36..94f8bcd83582 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,4 +1,4 @@ -%pure-parser +%define api.pure full %parse-param {void *_parse_state} %parse-param {void *scanner} %lex-param {void* scanner} @@ -9,13 +9,12 @@ #define YYDEBUG 1 #include <fnmatch.h> +#include <stdio.h> #include <linux/compiler.h> -#include <linux/list.h> #include <linux/types.h> -#include "util.h" +#include <linux/zalloc.h> #include "pmu.h" #include "evsel.h" -#include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -27,12 +26,28 @@ do { \ YYABORT; \ } while (0) -#define ALLOC_LIST(list) \ -do { \ - list = malloc(sizeof(*list)); \ - ABORT_ON(!list); \ - INIT_LIST_HEAD(list); \ -} while (0) +static struct list_head* alloc_list() +{ + struct list_head *list; + + list = malloc(sizeof(*list)); + if (!list) + return NULL; + + INIT_LIST_HEAD(list); + return list; +} + +static void free_list_evsel(struct list_head* list_evsel) +{ + struct evsel *evsel, *tmp; + + list_for_each_entry_safe(evsel, tmp, list_evsel, core.node) { + list_del_init(&evsel->core.node); + perf_evsel__delete(evsel); + } + free(list_evsel); +} static void inc_group_count(struct list_head *list, struct parse_events_state *parse_state) @@ -63,6 +78,7 @@ static void inc_group_count(struct list_head *list, %type <num> PE_VALUE_SYM_TOOL %type <num> PE_RAW %type <num> PE_TERM +%type <num> value_sym %type <str> PE_NAME %type <str> PE_BPF_OBJECT %type <str> PE_BPF_SOURCE @@ -73,37 +89,43 @@ static void inc_group_count(struct list_head *list, %type <str> PE_EVENT_NAME %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %type <str> PE_DRV_CFG_TERM -%type <num> value_sym -%type <head> event_config -%type <head> opt_event_config -%type <head> opt_pmu_config +%destructor { free ($$); } <str> %type <term> event_term -%type <head> event_pmu -%type <head> event_legacy_symbol -%type <head> event_legacy_cache -%type <head> event_legacy_mem -%type <head> event_legacy_tracepoint +%destructor { parse_events_term__delete ($$); } <term> +%type <list_terms> event_config +%type <list_terms> opt_event_config +%type <list_terms> opt_pmu_config +%destructor { parse_events_terms__delete ($$); } <list_terms> +%type <list_evsel> event_pmu +%type <list_evsel> event_legacy_symbol +%type <list_evsel> event_legacy_cache +%type <list_evsel> event_legacy_mem +%type <list_evsel> event_legacy_tracepoint +%type <list_evsel> event_legacy_numeric +%type <list_evsel> event_legacy_raw +%type <list_evsel> event_bpf_file +%type <list_evsel> event_def +%type <list_evsel> event_mod +%type <list_evsel> event_name +%type <list_evsel> event +%type <list_evsel> events +%type <list_evsel> group_def +%type <list_evsel> group +%type <list_evsel> groups +%destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name -%type <head> event_legacy_numeric -%type <head> event_legacy_raw -%type <head> event_bpf_file -%type <head> event_def -%type <head> event_mod -%type <head> event_name -%type <head> event -%type <head> events -%type <head> group_def -%type <head> group -%type <head> groups +%destructor { free ($$.sys); free ($$.event); } <tracepoint_name> %type <array> array %type <array> array_term %type <array> array_terms +%destructor { free ($$.ranges); } <array> %union { char *str; u64 num; - struct list_head *head; + struct list_head *list_evsel; + struct list_head *list_terms; struct parse_events_term *term; struct tracepoint_name { char *sys; @@ -122,6 +144,7 @@ start_events: groups { struct parse_events_state *parse_state = _parse_state; + /* frees $1 */ parse_events_update_lists($1, &parse_state->list); } @@ -131,6 +154,7 @@ groups ',' group struct list_head *list = $1; struct list_head *group = $3; + /* frees $3 */ parse_events_update_lists(group, list); $$ = list; } @@ -140,6 +164,7 @@ groups ',' event struct list_head *list = $1; struct list_head *event = $3; + /* frees $3 */ parse_events_update_lists(event, list); $$ = list; } @@ -152,8 +177,14 @@ group: group_def ':' PE_MODIFIER_EVENT { struct list_head *list = $1; + int err; - ABORT_ON(parse_events__modifier_group(list, $3)); + err = parse_events__modifier_group(list, $3); + free($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -166,6 +197,7 @@ PE_NAME '{' events '}' inc_group_count(list, _parse_state); parse_events__set_leader($1, list, _parse_state); + free($1); $$ = list; } | @@ -184,6 +216,7 @@ events ',' event struct list_head *event = $3; struct list_head *list = $1; + /* frees $3 */ parse_events_update_lists(event, list); $$ = list; } @@ -196,13 +229,19 @@ event_mod: event_name PE_MODIFIER_EVENT { struct list_head *list = $1; + int err; /* * Apply modifier on all events added by single event definition * (there could be more events added for multiple tracepoint * definitions via '*?'. */ - ABORT_ON(parse_events__modifier_event(list, $2, false)); + err = parse_events__modifier_event(list, $2, false); + free($2); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -211,8 +250,14 @@ event_name event_name: PE_EVENT_NAME event_def { - ABORT_ON(parse_events_name($2, $1)); + int err; + + err = parse_events_name($2, $1); free($1); + if (err) { + free_list_evsel($2); + YYABORT; + } $$ = $2; } | @@ -232,22 +277,34 @@ PE_NAME opt_pmu_config { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; - struct list_head *list, *orig_terms, *terms; + struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL; + char *pattern = NULL; + +#define CLEANUP_YYABORT \ + do { \ + parse_events_terms__delete($2); \ + parse_events_terms__delete(orig_terms); \ + free(list); \ + free($1); \ + free(pattern); \ + YYABORT; \ + } while(0) if (parse_events_copy_term_list($2, &orig_terms)) - YYABORT; + CLEANUP_YYABORT; if (error) error->idx = @1.first_column; - ALLOC_LIST(list); + list = alloc_list(); + if (!list) + CLEANUP_YYABORT; if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; int ok = 0; - char *pattern; if (asprintf(&pattern, "%s*", $1) < 0) - YYABORT; + CLEANUP_YYABORT; while ((pmu = perf_pmu__scan(pmu)) != NULL) { char *name = pmu->name; @@ -256,31 +313,32 @@ PE_NAME opt_pmu_config strncmp($1, "uncore_", 7)) name += 7; if (!fnmatch(pattern, name, 0)) { - if (parse_events_copy_term_list(orig_terms, &terms)) { - free(pattern); - YYABORT; - } + if (parse_events_copy_term_list(orig_terms, &terms)) + CLEANUP_YYABORT; if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) ok++; parse_events_terms__delete(terms); } } - free(pattern); - if (!ok) - YYABORT; + CLEANUP_YYABORT; } parse_events_terms__delete($2); parse_events_terms__delete(orig_terms); + free($1); $$ = list; +#undef CLEANUP_YYABORT } | PE_KERNEL_PMU_EVENT sep_dc { struct list_head *list; + int err; - if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0) + err = parse_events_multi_pmu_add(_parse_state, $1, &list); + free($1); + if (err < 0) YYABORT; $$ = list; } @@ -291,6 +349,8 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc char pmu_name[128]; snprintf(&pmu_name, 128, "%s-%s", $1, $3); + free($1); + free($3); if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) YYABORT; $$ = list; @@ -307,10 +367,16 @@ value_sym '/' event_config '/' struct list_head *list; int type = $1 >> 16; int config = $1 & 255; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, type, config, $3); parse_events_terms__delete($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -320,7 +386,8 @@ value_sym sep_slash_slash_dc int type = $1 >> 16; int config = $1 & 255; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } @@ -329,7 +396,8 @@ PE_VALUE_SYM_TOOL sep_slash_slash_dc { struct list_head *list; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); ABORT_ON(parse_events_add_tool(_parse_state, list, $1)); $$ = list; } @@ -340,10 +408,19 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_e struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6); parse_events_terms__delete($6); + free($1); + free($3); + free($5); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -352,10 +429,18 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4); parse_events_terms__delete($4); + free($1); + free($3); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } | @@ -364,10 +449,17 @@ PE_NAME_CACHE_TYPE opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2); parse_events_terms__delete($2); + free($1); + if (err) { + free_list_evsel(list); + YYABORT; + } $$ = list; } @@ -376,10 +468,17 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_state *parse_state = _parse_state; struct list_head *list; - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4)); + int err; + + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, $6, $4); + free($6); + if (err) { + free(list); + YYABORT; + } $$ = list; } | @@ -388,9 +487,13 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc struct parse_events_state *parse_state = _parse_state; struct list_head *list; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)); + list = alloc_list(); + ABORT_ON(!list); + if (parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, NULL, $4)) { + free(list); + YYABORT; + } $$ = list; } | @@ -398,10 +501,17 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_state *parse_state = _parse_state; struct list_head *list; - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0)); + int err; + + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, $4, 0); + free($4); + if (err) { + free(list); + YYABORT; + } $$ = list; } | @@ -410,9 +520,13 @@ PE_PREFIX_MEM PE_VALUE sep_dc struct parse_events_state *parse_state = _parse_state; struct list_head *list; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)); + list = alloc_list(); + ABORT_ON(!list); + if (parse_events_add_breakpoint(list, &parse_state->idx, + (void *) $2, NULL, 0)) { + free(list); + YYABORT; + } $$ = list; } @@ -422,28 +536,35 @@ tracepoint_name opt_event_config struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; struct list_head *list; + int err; - ALLOC_LIST(list); + list = alloc_list(); + ABORT_ON(!list); if (error) error->idx = @1.first_column; - if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, - error, $2)) - return -1; + err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, + error, $2); + parse_events_terms__delete($2); + free($1.sys); + free($1.event); + if (err) { + free(list); + YYABORT; + } $$ = list; } tracepoint_name: PE_NAME '-' PE_NAME ':' PE_NAME { - char sys_name[128]; struct tracepoint_name tracepoint; - snprintf(&sys_name, 128, "%s-%s", $1, $3); - tracepoint.sys = &sys_name; + ABORT_ON(asprintf(&tracepoint.sys, "%s-%s", $1, $3) < 0); tracepoint.event = $5; - + free($1); + free($3); $$ = tracepoint; } | @@ -458,10 +579,16 @@ event_legacy_numeric: PE_VALUE ':' PE_VALUE opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4); parse_events_terms__delete($4); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -469,10 +596,16 @@ event_legacy_raw: PE_RAW opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2); parse_events_terms__delete($2); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -481,20 +614,33 @@ PE_BPF_OBJECT opt_event_config { struct parse_events_state *parse_state = _parse_state; struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_load_bpf(parse_state, list, $1, false, $2); parse_events_terms__delete($2); + free($1); + if (err) { + free(list); + YYABORT; + } $$ = list; } | PE_BPF_SOURCE opt_event_config { struct list_head *list; + int err; - ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2)); + list = alloc_list(); + ABORT_ON(!list); + err = parse_events_load_bpf(_parse_state, list, $1, true, $2); parse_events_terms__delete($2); + if (err) { + free(list); + YYABORT; + } $$ = list; } @@ -527,6 +673,10 @@ opt_pmu_config: start_terms: event_config { struct parse_events_state *parse_state = _parse_state; + if (parse_state->terms) { + parse_events_terms__delete ($1); + YYABORT; + } parse_state->terms = $1; } @@ -536,7 +686,10 @@ event_config ',' event_term struct list_head *head = $1; struct parse_events_term *term = $3; - ABORT_ON(!head); + if (!head) { + parse_events_term__delete(term); + YYABORT; + } list_add_tail(&term->list, head); $$ = $1; } @@ -557,8 +710,12 @@ PE_NAME '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, &@1, &@3)); + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3, &@1, &@3)) { + free($1); + free($3); + YYABORT; + } $$ = term; } | @@ -566,8 +723,11 @@ PE_NAME '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, false, &@1, &@3)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3, false, &@1, &@3)) { + free($1); + YYABORT; + } $$ = term; } | @@ -576,7 +736,10 @@ PE_NAME '=' PE_VALUE_SYM_HW struct parse_events_term *term; int config = $3 & 255; - ABORT_ON(parse_events_term__sym_hw(&term, $1, config)); + if (parse_events_term__sym_hw(&term, $1, config)) { + free($1); + YYABORT; + } $$ = term; } | @@ -584,8 +747,11 @@ PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, true, &@1, NULL)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1, true, &@1, NULL)) { + free($1); + YYABORT; + } $$ = term; } | @@ -602,7 +768,10 @@ PE_TERM '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)); + if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) { + free($3); + YYABORT; + } $$ = term; } | @@ -626,9 +795,13 @@ PE_NAME array '=' PE_NAME { struct parse_events_term *term; - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, &@1, &@4)); - + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, &@1, &@4)) { + free($1); + free($4); + free($2.ranges); + YYABORT; + } term->array = $2; $$ = term; } @@ -637,8 +810,12 @@ PE_NAME array '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, false, &@1, &@4)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, false, &@1, &@4)) { + free($1); + free($2.ranges); + YYABORT; + } term->array = $2; $$ = term; } @@ -646,9 +823,15 @@ PE_NAME array '=' PE_VALUE PE_DRV_CFG_TERM { struct parse_events_term *term; + char *config = strdup($1); - ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, - $1, $1, &@1, NULL)); + ABORT_ON(!config); + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, + config, $1, &@1, NULL)) { + free($1); + free(config); + YYABORT; + } $$ = term; } @@ -670,14 +853,12 @@ array_terms ',' array_term struct parse_events_array new_array; new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges; - new_array.ranges = malloc(sizeof(new_array.ranges[0]) * - new_array.nr_ranges); + new_array.ranges = realloc($1.ranges, + sizeof(new_array.ranges[0]) * + new_array.nr_ranges); ABORT_ON(!new_array.ranges); - memcpy(&new_array.ranges[0], $1.ranges, - $1.nr_ranges * sizeof(new_array.ranges[0])); memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges, $3.nr_ranges * sizeof(new_array.ranges[0])); - free($1.ranges); free($3.ranges); $$ = new_array; } diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index ef46c2848808..e687497b3aac 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -13,7 +13,7 @@ static int __parse_regs(const struct option *opt, const char *str, int unset, bool intr) { uint64_t *mode = (uint64_t *)opt->value; - const struct sample_reg *r; + const struct sample_reg *r = NULL; char *s, *os = NULL, *p; int ret = -1; uint64_t mask; @@ -46,19 +46,23 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr) if (!strcmp(s, "?")) { fprintf(stderr, "available registers: "); +#ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { if (r->mask & mask) fprintf(stderr, "%s ", r->name); } +#endif fputc('\n', stderr); /* just printing available regs */ return -1; } +#ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { if ((r->mask & mask) && !strcasecmp(s, r->name)) break; } - if (!r->name) { +#endif + if (!r || !r->name) { ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n", s, intr ? "-I" : "--user-regs="); goto error; diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index ca56ba2dd3da..caed0336429f 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -11,11 +11,12 @@ * * which is what it's designed for. */ -#include "cache.h" #include "path.h" +#include "cache.h" #include <linux/kernel.h> #include <limits.h> #include <stdio.h> +#include <string.h> #include <sys/types.h> #include <sys/stat.h> #include <dirent.h> diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h index f014f905df50..083429b7efa3 100644 --- a/tools/perf/util/path.h +++ b/tools/perf/util/path.h @@ -2,6 +2,9 @@ #ifndef _PERF_PATH_H #define _PERF_PATH_H +#include <stddef.h> +#include <stdbool.h> + struct dirent; int path__join(char *bf, size_t size, const char *path1, const char *path2); diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c index 4f3aa8d99ef4..7a0ab3507bd5 100644 --- a/tools/perf/util/perf-hooks.c +++ b/tools/perf/util/perf-hooks.c @@ -8,10 +8,10 @@ #include <errno.h> #include <stdlib.h> +#include <string.h> #include <setjmp.h> #include <linux/err.h> #include <linux/kernel.h> -#include "util/util.h" #include "util/debug.h" #include "util/perf-hooks.h" diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c new file mode 100644 index 000000000000..651203126c71 --- /dev/null +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <stdio.h> +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/perf_event.h> +#include "util/evsel_fprintf.h" + +struct bit_names { + int bit; + const char *name; +}; + +static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) +{ + bool first_bit = true; + int i = 0; + + do { + if (value & bits[i].bit) { + buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); +} + +static void __p_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), + bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_branch_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n } + struct bit_names bits[] = { + bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY), + bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL), + bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), + bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), + bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_read_format(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +#define BUF_SIZE 1024 + +#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val)) +#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) +#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) +#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) +#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) +#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) + +#define PRINT_ATTRn(_n, _f, _p) \ +do { \ + if (attr->_f) { \ + _p(attr->_f); \ + ret += attr__fprintf(fp, _n, buf, priv);\ + } \ +} while (0) + +#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv) +{ + char buf[BUF_SIZE]; + int ret = 0; + + PRINT_ATTRf(type, p_unsigned); + PRINT_ATTRf(size, p_unsigned); + PRINT_ATTRf(config, p_hex); + PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); + PRINT_ATTRf(sample_type, p_sample_type); + PRINT_ATTRf(read_format, p_read_format); + + PRINT_ATTRf(disabled, p_unsigned); + PRINT_ATTRf(inherit, p_unsigned); + PRINT_ATTRf(pinned, p_unsigned); + PRINT_ATTRf(exclusive, p_unsigned); + PRINT_ATTRf(exclude_user, p_unsigned); + PRINT_ATTRf(exclude_kernel, p_unsigned); + PRINT_ATTRf(exclude_hv, p_unsigned); + PRINT_ATTRf(exclude_idle, p_unsigned); + PRINT_ATTRf(mmap, p_unsigned); + PRINT_ATTRf(comm, p_unsigned); + PRINT_ATTRf(freq, p_unsigned); + PRINT_ATTRf(inherit_stat, p_unsigned); + PRINT_ATTRf(enable_on_exec, p_unsigned); + PRINT_ATTRf(task, p_unsigned); + PRINT_ATTRf(watermark, p_unsigned); + PRINT_ATTRf(precise_ip, p_unsigned); + PRINT_ATTRf(mmap_data, p_unsigned); + PRINT_ATTRf(sample_id_all, p_unsigned); + PRINT_ATTRf(exclude_host, p_unsigned); + PRINT_ATTRf(exclude_guest, p_unsigned); + PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); + PRINT_ATTRf(exclude_callchain_user, p_unsigned); + PRINT_ATTRf(mmap2, p_unsigned); + PRINT_ATTRf(comm_exec, p_unsigned); + PRINT_ATTRf(use_clockid, p_unsigned); + PRINT_ATTRf(context_switch, p_unsigned); + PRINT_ATTRf(write_backward, p_unsigned); + PRINT_ATTRf(namespaces, p_unsigned); + PRINT_ATTRf(ksymbol, p_unsigned); + PRINT_ATTRf(bpf_event, p_unsigned); + PRINT_ATTRf(aux_output, p_unsigned); + + PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); + PRINT_ATTRf(bp_type, p_unsigned); + PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); + PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); + PRINT_ATTRf(branch_sample_type, p_branch_sample_type); + PRINT_ATTRf(sample_regs_user, p_hex); + PRINT_ATTRf(sample_stack_user, p_unsigned); + PRINT_ATTRf(clockid, p_signed); + PRINT_ATTRf(sample_regs_intr, p_hex); + PRINT_ATTRf(aux_watermark, p_unsigned); + PRINT_ATTRf(sample_max_stack, p_unsigned); + PRINT_ATTRf(aux_sample_size, p_unsigned); + + return ret; +} diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 2774cec1f15f..5ee47ae1509c 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -3,10 +3,6 @@ #include "perf_regs.h" #include "event.h" -const struct sample_reg __weak sample_reg_masks[] = { - SMPL_REG_END -}; - int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, char **new_op __maybe_unused) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 47fe34e5f7d5..a45499126184 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -15,8 +15,6 @@ struct sample_reg { #define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) } #define SMPL_REG_END { .name = NULL } -extern const struct sample_reg sample_reg_masks[]; - enum { SDT_ARG_VALID = 0, SDT_ARG_SKIP, @@ -27,6 +25,8 @@ uint64_t arch__intr_reg_mask(void); uint64_t arch__user_reg_mask(void); #ifdef HAVE_PERF_REGS_SUPPORT +extern const struct sample_reg sample_reg_masks[]; + #include <perf_regs.h> #define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP)) @@ -41,7 +41,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); static inline const char *perf_reg_name(int id __maybe_unused) { - return NULL; + return "unknown"; } static inline int perf_reg_value(u64 *valp __maybe_unused, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index f32b710347db..8b99fd312aae 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -3,6 +3,7 @@ #include <linux/compiler.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <subcmd/pager.h> #include <sys/types.h> #include <errno.h> #include <fcntl.h> @@ -15,13 +16,15 @@ #include <api/fs/fs.h> #include <locale.h> #include <regex.h> +#include <perf/cpumap.h> +#include "debug.h" #include "pmu.h" #include "parse-events.h" -#include "cpumap.h" #include "header.h" #include "pmu-events/pmu-events.h" -#include "cache.h" #include "string2.h" +#include "strbuf.h" +#include "fncache.h" struct perf_pmu_format { char *name; @@ -80,7 +83,6 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) */ static int pmu_format(const char *name, struct list_head *format) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -90,8 +92,8 @@ static int pmu_format(const char *name, struct list_head *format) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name); - if (stat(path, &st) < 0) - return 0; /* no error if format does not exist */ + if (!file_available(path)) + return 0; if (perf_pmu__format_parse(path, format)) return -1; @@ -99,7 +101,7 @@ static int pmu_format(const char *name, struct list_head *format) return 0; } -static int convert_scale(const char *scale, char **end, double *sval) +int perf_pmu__convert_scale(const char *scale, char **end, double *sval) { char *lc; int ret = 0; @@ -162,7 +164,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * else scale[sret] = '\0'; - ret = convert_scale(scale, NULL, &alias->scale); + ret = perf_pmu__convert_scale(scale, NULL, &alias->scale); error: close(fd); return ret; @@ -306,7 +308,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, char *long_desc, char *topic, char *unit, char *perpkg, char *metric_expr, - char *metric_name) + char *metric_name, + char *deprecated) { struct parse_events_term *term; struct perf_pmu_alias *alias; @@ -323,6 +326,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->unit[0] = '\0'; alias->per_pkg = false; alias->snapshot = false; + alias->deprecated = false; ret = parse_events_terms(&alias->terms, val); if (ret) { @@ -370,13 +374,16 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; if (unit) { - if (convert_scale(unit, &unit, &alias->scale) < 0) + if (perf_pmu__convert_scale(unit, &unit, &alias->scale) < 0) return -1; snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; alias->str = strdup(newval); + if (deprecated) + alias->deprecated = true; + if (!perf_pmu_merge_alias(alias, list)) list_add_tail(&alias->list, list); @@ -398,7 +405,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI strim(buf); return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, - NULL, NULL, NULL); + NULL, NULL, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -468,7 +475,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) */ static int pmu_aliases(const char *name, struct list_head *head) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -478,8 +484,8 @@ static int pmu_aliases(const char *name, struct list_head *head) snprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events", sysfs, name); - if (stat(path, &st) < 0) - return 0; /* no error if 'events' does not exist */ + if (!file_available(path)) + return 0; if (pmu_aliases_parse(path, head)) return -1; @@ -518,7 +524,6 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, */ static int pmu_type(const char *name, __u32 *type) { - struct stat st; char path[PATH_MAX]; FILE *file; int ret = 0; @@ -530,7 +535,7 @@ static int pmu_type(const char *name, __u32 *type) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name); - if (stat(path, &st) < 0) + if (access(path, R_OK) < 0) return -1; file = fopen(path, "r"); @@ -572,16 +577,16 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct cpu_map *__pmu_cpumask(const char *path) +static struct perf_cpu_map *__pmu_cpumask(const char *path) { FILE *file; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; file = fopen(path, "r"); if (!file) return NULL; - cpus = cpu_map__read(file); + cpus = perf_cpu_map__read(file); fclose(file); return cpus; } @@ -593,10 +598,10 @@ static struct cpu_map *__pmu_cpumask(const char *path) #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) +static struct perf_cpu_map *pmu_cpumask(const char *name) { char path[PATH_MAX]; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); const char *templates[] = { CPUS_TEMPLATE_UNCORE, @@ -621,14 +626,11 @@ static struct cpu_map *pmu_cpumask(const char *name) static bool pmu_is_uncore(const char *name) { char path[PATH_MAX]; - struct cpu_map *cpus; - const char *sysfs = sysfs__mountpoint(); + const char *sysfs; + sysfs = sysfs__mountpoint(); snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); - cpus = __pmu_cpumask(path); - cpu_map__put(cpus); - - return !!cpus; + return file_available(path); } /* @@ -638,7 +640,6 @@ static bool pmu_is_uncore(const char *name) */ static int is_arm_pmu_core(const char *name) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -648,10 +649,7 @@ static int is_arm_pmu_core(const char *name) /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); - if (stat(path, &st) == 0) - return 1; - - return 0; + return file_available(path); } static char *perf_pmu__getcpuid(struct perf_pmu *pmu) @@ -785,7 +783,8 @@ new_alias: (char *)pe->long_desc, (char *)pe->topic, (char *)pe->unit, (char *)pe->perpkg, (char *)pe->metric_expr, - (char *)pe->metric_name); + (char *)pe->metric_name, + (char *)pe->deprecated); } } @@ -923,6 +922,16 @@ __u64 perf_pmu__format_bits(struct list_head *formats, const char *name) return bits; } +int perf_pmu__format_type(struct list_head *formats, const char *name) +{ + struct perf_pmu_format *format = pmu_find_format(formats, name); + + if (!format) + return -1; + + return format->value; +} + /* * Sets value based on the format definition (format parameter) * and unformated value (value parameter). @@ -1042,9 +1051,9 @@ static int pmu_config_term(struct list_head *formats, if (err) { char *pmu_term = pmu_formats_string(formats); - err->idx = term->err_term; - err->str = strdup("unknown term"); - err->help = parse_events_formats_error_string(pmu_term); + parse_events__handle_error(err, term->err_term, + strdup("unknown term"), + parse_events_formats_error_string(pmu_term)); free(pmu_term); } return -EINVAL; @@ -1072,8 +1081,9 @@ static int pmu_config_term(struct list_head *formats, if (term->no_value && bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { if (err) { - err->idx = term->err_val; - err->str = strdup("no value assigned for term"); + parse_events__handle_error(err, term->err_val, + strdup("no value assigned for term"), + NULL); } return -EINVAL; } @@ -1086,8 +1096,9 @@ static int pmu_config_term(struct list_head *formats, term->config, term->val.str); } if (err) { - err->idx = term->err_val; - err->str = strdup("expected numeric value"); + parse_events__handle_error(err, term->err_val, + strdup("expected numeric value"), + NULL); } return -EINVAL; } @@ -1100,11 +1111,15 @@ static int pmu_config_term(struct list_head *formats, max_val = pmu_format_max_value(format->bits); if (val > max_val) { if (err) { - err->idx = term->err_val; - if (asprintf(&err->str, - "value too big for format, maximum is %llu", - (unsigned long long)max_val) < 0) - err->str = strdup("value too big for format"); + char *err_str; + + parse_events__handle_error(err, term->err_val, + asprintf(&err_str, + "value too big for format, maximum is %llu", + (unsigned long long)max_val) < 0 + ? strdup("value too big for format") + : err_str, + NULL); return -EINVAL; } /* @@ -1246,7 +1261,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->metric_name = alias->metric_name; list_del_init(&term->list); - free(term); + parse_events_term__delete(term); } /* @@ -1381,7 +1396,7 @@ static void wordwrap(char *s, int start, int max, int corr) } void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag) + bool long_desc, bool details_flag, bool deprecated) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1412,6 +1427,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, format_alias(buf, sizeof(buf), pmu, alias); bool is_cpu = !strcmp(pmu->name, "cpu"); + if (alias->deprecated && !deprecated) + continue; + if (event_glob != NULL && !(strglobmatch_nocase(name, event_glob) || (!is_cpu && strglobmatch_nocase(alias->name, @@ -1517,7 +1535,6 @@ bool pmu_have_event(const char *pname, const char *name) static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) { - struct stat st; char path[PATH_MAX]; const char *sysfs; @@ -1527,10 +1544,8 @@ static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name); - - if (stat(path, &st) < 0) + if (!file_available(path)) return NULL; - return fopen(path, "r"); } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index bd9ec2704a57..6737e3d5d568 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -26,9 +26,10 @@ struct perf_pmu { __u32 type; bool selectable; bool is_uncore; + bool auxtrace; int max_precise; struct perf_event_attr *default_config; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ struct list_head list; /* ELEM */ @@ -57,6 +58,7 @@ struct perf_pmu_alias { double scale; bool per_pkg; bool snapshot; + bool deprecated; char *metric_expr; char *metric_name; }; @@ -70,6 +72,7 @@ int perf_pmu__config_terms(struct list_head *formats, struct list_head *head_terms, bool zero, struct parse_events_error *error); __u64 perf_pmu__format_bits(struct list_head *formats, const char *name); +int perf_pmu__format_type(struct list_head *formats, const char *name); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, @@ -85,7 +88,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); void print_pmu_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc, bool details_flag); + bool long_desc, bool details_flag, + bool deprecated); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); @@ -96,4 +100,6 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); +int perf_pmu__convert_scale(const char *scale, char **end, double *sval); + #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8394d48f8b32..eea132f512b0 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,17 +19,17 @@ #include <limits.h> #include <elf.h> +#include "build-id.h" #include "event.h" #include "namespaces.h" #include "strlist.h" #include "strfilter.h" #include "debug.h" -#include "cache.h" +#include "dso.h" #include "color.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "symbol.h" -#include "thread.h" #include <api/fs/fs.h> #include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" @@ -37,14 +37,16 @@ #include "probe-file.h" #include "session.h" #include "string2.h" +#include "strbuf.h" +#include <subcmd/pager.h> #include <linux/ctype.h> #include <linux/zalloc.h> #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ -struct probe_conf probe_conf; +struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM }; #define semantic_error(msg ...) pr_err("Semantic error :" msg) @@ -151,7 +153,7 @@ static struct map *kernel_get_module_map(const char *module) return map__get(pos); } - for (pos = maps__first(maps); pos; pos = map__next(pos)) { + maps__for_each_entry(maps, pos) { /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && @@ -319,7 +321,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) char module_name[128]; snprintf(module_name, sizeof(module_name), "[%s]", module); - map = map_groups__find_by_name(&host_machine->kmaps, module_name); + map = maps__find_by_name(&host_machine->kmaps, module_name); if (map) { dso = map->dso; goto found; @@ -1677,6 +1679,14 @@ int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev) if (ret < 0) goto out; + /* Generate event name if needed */ + if (!pev->event && pev->point.function && pev->point.line + && !pev->point.lazy_line && !pev->point.offset) { + if (asprintf(&pev->event, "%s_L%d", pev->point.function, + pev->point.line) < 0) + return -ENOMEM; + } + /* Copy arguments and ensure return probe has no C argument */ pev->nargs = argc - 1; pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); @@ -2329,6 +2339,7 @@ void clear_probe_trace_event(struct probe_trace_event *tev) } } zfree(&tev->args); + tev->nargs = 0; } struct kprobe_blacklist_node { @@ -2727,8 +2738,13 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, if (tev->event == NULL || tev->group == NULL) return -ENOMEM; - /* Add added event name to namelist */ - strlist__add(namelist, event); + /* + * Add new event name to namelist if multiprobe event is NOT + * supported, since we have to use new event name for following + * probes in that case. + */ + if (!multiprobe_event_is_supported()) + strlist__add(namelist, event); return 0; } diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 96a319cd2378..4f0eb3a20c36 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -16,10 +16,13 @@ struct probe_conf { bool no_inlines; bool cache; int max_probes; + unsigned long magic_num; }; extern struct probe_conf probe_conf; extern bool probe_event_dry_run; +#define DEFAULT_PROBE_MAGIC_NUM 0xdeade12d /* u32: 3735937325 */ + struct symbol; /* kprobe-tracer and uprobe-tracer tracing point */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 5b4d49382932..5003ba403345 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -16,10 +16,11 @@ #include "strlist.h" #include "strfilter.h" #include "debug.h" -#include "cache.h" +#include "build-id.h" +#include "dso.h" #include "color.h" #include "symbol.h" -#include "thread.h" +#include "strbuf.h" #include <api/fs/tracing_path.h> #include "probe-event.h" #include "probe-file.h" @@ -1006,6 +1007,8 @@ enum ftrace_readme { FTRACE_README_KRETPROBE_OFFSET, FTRACE_README_UPROBE_REF_CTR, FTRACE_README_USER_ACCESS, + FTRACE_README_MULTIPROBE_EVENT, + FTRACE_README_IMMEDIATE_VALUE, FTRACE_README_END, }; @@ -1019,6 +1022,8 @@ static struct { DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"), DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"), + DEFINE_TYPE(FTRACE_README_MULTIPROBE_EVENT, "*Create/append/*"), + DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), }; static bool scan_ftrace_readme(enum ftrace_readme type) @@ -1084,3 +1089,13 @@ bool user_access_is_supported(void) { return scan_ftrace_readme(FTRACE_README_USER_ACCESS); } + +bool multiprobe_event_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_MULTIPROBE_EVENT); +} + +bool immediate_value_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_IMMEDIATE_VALUE); +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 986c1c94f64f..0dba88c0f5f0 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -71,6 +71,8 @@ bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); bool uprobe_ref_ctr_is_supported(void); bool user_access_is_supported(void); +bool multiprobe_event_is_supported(void); +bool immediate_value_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 025fc4491993..1c817add6ca4 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -24,6 +24,7 @@ #include "dso.h" #include "debug.h" #include "intlist.h" +#include "strbuf.h" #include "strlist.h" #include "symbol.h" #include "probe-finder.h" @@ -176,6 +177,17 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL) goto static_var; + /* Constant value */ + if (dwarf_attr(vr_die, DW_AT_const_value, &attr) && + immediate_value_is_supported()) { + Dwarf_Sword snum; + + dwarf_formsdata(&attr, &snum); + ret = asprintf(&tvar->value, "\\%ld", (long)snum); + + return ret < 0 ? -ENOMEM : 0; + } + /* TODO: handle more than 1 exprs */ if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) return -EINVAL; /* Broken DIE ? */ @@ -291,7 +303,8 @@ static int convert_variable_type(Dwarf_Die *vr_die, char prefix; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "x") != 0 && + if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "ustring") && + strcmp(cast, "x") != 0 && strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ /* and respect signedness/hexadecimal cast */ @@ -524,6 +537,14 @@ next: return 0; } +static void print_var_not_found(const char *varname) +{ + pr_err("Failed to find the location of the '%s' variable at this address.\n" + " Perhaps it has been optimized out.\n" + " Use -V with the --range option to show '%s' location range.\n", + varname, varname); +} + /* Show a variables in kprobe event format */ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) { @@ -535,11 +556,11 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, &pf->sp_die, pf->machine, pf->tvar); + if (ret == -ENOENT && pf->skip_empty_arg) + /* This can be found in other place. skip it */ + return 0; if (ret == -ENOENT || ret == -EINVAL) { - pr_err("Failed to find the location of the '%s' variable at this address.\n" - " Perhaps it has been optimized out.\n" - " Use -V with the --range option to show '%s' location range.\n", - pf->pvar->var, pf->pvar->var); + print_var_not_found(pf->pvar->var); } else if (ret == -ENOTSUP) pr_err("Sorry, we don't support this variable location yet.\n"); else if (ret == 0 && pf->pvar->field) { @@ -586,6 +607,8 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) /* Search again in global variables */ if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) { + if (pf->skip_empty_arg) + return 0; pr_warning("Failed to find '%s' in this function.\n", pf->pvar->var); ret = -ENOENT; @@ -603,38 +626,26 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, const char *function, struct probe_trace_point *tp) { - Dwarf_Addr eaddr, highaddr; + Dwarf_Addr eaddr; GElf_Sym sym; const char *symbol; /* Verify the address is correct */ - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", + if (!dwarf_haspc(sp_die, paddr)) { + pr_warning("Specified offset is out of %s\n", dwarf_diename(sp_die)); return -EINVAL; } - symbol = dwarf_diename(sp_die); + /* Try to get actual symbol name from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); if (!symbol) { - /* Try to get the symbol name from symtab */ - symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); - if (!symbol) { - pr_warning("Failed to find symbol at 0x%lx\n", - (unsigned long)paddr); - return -ENOENT; - } - eaddr = sym.st_value; + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; } + eaddr = sym.st_value; + tp->offset = (unsigned long)(paddr - eaddr); tp->address = (unsigned long)paddr; tp->symbol = strdup(symbol); @@ -755,6 +766,16 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) return 0; } +/* Return innermost DIE */ +static int find_inner_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; +} + /* Find an appropriate scope fits to given conditions */ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) { @@ -766,12 +787,50 @@ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) .die_mem = die_mem, .found = false, }; + int ret; - cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + ret = cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, + &fsp); + if (!ret && !fsp.found) + cu_walk_functions_at(&pf->cu_die, pf->addr, + find_inner_scope_cb, &fsp); return fsp.found ? die_mem : NULL; } +static int verify_representive_line(struct probe_finder *pf, const char *fname, + int lineno, Dwarf_Addr addr) +{ + const char *__fname, *__func = NULL; + Dwarf_Die die_mem; + int __lineno; + + /* Verify line number and address by reverse search */ + if (cu_find_lineinfo(&pf->cu_die, addr, &__fname, &__lineno) < 0) + return 0; + + pr_debug2("Reversed line: %s:%d\n", __fname, __lineno); + if (strcmp(fname, __fname) || lineno == __lineno) + return 0; + + pr_warning("This line is sharing the address with other lines.\n"); + + if (pf->pev->point.function) { + /* Find best match function name and lines */ + pf->addr = addr; + if (find_best_scope(pf, &die_mem) + && die_match_name(&die_mem, pf->pev->point.function) + && dwarf_decl_line(&die_mem, &lineno) == 0) { + __func = dwarf_diename(&die_mem); + __lineno -= lineno; + } + } + pr_warning("Please try to probe at %s:%d instead.\n", + __func ? : __fname, __lineno); + + return -ENOENT; +} + static int probe_point_line_walker(const char *fname, int lineno, Dwarf_Addr addr, void *data) { @@ -782,6 +841,9 @@ static int probe_point_line_walker(const char *fname, int lineno, if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0) return 0; + if (verify_representive_line(pf, fname, lineno, addr)) + return -ENOENT; + pf->addr = addr; sc_die = find_best_scope(pf, &die_mem); if (!sc_die) { @@ -941,7 +1003,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ - if (dwarf_entrypc(in_die, &addr) != 0) { + if (die_entrypc(in_die, &addr) != 0) { pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); return -ENOENT; @@ -993,7 +1055,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = find_probe_point_by_line(pf); } else if (die_is_func_instance(sp_die)) { /* Instances always have the entry address */ - dwarf_entrypc(sp_die, &pf->addr); + die_entrypc(sp_die, &pf->addr); /* But in some case the entry address is 0 */ if (pf->addr == 0) { pr_debug("%s has no entry PC. Skipped\n", @@ -1244,6 +1306,17 @@ static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, return n; } +static bool trace_event_finder_overlap(struct trace_event_finder *tf) +{ + int i; + + for (i = 0; i < tf->ntevs; i++) { + if (tf->pf.addr == tf->tevs[i].point.address) + return true; + } + return false; +} + /* Add a found probe point into trace event list */ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1254,6 +1327,14 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) struct perf_probe_arg *args = NULL; int ret, i; + /* + * For some reason (e.g. different column assigned to same address) + * This callback can be called with the address which already passed. + * Ignore it first. + */ + if (trace_event_finder_overlap(tf)) + return 0; + /* Check number of tevs */ if (tf->ntevs == tf->max_tevs) { pr_warning("Too many( > %d) probe point found.\n", @@ -1314,6 +1395,44 @@ end: return ret; } +static int fill_empty_trace_arg(struct perf_probe_event *pev, + struct probe_trace_event *tevs, int ntevs) +{ + char **valp; + char *type; + int i, j, ret; + + for (i = 0; i < pev->nargs; i++) { + type = NULL; + for (j = 0; j < ntevs; j++) { + if (tevs[j].args[i].value) { + type = tevs[j].args[i].type; + break; + } + } + if (j == ntevs) { + print_var_not_found(pev->args[i].var); + return -ENOENT; + } + for (j = 0; j < ntevs; j++) { + valp = &tevs[j].args[i].value; + if (*valp) + continue; + + ret = asprintf(valp, "\\%lx", probe_conf.magic_num); + if (ret < 0) + return -ENOMEM; + /* Note that type can be NULL */ + if (type) { + tevs[j].args[i].type = strdup(type); + if (!tevs[j].args[i].type) + return -ENOMEM; + } + } + } + return 0; +} + /* Find probe_trace_events specified by perf_probe_event from debuginfo */ int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, @@ -1332,7 +1451,13 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, tf.tevs = *tevs; tf.ntevs = 0; + if (pev->nargs != 0 && immediate_value_is_supported()) + tf.pf.skip_empty_arg = true; + ret = debuginfo__find_probes(dbg, &tf.pf); + if (ret >= 0 && tf.pf.skip_empty_arg) + ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs); + if (ret < 0) { for (i = 0; i < tf.ntevs; i++) clear_probe_trace_event(&tf.tevs[i]); @@ -1405,6 +1530,18 @@ error: return DIE_FIND_CB_END; } +static bool available_var_finder_overlap(struct available_var_finder *af) +{ + int i; + + for (i = 0; i < af->nvls; i++) { + if (af->pf.addr == af->vls[i].point.address) + return true; + } + return false; + +} + /* Add a found vars into available variables list */ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1415,6 +1552,14 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) Dwarf_Die die_mem; int ret; + /* + * For some reason (e.g. different column assigned to same address), + * this callback can be called with the address which already passed. + * Ignore it first. + */ + if (available_var_finder_overlap(af)) + return 0; + /* Check number of tevs */ if (af->nvls == af->max_vls) { pr_warning("Too many( > %d) probe point found.\n", af->max_vls); @@ -1558,7 +1703,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, /* Get function entry information */ func = basefunc = dwarf_diename(&spdie); if (!func || - dwarf_entrypc(&spdie, &baseaddr) != 0 || + die_entrypc(&spdie, &baseaddr) != 0 || dwarf_decl_line(&spdie, &baseline) != 0) { lineno = 0; goto post; @@ -1575,7 +1720,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { /* There is an inline function */ - if (dwarf_entrypc(&indie, &_addr) == 0 && + if (die_entrypc(&indie, &_addr) == 0 && _addr == addr) { /* * addr is at an inline function entry. @@ -1655,12 +1800,19 @@ static int line_range_walk_cb(const char *fname, int lineno, void *data) { struct line_finder *lf = data; + const char *__fname; + int __lineno; int err; if ((strtailcmp(fname, lf->fname) != 0) || (lf->lno_s > lineno || lf->lno_e < lineno)) return 0; + /* Make sure this line can be reversable */ + if (cu_find_lineinfo(&lf->cu_die, addr, &__fname, &__lineno) > 0 + && (lineno != __lineno || strcmp(fname, __fname))) + return 0; + err = line_range_add_line(fname, lineno, lf->lr); if (err < 0 && err != -EEXIST) return err; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 670c477bf8cf..11be10080613 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -87,6 +87,7 @@ struct probe_finder { unsigned int machine; /* Target machine arch */ struct perf_probe_arg *pvar; /* Current target variable */ struct probe_trace_arg *tvar; /* Current result variable */ + bool skip_empty_arg; /* Skip non-exist args */ }; struct trace_event_finder { diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index 28de8a4c2ce8..80ff41fc45be 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <stdlib.h> +#include <string.h> struct pstack { unsigned short top; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index ceb8afdf9a89..e7279ea6043a 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -7,8 +7,10 @@ util/python.c ../lib/ctype.c +util/cap.c util/evlist.c util/evsel.c +util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c util/mmap.c @@ -18,10 +20,8 @@ util/namespaces.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c -../lib/zalloc.c util/thread_map.c util/util.c -util/xyarray.c util/cgroup.c util/parse-branch-options.c util/rblist.c @@ -33,3 +33,4 @@ util/trace-event.c util/string.c util/symbol_fprintf.c util/units.c +util/affinity.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 1e5b6718dcea..83212c65848b 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -4,15 +4,20 @@ #include <inttypes.h> #include <poll.h> #include <linux/err.h> +#include <perf/cpumap.h> +#include <traceevent/event-parse.h> +#include <perf/mmap.h> #include "evlist.h" #include "callchain.h" #include "evsel.h" #include "event.h" -#include "cpumap.h" #include "print_binary.h" #include "thread_map.h" +#include "trace-event.h" #include "mmap.h" -#include "util.h" +#include "util/env.h" +#include <internal/lib.h> +#include "../perf-sys.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ @@ -51,10 +56,18 @@ int parse_callchain_record(const char *arg __maybe_unused, } /* + * Add this one here not to drag util/env.c + */ +struct perf_env perf_env; + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ int verbose; +int debug_peo_args; + +int eprintf(int level, int var, const char *fmt, ...); int eprintf(int level, int var, const char *fmt, ...) { @@ -93,7 +106,7 @@ PyMODINIT_FUNC PyInit_perf(void); struct pyrf_event { PyObject_HEAD - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_sample sample; union perf_event event; }; @@ -115,12 +128,12 @@ static PyMemberDef pyrf_mmap_event__members[] = { sample_members member_def(perf_event_header, type, T_UINT, "event type"), member_def(perf_event_header, misc, T_UINT, "event misc"), - member_def(mmap_event, pid, T_UINT, "event pid"), - member_def(mmap_event, tid, T_UINT, "event tid"), - member_def(mmap_event, start, T_ULONGLONG, "start of the map"), - member_def(mmap_event, len, T_ULONGLONG, "map length"), - member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"), - member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"), + member_def(perf_record_mmap, pid, T_UINT, "event pid"), + member_def(perf_record_mmap, tid, T_UINT, "event tid"), + member_def(perf_record_mmap, start, T_ULONGLONG, "start of the map"), + member_def(perf_record_mmap, len, T_ULONGLONG, "map length"), + member_def(perf_record_mmap, pgoff, T_ULONGLONG, "page offset"), + member_def(perf_record_mmap, filename, T_STRING_INPLACE, "backing store"), { .name = NULL, }, }; @@ -129,8 +142,8 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) PyObject *ret; char *s; - if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", " - "length: %#" PRIx64 ", offset: %#" PRIx64 ", " + if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRI_lx64 ", " + "length: %#" PRI_lx64 ", offset: %#" PRI_lx64 ", " "filename: %s }", pevent->event.mmap.pid, pevent->event.mmap.tid, pevent->event.mmap.start, pevent->event.mmap.len, @@ -158,18 +171,18 @@ static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event obje static PyMemberDef pyrf_task_event__members[] = { sample_members member_def(perf_event_header, type, T_UINT, "event type"), - member_def(fork_event, pid, T_UINT, "event pid"), - member_def(fork_event, ppid, T_UINT, "event ppid"), - member_def(fork_event, tid, T_UINT, "event tid"), - member_def(fork_event, ptid, T_UINT, "event ptid"), - member_def(fork_event, time, T_ULONGLONG, "timestamp"), + member_def(perf_record_fork, pid, T_UINT, "event pid"), + member_def(perf_record_fork, ppid, T_UINT, "event ppid"), + member_def(perf_record_fork, tid, T_UINT, "event tid"), + member_def(perf_record_fork, ptid, T_UINT, "event ptid"), + member_def(perf_record_fork, time, T_ULONGLONG, "timestamp"), { .name = NULL, }, }; static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) { return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " - "ptid: %u, time: %" PRIu64 "}", + "ptid: %u, time: %" PRI_lu64 "}", pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", pevent->event.fork.pid, pevent->event.fork.ppid, @@ -193,9 +206,9 @@ static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); static PyMemberDef pyrf_comm_event__members[] = { sample_members member_def(perf_event_header, type, T_UINT, "event type"), - member_def(comm_event, pid, T_UINT, "event pid"), - member_def(comm_event, tid, T_UINT, "event tid"), - member_def(comm_event, comm, T_STRING_INPLACE, "process name"), + member_def(perf_record_comm, pid, T_UINT, "event pid"), + member_def(perf_record_comm, tid, T_UINT, "event tid"), + member_def(perf_record_comm, comm, T_STRING_INPLACE, "process name"), { .name = NULL, }, }; @@ -222,18 +235,18 @@ static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object." static PyMemberDef pyrf_throttle_event__members[] = { sample_members member_def(perf_event_header, type, T_UINT, "event type"), - member_def(throttle_event, time, T_ULONGLONG, "timestamp"), - member_def(throttle_event, id, T_ULONGLONG, "event id"), - member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"), + member_def(perf_record_throttle, time, T_ULONGLONG, "timestamp"), + member_def(perf_record_throttle, id, T_ULONGLONG, "event id"), + member_def(perf_record_throttle, stream_id, T_ULONGLONG, "event stream id"), { .name = NULL, }, }; static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) { - struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1); + struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1); - return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64 - ", stream_id: %" PRIu64 " }", + return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64 + ", stream_id: %" PRI_lu64 " }", pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", te->time, te->id, te->stream_id); } @@ -252,8 +265,8 @@ static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); static PyMemberDef pyrf_lost_event__members[] = { sample_members - member_def(lost_event, id, T_ULONGLONG, "event id"), - member_def(lost_event, lost, T_ULONGLONG, "number of lost events"), + member_def(perf_record_lost, id, T_ULONGLONG, "event id"), + member_def(perf_record_lost, lost, T_ULONGLONG, "number of lost events"), { .name = NULL, }, }; @@ -262,8 +275,8 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) PyObject *ret; char *s; - if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", " - "lost: %#" PRIx64 " }", + if (asprintf(&s, "{ type: lost, id: %#" PRI_lx64 ", " + "lost: %#" PRI_lx64 " }", pevent->event.lost.id, pevent->event.lost.lost) < 0) { ret = PyErr_NoMemory(); } else { @@ -287,8 +300,8 @@ static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); static PyMemberDef pyrf_read_event__members[] = { sample_members - member_def(read_event, pid, T_UINT, "event pid"), - member_def(read_event, tid, T_UINT, "event tid"), + member_def(perf_record_read, pid, T_UINT, "event pid"), + member_def(perf_record_read, tid, T_UINT, "event tid"), { .name = NULL, }, }; @@ -337,7 +350,7 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) static bool is_tracepoint(struct pyrf_event *pevent) { - return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT; + return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT; } static PyObject* @@ -383,13 +396,13 @@ static PyObject* get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); - struct perf_evsel *evsel = pevent->evsel; + struct evsel *evsel = pevent->evsel; struct tep_format_field *field; if (!evsel->tp_format) { struct tep_event *tp_format; - tp_format = trace_event__tp_format_id(evsel->attr.config); + tp_format = trace_event__tp_format_id(evsel->core.attr.config); if (!tp_format) return NULL; @@ -430,8 +443,8 @@ static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch ev static PyMemberDef pyrf_context_switch_event__members[] = { sample_members member_def(perf_event_header, type, T_UINT, "event type"), - member_def(context_switch_event, next_prev_pid, T_UINT, "next/prev pid"), - member_def(context_switch_event, next_prev_tid, T_UINT, "next/prev tid"), + member_def(perf_record_switch, next_prev_pid, T_UINT, "next/prev pid"), + member_def(perf_record_switch, next_prev_tid, T_UINT, "next/prev tid"), { .name = NULL, }, }; @@ -536,7 +549,7 @@ static PyObject *pyrf_event__new(union perf_event *event) struct pyrf_cpu_map { PyObject_HEAD - struct cpu_map *cpus; + struct perf_cpu_map *cpus; }; static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, @@ -549,7 +562,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, kwlist, &cpustr)) return -1; - pcpus->cpus = cpu_map__new(cpustr); + pcpus->cpus = perf_cpu_map__new(cpustr); if (pcpus->cpus == NULL) return -1; return 0; @@ -557,7 +570,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) { - cpu_map__put(pcpus->cpus); + perf_cpu_map__put(pcpus->cpus); Py_TYPE(pcpus)->tp_free((PyObject*)pcpus); } @@ -605,7 +618,7 @@ static int pyrf_cpu_map__setup_types(void) struct pyrf_thread_map { PyObject_HEAD - struct thread_map *threads; + struct perf_thread_map *threads; }; static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, @@ -626,7 +639,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) { - thread_map__put(pthreads->threads); + perf_thread_map__put(pthreads->threads); Py_TYPE(pthreads)->tp_free((PyObject*)pthreads); } @@ -674,7 +687,7 @@ static int pyrf_thread_map__setup_types(void) struct pyrf_evsel { PyObject_HEAD - struct perf_evsel evsel; + struct evsel evsel; }; static int pyrf_evsel__init(struct pyrf_evsel *pevsel, @@ -782,7 +795,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel, attr.sample_id_all = sample_id_all; attr.size = sizeof(attr); - perf_evsel__init(&pevsel->evsel, &attr, idx); + evsel__init(&pevsel->evsel, &attr, idx); return 0; } @@ -795,9 +808,9 @@ static void pyrf_evsel__delete(struct pyrf_evsel *pevsel) static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, PyObject *args, PyObject *kwargs) { - struct perf_evsel *evsel = &pevsel->evsel; - struct cpu_map *cpus = NULL; - struct thread_map *threads = NULL; + struct evsel *evsel = &pevsel->evsel; + struct perf_cpu_map *cpus = NULL; + struct perf_thread_map *threads = NULL; PyObject *pcpus = NULL, *pthreads = NULL; int group = 0, inherit = 0; static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL }; @@ -812,12 +825,12 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, if (pcpus != NULL) cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; - evsel->attr.inherit = inherit; + evsel->core.attr.inherit = inherit; /* * This will group just the fds for this single evsel, to group * multiple events, use evlist.open(). */ - if (perf_evsel__open(evsel, cpus, threads) < 0) { + if (evsel__open(evsel, cpus, threads) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -858,35 +871,35 @@ static int pyrf_evsel__setup_types(void) struct pyrf_evlist { PyObject_HEAD - struct perf_evlist evlist; + struct evlist evlist; }; static int pyrf_evlist__init(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs __maybe_unused) { PyObject *pcpus = NULL, *pthreads = NULL; - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads)) return -1; threads = ((struct pyrf_thread_map *)pthreads)->threads; cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; - perf_evlist__init(&pevlist->evlist, cpus, threads); + evlist__init(&pevlist->evlist, cpus, threads); return 0; } static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) { - perf_evlist__exit(&pevlist->evlist); + evlist__exit(&pevlist->evlist); Py_TYPE(pevlist)->tp_free((PyObject*)pevlist); } static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; static char *kwlist[] = { "pages", "overwrite", NULL }; int pages = 128, overwrite = false; @@ -894,7 +907,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, &pages, &overwrite)) return NULL; - if (perf_evlist__mmap(evlist, pages) < 0) { + if (evlist__mmap(evlist, pages) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -906,14 +919,14 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; static char *kwlist[] = { "timeout", NULL }; int timeout = -1, n; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) return NULL; - n = perf_evlist__poll(evlist, timeout); + n = evlist__poll(evlist, timeout); if (n < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; @@ -926,21 +939,21 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, PyObject *args __maybe_unused, PyObject *kwargs __maybe_unused) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; PyObject *list = PyList_New(0); int i; - for (i = 0; i < evlist->pollfd.nr; ++i) { + for (i = 0; i < evlist->core.pollfd.nr; ++i) { PyObject *file; #if PY_MAJOR_VERSION < 3 - FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r"); + FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r"); if (fp == NULL) goto free_list; file = PyFile_FromFile(fp, "perf", "r", NULL); #else - file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, + file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 0); #endif if (file == NULL) @@ -964,29 +977,29 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs __maybe_unused) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; PyObject *pevsel; - struct perf_evsel *evsel; + struct evsel *evsel; if (!PyArg_ParseTuple(args, "O", &pevsel)) return NULL; Py_INCREF(pevsel); evsel = &((struct pyrf_evsel *)pevsel)->evsel; - evsel->idx = evlist->nr_entries; - perf_evlist__add(evlist, evsel); + evsel->idx = evlist->core.nr_entries; + evlist__add(evlist, evsel); - return Py_BuildValue("i", evlist->nr_entries); + return Py_BuildValue("i", evlist->core.nr_entries); } -static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) +static struct mmap *get_md(struct evlist *evlist, int cpu) { int i; - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *md = &evlist->mmap[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *md = &evlist->mmap[i]; - if (md->cpu == cpu) + if (md->core.cpu == cpu) return md; } @@ -996,11 +1009,11 @@ static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; union perf_event *event; int sample_id_all = 1, cpu; static char *kwlist[] = { "cpu", "sample_id_all", NULL }; - struct perf_mmap *md; + struct mmap *md; int err; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, @@ -1011,14 +1024,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (!md) return NULL; - if (perf_mmap__read_init(md) < 0) + if (perf_mmap__read_init(&md->core) < 0) goto end; - event = perf_mmap__read_event(md); + event = perf_mmap__read_event(&md->core); if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; - struct perf_evsel *evsel; + struct evsel *evsel; if (pyevent == NULL) return PyErr_NoMemory(); @@ -1034,7 +1047,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, err = perf_evsel__parse_sample(evsel, event, &pevent->sample); /* Consume the even only after we parsed it out. */ - perf_mmap__consume(md); + perf_mmap__consume(&md->core); if (err) return PyErr_Format(PyExc_OSError, @@ -1049,7 +1062,7 @@ end: static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; int group = 0; static char *kwlist[] = { "group", NULL }; @@ -1059,7 +1072,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, if (group) perf_evlist__set_leader(evlist); - if (perf_evlist__open(evlist) < 0) { + if (evlist__open(evlist) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -1112,15 +1125,15 @@ static Py_ssize_t pyrf_evlist__length(PyObject *obj) { struct pyrf_evlist *pevlist = (void *)obj; - return pevlist->evlist.nr_entries; + return pevlist->evlist.core.nr_entries; } static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) { struct pyrf_evlist *pevlist = (void *)obj; - struct perf_evsel *pos; + struct evsel *pos; - if (i >= pevlist->evlist.nr_entries) + if (i >= pevlist->evlist.core.nr_entries) return NULL; evlist__for_each_entry(&pevlist->evlist, pos) { diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 9cfc7bf16531..7def66168503 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -1,35 +1,39 @@ // SPDX-License-Identifier: GPL-2.0 +#include "debug.h" #include "evlist.h" #include "evsel.h" -#include "cpumap.h" #include "parse-events.h" #include <errno.h> +#include <limits.h> +#include <stdlib.h> #include <api/fs/fs.h> #include <subcmd/parse-options.h> -#include "util.h" +#include <perf/cpumap.h> #include "cloexec.h" +#include "record.h" +#include "../perf-sys.h" -typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); +typedef void (*setup_probe_fn_t)(struct evsel *evsel); static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) { - struct perf_evlist *evlist; - struct perf_evsel *evsel; + struct evlist *evlist; + struct evsel *evsel; unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; static pid_t pid = -1; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) return -ENOMEM; if (parse_events(evlist, str, NULL)) goto out_delete; - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); while (1) { - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); if (fd < 0) { if (pid == -1 && errno == EACCES) { pid = 0; @@ -43,7 +47,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) fn(evsel); - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -53,21 +57,21 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) err = 0; out_delete: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } static bool perf_probe_api(setup_probe_fn_t fn) { const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; int cpu, ret, i = 0; - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) return false; cpu = cpus->map[0]; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); do { ret = perf_do_probe_api(fn, cpu, try[i++]); @@ -78,19 +82,19 @@ static bool perf_probe_api(setup_probe_fn_t fn) return false; } -static void perf_probe_sample_identifier(struct perf_evsel *evsel) +static void perf_probe_sample_identifier(struct evsel *evsel) { - evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; + evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER; } -static void perf_probe_comm_exec(struct perf_evsel *evsel) +static void perf_probe_comm_exec(struct evsel *evsel) { - evsel->attr.comm_exec = 1; + evsel->core.attr.comm_exec = 1; } -static void perf_probe_context_switch(struct perf_evsel *evsel) +static void perf_probe_context_switch(struct evsel *evsel) { - evsel->attr.context_switch = 1; + evsel->core.attr.context_switch = 1; } bool perf_can_sample_identifier(void) @@ -115,14 +119,14 @@ bool perf_can_record_cpu_wide(void) .config = PERF_COUNT_SW_CPU_CLOCK, .exclude_kernel = 1, }; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; int cpu, fd; - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) return false; cpu = cpus->map[0]; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); if (fd < 0) @@ -132,10 +136,41 @@ bool perf_can_record_cpu_wide(void) return true; } -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, +/* + * Architectures are expected to know if AUX area sampling is supported by the + * hardware. Here we check for kernel support. + */ +bool perf_can_aux_sample(void) +{ + struct perf_event_attr attr = { + .size = sizeof(struct perf_event_attr), + .exclude_kernel = 1, + /* + * Non-zero value causes the kernel to calculate the effective + * attribute size up to that byte. + */ + .aux_sample_size = 1, + }; + int fd; + + fd = sys_perf_event_open(&attr, -1, 0, -1, 0); + /* + * If the kernel attribute is big enough to contain aux_sample_size + * then we assume that it is supported. We are relying on the kernel to + * validate the attribute size before anything else that could be wrong. + */ + if (fd < 0 && errno == E2BIG) + return false; + if (fd >= 0) + close(fd); + + return true; +} + +void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain) { - struct perf_evsel *evsel; + struct evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; bool sample_id = opts->sample_id; @@ -147,7 +182,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, if (opts->group) perf_evlist__set_leader(evlist); - if (evlist->cpus->map[0] < 0) + if (evlist->core.cpus->map[0] < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -155,7 +190,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, evlist__for_each_entry(evlist, evsel) { perf_evsel__config(evsel, opts, callchain); if (evsel->tracking && use_comm_exec) - evsel->attr.comm_exec = 1; + evsel->core.attr.comm_exec = 1; } if (opts->full_auxtrace) { @@ -166,11 +201,11 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, */ use_sample_identifier = perf_can_sample_identifier(); sample_id = true; - } else if (evlist->nr_entries > 1) { - struct perf_evsel *first = perf_evlist__first(evlist); + } else if (evlist->core.nr_entries > 1) { + struct evsel *first = evlist__first(evlist); evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.sample_type == first->attr.sample_type) + if (evsel->core.attr.sample_type == first->core.attr.sample_type) continue; use_sample_identifier = perf_can_sample_identifier(); break; @@ -256,15 +291,15 @@ int record_opts__config(struct record_opts *opts) return record_opts__config_freq(opts); } -bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) +bool perf_evlist__can_select_event(struct evlist *evlist, const char *str) { - struct perf_evlist *temp_evlist; - struct perf_evsel *evsel; + struct evlist *temp_evlist; + struct evsel *evsel; int err, fd, cpu; bool ret = false; pid_t pid = -1; - temp_evlist = perf_evlist__new(); + temp_evlist = evlist__new(); if (!temp_evlist) return false; @@ -272,19 +307,19 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) if (err) goto out_delete; - evsel = perf_evlist__last(temp_evlist); + evsel = evlist__last(temp_evlist); - if (!evlist || cpu_map__empty(evlist->cpus)) { - struct cpu_map *cpus = cpu_map__new(NULL); + if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { + struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); cpu = cpus ? cpus->map[0] : 0; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); } else { - cpu = evlist->cpus->map[0]; + cpu = evlist->core.cpus->map[0]; } while (1) { - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, perf_event_open_cloexec_flag()); if (fd < 0) { if (pid == -1 && errno == EACCES) { @@ -299,7 +334,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) ret = true; out_delete: - perf_evlist__delete(temp_evlist); + evlist__delete(temp_evlist); return ret; } diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h new file mode 100644 index 000000000000..5421fd2ad383 --- /dev/null +++ b/tools/perf/util/record.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PERF_RECORD_H +#define _PERF_RECORD_H + +#include <time.h> +#include <stdbool.h> +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/perf_event.h> +#include "util/target.h" + +struct option; + +struct record_opts { + struct target target; + bool group; + bool inherit_stat; + bool no_buffering; + bool no_inherit; + bool no_inherit_set; + bool no_samples; + bool raw_samples; + bool sample_address; + bool sample_phys_addr; + bool sample_weight; + bool sample_time; + bool sample_time_set; + bool sample_cpu; + bool period; + bool period_set; + bool running_time; + bool full_auxtrace; + bool auxtrace_snapshot_mode; + bool auxtrace_snapshot_on_exit; + bool auxtrace_sample_mode; + bool record_namespaces; + bool record_switch_events; + bool all_kernel; + bool all_user; + bool kernel_callchains; + bool user_callchains; + bool tail_synthesize; + bool overwrite; + bool ignore_missing_thread; + bool strict_freq; + bool sample_id; + bool no_bpf_event; + bool kcore; + unsigned int freq; + unsigned int mmap_pages; + unsigned int auxtrace_mmap_pages; + unsigned int user_freq; + u64 branch_stack; + u64 sample_intr_regs; + u64 sample_user_regs; + u64 default_interval; + u64 user_interval; + size_t auxtrace_snapshot_size; + const char *auxtrace_snapshot_opts; + const char *auxtrace_sample_opts; + bool sample_transaction; + unsigned initial_delay; + bool use_clockid; + clockid_t clockid; + u64 clockid_res_ns; + int nr_cblocks; + int affinity; + int mmap_flush; + unsigned int comp_level; +}; + +extern const char * const *record_usage; +extern struct option *record_options; + +int record__parse_freq(const struct option *opt, const char *str, int unset); + +#endif // _PERF_RECORD_H diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c index 5e52e7baa7b6..f3d29d8ddc99 100644 --- a/tools/perf/util/rwsem.c +++ b/tools/perf/util/rwsem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include "rwsem.h" diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 83d2e149ef19..6785cd87aa4d 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -151,13 +151,12 @@ #include <sys/stat.h> #include <sys/types.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" #include "evlist.h" #include "machine.h" #include "session.h" -#include "thread.h" +#include "tool.h" #include "debug.h" #include "auxtrace.h" #include "s390-cpumsf.h" @@ -918,7 +917,7 @@ s390_cpumsf_process_event(struct perf_session *session, struct s390_cpumsf, auxtrace); u64 timestamp = sample->time; - struct perf_evsel *ev_bc000; + struct evsel *ev_bc000; int err = 0; @@ -935,7 +934,7 @@ s390_cpumsf_process_event(struct perf_session *session, /* Handle event with raw data */ ev_bc000 = perf_evlist__event2evsel(session->evlist, event); if (ev_bc000 && - ev_bc000->attr.config == PERF_EVENT_CPUM_CF_DIAG) + ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) err = s390_cpumcf_dumpctr(sf, sample); return err; } @@ -1109,11 +1108,11 @@ static int s390_cpumsf__config(const char *var, const char *value, void *cb) int s390_cpumsf_process_auxtrace_info(union perf_event *event, struct perf_session *session) { - struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct s390_cpumsf *sf; int err; - if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event)) + if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info)) return -EINVAL; sf = zalloc(sizeof(struct s390_cpumsf)); diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 6650f599ed9c..05b43ab4eeef 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -22,11 +22,8 @@ #include <asm/byteorder.h> #include "debug.h" -#include "util.h" -#include "auxtrace.h" #include "session.h" #include "evlist.h" -#include "config.h" #include "color.h" #include "sample-raw.h" #include "s390-cpumcf-kernel.h" @@ -200,17 +197,17 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) * its raw data. * The function is only invoked when the dump flag -D is set. */ -void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, union perf_event *event, +void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *ev_bc000; + struct evsel *ev_bc000; if (event->header.type != PERF_RECORD_SAMPLE) return; ev_bc000 = perf_evlist__event2evsel(evlist, event); if (ev_bc000 == NULL || - ev_bc000->attr.config != PERF_EVENT_CPUM_CF_DIAG) + ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) return; /* Display raw data on screen */ diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c index c21e1311fb0f..e84bbe0e441a 100644 --- a/tools/perf/util/sample-raw.c +++ b/tools/perf/util/sample-raw.c @@ -9,7 +9,7 @@ * Check platform the perf data file was created on and perform platform * specific interpretation. */ -void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist) +void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist) { const char *arch_pf = perf_env__arch(evlist->env); diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h index 95d445c87e93..afe1491a117e 100644 --- a/tools/perf/util/sample-raw.h +++ b/tools/perf/util/sample-raw.h @@ -2,13 +2,13 @@ #ifndef __SAMPLE_RAW_H #define __SAMPLE_RAW_H 1 -struct perf_evlist; +struct evlist; union perf_event; struct perf_sample; -void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, +void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); -void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist); +void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 61aa7f3df915..0e608a5ef599 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -34,8 +34,8 @@ #include <EXTERN.h> #include <perl.h> -#include "../../perf.h" #include "../callchain.h" +#include "../dso.h" #include "../machine.h" #include "../map.h" #include "../symbol.h" @@ -258,7 +258,7 @@ static void define_event_symbols(struct tep_event *event, } static SV *perl_process_callchain(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { AV *list; @@ -294,17 +294,17 @@ static SV *perl_process_callchain(struct perf_sample *sample, goto exit; } - if (node->sym) { + if (node->ms.sym) { HV *sym = newHV(); if (!sym) { hv_undef(elem); goto exit; } - if (!hv_stores(sym, "start", newSVuv(node->sym->start)) || - !hv_stores(sym, "end", newSVuv(node->sym->end)) || - !hv_stores(sym, "binding", newSVuv(node->sym->binding)) || - !hv_stores(sym, "name", newSVpvn(node->sym->name, - node->sym->namelen)) || + if (!hv_stores(sym, "start", newSVuv(node->ms.sym->start)) || + !hv_stores(sym, "end", newSVuv(node->ms.sym->end)) || + !hv_stores(sym, "binding", newSVuv(node->ms.sym->binding)) || + !hv_stores(sym, "name", newSVpvn(node->ms.sym->name, + node->ms.sym->namelen)) || !hv_stores(elem, "sym", newRV_noinc((SV*)sym))) { hv_undef(sym); hv_undef(elem); @@ -312,8 +312,8 @@ static SV *perl_process_callchain(struct perf_sample *sample, } } - if (node->map) { - struct map *map = node->map; + if (node->ms.map) { + struct map *map = node->ms.map; const char *dsoname = "[unknown]"; if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) @@ -336,7 +336,7 @@ exit: } static void perl_process_tracepoint(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct thread *thread = al->thread; @@ -353,11 +353,11 @@ static void perl_process_tracepoint(struct perf_sample *sample, dSP; - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return; if (!event) { - pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); return; } @@ -431,7 +431,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, static void perl_process_event_generic(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { dSP; @@ -442,7 +442,7 @@ static void perl_process_event_generic(union perf_event *event, SAVETMPS; PUSHMARK(SP); XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size))); - XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->core.attr, sizeof(evsel->core.attr)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size))); PUTBACK; @@ -455,7 +455,7 @@ static void perl_process_event_generic(union perf_event *event, static void perl_process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { perl_process_tracepoint(sample, evsel, al); @@ -539,10 +539,11 @@ static int perl_stop_script(void) static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.pl", outfile); @@ -603,8 +604,11 @@ sub print_backtrace\n\ }\n\n\ "); + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); - while ((event = trace_find_next_event(pevent, event))) { + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 25dc1d765553..80ca5d0ab7fe 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -31,11 +31,12 @@ #include <linux/compiler.h> #include <linux/time64.h> -#include "../../perf.h" +#include "../build-id.h" +#include "../counts.h" #include "../debug.h" +#include "../dso.h" #include "../callchain.h" #include "../evsel.h" -#include "../util.h" #include "../event.h" #include "../thread.h" #include "../comm.h" @@ -47,7 +48,6 @@ #include "map.h" #include "symbol.h" #include "thread_map.h" -#include "cpumap.h" #include "print_binary.h" #include "stat.h" #include "mem-events.h" @@ -392,7 +392,7 @@ static const char *get_dsoname(struct map *map) } static PyObject *python_process_callchain(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { PyObject *pylist; @@ -428,24 +428,24 @@ static PyObject *python_process_callchain(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "ip", PyLong_FromUnsignedLongLong(node->ip)); - if (node->sym) { + if (node->ms.sym) { PyObject *pysym = PyDict_New(); if (!pysym) Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(pysym, "start", - PyLong_FromUnsignedLongLong(node->sym->start)); + PyLong_FromUnsignedLongLong(node->ms.sym->start)); pydict_set_item_string_decref(pysym, "end", - PyLong_FromUnsignedLongLong(node->sym->end)); + PyLong_FromUnsignedLongLong(node->ms.sym->end)); pydict_set_item_string_decref(pysym, "binding", - _PyLong_FromLong(node->sym->binding)); + _PyLong_FromLong(node->ms.sym->binding)); pydict_set_item_string_decref(pysym, "name", - _PyUnicode_FromStringAndSize(node->sym->name, - node->sym->namelen)); + _PyUnicode_FromStringAndSize(node->ms.sym->name, + node->ms.sym->namelen)); pydict_set_item_string_decref(pyelem, "sym", pysym); } - if (node->map) { - const char *dsoname = get_dsoname(node->map); + if (node->ms.map) { + const char *dsoname = get_dsoname(node->ms.map); pydict_set_item_string_decref(pyelem, "dso", _PyUnicode_FromString(dsoname)); @@ -634,9 +634,9 @@ static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) static void set_sample_read_in_dict(PyObject *dict_sample, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; PyObject *values; unsigned int i; @@ -705,9 +705,9 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) static void set_regs_in_dict(PyObject *dict, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; char bf[512]; regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); @@ -722,7 +722,7 @@ static void set_regs_in_dict(PyObject *dict, } static PyObject *get_perf_sample_dict(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al, PyObject *callchain) { @@ -737,7 +737,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->attr, sizeof(evsel->attr))); + pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr))); pydict_set_item_string_decref(dict_sample, "pid", _PyLong_FromLong(sample->pid)); @@ -790,7 +790,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, } static void python_process_tracepoint(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct tep_event *event = evsel->tp_format; @@ -809,7 +809,7 @@ static void python_process_tracepoint(struct perf_sample *sample, if (!event) { snprintf(handler_name, sizeof(handler_name), - "ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + "ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); Py_FatalError(handler_name); } @@ -955,7 +955,7 @@ static int tuple_set_bytes(PyObject *t, unsigned int pos, void *bytes, return PyTuple_SetItem(t, pos, _PyBytes_FromStringAndSize(bytes, sz)); } -static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel) +static int python_export_evsel(struct db_export *dbe, struct evsel *evsel) { struct tables *tables = container_of(dbe, struct tables, dbe); PyObject *t; @@ -1127,7 +1127,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_u64(t, 0, es->db_id); tuple_set_u64(t, 1, es->evsel->db_id); - tuple_set_u64(t, 2, es->al->machine->db_id); + tuple_set_u64(t, 2, es->al->maps->machine->db_id); tuple_set_u64(t, 3, es->al->thread->db_id); tuple_set_u64(t, 4, es->comm_db_id); tuple_set_u64(t, 5, es->dso_db_id); @@ -1163,7 +1163,7 @@ static void python_export_synth(struct db_export *dbe, struct export_sample *es) t = tuple_new(3); tuple_set_u64(t, 0, es->db_id); - tuple_set_u64(t, 1, es->evsel->attr.config); + tuple_set_u64(t, 1, es->evsel->core.attr.config); tuple_set_bytes(t, 2, es->sample->raw_data, es->sample->raw_size); call_object(tables->synth_handler, t, "synth_data"); @@ -1178,7 +1178,7 @@ static int python_export_sample(struct db_export *dbe, python_export_sample_table(dbe, es); - if (es->evsel->attr.type == PERF_TYPE_SYNTH && tables->synth_handler) + if (es->evsel->core.attr.type == PERF_TYPE_SYNTH && tables->synth_handler) python_export_synth(dbe, es); return 0; @@ -1275,7 +1275,7 @@ static int python_process_call_return(struct call_return *cr, u64 *parent_db_id, } static void python_process_general_event(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { PyObject *handler, *t, *dict, *callchain; @@ -1311,12 +1311,12 @@ static void python_process_general_event(struct perf_sample *sample, static void python_process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct tables *tables = &tables_global; - switch (evsel->attr.type) { + switch (evsel->core.attr.type) { case PERF_TYPE_TRACEPOINT: python_process_tracepoint(sample, evsel, al); break; @@ -1340,7 +1340,7 @@ static void python_process_switch(union perf_event *event, } static void get_handler_name(char *str, size_t size, - struct perf_evsel *evsel) + struct evsel *evsel) { char *p = str; @@ -1353,7 +1353,7 @@ static void get_handler_name(char *str, size_t size, } static void -process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, +process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, struct perf_counts_values *count) { PyObject *handler, *t; @@ -1390,10 +1390,10 @@ process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, } static void python_process_stat(struct perf_stat_config *config, - struct perf_evsel *counter, u64 tstamp) + struct evsel *counter, u64 tstamp) { - struct thread_map *threads = counter->threads; - struct cpu_map *cpus = counter->cpus; + struct perf_thread_map *threads = counter->core.threads; + struct perf_cpu_map *cpus = counter->core.cpus; int cpu, thread; if (config->aggr_mode == AGGR_GLOBAL) { @@ -1405,7 +1405,7 @@ static void python_process_stat(struct perf_stat_config *config, for (thread = 0; thread < threads->nr; thread++) { for (cpu = 0; cpu < cpus->nr; cpu++) { process_stat(counter, cpus->map[cpu], - thread_map__pid(threads, thread), tstamp, + perf_thread_map__pid(threads, thread), tstamp, perf_counts(counter->counts, cpu, thread)); } } @@ -1687,10 +1687,11 @@ static int python_stop_script(void) static int python_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.py", outfile); @@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); - while ((event = trace_find_next_event(pevent, event))) { + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); + + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 37efa1f43d8b..d0d7d25b23e3 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,16 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/zalloc.h> -#include <traceevent/event-parse.h> #include <api/fs/fs.h> #include <byteswap.h> #include <unistd.h> #include <sys/types.h> #include <sys/mman.h> +#include <perf/cpumap.h> +#include "map_symbol.h" +#include "branch.h" +#include "debug.h" #include "evlist.h" #include "evsel.h" #include "memswap.h" @@ -18,8 +22,6 @@ #include "symbol.h" #include "session.h" #include "tool.h" -#include "sort.h" -#include "cpumap.h" #include "perf_regs.h" #include "asm/bug.h" #include "auxtrace.h" @@ -27,7 +29,11 @@ #include "thread-stack.h" #include "sample-raw.h" #include "stat.h" +#include "ui/progress.h" +#include "../perf.h" #include "arch/common.h" +#include <internal/lib.h> +#include <linux/err.h> #ifdef HAVE_ZSTD_SUPPORT static int perf_session__process_compressed_event(struct perf_session *session, @@ -61,8 +67,8 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp->size = decomp_last_rem; } - src = (void *)event + sizeof(struct compressed_event); - src_size = event->pack.header.size - sizeof(struct compressed_event); + src = (void *)event + sizeof(struct perf_record_compressed); + src_size = event->pack.header.size - sizeof(struct perf_record_compressed); decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); @@ -151,10 +157,10 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session) static bool perf_session__has_comm_exec(struct perf_session *session) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.comm_exec) + if (evsel->core.attr.comm_exec) return true; } @@ -181,6 +187,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe, struct perf_session *perf_session__new(struct perf_data *data, bool repipe, struct perf_tool *tool) { + int ret = -ENOMEM; struct perf_session *session = zalloc(sizeof(*session)); if (!session) @@ -195,13 +202,15 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_env__init(&session->header.env); if (data) { - if (perf_data__open(data)) + ret = perf_data__open(data); + if (ret < 0) goto out_delete; session->data = data; if (perf_data__is_read(data)) { - if (perf_session__open(session) < 0) + ret = perf_session__open(session); + if (ret < 0) goto out_delete; /* @@ -216,8 +225,15 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_evlist__init_trace_event_sample_raw(session->evlist); /* Open the directory data. */ - if (data->is_dir && perf_data__open_dir(data)) - goto out_delete; + if (data->is_dir) { + ret = perf_data__open_dir(data); + if (ret) + goto out_delete; + } + + if (!symbol_conf.kallsyms_name && + !symbol_conf.vmlinux_name) + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { session->machines.host.env = &perf_env; @@ -250,7 +266,7 @@ struct perf_session *perf_session__new(struct perf_data *data, out_delete: perf_session__delete(session); out: - return NULL; + return ERR_PTR(ret); } static void perf_session__delete_threads(struct perf_session *session) @@ -300,7 +316,7 @@ static int process_event_synth_tracing_data_stub(struct perf_session *session static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_evlist **pevlist + struct evlist **pevlist __maybe_unused) { dump_printf(": unhandled!\n"); @@ -309,7 +325,7 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_evlist **pevlist + struct evlist **pevlist __maybe_unused) { if (dump_trace) @@ -322,7 +338,7 @@ static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_ static int process_event_sample_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine __maybe_unused) { dump_printf(": unhandled!\n"); @@ -471,8 +487,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->context_switch = perf_event__process_switch; if (tool->ksymbol == NULL) tool->ksymbol = perf_event__process_ksymbol; - if (tool->bpf_event == NULL) - tool->bpf_event = perf_event__process_bpf_event; + if (tool->bpf == NULL) + tool->bpf = perf_event__process_bpf; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -736,6 +752,7 @@ do { \ bswap_field_32(sample_stack_user); bswap_field_32(aux_watermark); bswap_field_16(sample_max_stack); + bswap_field_32(aux_sample_size); /* * After read_format are bitfields. Check read_format because @@ -833,9 +850,9 @@ static void perf_event__thread_map_swap(union perf_event *event, static void perf_event__cpu_map_swap(union perf_event *event, bool sample_id_all __maybe_unused) { - struct cpu_map_data *data = &event->cpu_map.data; + struct perf_record_cpu_map_data *data = &event->cpu_map.data; struct cpu_map_entries *cpus; - struct cpu_map_mask *mask; + struct perf_record_record_cpu_map *mask; unsigned i; data->type = bswap_64(data->type); @@ -850,7 +867,7 @@ static void perf_event__cpu_map_swap(union perf_event *event, cpus->cpu[i] = bswap_16(cpus->cpu[i]); break; case PERF_CPU_MAP__MASK: - mask = (struct cpu_map_mask *) data->data; + mask = (struct perf_record_record_cpu_map *)data->data; mask->nr = bswap_16(mask->nr); mask->long_size = bswap_16(mask->long_size); @@ -1033,7 +1050,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample) } } -static void callchain__printf(struct perf_evsel *evsel, +static void callchain__printf(struct evsel *evsel, struct perf_sample *sample) { unsigned int i; @@ -1049,23 +1066,30 @@ static void callchain__printf(struct perf_evsel *evsel, i, callchain->ips[i]); } -static void branch_stack__printf(struct perf_sample *sample) +static void branch_stack__printf(struct perf_sample *sample, bool callstack) { uint64_t i; - printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); + printf("%s: nr:%" PRIu64 "\n", + !callstack ? "... branch stack" : "... branch callstack", + sample->branch_stack->nr); for (i = 0; i < sample->branch_stack->nr; i++) { struct branch_entry *e = &sample->branch_stack->entries[i]; - printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", - i, e->from, e->to, - (unsigned short)e->flags.cycles, - e->flags.mispred ? "M" : " ", - e->flags.predicted ? "P" : " ", - e->flags.abort ? "A" : " ", - e->flags.in_tx ? "T" : " ", - (unsigned)e->flags.reserved); + if (!callstack) { + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", + i, e->from, e->to, + (unsigned short)e->flags.cycles, + e->flags.mispred ? "M" : " ", + e->flags.predicted ? "P" : " ", + e->flags.abort ? "A" : " ", + e->flags.in_tx ? "T" : " ", + (unsigned)e->flags.reserved); + } else { + printf("..... %2"PRIu64": %016" PRIx64 "\n", + i, i > 0 ? e->from : e->to); + } } } @@ -1129,7 +1153,7 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_evlist__print_tstamp(struct perf_evlist *evlist, +static void perf_evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { @@ -1178,7 +1202,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.one.id, sample->read.one.value); } -static void dump_event(struct perf_evlist *evlist, union perf_event *event, +static void dump_event(struct evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -1198,7 +1222,7 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event, event->header.size, perf_event__name(event->header.type)); } -static void dump_sample(struct perf_evsel *evsel, union perf_event *event, +static void dump_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample) { u64 sample_type; @@ -1210,13 +1234,13 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); - sample_type = evsel->attr.sample_type; + sample_type = evsel->core.attr.sample_type; if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); - if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) - branch_stack__printf(sample); + if (sample_type & PERF_SAMPLE_BRANCH_STACK) + branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel)); if (sample_type & PERF_SAMPLE_REGS_USER) regs_user__printf(sample); @@ -1240,34 +1264,34 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, printf("... transaction: %" PRIx64 "\n", sample->transaction); if (sample_type & PERF_SAMPLE_READ) - sample_read__printf(sample, evsel->attr.read_format); + sample_read__printf(sample, evsel->core.attr.read_format); } -static void dump_read(struct perf_evsel *evsel, union perf_event *event) +static void dump_read(struct evsel *evsel, union perf_event *event) { - struct read_event *read_event = &event->read; + struct perf_record_read *read_event = &event->read; u64 read_format; if (!dump_trace) return; - printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, + printf(": %d %d %s %" PRI_lu64 "\n", event->read.pid, event->read.tid, perf_evsel__name(evsel), event->read.value); if (!evsel) return; - read_format = evsel->attr.read_format; + read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled); + printf("... time enabled : %" PRI_lu64 "\n", read_event->time_enabled); if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - printf("... time running : %" PRIu64 "\n", read_event->time_running); + printf("... time running : %" PRI_lu64 "\n", read_event->time_running); if (read_format & PERF_FORMAT_ID) - printf("... id : %" PRIu64 "\n", read_event->id); + printf("... id : %" PRI_lu64 "\n", read_event->id); } static struct machine *machines__find_for_cpumode(struct machines *machines, @@ -1296,7 +1320,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, return &machines->host; } -static int deliver_sample_value(struct perf_evlist *evlist, +static int deliver_sample_value(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1304,6 +1328,7 @@ static int deliver_sample_value(struct perf_evlist *evlist, struct machine *machine) { struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); + struct evsel *evsel; if (sid) { sample->id = v->id; @@ -1323,10 +1348,11 @@ static int deliver_sample_value(struct perf_evlist *evlist, if (!sample->period) return 0; - return tool->sample(tool, event, sample, sid->evsel, machine); + evsel = container_of(sid->evsel, struct evsel, core); + return tool->sample(tool, event, sample, evsel, machine); } -static int deliver_sample_group(struct perf_evlist *evlist, +static int deliver_sample_group(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1347,16 +1373,16 @@ static int deliver_sample_group(struct perf_evlist *evlist, } static int - perf_evlist__deliver_sample(struct perf_evlist *evlist, + perf_evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { /* We know evsel != NULL. */ - u64 sample_type = evsel->attr.sample_type; - u64 read_format = evsel->attr.read_format; + u64 sample_type = evsel->core.attr.sample_type; + u64 read_format = evsel->core.attr.read_format; /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) @@ -1372,12 +1398,12 @@ static int } static int machines__deliver_event(struct machines *machines, - struct perf_evlist *evlist, + struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset) { - struct perf_evsel *evsel; + struct evsel *evsel; struct machine *machine; dump_event(evlist, event, file_offset, sample); @@ -1443,7 +1469,7 @@ static int machines__deliver_event(struct machines *machines, case PERF_RECORD_KSYMBOL: return tool->ksymbol(tool, event, sample, machine); case PERF_RECORD_BPF_EVENT: - return tool->bpf_event(tool, event, sample, machine); + return tool->bpf(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -1470,8 +1496,13 @@ static int perf_session__deliver_event(struct perf_session *session, if (ret > 0) return 0; - return machines__deliver_event(&session->machines, session->evlist, - event, &sample, tool, file_offset); + ret = machines__deliver_event(&session->machines, session->evlist, + event, &sample, tool, file_offset); + + if (dump_trace && sample.aux_sample.size) + auxtrace__dump_auxtrace_sample(session, &sample); + + return ret; } static s64 perf_session__process_user_event(struct perf_session *session, @@ -1553,7 +1584,7 @@ int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample) { - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; struct perf_tool *tool = session->tool; events_stats__inc(&evlist->stats, event->header.type); @@ -1628,10 +1659,38 @@ out_parse_sample: return 0; } +int perf_session__peek_events(struct perf_session *session, u64 offset, + u64 size, peek_events_cb_t cb, void *data) +{ + u64 max_offset = offset + size; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *event; + int err; + + do { + err = perf_session__peek_event(session, offset, buf, + PERF_SAMPLE_MAX_SIZE, &event, + NULL); + if (err) + return err; + + err = cb(session, event, offset, data); + if (err) + return err; + + offset += event->header.size; + if (event->header.type == PERF_RECORD_AUXTRACE) + offset += event->auxtrace.size; + + } while (offset < max_offset); + + return err; +} + static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, u64 file_offset) { - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; struct perf_tool *tool = session->tool; int ret; @@ -1705,11 +1764,11 @@ static void perf_session__warn_order(const struct perf_session *session) { const struct ordered_events *oe = &session->ordered_events; - struct perf_evsel *evsel; + struct evsel *evsel; bool should_warn = true; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.write_backward) + if (evsel->core.attr.write_backward) should_warn = false; } @@ -1933,8 +1992,8 @@ out_err: } static union perf_event * -fetch_mmaped_event(struct perf_session *session, - u64 head, size_t mmap_size, char *buf) +prefetch_event(char *buf, u64 head, size_t mmap_size, + bool needs_swap, union perf_event *error) { union perf_event *event; @@ -1946,18 +2005,32 @@ fetch_mmaped_event(struct perf_session *session, return NULL; event = (union perf_event *)(buf + head); + if (needs_swap) + perf_event_header__bswap(&event->header); - if (session->header.needs_swap) + if (head + event->header.size <= mmap_size) + return event; + + /* We're not fetching the event so swap back again */ + if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) { - /* We're not fetching the event so swap back again */ - if (session->header.needs_swap) - perf_event_header__bswap(&event->header); - return NULL; - } + pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); - return event; + return error; +} + +static union perf_event * +fetch_mmaped_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, ERR_PTR(-EINVAL)); +} + +static union perf_event * +fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, NULL); } static int __perf_session__process_decomp_events(struct perf_session *session) @@ -1970,7 +2043,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session) return 0; while (decomp->head < decomp->size && !session_done()) { - union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data); + union perf_event *event = fetch_decomp_event(decomp->head, decomp->size, decomp->data, + session->header.needs_swap); if (!event) break; @@ -2070,7 +2144,10 @@ remap: } more: - event = fetch_mmaped_event(session, head, mmap_size, buf); + event = fetch_mmaped_event(head, mmap_size, buf, session->header.needs_swap); + if (IS_ERR(event)) + return PTR_ERR(event); + if (!event) { if (mmaps[map_idx]) { munmap(mmaps[map_idx], mmap_size); @@ -2183,10 +2260,10 @@ int perf_session__process_events(struct perf_session *session) bool perf_session__has_traces(struct perf_session *session, const char *msg) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) return true; } @@ -2257,13 +2334,13 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp) return machine__fprintf(&session->machines.host, fp); } -struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, +struct evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(session->evlist, pos) { - if (pos->attr.type == type) + if (pos->core.attr.type == type) return pos; } return NULL; @@ -2273,23 +2350,24 @@ int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { int i, err = -1; - struct cpu_map *map; + struct perf_cpu_map *map; + int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS); for (i = 0; i < PERF_TYPE_MAX; ++i) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = perf_session__find_first_evtype(session, i); if (!evsel) continue; - if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { + if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CPU)) { pr_err("File does not contain CPU events. " "Remove -C option to proceed.\n"); return -1; } } - map = cpu_map__new(cpu_list); + map = perf_cpu_map__new(cpu_list); if (map == NULL) { pr_err("Invalid cpu_list\n"); return -1; @@ -2298,7 +2376,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, for (i = 0; i < map->nr; i++) { int cpu = map->map[i]; - if (cpu >= MAX_NR_CPUS) { + if (cpu >= nr_cpus) { pr_err("Requested CPU %d too large. " "Consider raising MAX_NR_CPUS\n", cpu); goto out_delete_map; @@ -2310,7 +2388,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, err = 0; out_delete_map: - cpu_map__put(map); + perf_cpu_map__put(map); return err; } @@ -2325,43 +2403,14 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp, fprintf(fp, "# ========\n#\n"); } - -int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct perf_evsel_str_handler *assocs, - size_t nr_assocs) -{ - struct perf_evsel *evsel; - size_t i; - int err; - - for (i = 0; i < nr_assocs; i++) { - /* - * Adding a handler for an event not in the session, - * just ignore it. - */ - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name); - if (evsel == NULL) - continue; - - err = -EEXIST; - if (evsel->handler != NULL) - goto out; - evsel->handler = assocs[i].handler; - } - - err = 0; -out: - return err; -} - int perf_event__process_id_index(struct perf_session *session, union perf_event *event) { - struct perf_evlist *evlist = session->evlist; - struct id_index_event *ie = &event->id_index; + struct evlist *evlist = session->evlist; + struct perf_record_id_index *ie = &event->id_index; size_t i, nr, max_nr; - max_nr = (ie->header.size - sizeof(struct id_index_event)) / + max_nr = (ie->header.size - sizeof(struct perf_record_id_index)) / sizeof(struct id_index_entry); nr = ie->nr; if (nr > max_nr) @@ -2375,10 +2424,10 @@ int perf_event__process_id_index(struct perf_session *session, struct perf_sample_id *sid; if (dump_trace) { - fprintf(stdout, " ... id: %"PRIu64, e->id); - fprintf(stdout, " idx: %"PRIu64, e->idx); - fprintf(stdout, " cpu: %"PRId64, e->cpu); - fprintf(stdout, " tid: %"PRId64"\n", e->tid); + fprintf(stdout, " ... id: %"PRI_lu64, e->id); + fprintf(stdout, " idx: %"PRI_lu64, e->idx); + fprintf(stdout, " cpu: %"PRI_ld64, e->cpu); + fprintf(stdout, " tid: %"PRI_ld64"\n", e->tid); } sid = perf_evlist__id2sid(evlist, e->id); @@ -2390,73 +2439,3 @@ int perf_event__process_id_index(struct perf_session *session, } return 0; } - -int perf_event__synthesize_id_index(struct perf_tool *tool, - perf_event__handler_t process, - struct perf_evlist *evlist, - struct machine *machine) -{ - union perf_event *ev; - struct perf_evsel *evsel; - size_t nr = 0, i = 0, sz, max_nr, n; - int err; - - pr_debug2("Synthesizing id index\n"); - - max_nr = (UINT16_MAX - sizeof(struct id_index_event)) / - sizeof(struct id_index_entry); - - evlist__for_each_entry(evlist, evsel) - nr += evsel->ids; - - n = nr > max_nr ? max_nr : nr; - sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry); - ev = zalloc(sz); - if (!ev) - return -ENOMEM; - - ev->id_index.header.type = PERF_RECORD_ID_INDEX; - ev->id_index.header.size = sz; - ev->id_index.nr = n; - - evlist__for_each_entry(evlist, evsel) { - u32 j; - - for (j = 0; j < evsel->ids; j++) { - struct id_index_entry *e; - struct perf_sample_id *sid; - - if (i >= n) { - err = process(tool, ev, NULL, machine); - if (err) - goto out_err; - nr -= n; - i = 0; - } - - e = &ev->id_index.entries[i++]; - - e->id = evsel->id[j]; - - sid = perf_evlist__id2sid(evlist, e->id); - if (!sid) { - free(ev); - return -ENOENT; - } - - e->idx = sid->idx; - e->cpu = sid->cpu; - e->tid = sid->tid; - } - } - - sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry); - ev->id_index.header.size = sz; - ev->id_index.nr = nr; - - err = process(tool, ev, NULL, machine); -out_err: - free(ev); - - return err; -} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 863dbad87849..f76480166d38 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -23,12 +23,12 @@ struct itrace_synth_opts; struct perf_session { struct perf_header header; struct machines machines; - struct perf_evlist *evlist; + struct evlist *evlist; struct auxtrace *auxtrace; struct itrace_synth_opts *itrace_synth_opts; struct list_head auxtrace_index; struct trace_event tevent; - struct time_conv_event time_conv; + struct perf_record_time_conv time_conv; bool repipe; bool one_mmap; void *one_mmap_addr; @@ -64,6 +64,11 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, void *buf, size_t buf_sz, union perf_event **event_ptr, struct perf_sample *sample); +typedef int (*peek_events_cb_t)(struct perf_session *session, + union perf_event *event, u64 offset, + void *data); +int perf_session__peek_events(struct perf_session *session, u64 offset, + u64 size, peek_events_cb_t cb, void *data); int perf_session__process_events(struct perf_session *session); @@ -73,7 +78,7 @@ int perf_session__queue_event(struct perf_session *s, union perf_event *event, void perf_tool__fill_defaults(struct perf_tool *tool); int perf_session__resolve_callchain(struct perf_session *session, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct ip_callchain *chain, struct symbol **parent); @@ -110,7 +115,7 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); -struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, +struct evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); int perf_session__cpu_bitmap(struct perf_session *session, @@ -118,14 +123,10 @@ int perf_session__cpu_bitmap(struct perf_session *session, void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); -struct perf_evsel_str_handler; - -int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct perf_evsel_str_handler *assocs, - size_t nr_assocs); +struct evsel_str_handler; #define perf_session__set_tracepoints_handlers(session, array) \ - __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + __evlist__set_tracepoints_handlers(session->evlist, array, ARRAY_SIZE(array)) extern volatile int session_done; @@ -138,9 +139,4 @@ int perf_session__deliver_synth_event(struct perf_session *session, int perf_event__process_id_index(struct perf_session *session, union perf_event *event); -int perf_event__synthesize_id_index(struct perf_tool *tool, - perf_event__handler_t process, - struct perf_evlist *evlist, - struct machine *machine); - #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index a1a68a2fa917..aa344a163eaf 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -48,6 +48,7 @@ build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') libapikfs = getenv('LIBAPI') +libperf = getenv('LIBPERF') ext_sources = [f.strip() for f in open('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] @@ -58,13 +59,15 @@ ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)) extra_libraries = [] if '-DHAVE_LIBNUMA_SUPPORT' in cflags: extra_libraries = [ 'numa' ] +if '-DHAVE_LIBCAP_SUPPORT' in cflags: + extra_libraries += [ 'cap' ] perf = Extension('perf', sources = ext_sources, include_dirs = ['util/include'], libraries = extra_libraries, extra_compile_args = cflags, - extra_objects = [libtraceevent, libapikfs], + extra_objects = [libtraceevent, libapikfs, libperf], ) setup(name='perf', diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5d2518e89fc4..ab0cfd790ad0 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2,16 +2,23 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> +#include <stdlib.h> #include <linux/mman.h> #include <linux/time64.h> +#include "debug.h" +#include "dso.h" #include "sort.h" #include "hist.h" +#include "cacheline.h" #include "comm.h" #include "map.h" #include "symbol.h" +#include "map_symbol.h" +#include "branch.h" #include "thread.h" #include "evsel.h" #include "evlist.h" +#include "srcline.h" #include "strlist.h" #include "strbuf.h" #include <traceevent/event-parse.h> @@ -19,6 +26,7 @@ #include "annotate.h" #include "time-utils.h" #include <linux/kernel.h> +#include <linux/string.h> regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -279,10 +287,12 @@ sort__sym_sort(struct hist_entry *left, struct hist_entry *right) return strcmp(right->ms.sym->name, left->ms.sym->name); } -static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, +static int _hist_entry__sym_snprintf(struct map_symbol *ms, u64 ip, char level, char *bf, size_t size, unsigned int width) { + struct symbol *sym = ms->sym; + struct map *map = ms->map; size_t ret = 0; if (verbose > 0) { @@ -314,10 +324,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, return ret; } -static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, - size_t size, unsigned int width) +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip, + return _hist_entry__sym_snprintf(&he->ms, he->ip, he->level, bf, size, width); } @@ -378,7 +387,7 @@ struct sort_entry sort_srcline = { static char *addr_map_symbol__srcline(struct addr_map_symbol *ams) { - return map__srcline(ams->map, ams->al_addr, ams->sym); + return map__srcline(ams->ms.map, ams->al_addr, ams->ms.sym); } static int64_t @@ -668,17 +677,11 @@ sort__time_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__time_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - unsigned long secs; - unsigned long long nsecs; char he_time[32]; - nsecs = he->time; - secs = nsecs / NSEC_PER_SEC; - nsecs -= secs * NSEC_PER_SEC; - if (symbol_conf.nanosecs) - snprintf(he_time, sizeof he_time, "%5lu.%09llu: ", - secs, nsecs); + timestamp__scnprintf_nsec(he->time, he_time, + sizeof(he_time)); else timestamp__scnprintf_usec(he->time, he_time, sizeof(he_time)); @@ -698,7 +701,7 @@ struct sort_entry sort_time = { static char *get_trace_output(struct hist_entry *he) { struct trace_seq seq; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_record rec = { .data = he->raw_data, .size = he->raw_size, @@ -711,7 +714,8 @@ static char *get_trace_output(struct hist_entry *he) tep_print_fields(&seq, he->raw_data, he->raw_size, evsel->tp_format); } else { - tep_event_info(&seq, evsel->tp_format, &rec); + tep_print_event(evsel->tp_format->tep, + &seq, &rec, "%s", TEP_PRINT_INFO); } /* * Trim the buffer, it starts at 4KB and we're not going to @@ -723,10 +727,10 @@ static char *get_trace_output(struct hist_entry *he) static int64_t sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = hists_to_evsel(left->hists); - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return 0; if (left->trace_output == NULL) @@ -740,10 +744,10 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = hists_to_evsel(he->hists); - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->trace_output == NULL) @@ -766,15 +770,15 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); - return _sort__dso_cmp(left->branch_info->from.map, - right->branch_info->from.map); + return _sort__dso_cmp(left->branch_info->from.ms.map, + right->branch_info->from.ms.map); } static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (he->branch_info) - return _hist_entry__dso_snprintf(he->branch_info->from.map, + return _hist_entry__dso_snprintf(he->branch_info->from.ms.map, bf, size, width); else return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -788,8 +792,8 @@ static int hist_entry__dso_from_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__DSO) return -1; - return dso && (!he->branch_info || !he->branch_info->from.map || - he->branch_info->from.map->dso != dso); + return dso && (!he->branch_info || !he->branch_info->from.ms.map || + he->branch_info->from.ms.map->dso != dso); } static int64_t @@ -798,15 +802,15 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); - return _sort__dso_cmp(left->branch_info->to.map, - right->branch_info->to.map); + return _sort__dso_cmp(left->branch_info->to.ms.map, + right->branch_info->to.ms.map); } static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (he->branch_info) - return _hist_entry__dso_snprintf(he->branch_info->to.map, + return _hist_entry__dso_snprintf(he->branch_info->to.ms.map, bf, size, width); else return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -820,8 +824,8 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__DSO) return -1; - return dso && (!he->branch_info || !he->branch_info->to.map || - he->branch_info->to.map->dso != dso); + return dso && (!he->branch_info || !he->branch_info->to.ms.map || + he->branch_info->to.ms.map->dso != dso); } static int64_t @@ -836,10 +840,10 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) from_l = &left->branch_info->from; from_r = &right->branch_info->from; - if (!from_l->sym && !from_r->sym) + if (!from_l->ms.sym && !from_r->ms.sym) return _sort__addr_cmp(from_l->addr, from_r->addr); - return _sort__sym_cmp(from_l->sym, from_r->sym); + return _sort__sym_cmp(from_l->ms.sym, from_r->ms.sym); } static int64_t @@ -853,10 +857,10 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) to_l = &left->branch_info->to; to_r = &right->branch_info->to; - if (!to_l->sym && !to_r->sym) + if (!to_l->ms.sym && !to_r->ms.sym) return _sort__addr_cmp(to_l->addr, to_r->addr); - return _sort__sym_cmp(to_l->sym, to_r->sym); + return _sort__sym_cmp(to_l->ms.sym, to_r->ms.sym); } static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, @@ -865,8 +869,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *from = &he->branch_info->from; - return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - he->level, bf, size, width); + return _hist_entry__sym_snprintf(&from->ms, from->addr, he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -878,8 +881,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *to = &he->branch_info->to; - return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - he->level, bf, size, width); + return _hist_entry__sym_snprintf(&to->ms, to->addr, he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -893,8 +895,8 @@ static int hist_entry__sym_from_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__SYMBOL) return -1; - return sym && !(he->branch_info && he->branch_info->from.sym && - strstr(he->branch_info->from.sym->name, sym)); + return sym && !(he->branch_info && he->branch_info->from.ms.sym && + strstr(he->branch_info->from.ms.sym->name, sym)); } static int hist_entry__sym_to_filter(struct hist_entry *he, int type, @@ -905,8 +907,8 @@ static int hist_entry__sym_to_filter(struct hist_entry *he, int type, if (type != HIST_FILTER__SYMBOL) return -1; - return sym && !(he->branch_info && he->branch_info->to.sym && - strstr(he->branch_info->to.sym->name, sym)); + return sym && !(he->branch_info && he->branch_info->to.ms.sym && + strstr(he->branch_info->to.ms.sym->name, sym)); } struct sort_entry sort_dso_from = { @@ -1014,16 +1016,13 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; if (he->mem_info) { addr = he->mem_info->daddr.addr; - map = he->mem_info->daddr.map; - sym = he->mem_info->daddr.sym; + ms = &he->mem_info->daddr.ms; } - return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width); } int64_t @@ -1043,16 +1042,13 @@ static int hist_entry__iaddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; if (he->mem_info) { addr = he->mem_info->iaddr.addr; - map = he->mem_info->iaddr.map; - sym = he->mem_info->iaddr.sym; + ms = &he->mem_info->iaddr.ms; } - return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width); } static int64_t @@ -1062,9 +1058,9 @@ sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) struct map *map_r = NULL; if (left->mem_info) - map_l = left->mem_info->daddr.map; + map_l = left->mem_info->daddr.ms.map; if (right->mem_info) - map_r = right->mem_info->daddr.map; + map_r = right->mem_info->daddr.ms.map; return _sort__dso_cmp(map_l, map_r); } @@ -1075,7 +1071,7 @@ static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf, struct map *map = NULL; if (he->mem_info) - map = he->mem_info->daddr.map; + map = he->mem_info->daddr.ms.map; return _hist_entry__dso_snprintf(map, bf, size, width); } @@ -1197,6 +1193,7 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) { u64 l, r; struct map *l_map, *r_map; + int rc; if (!left->mem_info) return -1; if (!right->mem_info) return 1; @@ -1205,8 +1202,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (left->cpumode > right->cpumode) return -1; if (left->cpumode < right->cpumode) return 1; - l_map = left->mem_info->daddr.map; - r_map = right->mem_info->daddr.map; + l_map = left->mem_info->daddr.ms.map; + r_map = right->mem_info->daddr.ms.map; /* if both are NULL, jump to sort on al_addr instead */ if (!l_map && !r_map) @@ -1215,18 +1212,9 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (!l_map) return -1; if (!r_map) return 1; - if (l_map->maj > r_map->maj) return -1; - if (l_map->maj < r_map->maj) return 1; - - if (l_map->min > r_map->min) return -1; - if (l_map->min < r_map->min) return 1; - - if (l_map->ino > r_map->ino) return -1; - if (l_map->ino < r_map->ino) return 1; - - if (l_map->ino_generation > r_map->ino_generation) return -1; - if (l_map->ino_generation < r_map->ino_generation) return 1; - + rc = dso__cmp_id(l_map->dso, r_map->dso); + if (rc) + return rc; /* * Addresses with no major/minor numbers are assumed to be * anonymous in userspace. Sort those on pid then address. @@ -1237,8 +1225,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && (!(l_map->flags & MAP_SHARED)) && - !l_map->maj && !l_map->min && !l_map->ino && - !l_map->ino_generation) { + !l_map->dso->id.maj && !l_map->dso->id.min && + !l_map->dso->id.ino && !l_map->dso->id.ino_generation) { /* userspace anonymous */ if (left->thread->pid_ > right->thread->pid_) return -1; @@ -1261,27 +1249,26 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, { uint64_t addr = 0; - struct map *map = NULL; - struct symbol *sym = NULL; + struct map_symbol *ms = NULL; char level = he->level; if (he->mem_info) { + struct map *map = he->mem_info->daddr.ms.map; + addr = cl_address(he->mem_info->daddr.al_addr); - map = he->mem_info->daddr.map; - sym = he->mem_info->daddr.sym; + ms = &he->mem_info->daddr.ms; /* print [s] for shared data mmaps */ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && map && !(map->prot & PROT_EXEC) && (map->flags & MAP_SHARED) && - (map->maj || map->min || map->ino || - map->ino_generation)) + (map->dso->id.maj || map->dso->id.min || + map->dso->id.ino || map->dso->id.ino_generation)) level = 's'; else if (!map) level = 'X'; } - return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, - width); + return _hist_entry__sym_snprintf(ms, addr, level, bf, size, width); } struct sort_entry sort_mispredict = { @@ -1984,7 +1971,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd, struct hpp_dynamic_entry { struct perf_hpp_fmt hpp; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; unsigned dynamic_len; bool raw_trace; @@ -2218,7 +2205,7 @@ static void hde_free(struct perf_hpp_fmt *fmt) } static struct hpp_dynamic_entry * -__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field, +__alloc_dynamic_entry(struct evsel *evsel, struct tep_format_field *field, int level) { struct hpp_dynamic_entry *hde; @@ -2313,20 +2300,20 @@ static int parse_field_name(char *str, char **event, char **field, char **opt) * 2. full event name (e.g. sched:sched_switch) * 3. partial event name (should not contain ':') */ -static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name) +static struct evsel *find_evsel(struct evlist *evlist, char *event_name) { - struct perf_evsel *evsel = NULL; - struct perf_evsel *pos; + struct evsel *evsel = NULL; + struct evsel *pos; bool full_name; /* case 1 */ if (event_name[0] == '%') { int nr = strtol(event_name+1, NULL, 0); - if (nr > evlist->nr_entries) + if (nr > evlist->core.nr_entries) return NULL; - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); while (--nr > 0) evsel = perf_evsel__next(evsel); @@ -2352,7 +2339,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam return evsel; } -static int __dynamic_dimension__add(struct perf_evsel *evsel, +static int __dynamic_dimension__add(struct evsel *evsel, struct tep_format_field *field, bool raw_trace, int level) { @@ -2368,7 +2355,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel, return 0; } -static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) +static int add_evsel_fields(struct evsel *evsel, bool raw_trace, int level) { int ret; struct tep_format_field *field; @@ -2384,14 +2371,14 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) return 0; } -static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, +static int add_all_dynamic_fields(struct evlist *evlist, bool raw_trace, int level) { int ret; - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; ret = add_evsel_fields(evsel, raw_trace, level); @@ -2401,15 +2388,15 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, return 0; } -static int add_all_matching_fields(struct perf_evlist *evlist, +static int add_all_matching_fields(struct evlist *evlist, char *field_name, bool raw_trace, int level) { int ret = -ESRCH; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; field = tep_find_any_field(evsel->tp_format, field_name); @@ -2423,11 +2410,11 @@ static int add_all_matching_fields(struct perf_evlist *evlist, return ret; } -static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, +static int add_dynamic_entry(struct evlist *evlist, const char *tok, int level) { char *str, *event_name, *field_name, *opt_name; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; bool raw_trace = symbol_conf.raw_trace; int ret = 0; @@ -2470,7 +2457,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, goto out; } - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { pr_debug("%s is not a tracepoint event\n", event_name); ret = -EINVAL; goto out; @@ -2567,7 +2554,7 @@ int hpp_dimension__add_output(unsigned col) } int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct perf_evlist *evlist, + struct evlist *evlist, int level) { unsigned int i; @@ -2663,7 +2650,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, } static int setup_sort_list(struct perf_hpp_list *list, char *str, - struct perf_evlist *evlist) + struct evlist *evlist) { char *tmp, *tok; int ret = 0; @@ -2693,12 +2680,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) - pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - pr_err("Invalid --sort key: `%s'", tok); + ui__error("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - pr_err("Unknown --sort key: `%s'", tok); + ui__error("Unknown --sort key: `%s'", tok); break; } } @@ -2709,7 +2696,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, return ret; } -static const char *get_default_sort_order(struct perf_evlist *evlist) +static const char *get_default_sort_order(struct evlist *evlist) { const char *default_sort_orders[] = { default_sort_order, @@ -2720,7 +2707,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) default_tracepoint_sort_order, }; bool use_trace = true; - struct perf_evsel *evsel; + struct evsel *evsel; BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); @@ -2728,7 +2715,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { use_trace = false; break; } @@ -2743,7 +2730,7 @@ out_no_evlist: return default_sort_orders[sort__mode]; } -static int setup_sort_order(struct perf_evlist *evlist) +static int setup_sort_order(struct evlist *evlist) { char *new_sort_order; @@ -2755,7 +2742,7 @@ static int setup_sort_order(struct perf_evlist *evlist) return 0; if (sort_order[1] == '\0') { - pr_err("Invalid --sort key: `+'"); + ui__error("Invalid --sort key: `+'"); return -EINVAL; } @@ -2804,7 +2791,7 @@ static char *setup_overhead(char *keys) return keys; } -static int __setup_sorting(struct perf_evlist *evlist) +static int __setup_sorting(struct evlist *evlist) { char *str; const char *sort_keys; @@ -2971,6 +2958,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__MEMORY) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -2980,6 +2970,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__BRANCH) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -3046,7 +3039,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - pr_err("Invalid --fields key: `+'"); + ui__error("Invalid --fields key: `+'"); goto out; } @@ -3057,7 +3050,7 @@ out: return ret; } -int setup_sorting(struct perf_evlist *evlist) +int setup_sorting(struct evlist *evlist) { int err; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index a0f232151d6f..6c862d62d052 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -1,29 +1,19 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PERF_SORT_H #define __PERF_SORT_H -#include "../builtin.h" - #include <regex.h> - -#include "color.h" +#include <stdbool.h> #include <linux/list.h> -#include "cache.h" #include <linux/rbtree.h> #include "map_symbol.h" #include "symbol_conf.h" -#include "string.h" #include "callchain.h" #include "values.h" - -#include "../perf.h" -#include "debug.h" -#include "header.h" - -#include <subcmd/parse-options.h> -#include "parse-events.h" #include "hist.h" -#include "srcline.h" +#include "stat.h" +#include "spark.h" +struct option; struct thread; extern regex_t parent_regex; @@ -83,6 +73,8 @@ struct hist_entry_diff { /* PERF_HPP_DIFF__CYCLES */ s64 cycles; }; + struct stats stats; + unsigned long svals[NUM_SPARKS]; }; struct hist_entry_ops { @@ -172,6 +164,8 @@ static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) return he->callchain_size != 0; } +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width); + static inline bool hist_entry__has_pairs(struct hist_entry *he) { return !list_empty(&he->pairs.node); @@ -204,18 +198,6 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he) return period * 100.0 / total_period; } -static inline u64 cl_address(u64 address) -{ - /* return the cacheline of the address */ - return (address & ~(cacheline_size() - 1)); -} - -static inline u64 cl_offset(u64 address) -{ - /* return the cacheline of the address */ - return (address & (cacheline_size() - 1)); -} - enum sort_mode { SORT_MODE__NORMAL, SORT_MODE__BRANCH, @@ -301,9 +283,9 @@ struct block_hist { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -struct perf_evlist; +struct evlist; struct tep_handle; -int setup_sorting(struct perf_evlist *evlist); +int setup_sorting(struct evlist *evlist); int setup_output_field(void); void reset_output_field(void); void sort__setup_elide(FILE *fp); @@ -318,7 +300,7 @@ bool is_strict_order(const char *order); int hpp_dimension__add_output(unsigned col); void reset_dimensions(void); int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct perf_evlist *evlist, + struct evlist *evlist, int level); int output_field_add(struct perf_hpp_list *list, char *tok); int64_t diff --git a/tools/perf/util/spark.c b/tools/perf/util/spark.c new file mode 100644 index 000000000000..70272a8b81a6 --- /dev/null +++ b/tools/perf/util/spark.c @@ -0,0 +1,34 @@ +#include <stdio.h> +#include <limits.h> +#include <string.h> +#include <stdlib.h> +#include "spark.h" +#include "stat.h" + +#define SPARK_SHIFT 8 + +/* Print spark lines on outf for numval values in val. */ +int print_spark(char *bf, int size, unsigned long *val, int numval) +{ + static const char *ticks[NUM_SPARKS] = { + "▁", "▂", "▃", "▄", "▅", "▆", "▇", "█" + }; + int i, printed = 0; + unsigned long min = ULONG_MAX, max = 0, f; + + for (i = 0; i < numval; i++) { + if (val[i] < min) + min = val[i]; + if (val[i] > max) + max = val[i]; + } + f = ((max - min) << SPARK_SHIFT) / (NUM_SPARKS - 1); + if (f < 1) + f = 1; + for (i = 0; i < numval; i++) { + printed += scnprintf(bf + printed, size - printed, "%s", + ticks[((val[i] - min) << SPARK_SHIFT) / f]); + } + + return printed; +} diff --git a/tools/perf/util/spark.h b/tools/perf/util/spark.h new file mode 100644 index 000000000000..25402d7d7a64 --- /dev/null +++ b/tools/perf/util/spark.h @@ -0,0 +1,8 @@ +#ifndef SPARK_H +#define SPARK_H 1 + +#define NUM_SPARKS 8 + +int print_spark(char *bf, int size, unsigned long *val, int numval); + +#endif diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c index adfcf1ff464c..c29edaaca863 100644 --- a/tools/perf/util/srccode.c +++ b/tools/perf/util/srccode.c @@ -15,7 +15,8 @@ #include <string.h> #include "srccode.h" #include "debug.h" -#include "util.h" +#include <internal/lib.h> // page_size +#include "fncache.h" #define MAXSRCCACHE (32*1024*1024) #define MAXSRCFILES 64 @@ -36,14 +37,6 @@ static LIST_HEAD(srcfile_list); static long map_total_sz; static int num_srcfiles; -static unsigned shash(unsigned char *s) -{ - unsigned h = 0; - while (*s) - h = 65599 * h + *s++; - return h ^ (h >> 16); -} - static int countlines(char *map, int maplen) { int numl; diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 6ccf6f6d09df..5b7d6c16d33f 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -193,16 +193,30 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) bfd_vma pc, vma; bfd_size_type size; struct a2l_data *a2l = data; + flagword flags; if (a2l->found) return; - if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) +#ifdef bfd_get_section_flags + flags = bfd_get_section_flags(abfd, section); +#else + flags = bfd_section_flags(section); +#endif + if ((flags & SEC_ALLOC) == 0) return; pc = a2l->addr; +#ifdef bfd_get_section_vma vma = bfd_get_section_vma(abfd, section); +#else + vma = bfd_section_vma(section); +#endif +#ifdef bfd_get_section_size size = bfd_get_section_size(section); +#else + size = bfd_section_size(section); +#endif if (pc < vma || pc >= vma + size) return; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 58df6a0dbb9f..bc31fccc0057 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -1,9 +1,11 @@ +#include <stdlib.h> #include <stdio.h> #include <inttypes.h> #include <linux/string.h> #include <linux/time64.h> #include <math.h> #include "color.h" +#include "counts.h" #include "evlist.h" #include "evsel.h" #include "stat.h" @@ -13,7 +15,6 @@ #include "string2.h" #include <linux/ctype.h> #include "cgroup.h" -#include <math.h> #include <api/fs/fs.h> #define CNTR_NOT_SUPPORTED "<not supported>" @@ -45,7 +46,7 @@ static void print_noise_pct(struct perf_stat_config *config, } static void print_noise(struct perf_stat_config *config, - struct perf_evsel *evsel, double avg) + struct evsel *evsel, double avg) { struct perf_stat_evsel *ps; @@ -56,7 +57,7 @@ static void print_noise(struct perf_stat_config *config, print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg); } -static void print_cgroup(struct perf_stat_config *config, struct perf_evsel *evsel) +static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel) { if (nr_cgroups) { const char *cgrp_name = evsel->cgrp ? evsel->cgrp->name : ""; @@ -66,7 +67,7 @@ static void print_cgroup(struct perf_stat_config *config, struct perf_evsel *evs static void aggr_printout(struct perf_stat_config *config, - struct perf_evsel *evsel, int id, int nr) + struct evsel *evsel, int id, int nr) { switch (config->aggr_mode) { case AGGR_CORE: @@ -99,6 +100,15 @@ static void aggr_printout(struct perf_stat_config *config, nr, config->csv_sep); break; + case AGGR_NODE: + fprintf(config->output, "N%*d%s%*d%s", + config->csv_output ? 0 : -5, + id, + config->csv_sep, + config->csv_output ? 0 : 4, + nr, + config->csv_sep); + break; case AGGR_NONE: if (evsel->percore) { fprintf(config->output, "S%d-D%d-C%*d%s", @@ -109,16 +119,16 @@ static void aggr_printout(struct perf_stat_config *config, } else { fprintf(config->output, "CPU%*d%s ", config->csv_output ? 0 : -5, - perf_evsel__cpus(evsel)->map[id], + evsel__cpus(evsel)->map[id], config->csv_sep); } break; case AGGR_THREAD: fprintf(config->output, "%*s-%*d%s", config->csv_output ? 0 : 16, - thread_map__comm(evsel->threads, id), + perf_thread_map__comm(evsel->core.threads, id), config->csv_output ? 0 : -8, - thread_map__pid(evsel->threads, id), + perf_thread_map__pid(evsel->core.threads, id), config->csv_sep); break; case AGGR_GLOBAL: @@ -134,7 +144,7 @@ struct outstate { const char *prefix; int nfields; int id, nr; - struct perf_evsel *evsel; + struct evsel *evsel; }; #define METRIC_LEN 35 @@ -233,7 +243,7 @@ static bool valid_only_metric(const char *unit) return true; } -static const char *fixunit(char *buf, struct perf_evsel *evsel, +static const char *fixunit(char *buf, struct evsel *evsel, const char *unit) { if (!strncmp(unit, "of all", 6)) { @@ -310,9 +320,9 @@ static void print_metric_header(struct perf_stat_config *config, } static int first_shadow_cpu(struct perf_stat_config *config, - struct perf_evsel *evsel, int id) + struct evsel *evsel, int id) { - struct perf_evlist *evlist = evsel->evlist; + struct evlist *evlist = evsel->evlist; int i; if (!config->aggr_get_id) @@ -325,16 +335,16 @@ static int first_shadow_cpu(struct perf_stat_config *config, return 0; for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { - int cpu2 = perf_evsel__cpus(evsel)->map[i]; + int cpu2 = evsel__cpus(evsel)->map[i]; - if (config->aggr_get_id(config, evlist->cpus, cpu2) == id) + if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id) return cpu2; } return 0; } static void abs_printout(struct perf_stat_config *config, - int id, int nr, struct perf_evsel *evsel, double avg) + int id, int nr, struct evsel *evsel, double avg) { FILE *output = config->output; double sc = evsel->scale; @@ -363,24 +373,24 @@ static void abs_printout(struct perf_stat_config *config, print_cgroup(config, evsel); } -static bool is_mixed_hw_group(struct perf_evsel *counter) +static bool is_mixed_hw_group(struct evsel *counter) { - struct perf_evlist *evlist = counter->evlist; - u32 pmu_type = counter->attr.type; - struct perf_evsel *pos; + struct evlist *evlist = counter->evlist; + u32 pmu_type = counter->core.attr.type; + struct evsel *pos; - if (counter->nr_members < 2) + if (counter->core.nr_members < 2) return false; evlist__for_each_entry(evlist, pos) { /* software events can be part of any hardware group */ - if (pos->attr.type == PERF_TYPE_SOFTWARE) + if (pos->core.attr.type == PERF_TYPE_SOFTWARE) continue; if (pmu_type == PERF_TYPE_SOFTWARE) { - pmu_type = pos->attr.type; + pmu_type = pos->core.attr.type; continue; } - if (pmu_type != pos->attr.type) + if (pmu_type != pos->core.attr.type) return true; } @@ -388,7 +398,7 @@ static bool is_mixed_hw_group(struct perf_evsel *counter) } static void printout(struct perf_stat_config *config, int id, int nr, - struct perf_evsel *counter, double uval, + struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) { @@ -489,18 +499,18 @@ static void printout(struct perf_stat_config *config, int id, int nr, } static void aggr_update_shadow(struct perf_stat_config *config, - struct perf_evlist *evlist) + struct evlist *evlist) { int cpu, s2, id, s; u64 val; - struct perf_evsel *counter; + struct evsel *counter; for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; evlist__for_each_entry(evlist, counter) { val = 0; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = config->aggr_get_id(config, evlist->cpus, cpu); + s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); if (s2 != id) continue; val += perf_counts(counter->counts, cpu, 0)->val; @@ -512,7 +522,7 @@ static void aggr_update_shadow(struct perf_stat_config *config, } } -static void uniquify_event_name(struct perf_evsel *counter) +static void uniquify_event_name(struct evsel *counter) { char *new_name; char *config; @@ -540,16 +550,16 @@ static void uniquify_event_name(struct perf_evsel *counter) counter->uniquified_name = true; } -static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter, - void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, +static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter, + void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), void *data) { - struct perf_evlist *evlist = counter->evlist; - struct perf_evsel *alias; + struct evlist *evlist = counter->evlist; + struct evsel *alias; - alias = list_prepare_entry(counter, &(evlist->entries), node); - list_for_each_entry_continue (alias, &evlist->entries, node) { + alias = list_prepare_entry(counter, &(evlist->core.entries), core.node); + list_for_each_entry_continue (alias, &evlist->core.entries, core.node) { if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || alias->scale != counter->scale || alias->cgrp != counter->cgrp || @@ -562,8 +572,8 @@ static void collect_all_aliases(struct perf_stat_config *config, struct perf_evs } } -static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter, - void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, +static bool collect_data(struct perf_stat_config *config, struct evsel *counter, + void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), void *data) { @@ -585,7 +595,7 @@ struct aggr_data { }; static void aggr_cb(struct perf_stat_config *config, - struct perf_evsel *counter, void *data, bool first) + struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; int cpu, s2; @@ -593,7 +603,7 @@ static void aggr_cb(struct perf_stat_config *config, for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { struct perf_counts_values *counts; - s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu); + s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); if (s2 != ad->id) continue; if (first) @@ -616,7 +626,7 @@ static void aggr_cb(struct perf_stat_config *config, } static void print_counter_aggrdata(struct perf_stat_config *config, - struct perf_evsel *counter, int s, + struct evsel *counter, int s, char *prefix, bool metric_only, bool *first) { @@ -651,12 +661,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config, } static void print_aggr(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; - struct perf_evsel *counter; + struct evsel *counter; int s; bool first; @@ -691,7 +701,7 @@ static int cmp_val(const void *a, const void *b) } static struct perf_aggr_thread_value *sort_aggr_thread( - struct perf_evsel *counter, + struct evsel *counter, int nthreads, int ncpus, int *ret, struct target *_target) @@ -741,11 +751,11 @@ static struct perf_aggr_thread_value *sort_aggr_thread( static void print_aggr_thread(struct perf_stat_config *config, struct target *_target, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { FILE *output = config->output; - int nthreads = thread_map__nr(counter->threads); - int ncpus = cpu_map__nr(counter->cpus); + int nthreads = perf_thread_map__nr(counter->core.threads); + int ncpus = perf_cpu_map__nr(counter->core.cpus); int thread, sorted_threads, id; struct perf_aggr_thread_value *buf; @@ -779,7 +789,7 @@ struct caggr_data { }; static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused, - struct perf_evsel *counter, void *data, + struct evsel *counter, void *data, bool first __maybe_unused) { struct caggr_data *cd = data; @@ -795,7 +805,7 @@ static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused, * aggregated counts in system-wide mode */ static void print_counter_aggr(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; @@ -816,7 +826,7 @@ static void print_counter_aggr(struct perf_stat_config *config, } static void counter_cb(struct perf_stat_config *config __maybe_unused, - struct perf_evsel *counter, void *data, + struct evsel *counter, void *data, bool first __maybe_unused) { struct aggr_data *ad = data; @@ -831,7 +841,7 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused, * does not use aggregated count in system-wide */ static void print_counter(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { FILE *output = config->output; u64 ena, run, val; @@ -859,16 +869,16 @@ static void print_counter(struct perf_stat_config *config, } static void print_no_aggr_metric(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix) { int cpu; int nrcpus = 0; - struct perf_evsel *counter; + struct evsel *counter; u64 ena, run, val; double uval; - nrcpus = evlist->cpus->nr; + nrcpus = evlist->core.cpus->nr; for (cpu = 0; cpu < nrcpus; cpu++) { bool first = true; @@ -910,11 +920,11 @@ static const char *aggr_header_csv[] = { }; static void print_metric_headers(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, const char *prefix, bool no_indent) { struct perf_stat_output_ctx out; - struct perf_evsel *counter; + struct evsel *counter; struct outstate os = { .fh = config->output }; @@ -949,7 +959,7 @@ static void print_metric_headers(struct perf_stat_config *config, } static void print_interval(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix, struct timespec *ts) { bool metric_only = config->metric_only; @@ -964,6 +974,11 @@ static void print_interval(struct perf_stat_config *config, if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { + case AGGR_NODE: + fprintf(output, "# time node cpus"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + break; case AGGR_SOCKET: fprintf(output, "# time socket cpus"); if (!metric_only) @@ -1132,7 +1147,7 @@ static void print_footer(struct perf_stat_config *config) } static void print_percore(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; @@ -1156,7 +1171,7 @@ static void print_percore(struct perf_stat_config *config, } void -perf_evlist__print_counters(struct perf_evlist *evlist, +perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, @@ -1164,7 +1179,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist, { bool metric_only = config->metric_only; int interval = config->interval; - struct perf_evsel *counter; + struct evsel *counter; char buf[64], *prefix = NULL; if (interval) @@ -1187,6 +1202,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist, case AGGR_CORE: case AGGR_DIE: case AGGR_SOCKET: + case AGGR_NODE: print_aggr(config, evlist, prefix); break; case AGGR_THREAD: diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index accb1bf1cfd8..90d23cc3c8d4 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -18,19 +18,20 @@ * AGGR_NONE: Use matching CPU * AGGR_THREAD: Not supported? */ -static bool have_frontend_stalled; struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; struct saved_value { struct rb_node rb_node; - struct perf_evsel *evsel; + struct evsel *evsel; enum stat_type type; int ctx; int cpu; struct runtime_stat *stat; struct stats stats; + u64 metric_total; + int metric_other; }; static int saved_value_cmp(struct rb_node *rb_node, const void *entry) @@ -94,7 +95,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused, free(v); } -static struct saved_value *saved_value_lookup(struct perf_evsel *evsel, +static struct saved_value *saved_value_lookup(struct evsel *evsel, int cpu, bool create, enum stat_type type, @@ -142,23 +143,22 @@ void runtime_stat__exit(struct runtime_stat *st) void perf_stat__init_shadow_stats(void) { - have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); runtime_stat__init(&rt_stat); } -static int evsel_context(struct perf_evsel *evsel) +static int evsel_context(struct evsel *evsel) { int ctx = 0; - if (evsel->attr.exclude_kernel) + if (evsel->core.attr.exclude_kernel) ctx |= CTX_BIT_KERNEL; - if (evsel->attr.exclude_user) + if (evsel->core.attr.exclude_user) ctx |= CTX_BIT_USER; - if (evsel->attr.exclude_hv) + if (evsel->core.attr.exclude_hv) ctx |= CTX_BIT_HV; - if (evsel->attr.exclude_host) + if (evsel->core.attr.exclude_host) ctx |= CTX_BIT_HOST; - if (evsel->attr.exclude_idle) + if (evsel->core.attr.exclude_idle) ctx |= CTX_BIT_IDLE; return ctx; @@ -207,11 +207,12 @@ static void update_runtime_stat(struct runtime_stat *st, * 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 evsel *counter, u64 count, int cpu, struct runtime_stat *st) { int ctx = evsel_context(counter); u64 count_ns = count; + struct saved_value *v; count *= counter->scale; @@ -266,9 +267,15 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, update_runtime_stat(st, STAT_APERF, ctx, cpu, count); if (counter->collect_stat) { - struct saved_value *v = saved_value_lookup(counter, cpu, true, - STAT_NONE, 0, st); + v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st); update_stats(&v->stats, count); + if (counter->metric_leader) + v->metric_total += count; + } else if (counter->metric_leader) { + v = saved_value_lookup(counter->metric_leader, + cpu, true, STAT_NONE, 0, st); + v->metric_total += count; + v->metric_other++; } } @@ -299,10 +306,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, +static struct evsel *perf_stat__find_event(struct evlist *evsel_list, const char *name) { - struct perf_evsel *c2; + struct evsel *c2; evlist__for_each_entry (evsel_list, c2) { if (!strcasecmp(c2->name, name) && !c2->collect_stat) @@ -312,9 +319,9 @@ static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, } /* Mark MetricExpr target events and link events using them to them. */ -void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) +void perf_stat__collect_metric_expr(struct evlist *evsel_list) { - struct perf_evsel *counter, *leader, **metric_events, *oc; + struct evsel *counter, *leader, **metric_events, *oc; bool found; const char **metric_names; int i; @@ -332,7 +339,7 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) &metric_names, &num_metric_names) < 0) continue; - metric_events = calloc(sizeof(struct perf_evsel *), + metric_events = calloc(sizeof(struct evsel *), num_metric_names + 1); if (!metric_events) return; @@ -415,7 +422,7 @@ static double runtime_stat_n(struct runtime_stat *st, static void print_stalled_cycles_frontend(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, double avg, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -439,7 +446,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, static void print_stalled_cycles_backend(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, double avg, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -459,7 +466,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, static void print_branch_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -480,7 +487,7 @@ static void print_branch_misses(struct perf_stat_config *config, static void print_l1_dcache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -502,7 +509,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, static void print_l1_icache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -523,7 +530,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, static void print_dtlb_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -543,7 +550,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, static void print_itlb_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -563,7 +570,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, static void print_ll_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -686,7 +693,7 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st) } static void print_smi_cost(struct perf_stat_config *config, - int cpu, struct perf_evsel *evsel, + int cpu, struct evsel *evsel, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -712,9 +719,10 @@ static void print_smi_cost(struct perf_stat_config *config, static void generic_metric(struct perf_stat_config *config, const char *metric_expr, - struct perf_evsel **metric_events, + struct evsel **metric_events, char *name, const char *metric_name, + const char *metric_unit, double avg, int cpu, struct perf_stat_output_ctx *out, @@ -722,17 +730,18 @@ static void generic_metric(struct perf_stat_config *config, { print_metric_t print_metric = out->print_metric; struct parse_ctx pctx; - double ratio; + double ratio, scale; int i; void *ctxp = out->ctx; char *n, *pn; expr__ctx_init(&pctx); + /* Must be first id entry */ expr__add_id(&pctx, name, avg); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; - double scale; + u64 metric_total = 0; if (!strcmp(metric_events[i]->name, "duration_time")) { stats = &walltime_nsecs_stats; @@ -744,6 +753,9 @@ static void generic_metric(struct perf_stat_config *config, break; stats = &v->stats; scale = 1.0; + + if (v->metric_other) + metric_total = v->metric_total; } n = strdup(metric_events[i]->name); @@ -757,21 +769,42 @@ static void generic_metric(struct perf_stat_config *config, pn = strchr(n, ' '); if (pn) *pn = 0; - expr__add_id(&pctx, n, avg_stats(stats)*scale); + + if (metric_total) + expr__add_id(&pctx, n, metric_total); + else + expr__add_id(&pctx, n, avg_stats(stats)*scale); } + if (!metric_events[i]) { const char *p = metric_expr; - if (expr__parse(&ratio, &pctx, &p) == 0) - print_metric(config, ctxp, NULL, "%8.1f", - metric_name ? - metric_name : - out->force_header ? name : "", - ratio); - else + if (expr__parse(&ratio, &pctx, &p) == 0) { + char *unit; + char metric_bf[64]; + + if (metric_unit && metric_name) { + if (perf_pmu__convert_scale(metric_unit, + &unit, &scale) >= 0) { + ratio *= scale; + } + + scnprintf(metric_bf, sizeof(metric_bf), + "%s %s", unit, metric_name); + print_metric(config, ctxp, NULL, "%8.1f", + metric_bf, ratio); + } else { + print_metric(config, ctxp, NULL, "%8.1f", + metric_name ? + metric_name : + out->force_header ? name : "", + ratio); + } + } else { print_metric(config, ctxp, NULL, NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); + } } else print_metric(config, ctxp, NULL, NULL, "", 0); @@ -780,7 +813,7 @@ static void generic_metric(struct perf_stat_config *config, } void perf_stat__print_shadow_stats(struct perf_stat_config *config, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, @@ -818,10 +851,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", ratio); - } else if (have_frontend_stalled) { - out->new_line(config, ctxp); - print_metric(config, ctxp, NULL, "%7.2f ", - "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0) @@ -829,8 +858,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1D | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -839,8 +868,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1I | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -849,8 +878,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_DTLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -859,8 +888,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_ITLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -869,8 +898,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_LL | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -992,7 +1021,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, name, 0); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name, - evsel->metric_name, avg, cpu, out, st); + evsel->metric_name, NULL, avg, cpu, out, st); } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) { char unit = 'M'; char unit_buf[10]; @@ -1021,7 +1050,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, out->new_line(config, ctxp); generic_metric(config, mexp->metric_expr, mexp->metric_events, evsel->name, mexp->metric_name, - avg, cpu, out, st); + mexp->metric_unit, avg, cpu, out, st); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index db8a6cf336be..5f26137b8d60 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -2,7 +2,14 @@ #include <errno.h> #include <inttypes.h> #include <math.h> +#include <string.h> +#include "counts.h" +#include "cpumap.h" +#include "debug.h" +#include "header.h" #include "stat.h" +#include "session.h" +#include "target.h" #include "evlist.h" #include "evsel.h" #include "thread_map.h" @@ -68,7 +75,7 @@ double rel_stddev_stats(double stddev, double avg) return pct; } -bool __perf_evsel_stat__is(struct perf_evsel *evsel, +bool __perf_evsel_stat__is(struct evsel *evsel, enum perf_stat_evsel_id id) { struct perf_stat_evsel *ps = evsel->stats; @@ -93,7 +100,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { }; #undef ID -static void perf_stat_evsel_id_init(struct perf_evsel *evsel) +static void perf_stat_evsel_id_init(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; int i; @@ -108,7 +115,7 @@ static void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__reset_stat_priv(struct evsel *evsel) { int i; struct perf_stat_evsel *ps = evsel->stats; @@ -119,7 +126,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) perf_stat_evsel_id_init(evsel); } -static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +static int perf_evsel__alloc_stat_priv(struct evsel *evsel) { evsel->stats = zalloc(sizeof(struct perf_stat_evsel)); if (evsel->stats == NULL) @@ -128,7 +135,7 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) return 0; } -static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__free_stat_priv(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; @@ -137,7 +144,7 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) zfree(&evsel->stats); } -static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, +static int perf_evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads) { struct perf_counts *counts; @@ -149,16 +156,25 @@ static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, return counts ? 0 : -ENOMEM; } -static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct evsel *evsel) { perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } -static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel) +{ + if (evsel->prev_raw_counts) { + evsel->prev_raw_counts->aggr.val = 0; + evsel->prev_raw_counts->aggr.ena = 0; + evsel->prev_raw_counts->aggr.run = 0; + } +} + +static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); - int nthreads = thread_map__nr(evsel->threads); + int nthreads = perf_thread_map__nr(evsel->core.threads); if (perf_evsel__alloc_stat_priv(evsel) < 0 || perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || @@ -168,9 +184,9 @@ static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) return 0; } -int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (perf_evsel__alloc_stats(evsel, alloc_raw)) @@ -184,9 +200,9 @@ out_free: return -1; } -void perf_evlist__free_stats(struct perf_evlist *evlist) +void perf_evlist__free_stats(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { perf_evsel__free_stat_priv(evsel); @@ -195,9 +211,9 @@ void perf_evlist__free_stats(struct perf_evlist *evlist) } } -void perf_evlist__reset_stats(struct perf_evlist *evlist) +void perf_evlist__reset_stats(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { perf_evsel__reset_stat_priv(evsel); @@ -205,17 +221,25 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist) } } -static void zero_per_pkg(struct perf_evsel *counter) +void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + perf_evsel__reset_prev_raw_counts(evsel); +} + +static void zero_per_pkg(struct evsel *counter) { if (counter->per_pkg_mask) - memset(counter->per_pkg_mask, 0, MAX_NR_CPUS); + memset(counter->per_pkg_mask, 0, cpu__max_cpu()); } -static int check_per_pkg(struct perf_evsel *counter, +static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, int cpu, bool *skip) { unsigned long *mask = counter->per_pkg_mask; - struct cpu_map *cpus = perf_evsel__cpus(counter); + struct perf_cpu_map *cpus = evsel__cpus(counter); int s; *skip = false; @@ -223,11 +247,11 @@ static int check_per_pkg(struct perf_evsel *counter, if (!counter->per_pkg) return 0; - if (cpu_map__empty(cpus)) + if (perf_cpu_map__empty(cpus)) return 0; if (!mask) { - mask = zalloc(MAX_NR_CPUS); + mask = zalloc(cpu__max_cpu()); if (!mask) return -ENOMEM; @@ -254,7 +278,7 @@ static int check_per_pkg(struct perf_evsel *counter, } static int -process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel, +process_counter_values(struct perf_stat_config *config, struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { @@ -275,6 +299,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel case AGGR_CORE: case AGGR_DIE: case AGGR_SOCKET: + case AGGR_NODE: case AGGR_NONE: if (!evsel->snapshot) perf_evsel__compute_deltas(evsel, cpu, thread, count); @@ -306,13 +331,13 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel } static int process_counter_maps(struct perf_stat_config *config, - struct perf_evsel *counter) + struct evsel *counter) { - int nthreads = thread_map__nr(counter->threads); + int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = perf_evsel__nr_cpus(counter); int cpu, thread; - if (counter->system_wide) + if (counter->core.system_wide) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { @@ -327,7 +352,7 @@ static int process_counter_maps(struct perf_stat_config *config, } int perf_stat_process_counter(struct perf_stat_config *config, - struct perf_evsel *counter) + struct evsel *counter) { struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat_evsel *ps = counter->stats; @@ -380,8 +405,8 @@ int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { struct perf_counts_values count; - struct stat_event *st = &event->stat; - struct perf_evsel *counter; + struct perf_record_stat *st = &event->stat; + struct evsel *counter; count.val = st->val; count.ena = st->ena; @@ -400,12 +425,12 @@ int perf_event__process_stat_event(struct perf_session *session, size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp) { - struct stat_event *st = (struct stat_event *) event; + struct perf_record_stat *st = (struct perf_record_stat *)event; size_t ret; - ret = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n", + ret = fprintf(fp, "\n... id %" PRI_lu64 ", cpu %d, thread %d\n", st->id, st->cpu, st->thread); - ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n", + ret += fprintf(fp, "... value %" PRI_lu64 ", enabled %" PRI_lu64 ", running %" PRI_lu64 "\n", st->val, st->ena, st->run); return ret; @@ -413,10 +438,10 @@ size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp) size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp) { - struct stat_round_event *rd = (struct stat_round_event *)event; + struct perf_record_stat_round *rd = (struct perf_record_stat_round *)event; size_t ret; - ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time, + ret = fprintf(fp, "\n... time %" PRI_lu64 ", type %s\n", rd->time, rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL"); return ret; @@ -437,12 +462,13 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) return ret; } -int create_perf_stat_counter(struct perf_evsel *evsel, +int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target) + struct target *target, + int cpu) { - struct perf_event_attr *attr = &evsel->attr; - struct perf_evsel *leader = evsel->leader; + struct perf_event_attr *attr = &evsel->core.attr; + struct evsel *leader = evsel->leader; attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; @@ -452,7 +478,7 @@ int create_perf_stat_counter(struct perf_evsel *evsel, * the group read (for leader) and ID retrieval for all * members. */ - if (leader->nr_members > 1) + if (leader->core.nr_members > 1) attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; attr->inherit = !config->no_inherit; @@ -466,6 +492,16 @@ int create_perf_stat_counter(struct perf_evsel *evsel, if (config->identifier) attr->sample_type = PERF_SAMPLE_IDENTIFIER; + if (config->all_user) { + attr->exclude_kernel = 1; + attr->exclude_user = 0; + } + + if (config->all_kernel) { + attr->exclude_kernel = 0; + attr->exclude_user = 1; + } + /* * Disabling all counters initially, they will be enabled * either manually by us or by kernel via enable_on_exec @@ -483,49 +519,7 @@ int create_perf_stat_counter(struct perf_evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); - - return perf_evsel__open_per_thread(evsel, evsel->threads); -} + return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu); -int perf_stat_synthesize_config(struct perf_stat_config *config, - struct perf_tool *tool, - struct perf_evlist *evlist, - perf_event__handler_t process, - bool attrs) -{ - int err; - - if (attrs) { - err = perf_event__synthesize_attrs(tool, evlist, process); - if (err < 0) { - pr_err("Couldn't synthesize attrs.\n"); - return err; - } - } - - err = perf_event__synthesize_extra_attr(tool, evlist, process, - attrs); - - err = perf_event__synthesize_thread_map2(tool, evlist->threads, - process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_cpu_map(tool, evlist->cpus, - process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_stat_config(tool, config, process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize config.\n"); - return err; - } - - return 0; + return perf_evsel__open_per_thread(evsel, evsel->core.threads); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 7032dd1eeac2..fb990efa54a8 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -5,13 +5,12 @@ #include <linux/types.h> #include <stdio.h> #include <sys/types.h> -#include <sys/time.h> #include <sys/resource.h> -#include <sys/wait.h> -#include "xyarray.h" #include "rblist.h" -#include "perf.h" -#include "event.h" + +struct perf_cpu_map; +struct perf_stat_config; +struct timespec; struct stats { double n, mean, M2; @@ -48,6 +47,7 @@ enum aggr_mode { AGGR_CORE, AGGR_THREAD, AGGR_UNSET, + AGGR_NODE, }; enum { @@ -92,7 +92,7 @@ struct runtime_stat { }; typedef int (*aggr_get_id_t)(struct perf_stat_config *config, - struct cpu_map *m, int cpu); + struct perf_cpu_map *m, int cpu); struct perf_stat_config { enum aggr_mode aggr_mode; @@ -107,6 +107,8 @@ struct perf_stat_config { bool big_num; bool no_merge; bool walltime_run_table; + bool all_kernel; + bool all_user; FILE *output; unsigned int interval; unsigned int timeout; @@ -122,9 +124,9 @@ struct perf_stat_config { const char *csv_sep; struct stats *walltime_nsecs_stats; struct rusage ru_data; - struct cpu_map *aggr_map; + struct perf_cpu_map *aggr_map; aggr_get_id_t aggr_get_id; - struct cpu_map *cpus_aggr_map; + struct perf_cpu_map *cpus_aggr_map; u64 *walltime_run; struct rblist metric_events; }; @@ -143,11 +145,11 @@ static inline void init_stats(struct stats *stats) stats->max = 0; } -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct perf_aggr_thread_value { - struct perf_evsel *counter; + struct evsel *counter; int id; double uval; u64 val; @@ -155,7 +157,7 @@ struct perf_aggr_thread_value { u64 ena; }; -bool __perf_evsel_stat__is(struct perf_evsel *evsel, +bool __perf_evsel_stat__is(struct evsel *evsel, enum perf_stat_evsel_id id); #define perf_stat_evsel__is(evsel, id) \ @@ -174,7 +176,7 @@ void runtime_stat__exit(struct runtime_stat *st); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); -void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int cpu, struct runtime_stat *st); struct perf_stat_output_ctx { void *ctx; @@ -184,22 +186,25 @@ struct perf_stat_output_ctx { }; void perf_stat__print_shadow_stats(struct perf_stat_config *config, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, struct runtime_stat *st); -void perf_stat__collect_metric_expr(struct perf_evlist *); +void perf_stat__collect_metric_expr(struct evlist *); -int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); -void perf_evlist__free_stats(struct perf_evlist *evlist); -void perf_evlist__reset_stats(struct perf_evlist *evlist); +int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); +void perf_evlist__free_stats(struct evlist *evlist); +void perf_evlist__reset_stats(struct evlist *evlist); +void perf_evlist__reset_prev_raw_counts(struct evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, - struct perf_evsel *counter); + struct evsel *counter); struct perf_tool; union perf_event; struct perf_session; +struct target; + int perf_event__process_stat_event(struct perf_session *session, union perf_event *event); @@ -207,16 +212,12 @@ size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); -int create_perf_stat_counter(struct perf_evsel *evsel, +int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target); -int perf_stat_synthesize_config(struct perf_stat_config *config, - struct perf_tool *tool, - struct perf_evlist *evlist, - perf_event__handler_t process, - bool attrs); + struct target *target, + int cpu); void -perf_evlist__print_counters(struct perf_evlist *evlist, +perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 2ce0dc887364..a64a37628f12 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,9 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 +#include "cache.h" #include "debug.h" +#include "strbuf.h" #include <linux/kernel.h> +#include <linux/string.h> #include <linux/zalloc.h> #include <errno.h> +#include <stdio.h> #include <stdlib.h> +#include <unistd.h> /* * Used as the default ->buf value, so that people can always assume diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h index 708805f5573e..73df616ced43 100644 --- a/tools/perf/util/string2.h +++ b/tools/perf/util/string2.h @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/types.h> +#include <sys/types.h> // pid_t #include <stddef.h> #include <string.h> @@ -32,6 +33,8 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int return asprintf_expr_inout_ints(var, false, nints, ints); } +char *asprintf__tp_filter_pids(size_t npids, pid_t *pids); + char *strpbrk_esc(char *str, const char *stopset); char *strdup_esc(const char *str); diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 76cc54000483..96f941e01681 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -14,12 +14,14 @@ #include <unistd.h> #include <string.h> #include <linux/bitmap.h> +#include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <internal/cpumap.h> +#include <perf/cpumap.h> -#include "perf.h" +#include "env.h" #include "svghelper.h" -#include "cpumap.h" static u64 first_time, last_time; static u64 turbo_frequency, max_freq; @@ -694,7 +696,8 @@ struct topology { int sib_thr_nr; }; -static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos) +static void scan_thread_topology(int *map, struct topology *t, int cpu, + int *pos, int nr_cpus) { int i; int thr; @@ -703,41 +706,37 @@ static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i]))) continue; - for_each_set_bit(thr, - cpumask_bits(&t->sib_thr[i]), - MAX_NR_CPUS) + for_each_set_bit(thr, cpumask_bits(&t->sib_thr[i]), nr_cpus) if (map[thr] == -1) map[thr] = (*pos)++; } } -static void scan_core_topology(int *map, struct topology *t) +static void scan_core_topology(int *map, struct topology *t, int nr_cpus) { int pos = 0; int i; int cpu; for (i = 0; i < t->sib_core_nr; i++) - for_each_set_bit(cpu, - cpumask_bits(&t->sib_core[i]), - MAX_NR_CPUS) - scan_thread_topology(map, t, cpu, &pos); + for_each_set_bit(cpu, cpumask_bits(&t->sib_core[i]), nr_cpus) + scan_thread_topology(map, t, cpu, &pos, nr_cpus); } -static int str_to_bitmap(char *s, cpumask_t *b) +static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus) { int i; int ret = 0; - struct cpu_map *m; + struct perf_cpu_map *m; int c; - m = cpu_map__new(s); + m = perf_cpu_map__new(s); if (!m) return -1; for (i = 0; i < m->nr; i++) { c = m->map[i]; - if (c >= MAX_NR_CPUS) { + if (c >= nr_cpus) { ret = -1; break; } @@ -745,29 +744,34 @@ static int str_to_bitmap(char *s, cpumask_t *b) set_bit(c, cpumask_bits(b)); } - cpu_map__put(m); + perf_cpu_map__put(m); return ret; } -int svg_build_topology_map(char *sib_core, int sib_core_nr, - char *sib_thr, int sib_thr_nr) +int svg_build_topology_map(struct perf_env *env) { - int i; + int i, nr_cpus; struct topology t; + char *sib_core, *sib_thr; + + nr_cpus = min(env->nr_cpus_online, MAX_NR_CPUS); + + t.sib_core_nr = env->nr_sibling_cores; + t.sib_thr_nr = env->nr_sibling_threads; + t.sib_core = calloc(env->nr_sibling_cores, sizeof(cpumask_t)); + t.sib_thr = calloc(env->nr_sibling_threads, sizeof(cpumask_t)); - t.sib_core_nr = sib_core_nr; - t.sib_thr_nr = sib_thr_nr; - t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t)); - t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t)); + sib_core = env->sibling_cores; + sib_thr = env->sibling_threads; if (!t.sib_core || !t.sib_thr) { fprintf(stderr, "topology: no memory\n"); goto exit; } - for (i = 0; i < sib_core_nr; i++) { - if (str_to_bitmap(sib_core, &t.sib_core[i])) { + for (i = 0; i < env->nr_sibling_cores; i++) { + if (str_to_bitmap(sib_core, &t.sib_core[i], nr_cpus)) { fprintf(stderr, "topology: can't parse siblings map\n"); goto exit; } @@ -775,8 +779,8 @@ int svg_build_topology_map(char *sib_core, int sib_core_nr, sib_core += strlen(sib_core) + 1; } - for (i = 0; i < sib_thr_nr; i++) { - if (str_to_bitmap(sib_thr, &t.sib_thr[i])) { + for (i = 0; i < env->nr_sibling_threads; i++) { + if (str_to_bitmap(sib_thr, &t.sib_thr[i], nr_cpus)) { fprintf(stderr, "topology: can't parse siblings map\n"); goto exit; } @@ -784,16 +788,16 @@ int svg_build_topology_map(char *sib_core, int sib_core_nr, sib_thr += strlen(sib_thr) + 1; } - topology_map = malloc(sizeof(int) * MAX_NR_CPUS); + topology_map = malloc(sizeof(int) * nr_cpus); if (!topology_map) { fprintf(stderr, "topology: no memory\n"); goto exit; } - for (i = 0; i < MAX_NR_CPUS; i++) + for (i = 0; i < nr_cpus; i++) topology_map[i] = -1; - scan_core_topology(topology_map, &t); + scan_core_topology(topology_map, &t, nr_cpus); return 0; diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index e55338d5c3bd..81823e8bae3e 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -4,6 +4,8 @@ #include <linux/types.h> +struct perf_env; + void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); @@ -28,7 +30,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc void svg_interrupt(u64 start, int row, const char *backtrace); void svg_text(int Yslot, u64 start, const char *text); void svg_close(void); -int svg_build_topology_map(char *sib_core, int sib_core_nr, char *sib_thr, int sib_thr_nr); +int svg_build_topology_map(struct perf_env *env); extern int svg_page_width; extern u64 svg_highlight; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 7d504dc22108..1965aefccb02 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -7,18 +7,22 @@ #include <unistd.h> #include <inttypes.h> +#include "dso.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "symbol.h" +#include "symsrc.h" #include "demangle-java.h" #include "demangle-rust.h" #include "machine.h" #include "vdso.h" #include "debug.h" -#include "util.h" +#include "util/copyfile.h" #include <linux/ctype.h> +#include <linux/kernel.h> #include <linux/zalloc.h> #include <symbol/kallsyms.h> +#include <internal/lib.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ @@ -40,6 +44,12 @@ typedef Elf64_Nhdr GElf_Nhdr; +#ifndef DMGL_PARAMS +#define DMGL_NO_OPTS 0 /* For readability... */ +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif + #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); @@ -834,7 +844,7 @@ void __weak arch__sym_update(struct symbol *s __maybe_unused, static int dso__process_kernel_symbol(struct dso *dso, struct map *map, GElf_Sym *sym, GElf_Shdr *shdr, - struct map_groups *kmaps, struct kmap *kmap, + struct maps *kmaps, struct kmap *kmap, struct dso **curr_dsop, struct map **curr_mapp, const char *section_name, bool adjust_kernel_syms, bool kmodule, bool *remap_kernel) @@ -866,8 +876,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, /* Ensure maps are correctly ordered */ if (kmaps) { map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); + maps__remove(kmaps, map); + maps__insert(kmaps, map); map__put(map); } } @@ -892,7 +902,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); - curr_map = map_groups__find_by_name(kmaps, dso_name); + curr_map = maps__find_by_name(kmaps, dso_name); if (curr_map == NULL) { u64 start = sym->st_value; @@ -910,6 +920,9 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, if (curr_map == NULL) return -1; + if (curr_dso->kernel) + map__kmap(curr_map)->kmaps = kmaps; + if (adjust_kernel_syms) { curr_map->start = shdr->sh_addr + ref_reloc(kmap); curr_map->end = curr_map->start + shdr->sh_size; @@ -918,13 +931,13 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; } curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmaps, curr_map); + maps__insert(kmaps, curr_map); /* * Add it before we drop the referece to curr_map, i.e. while * we still are sure to have a reference to this DSO via * *curr_map->dso. */ - dsos__add(&map->groups->machine->dsos, curr_dso); + dsos__add(&kmaps->machine->dsos, curr_dso); /* kmaps already got it */ map__put(curr_map); dso__set_loaded(curr_dso); @@ -940,7 +953,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; - struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL; + struct maps *kmaps = kmap ? map__kmaps(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = dso; Elf_Data *symstrs, *secstrs; @@ -1152,7 +1165,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, * We need to fixup this here too because we create new * maps here, for things like vsyscall sections. */ - map_groups__fixup_end(kmaps); + maps__fixup_end(kmaps); } } err = nr; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 3bc8b7e3300e..d6e99af263ec 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,6 +1,6 @@ -// SPDX-License-Identifier: GPL-2.0 +#include "dso.h" #include "symbol.h" -#include "util.h" +#include "symsrc.h" #include <errno.h> #include <unistd.h> @@ -11,6 +11,7 @@ #include <byteswap.h> #include <sys/stat.h> #include <linux/zalloc.h> +#include <internal/lib.h> static bool check_need_swap(int file_endian) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 4efde7879474..1077013d8ce2 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -4,8 +4,10 @@ #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <linux/capability.h> #include <linux/kernel.h> #include <linux/mman.h> +#include <linux/string.h> #include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> @@ -15,11 +17,17 @@ #include <inttypes.h> #include "annotate.h" #include "build-id.h" -#include "util.h" +#include "cap.h" +#include "dso.h" +#include "util.h" // lsdir() #include "debug.h" +#include "event.h" #include "machine.h" #include "map.h" #include "symbol.h" +#include "map_symbol.h" +#include "mem-events.h" +#include "symsrc.h" #include "strlist.h" #include "intlist.h" #include "namespaces.h" @@ -231,31 +239,26 @@ void symbols__fixup_end(struct rb_root_cached *symbols) curr->end = roundup(curr->start, 4096) + 4096; } -void map_groups__fixup_end(struct map_groups *mg) +void maps__fixup_end(struct maps *maps) { - struct maps *maps = &mg->maps; - struct map *next, *curr; + struct map *prev = NULL, *curr; down_write(&maps->lock); - curr = maps__first(maps); - if (curr == NULL) - goto out_unlock; + maps__for_each_entry(maps, curr) { + if (prev != NULL && !prev->end) + prev->end = curr->start; - for (next = map__next(curr); next; next = map__next(curr)) { - if (!curr->end) - curr->end = next->start; - curr = next; + prev = curr; } /* * We still haven't the actual symbols, so guess the * last map final address. */ - if (!curr->end) + if (curr && !curr->end) curr->end = ~0ULL; -out_unlock: up_write(&maps->lock); } @@ -632,9 +635,12 @@ out: static bool symbol__is_idle(const char *name) { const char * const idle_symbols[] = { + "acpi_idle_do_entry", + "acpi_processor_ffh_cstate_enter", "arch_cpu_idle", "cpu_idle", "cpu_startup_entry", + "idle_cpu", "intel_idle", "default_idle", "native_safe_halt", @@ -648,13 +654,17 @@ static bool symbol__is_idle(const char *name) NULL }; int i; + static struct strlist *idle_symbols_list; - for (i = 0; idle_symbols[i]; i++) { - if (!strcmp(idle_symbols[i], name)) - return true; - } + if (idle_symbols_list) + return strlist__has_entry(idle_symbols_list, name); - return false; + idle_symbols_list = strlist__new(NULL, NULL); + + for (i = 0; idle_symbols[i]; i++) + strlist__add(idle_symbols_list, idle_symbols[i]); + + return strlist__has_entry(idle_symbols_list, name); } static int map__process_kallsym_symbol(void *arg, const char *name, @@ -694,7 +704,7 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename) return kallsyms__parse(filename, dso, map__process_kallsym_symbol); } -static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso) +static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) { struct map *curr_map; struct symbol *pos; @@ -720,7 +730,7 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct if (module) *module = '\0'; - curr_map = map_groups__find(kmaps, pos->start); + curr_map = maps__find(kmaps, pos->start); if (!curr_map) { symbol__delete(pos); @@ -747,8 +757,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta, - struct map *initial_map) +static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, + struct map *initial_map) { struct machine *machine; struct map *curr_map = initial_map; @@ -793,7 +803,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, dso__set_loaded(curr_map->dso); } - curr_map = map_groups__find_by_name(kmaps, module); + curr_map = maps__find_by_name(kmaps, module); if (curr_map == NULL) { pr_debug("%s/proc/{kallsyms,modules} " "inconsistency while looking " @@ -860,7 +870,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, } curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; - map_groups__insert(kmaps, curr_map); + maps__insert(kmaps, curr_map); ++kernel_range; } else if (delta) { /* Kernel was relocated at boot time */ @@ -1045,13 +1055,7 @@ out_delete_from: return ret; } -struct map *map_groups__first(struct map_groups *mg) -{ - return maps__first(&mg->maps); -} - -static int do_validate_kcore_modules(const char *filename, - struct map_groups *kmaps) +static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) { struct rb_root modules = RB_ROOT; struct map *old_map; @@ -1061,13 +1065,10 @@ static int do_validate_kcore_modules(const char *filename, if (err) return err; - old_map = map_groups__first(kmaps); - while (old_map) { - struct map *next = map_groups__next(old_map); + maps__for_each_entry(kmaps, old_map) { struct module_info *mi; if (!__map__is_kmodule(old_map)) { - old_map = next; continue; } @@ -1077,8 +1078,6 @@ static int do_validate_kcore_modules(const char *filename, err = -EINVAL; goto out; } - - old_map = next; } out: delete_modules(&modules); @@ -1113,7 +1112,7 @@ static bool filename_from_kallsyms_filename(char *filename, static int validate_kcore_modules(const char *kallsyms_filename, struct map *map) { - struct map_groups *kmaps = map__kmaps(map); + struct maps *kmaps = map__kmaps(map); char modules_filename[PATH_MAX]; if (!kmaps) @@ -1173,17 +1172,15 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) } /* - * Merges map into map_groups by splitting the new map - * within the existing map regions. + * Merges map into maps by splitting the new map within the existing map + * regions. */ -int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) +int maps__merge_in(struct maps *kmaps, struct map *new_map) { struct map *old_map; LIST_HEAD(merged); - for (old_map = map_groups__first(kmaps); old_map; - old_map = map_groups__next(old_map)) { - + maps__for_each_entry(kmaps, old_map) { /* no overload with this one */ if (new_map->end < old_map->start || new_map->start >= old_map->end) @@ -1240,12 +1237,12 @@ int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) while (!list_empty(&merged)) { old_map = list_entry(merged.next, struct map, node); list_del_init(&old_map->node); - map_groups__insert(kmaps, old_map); + maps__insert(kmaps, old_map); map__put(old_map); } if (new_map) { - map_groups__insert(kmaps, new_map); + maps__insert(kmaps, new_map); map__put(new_map); } return 0; @@ -1254,9 +1251,9 @@ int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { - struct map_groups *kmaps = map__kmaps(map); + struct maps *kmaps = map__kmaps(map); struct kcore_mapfn_data md; - struct map *old_map, *new_map, *replacement_map = NULL; + struct map *old_map, *new_map, *replacement_map = NULL, *next; struct machine *machine; bool is_64_bit; int err, fd; @@ -1303,18 +1300,14 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - old_map = map_groups__first(kmaps); - while (old_map) { - struct map *next = map_groups__next(old_map); - + maps__for_each_entry_safe(kmaps, old_map, next) { /* * We need to preserve eBPF maps even if they are * covered by kcore, because we need to access * eBPF dso for source data. */ if (old_map != map && !__map__is_bpf_prog(old_map)) - map_groups__remove(kmaps, old_map); - old_map = next; + maps__remove(kmaps, old_map); } machine->trampolines_mapped = false; @@ -1343,8 +1336,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map->unmap_ip = new_map->unmap_ip; /* Ensure maps are correctly ordered */ map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); + maps__remove(kmaps, map); + maps__insert(kmaps, map); map__put(map); map__put(new_map); } else { @@ -1353,7 +1346,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, * and ensure that current maps (eBPF) * stay intact. */ - if (map_groups__merge_in(kmaps, new_map)) + if (maps__merge_in(kmaps, new_map)) goto out_err; } } @@ -1445,9 +1438,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; if (!no_kcore && !dso__load_kcore(dso, map, filename)) - return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso); + return maps__split_kallsyms_for_kcore(kmap->kmaps, dso); else - return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map); + return maps__split_kallsyms(kmap->kmaps, dso, delta, map); } int dso__load_kallsyms(struct dso *dso, const char *filename, @@ -1542,7 +1535,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: /* * kernel modules know their symtab type - it's set when - * creating a module dso in machine__findnew_module_map(). + * creating a module dso in machine__addnew_module_map(). */ return kmod && dso->symtab_type == type; @@ -1600,7 +1593,7 @@ int dso__load(struct dso *dso, struct map *map) char *name; int ret = -1; u_int i; - struct machine *machine; + struct machine *machine = NULL; char *root_dir = (char *) ""; int ss_pos = 0; struct symsrc ss_[2]; @@ -1629,17 +1622,13 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - if (map->groups && map->groups->machine) - machine = map->groups->machine; - else - machine = NULL; - if (dso->kernel) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) ret = dso__load_guest_kernel_sym(dso, map); + machine = map__kmaps(map)->machine; if (machine__is(machine, "x86_64")) machine__map_x86_64_entry_trampolines(machine, dso); goto out; @@ -1776,28 +1765,81 @@ out: return ret; } -struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) +static int map__strcmp(const void *a, const void *b) +{ + const struct map *ma = *(const struct map **)a, *mb = *(const struct map **)b; + return strcmp(ma->dso->short_name, mb->dso->short_name); +} + +static int map__strcmp_name(const void *name, const void *b) +{ + const struct map *map = *(const struct map **)b; + return strcmp(name, map->dso->short_name); +} + +void __maps__sort_by_name(struct maps *maps) +{ + qsort(maps->maps_by_name, maps->nr_maps, sizeof(struct map *), map__strcmp); +} + +static int map__groups__sort_by_name_from_rbtree(struct maps *maps) { - struct maps *maps = &mg->maps; struct map *map; - struct rb_node *node; + struct map **maps_by_name = realloc(maps->maps_by_name, maps->nr_maps * sizeof(map)); + int i = 0; - down_read(&maps->lock); + if (maps_by_name == NULL) + return -1; - for (node = maps->names.rb_node; node; ) { - int rc; + maps->maps_by_name = maps_by_name; + maps->nr_maps_allocated = maps->nr_maps; - map = rb_entry(node, struct map, rb_node_name); + maps__for_each_entry(maps, map) + maps_by_name[i++] = map; - rc = strcmp(map->dso->short_name, name); - if (rc < 0) - node = node->rb_left; - else if (rc > 0) - node = node->rb_right; - else + __maps__sort_by_name(maps); + return 0; +} - goto out_unlock; +static struct map *__maps__find_by_name(struct maps *maps, const char *name) +{ + struct map **mapp; + + if (maps->maps_by_name == NULL && + map__groups__sort_by_name_from_rbtree(maps)) + return NULL; + + mapp = bsearch(name, maps->maps_by_name, maps->nr_maps, sizeof(*mapp), map__strcmp_name); + if (mapp) + return *mapp; + return NULL; +} + +struct map *maps__find_by_name(struct maps *maps, const char *name) +{ + struct map *map; + + down_read(&maps->lock); + + if (maps->last_search_by_name && strcmp(maps->last_search_by_name->dso->short_name, name) == 0) { + map = maps->last_search_by_name; + goto out_unlock; } + /* + * If we have maps->maps_by_name, then the name isn't in the rbtree, + * as maps->maps_by_name mirrors the rbtree when lookups by name are + * made. + */ + map = __maps__find_by_name(maps, name); + if (map || maps->maps_by_name != NULL) + goto out_unlock; + + /* Fallback to traversing the rbtree... */ + maps__for_each_entry(maps, map) + if (strcmp(map->dso->short_name, name) == 0) { + maps->last_search_by_name = map; + goto out_unlock; + } map = NULL; @@ -2039,15 +2081,9 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map) { int err; const char *kallsyms_filename = NULL; - struct machine *machine; + struct machine *machine = map__kmaps(map)->machine; char path[PATH_MAX]; - if (!map->groups) { - pr_debug("Guest kernel map hasn't the point to groups\n"); - return -1; - } - machine = map->groups->machine; - if (machine__is_default_guest(machine)) { /* * if the user specified a vmlinux filename, use it and only @@ -2195,13 +2231,19 @@ static bool symbol__read_kptr_restrict(void) char line[8]; if (fgets(line, sizeof(line), fp) != NULL) - value = ((geteuid() != 0) || (getuid() != 0)) ? - (atoi(line) != 0) : - (atoi(line) == 2); + value = perf_cap__capable(CAP_SYSLOG) ? + (atoi(line) >= 2) : + (atoi(line) != 0); fclose(fp); } + /* Per kernel/kallsyms.c: + * we also restrict when perf_event_paranoid > 1 w/o CAP_SYSLOG + */ + if (perf_event_paranoid() > 1 && !perf_cap__capable(CAP_SYSLOG)) + value = true; + return value; } @@ -2357,25 +2399,3 @@ struct mem_info *mem_info__new(void) refcount_set(&mi->refcnt, 1); return mi; } - -struct block_info *block_info__get(struct block_info *bi) -{ - if (bi) - refcount_inc(&bi->refcnt); - return bi; -} - -void block_info__put(struct block_info *bi) -{ - if (bi && refcount_dec_and_test(&bi->refcnt)) - free(bi); -} - -struct block_info *block_info__new(void) -{ - struct block_info *bi = zalloc(sizeof(*bi)); - - if (bi) - refcount_set(&bi->refcnt, 1); - return bi; -} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 183f630cb5f1..93fc43db1be3 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -3,15 +3,15 @@ #define __PERF_SYMBOL 1 #include <linux/types.h> +#include <linux/refcount.h> #include <stdbool.h> #include <stdint.h> #include <linux/list.h> #include <linux/rbtree.h> #include <stdio.h> -#include "map_symbol.h" -#include "branch.h" #include "path.h" #include "symbol_conf.h" +#include "spark.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -19,10 +19,9 @@ #endif #include <elf.h> -#include "dso.h" - +struct dso; struct map; -struct map_groups; +struct maps; struct option; /* @@ -40,15 +39,6 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, GElf_Shdr *shp, const char *name, size_t *idx); #endif -#ifndef DMGL_PARAMS -#define DMGL_NO_OPTS 0 /* For readability... */ -#define DMGL_PARAMS (1 << 0) /* Include function args */ -#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ -#endif - -#define DSO__NAME_KALLSYMS "[kernel.kallsyms]" -#define DSO__NAME_KCORE "[kernel.kcore]" - /** struct symbol - symtab entry * * @ignore - resolvable but tools ignore it (e.g. idle routines) @@ -116,35 +106,9 @@ struct ref_reloc_sym { u64 unrelocated_addr; }; -struct branch_info { - struct addr_map_symbol from; - struct addr_map_symbol to; - struct branch_flags flags; - char *srcline_from; - char *srcline_to; -}; - -struct mem_info { - struct addr_map_symbol iaddr; - struct addr_map_symbol daddr; - union perf_mem_data_src data_src; - refcount_t refcnt; -}; - -struct block_info { - struct symbol *sym; - u64 start; - u64 end; - u64 cycles; - u64 cycles_aggr; - int num; - int num_aggr; - refcount_t refcnt; -}; - struct addr_location { - struct machine *machine; struct thread *thread; + struct maps *maps; struct map *map; struct symbol *sym; const char *srcline; @@ -156,37 +120,6 @@ struct addr_location { s32 socket; }; -struct symsrc { - char *name; - int fd; - enum dso_binary_type type; - -#ifdef HAVE_LIBELF_SUPPORT - Elf *elf; - GElf_Ehdr ehdr; - - Elf_Scn *opdsec; - size_t opdidx; - GElf_Shdr opdshdr; - - Elf_Scn *symtab; - GElf_Shdr symshdr; - - Elf_Scn *dynsym; - size_t dynsym_idx; - GElf_Shdr dynshdr; - - bool adjust_symbols; - bool is_64_bit; -#endif -}; - -void symsrc__destroy(struct symsrc *ss); -int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, - enum dso_binary_type type); -bool symsrc__has_symtab(struct symsrc *ss); -bool symsrc__possibly_runtime(struct symsrc *ss); - int dso__load(struct dso *dso, struct map *map); int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated); @@ -240,6 +173,8 @@ bool symbol__restricted_filename(const char *filename, int symbol__config_symfs(const struct option *opt __maybe_unused, const char *dir, int unset __maybe_unused); +struct symsrc; + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule); int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); @@ -251,7 +186,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); void symbols__fixup_end(struct rb_root_cached *symbols); -void map_groups__fixup_end(struct map_groups *mg); +void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, @@ -344,16 +279,4 @@ static inline void __mem_info__zput(struct mem_info **mi) #define mem_info__zput(mi) __mem_info__zput(&mi) -struct block_info *block_info__new(void); -struct block_info *block_info__get(struct block_info *bi); -void block_info__put(struct block_info *bi); - -static inline void __block_info__zput(struct block_info **bi) -{ - block_info__put(*bi); - *bi = NULL; -} - -#define block_info__zput(bi) __block_info__zput(&bi) - #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index e6880789864c..10f1ec3e0349 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -40,6 +40,7 @@ struct symbol_conf { raw_trace, report_hierarchy, report_block, + report_individual_block, inline_name, disable_add2line_warn; const char *vmlinux_name, diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 02e89b02c2ce..35c936ce33ef 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -3,6 +3,7 @@ #include <inttypes.h> #include <stdio.h> +#include "dso.h" #include "map.h" #include "symbol.h" diff --git a/tools/perf/util/symsrc.h b/tools/perf/util/symsrc.h new file mode 100644 index 000000000000..2665b4bde751 --- /dev/null +++ b/tools/perf/util/symsrc.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_SYMSRC_ +#define __PERF_SYMSRC_ 1 + +#include <stdbool.h> +#include <stddef.h> +#include "dso.h" + +#ifdef HAVE_LIBELF_SUPPORT +#include <libelf.h> +#include <gelf.h> +#endif +#include <elf.h> + +struct symsrc { + char *name; + int fd; + enum dso_binary_type type; + +#ifdef HAVE_LIBELF_SUPPORT + Elf *elf; + GElf_Ehdr ehdr; + + Elf_Scn *opdsec; + size_t opdidx; + GElf_Shdr opdshdr; + + Elf_Scn *symtab; + GElf_Shdr symshdr; + + Elf_Scn *dynsym; + size_t dynsym_idx; + GElf_Shdr dynshdr; + + bool adjust_symbols; + bool is_64_bit; +#endif +}; + +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type); +void symsrc__destroy(struct symsrc *ss); + +bool symsrc__has_symtab(struct symsrc *ss); +bool symsrc__possibly_runtime(struct symsrc *ss); + +#endif /* __PERF_SYMSRC_ */ diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c new file mode 100644 index 000000000000..c423298fe62d --- /dev/null +++ b/tools/perf/util/synthetic-events.c @@ -0,0 +1,1896 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "util/debug.h" +#include "util/dso.h" +#include "util/event.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/map.h" +#include "util/map_symbol.h" +#include "util/branch.h" +#include "util/memswap.h" +#include "util/namespaces.h" +#include "util/session.h" +#include "util/stat.h" +#include "util/symbol.h" +#include "util/synthetic-events.h" +#include "util/target.h" +#include "util/time-utils.h" +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/zalloc.h> +#include <linux/perf_event.h> +#include <asm/bug.h> +#include <perf/evsel.h> +#include <internal/cpumap.h> +#include <perf/cpumap.h> +#include <internal/lib.h> // page_size +#include <internal/threadmap.h> +#include <perf/threadmap.h> +#include <symbol/kallsyms.h> +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <stdio.h> +#include <string.h> +#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ +#include <api/fs/fs.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500 + +unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT; + +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process) +{ + struct perf_sample synth_sample = { + .pid = -1, + .tid = -1, + .time = -1, + .stream_id = -1, + .cpu = -1, + .period = 1, + .cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK, + }; + + return process(tool, event, &synth_sample, machine); +}; + +/* + * Assumes that the first 4095 bytes of /proc/pid/stat contains + * the comm, tgid and ppid. + */ +static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, + pid_t *tgid, pid_t *ppid) +{ + char filename[PATH_MAX]; + char bf[4096]; + int fd; + size_t size = 0; + ssize_t n; + char *name, *tgids, *ppids; + + *tgid = -1; + *ppid = -1; + + snprintf(filename, sizeof(filename), "/proc/%d/status", pid); + + fd = open(filename, O_RDONLY); + if (fd < 0) { + pr_debug("couldn't open %s\n", filename); + return -1; + } + + n = read(fd, bf, sizeof(bf) - 1); + close(fd); + if (n <= 0) { + pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", + pid); + return -1; + } + bf[n] = '\0'; + + name = strstr(bf, "Name:"); + tgids = strstr(bf, "Tgid:"); + ppids = strstr(bf, "PPid:"); + + if (name) { + char *nl; + + name = skip_spaces(name + 5); /* strlen("Name:") */ + nl = strchr(name, '\n'); + if (nl) + *nl = '\0'; + + size = strlen(name); + if (size >= len) + size = len - 1; + memcpy(comm, name, size); + comm[size] = '\0'; + } else { + pr_debug("Name: string not found for pid %d\n", pid); + } + + if (tgids) { + tgids += 5; /* strlen("Tgid:") */ + *tgid = atoi(tgids); + } else { + pr_debug("Tgid: string not found for pid %d\n", pid); + } + + if (ppids) { + ppids += 5; /* strlen("PPid:") */ + *ppid = atoi(ppids); + } else { + pr_debug("PPid: string not found for pid %d\n", pid); + } + + return 0; +} + +static int perf_event__prepare_comm(union perf_event *event, pid_t pid, + struct machine *machine, + pid_t *tgid, pid_t *ppid) +{ + size_t size; + + *ppid = -1; + + memset(&event->comm, 0, sizeof(event->comm)); + + if (machine__is_host(machine)) { + if (perf_event__get_comm_ids(pid, event->comm.comm, + sizeof(event->comm.comm), + tgid, ppid) != 0) { + return -1; + } + } else { + *tgid = machine->pid; + } + + if (*tgid < 0) + return -1; + + event->comm.pid = *tgid; + event->comm.header.type = PERF_RECORD_COMM; + + size = strlen(event->comm.comm) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + memset(event->comm.comm + size, 0, machine->id_hdr_size); + event->comm.header.size = (sizeof(event->comm) - + (sizeof(event->comm.comm) - size) + + machine->id_hdr_size); + event->comm.tid = pid; + + return 0; +} + +pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + pid_t tgid, ppid; + + if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) + return -1; + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return tgid; +} + +static void perf_event__get_ns_link_info(pid_t pid, const char *ns, + struct perf_ns_link_info *ns_link_info) +{ + struct stat64 st; + char proc_ns[128]; + + sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); + if (stat64(proc_ns, &st) == 0) { + ns_link_info->dev = st.st_dev; + ns_link_info->ino = st.st_ino; + } +} + +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine) +{ + u32 idx; + struct perf_ns_link_info *ns_link_info; + + if (!tool || !tool->namespace_events) + return 0; + + memset(&event->namespaces, 0, (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size)); + + event->namespaces.pid = tgid; + event->namespaces.tid = pid; + + event->namespaces.nr_namespaces = NR_NAMESPACES; + + ns_link_info = event->namespaces.link_info; + + for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) + perf_event__get_ns_link_info(pid, perf_ns__name(idx), + &ns_link_info[idx]); + + event->namespaces.header.type = PERF_RECORD_NAMESPACES; + + event->namespaces.header.size = (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + +static int perf_event__synthesize_fork(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, pid_t ppid, + perf_event__handler_t process, + struct machine *machine) +{ + memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); + + /* + * for main thread set parent to ppid from status file. For other + * threads set parent pid to main thread. ie., assume main thread + * spawns all threads in a process + */ + if (tgid == pid) { + event->fork.ppid = ppid; + event->fork.ptid = ppid; + } else { + event->fork.ppid = tgid; + event->fork.ptid = tgid; + } + event->fork.pid = tgid; + event->fork.tid = pid; + event->fork.header.type = PERF_RECORD_FORK; + event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC; + + event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + +int perf_event__synthesize_mmap_events(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) +{ + char filename[PATH_MAX]; + FILE *fp; + unsigned long long t; + bool truncation = false; + unsigned long long timeout = proc_map_timeout * 1000000ULL; + int rc = 0; + const char *hugetlbfs_mnt = hugetlbfs__mountpoint(); + int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0; + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", + machine->root_dir, pid, pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { + /* + * We raced with a task exiting - just return: + */ + pr_debug("couldn't open %s\n", filename); + return -1; + } + + event->header.type = PERF_RECORD_MMAP2; + t = rdclock(); + + while (1) { + char bf[BUFSIZ]; + char prot[5]; + char execname[PATH_MAX]; + char anonstr[] = "//anon"; + unsigned int ino; + size_t size; + ssize_t n; + + if (fgets(bf, sizeof(bf), fp) == NULL) + break; + + if ((rdclock() - t) > timeout) { + pr_warning("Reading %s time out. " + "You may want to increase " + "the time limit by --proc-map-timeout\n", + filename); + truncation = true; + goto out; + } + + /* ensure null termination since stack will be reused. */ + strcpy(execname, ""); + + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ + n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + + /* + * Anon maps don't have the execname. + */ + if (n < 7) + continue; + + event->mmap2.ino = (u64)ino; + + /* + * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_USER; + else + event->header.misc = PERF_RECORD_MISC_GUEST_USER; + + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; + + if (prot[2] != 'x') { + if (!mmap_data || prot[0] != 'r') + continue; + + event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; + } + +out: + if (truncation) + event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT; + + if (!strcmp(execname, "")) + strcpy(execname, anonstr); + + if (hugetlbfs_mnt_len && + !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) { + strcpy(execname, anonstr); + event->mmap2.flags |= MAP_HUGETLB; + } + + size = strlen(execname) + 1; + memcpy(event->mmap2.filename, execname, size); + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { + rc = -1; + break; + } + + if (truncation) + break; + } + + fclose(fp); + return rc; +} + +int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, + struct machine *machine) +{ + int rc = 0; + struct map *pos; + struct maps *maps = machine__kernel_maps(machine); + union perf_event *event = zalloc((sizeof(event->mmap) + + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } + + event->header.type = PERF_RECORD_MMAP; + + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_KERNEL; + else + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + + maps__for_each_entry(maps, pos) { + size_t size; + + if (!__map__is_kmodule(pos)) + continue; + + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pid = machine->pid; + + memcpy(event->mmap.filename, pos->dso->long_name, + pos->dso->long_name_len + 1); + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { + rc = -1; + break; + } + } + + free(event); + return rc; +} + +static int __event__synthesize_thread(union perf_event *comm_event, + union perf_event *mmap_event, + union perf_event *fork_event, + union perf_event *namespaces_event, + pid_t pid, int full, perf_event__handler_t process, + struct perf_tool *tool, struct machine *machine, bool mmap_data) +{ + char filename[PATH_MAX]; + DIR *tasks; + struct dirent *dirent; + pid_t tgid, ppid; + int rc = 0; + + /* special case: only send one comm event using passed in pid */ + if (!full) { + tgid = perf_event__synthesize_comm(tool, comm_event, pid, + process, machine); + + if (tgid == -1) + return -1; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, + tgid, process, machine) < 0) + return -1; + + /* + * send mmap only for thread group leader + * see thread__init_maps() + */ + if (pid == tgid && + perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data)) + return -1; + + return 0; + } + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task", + machine->root_dir, pid); + + tasks = opendir(filename); + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } + + while ((dirent = readdir(tasks)) != NULL) { + char *end; + pid_t _pid; + + _pid = strtol(dirent->d_name, &end, 10); + if (*end) + continue; + + rc = -1; + if (perf_event__prepare_comm(comm_event, _pid, machine, + &tgid, &ppid) != 0) + break; + + if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + ppid, process, machine) < 0) + break; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, + tgid, process, machine) < 0) + break; + + /* + * Send the prepared comm event + */ + if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0) + break; + + rc = 0; + if (_pid == pid) { + /* process the parent's maps too */ + rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + if (rc) + break; + } + } + + closedir(tasks); + return rc; +} + +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct perf_thread_map *threads, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) +{ + union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; + int err = -1, thread, j; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + + err = 0; + for (thread = 0; thread < threads->nr; ++thread) { + if (__event__synthesize_thread(comm_event, mmap_event, + fork_event, namespaces_event, + perf_thread_map__pid(threads, thread), 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + + /* + * comm.pid is set to thread group id by + * perf_event__synthesize_comm + */ + if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) { + bool need_leader = true; + + /* is thread group leader in thread_map? */ + for (j = 0; j < threads->nr; ++j) { + if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) { + need_leader = false; + break; + } + } + + /* if not, generate events for it */ + if (need_leader && + __event__synthesize_thread(comm_event, mmap_event, + fork_event, namespaces_event, + comm_event->comm.pid, 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + } + } + free(namespaces_event); +out_free_fork: + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; +} + +static int __perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + struct dirent **dirent, + int start, + int num) +{ + union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; + int err = -1; + char *end; + pid_t pid; + int i; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + + for (i = start; i < start + num; i++) { + if (!isdigit(dirent[i]->d_name[0])) + continue; + + 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. + */ + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data); + } + err = 0; + + free(namespaces_event); +out_free_fork: + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; +} + +struct synthesize_threads_arg { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + bool mmap_data; + 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->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 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, + 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].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++) + zfree(&dirent[i]); + free(dirent); + + return err; +} + +int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + size_t size; + struct map *map = machine__kernel_map(machine); + struct kmap *kmap; + int err; + union perf_event *event; + + if (map == NULL) + return -1; + + kmap = map__kmap(map); + if (!kmap->ref_reloc_sym) + return -1; + + /* + * We should get this from /sys/kernel/sections/.text, but till that is + * available use this, and after it is use this as a fallback for older + * kernels. + */ + event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } + + if (machine__is_host(machine)) { + /* + * kernel uses PERF_RECORD_MISC_USER for user space maps, + * see kernel/perf_event.c __perf_event_mmap + */ + event->header.misc = PERF_RECORD_MISC_KERNEL; + } else { + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + } + + size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), + "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); + event->mmap.pgoff = kmap->ref_reloc_sym->addr; + event->mmap.start = map->start; + event->mmap.len = map->end - event->mmap.start; + event->mmap.pid = machine->pid; + + err = perf_tool__process_synth_event(tool, event, machine, process); + free(event); + + return err; +} + +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int err; + + err = __perf_event__synthesize_kernel_mmap(tool, process, machine); + if (err < 0) + return err; + + return perf_event__synthesize_extra_kmaps(tool, process, machine); +} + +int perf_event__synthesize_thread_map2(struct perf_tool *tool, + struct perf_thread_map *threads, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event *event; + int i, err, size; + + size = sizeof(event->thread_map); + size += threads->nr * sizeof(event->thread_map.entries[0]); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_THREAD_MAP; + event->header.size = size; + event->thread_map.nr = threads->nr; + + for (i = 0; i < threads->nr; i++) { + struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i]; + char *comm = perf_thread_map__comm(threads, i); + + if (!comm) + comm = (char *) ""; + + entry->pid = perf_thread_map__pid(threads, i); + strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); + } + + err = process(tool, event, NULL, machine); + + free(event); + return err; +} + +static void synthesize_cpus(struct cpu_map_entries *cpus, + struct perf_cpu_map *map) +{ + int i; + + cpus->nr = map->nr; + + for (i = 0; i < map->nr; i++) + cpus->cpu[i] = map->map[i]; +} + +static void synthesize_mask(struct perf_record_record_cpu_map *mask, + struct perf_cpu_map *map, int max) +{ + int i; + + mask->nr = BITS_TO_LONGS(max); + mask->long_size = sizeof(long); + + for (i = 0; i < map->nr; i++) + set_bit(map->map[i], mask->mask); +} + +static size_t cpus_size(struct perf_cpu_map *map) +{ + return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); +} + +static size_t mask_size(struct perf_cpu_map *map, int *max) +{ + int i; + + *max = 0; + + for (i = 0; i < map->nr; i++) { + /* bit possition of the cpu is + 1 */ + int bit = map->map[i] + 1; + + if (bit > *max) + *max = bit; + } + + return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long); +} + +void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max) +{ + size_t size_cpus, size_mask; + bool is_dummy = perf_cpu_map__empty(map); + + /* + * Both array and mask data have variable size based + * on the number of cpus and their actual values. + * The size of the 'struct perf_record_cpu_map_data' is: + * + * array = size of 'struct cpu_map_entries' + + * number of cpus * sizeof(u64) + * + * mask = size of 'struct perf_record_record_cpu_map' + + * maximum cpu bit converted to size of longs + * + * and finaly + the size of 'struct perf_record_cpu_map_data'. + */ + size_cpus = cpus_size(map); + size_mask = mask_size(map, max); + + if (is_dummy || (size_cpus < size_mask)) { + *size += size_cpus; + *type = PERF_CPU_MAP__CPUS; + } else { + *size += size_mask; + *type = PERF_CPU_MAP__MASK; + } + + *size += sizeof(struct perf_record_cpu_map_data); + *size = PERF_ALIGN(*size, sizeof(u64)); + return zalloc(*size); +} + +void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, + u16 type, int max) +{ + data->type = type; + + switch (type) { + case PERF_CPU_MAP__CPUS: + synthesize_cpus((struct cpu_map_entries *) data->data, map); + break; + case PERF_CPU_MAP__MASK: + synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max); + default: + break; + }; +} + +static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map) +{ + size_t size = sizeof(struct perf_record_cpu_map); + struct perf_record_cpu_map *event; + int max; + u16 type; + + event = cpu_map_data__alloc(map, &size, &type, &max); + if (!event) + return NULL; + + event->header.type = PERF_RECORD_CPU_MAP; + event->header.size = size; + event->data.type = type; + + cpu_map_data__synthesize(&event->data, map, type, max); + return event; +} + +int perf_event__synthesize_cpu_map(struct perf_tool *tool, + struct perf_cpu_map *map, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_cpu_map *event; + int err; + + event = cpu_map_event__new(map); + if (!event) + return -ENOMEM; + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat_config(struct perf_tool *tool, + struct perf_stat_config *config, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat_config *event; + int size, i = 0, err; + + size = sizeof(*event); + size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0])); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_STAT_CONFIG; + event->header.size = size; + event->nr = PERF_STAT_CONFIG_TERM__MAX; + +#define ADD(__term, __val) \ + event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \ + event->data[i].val = __val; \ + i++; + + ADD(AGGR_MODE, config->aggr_mode) + ADD(INTERVAL, config->interval) + ADD(SCALE, config->scale) + + WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, + "stat config terms unbalanced\n"); +#undef ADD + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat(struct perf_tool *tool, + u32 cpu, u32 thread, u64 id, + struct perf_counts_values *count, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat event; + + event.header.type = PERF_RECORD_STAT; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.id = id; + event.cpu = cpu; + event.thread = thread; + event.val = count->val; + event.ena = count->ena; + event.run = count->run; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +int perf_event__synthesize_stat_round(struct perf_tool *tool, + u64 evtime, u64 type, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat_round event; + + event.header.type = PERF_RECORD_STAT_ROUND; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.time = evtime; + event.type = type; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format) +{ + size_t sz, result = sizeof(struct perf_record_sample); + + if (type & PERF_SAMPLE_IDENTIFIER) + result += sizeof(u64); + + if (type & PERF_SAMPLE_IP) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TIME) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ADDR) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_STREAM_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_CPU) + result += sizeof(u64); + + if (type & PERF_SAMPLE_PERIOD) + result += sizeof(u64); + + if (type & PERF_SAMPLE_READ) { + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + result += sizeof(u64); + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_RAW) { + result += sizeof(u32); + result += sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + result += sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + result += sizeof(u64); + if (sz) { + result += sz; + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_WEIGHT) + result += sizeof(u64); + + if (type & PERF_SAMPLE_DATA_SRC) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TRANSACTION) + result += sizeof(u64); + + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + result += sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_PHYS_ADDR) + result += sizeof(u64); + + if (type & PERF_SAMPLE_AUX) { + result += sizeof(u64); + result += sample->aux_sample.size; + } + + return result; +} + +int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, + const struct perf_sample *sample) +{ + __u64 *array; + size_t sz; + /* + * used for cross-endian analysis. See git commit 65014ab3 + * for why this goofiness is needed. + */ + union u64_swap u; + + array = event->sample.array; + + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_IP) { + *array = sample->ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u.val32[0] = sample->pid; + u.val32[1] = sample->tid; + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + *array = sample->time; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + *array = sample->addr; + array++; + } + + if (type & PERF_SAMPLE_ID) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + *array = sample->stream_id; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u.val32[0] = sample->cpu; + u.val32[1] = 0; + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + *array = sample->period; + array++; + } + + if (type & PERF_SAMPLE_READ) { + if (read_format & PERF_FORMAT_GROUP) + *array = sample->read.group.nr; + else + *array = sample->read.one.value; + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + *array = sample->read.time_enabled; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + *array = sample->read.time_running; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + memcpy(array, sample->read.group.values, sz); + array = (void *)array + sz; + } else { + *array = sample->read.one.id; + array++; + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + memcpy(array, sample->callchain, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_RAW) { + u.val32[0] = sample->raw_size; + *array = u.val64; + array = (void *)array + sizeof(u32); + + memcpy(array, sample->raw_data, sample->raw_size); + array = (void *)array + sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + memcpy(array, sample->branch_stack, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + *array++ = sample->user_regs.abi; + sz = hweight64(sample->user_regs.mask) * sizeof(u64); + memcpy(array, sample->user_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + *array++ = sz; + if (sz) { + memcpy(array, sample->user_stack.data, sz); + array = (void *)array + sz; + *array++ = sz; + } + } + + if (type & PERF_SAMPLE_WEIGHT) { + *array = sample->weight; + array++; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + *array = sample->data_src; + array++; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + *array = sample->transaction; + array++; + } + + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + *array++ = sample->intr_regs.abi; + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + memcpy(array, sample->intr_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_PHYS_ADDR) { + *array = sample->phys_addr; + array++; + } + + if (type & PERF_SAMPLE_AUX) { + sz = sample->aux_sample.size; + *array++ = sz; + memcpy(array, sample->aux_sample.data, sz); + array = (void *)array + sz; + } + + return 0; +} + +int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, + struct evlist *evlist, struct machine *machine) +{ + union perf_event *ev; + struct evsel *evsel; + size_t nr = 0, i = 0, sz, max_nr, n; + int err; + + pr_debug2("Synthesizing id index\n"); + + max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) / + sizeof(struct id_index_entry); + + evlist__for_each_entry(evlist, evsel) + nr += evsel->core.ids; + + n = nr > max_nr ? max_nr : nr; + sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry); + ev = zalloc(sz); + if (!ev) + return -ENOMEM; + + ev->id_index.header.type = PERF_RECORD_ID_INDEX; + ev->id_index.header.size = sz; + ev->id_index.nr = n; + + evlist__for_each_entry(evlist, evsel) { + u32 j; + + for (j = 0; j < evsel->core.ids; j++) { + struct id_index_entry *e; + struct perf_sample_id *sid; + + if (i >= n) { + err = process(tool, ev, NULL, machine); + if (err) + goto out_err; + nr -= n; + i = 0; + } + + e = &ev->id_index.entries[i++]; + + e->id = evsel->core.id[j]; + + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) { + free(ev); + return -ENOENT; + } + + e->idx = sid->idx; + e->cpu = sid->cpu; + e->tid = sid->tid; + } + } + + sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry); + ev->id_index.header.size = sz; + ev->id_index.nr = nr; + + err = process(tool, ev, NULL, machine); +out_err: + free(ev); + + return err; +} + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct perf_thread_map *threads, + perf_event__handler_t process, bool data_mmap, + unsigned int nr_threads_synthesize) +{ + if (target__has_task(target)) + return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + else if (target__has_cpu(target)) + return perf_event__synthesize_threads(tool, process, + machine, data_mmap, + nr_threads_synthesize); + /* command specified */ + return 0; +} + +int machine__synthesize_threads(struct machine *machine, struct target *target, + struct perf_thread_map *threads, bool data_mmap, + unsigned int nr_threads_synthesize) +{ + return __machine__synthesize_threads(machine, NULL, target, threads, + perf_event__process, data_mmap, + nr_threads_synthesize); +} + +static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) +{ + struct perf_record_event_update *ev; + + size += sizeof(*ev); + size = PERF_ALIGN(size, sizeof(u64)); + + ev = zalloc(size); + if (ev) { + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = type; + ev->id = id; + } + return ev; +} + +int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + size_t size = strlen(evsel->unit); + struct perf_record_event_update *ev; + int err; + + ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + strlcpy(ev->data, evsel->unit, size + 1); + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + struct perf_record_event_update *ev; + struct perf_record_event_update_scale *ev_data; + int err; + + ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + ev_data = (struct perf_record_event_update_scale *)ev->data; + ev_data->scale = evsel->scale; + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + struct perf_record_event_update *ev; + size_t len = strlen(evsel->name); + int err; + + ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + strlcpy(ev->data, evsel->name, len + 1); + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + size_t size = sizeof(struct perf_record_event_update); + struct perf_record_event_update *ev; + int max, err; + u16 type; + + if (!evsel->core.own_cpus) + return 0; + + ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max); + if (!ev) + return -ENOMEM; + + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = PERF_EVENT_UPDATE__CPUS; + ev->id = evsel->core.id[0]; + + cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data, + evsel->core.own_cpus, type, max); + + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, + perf_event__handler_t process) +{ + struct evsel *evsel; + int err = 0; + + evlist__for_each_entry(evlist, evsel) { + err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->core.ids, + evsel->core.id, process); + if (err) { + pr_debug("failed to create perf header attribute\n"); + return err; + } + } + + return err; +} + +static bool has_unit(struct evsel *evsel) +{ + return evsel->unit && *evsel->unit; +} + +static bool has_scale(struct evsel *evsel) +{ + return evsel->scale != 1; +} + +int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, + perf_event__handler_t process, bool is_pipe) +{ + struct evsel *evsel; + int err; + + /* + * Synthesize other events stuff not carried within + * attr event - unit, scale, name + */ + evlist__for_each_entry(evsel_list, evsel) { + if (!evsel->supported) + continue; + + /* + * Synthesize unit and scale only if it's defined. + */ + if (has_unit(evsel)) { + err = perf_event__synthesize_event_update_unit(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel unit.\n"); + return err; + } + } + + if (has_scale(evsel)) { + err = perf_event__synthesize_event_update_scale(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel evsel.\n"); + return err; + } + } + + if (evsel->core.own_cpus) { + err = perf_event__synthesize_event_update_cpus(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel cpus.\n"); + return err; + } + } + + /* + * Name is needed only for pipe output, + * perf.data carries event names. + */ + if (is_pipe) { + err = perf_event__synthesize_event_update_name(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel name.\n"); + return err; + } + } + } + return 0; +} + +int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, + u32 ids, u64 *id, perf_event__handler_t process) +{ + union perf_event *ev; + size_t size; + int err; + + size = sizeof(struct perf_event_attr); + size = PERF_ALIGN(size, sizeof(u64)); + size += sizeof(struct perf_event_header); + size += ids * sizeof(u64); + + ev = zalloc(size); + + if (ev == NULL) + return -ENOMEM; + + ev->attr.attr = *attr; + memcpy(ev->attr.id, id, ids * sizeof(u64)); + + ev->attr.header.type = PERF_RECORD_HEADER_ATTR; + ev->attr.header.size = (u16)size; + + if (ev->attr.header.size == size) + err = process(tool, ev, NULL, NULL); + else + err = -E2BIG; + + free(ev); + + return err; +} + +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, + perf_event__handler_t process) +{ + union perf_event ev; + struct tracing_data *tdata; + ssize_t size = 0, aligned_size = 0, padding; + struct feat_fd ff; + + /* + * We are going to store the size of the data followed + * by the data contents. Since the fd descriptor is a pipe, + * we cannot seek back to store the size of the data once + * we know it. Instead we: + * + * - write the tracing data to the temp file + * - get/write the data size to pipe + * - write the tracing data from the temp file + * to the pipe + */ + tdata = tracing_data_get(&evlist->core.entries, fd, true); + if (!tdata) + return -1; + + memset(&ev, 0, sizeof(ev)); + + ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; + size = tdata->size; + aligned_size = PERF_ALIGN(size, sizeof(u64)); + padding = aligned_size - size; + ev.tracing_data.header.size = sizeof(ev.tracing_data); + ev.tracing_data.size = aligned_size; + + process(tool, &ev, NULL, NULL); + + /* + * The put function will copy all the tracing data + * stored in temp file to the pipe. + */ + tracing_data_put(tdata); + + ff = (struct feat_fd){ .fd = fd }; + if (write_padded(&ff, NULL, 0, padding)) + return -1; + + return aligned_size; +} + +int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, + perf_event__handler_t process, struct machine *machine) +{ + union perf_event ev; + size_t len; + + if (!pos->hit) + return 0; + + memset(&ev, 0, sizeof(ev)); + + len = pos->long_name_len + 1; + len = PERF_ALIGN(len, NAME_ALIGN); + memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); + ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; + ev.build_id.header.misc = misc; + ev.build_id.pid = machine->pid; + ev.build_id.header.size = sizeof(ev.build_id) + len; + memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); + + return process(tool, &ev, NULL, machine); +} + +int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, + struct evlist *evlist, perf_event__handler_t process, bool attrs) +{ + int err; + + if (attrs) { + err = perf_event__synthesize_attrs(tool, evlist, process); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + return err; + } + } + + err = perf_event__synthesize_extra_attr(tool, evlist, process, attrs); + err = perf_event__synthesize_thread_map2(tool, evlist->core.threads, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_stat_config(tool, config, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize config.\n"); + return err; + } + + return 0; +} + +int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, + struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; + +int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, + struct evlist *evlist, perf_event__handler_t process) +{ + struct perf_header *header = &session->header; + struct perf_record_header_feature *fe; + struct feat_fd ff; + 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; + ff.ph = &session->header; + + 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; + } + } + + /* Send HEADER_LAST_FEATURE mark. */ + fe = ff.buf; + fe->feat_id = HEADER_LAST_FEATURE; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = sizeof(*fe); + + ret = process(tool, ff.buf, NULL, NULL); + + free(ff.buf); + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h new file mode 100644 index 000000000000..baead0cdc381 --- /dev/null +++ b/tools/perf/util/synthetic-events.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_SYNTHETIC_EVENTS_H +#define __PERF_SYNTHETIC_EVENTS_H + +#include <stdbool.h> +#include <sys/types.h> // pid_t +#include <linux/compiler.h> +#include <linux/types.h> + +struct auxtrace_record; +struct dso; +struct evlist; +struct evsel; +struct machine; +struct perf_counts_values; +struct perf_cpu_map; +struct perf_event_attr; +struct perf_event_mmap_page; +struct perf_sample; +struct perf_session; +struct perf_stat_config; +struct perf_thread_map; +struct perf_tool; +struct record_opts; +struct target; + +union perf_event; + +typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine); + +int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); +int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe); +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine); +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data); +int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample); +int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs); +int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); + +int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process); + +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format); + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct perf_thread_map *threads, + perf_event__handler_t process, bool data_mmap, + unsigned int nr_threads_synthesize); +int machine__synthesize_threads(struct machine *machine, struct target *target, + struct perf_thread_map *threads, bool data_mmap, + unsigned int nr_threads_synthesize); + +#ifdef HAVE_AUXTRACE_SUPPORT +int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, struct perf_tool *tool, + struct perf_session *session, perf_event__handler_t process); + +#else // HAVE_AUXTRACE_SUPPORT + +#include <errno.h> + +static inline int +perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, + struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, + perf_event__handler_t process __maybe_unused) +{ + return -EINVAL; +} +#endif // HAVE_AUXTRACE_SUPPORT + +#ifdef HAVE_LIBBPF_SUPPORT +int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, + struct machine *machine, struct record_opts *opts); +#else // HAVE_LIBBPF_SUPPORT +static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused, + struct record_opts *opts __maybe_unused) +{ + return 0; +} +#endif // HAVE_LIBBPF_SUPPORT + +#endif // __PERF_SYNTHETIC_EVENTS_H diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 022a9c670338..820fceeb19a9 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -79,6 +79,7 @@ static int syscalltbl__init_native(struct syscalltbl *tbl) qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); tbl->syscalls.nr_entries = nr_entries; + tbl->syscalls.max_id = syscalltbl_native_max_id; return 0; } diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index c8e7e9ce0f01..9172613028d0 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -6,6 +6,7 @@ struct syscalltbl { union { int audit_machine; struct { + int max_id; int nr_entries; void *entries; } syscalls; diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 3adc65480349..a3db13dea937 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -6,12 +6,13 @@ */ #include "target.h" -#include "util.h" -#include "debug.h" #include <pwd.h> +#include <stdio.h> #include <stdlib.h> #include <string.h> +#include <linux/kernel.h> +#include <linux/string.h> enum target_errno target__validate(struct target *target) { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 15134ac9b8f1..0885967d5bc3 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -10,6 +10,7 @@ #include <linux/zalloc.h> #include <errno.h> #include <stdlib.h> +#include <string.h> #include "thread.h" #include "event.h" #include "machine.h" @@ -133,8 +134,8 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread, if (err) return err; - if (thread->mg && thread->mg->machine) { - struct machine *machine = thread->mg->machine; + if (thread->maps && thread->maps->machine) { + struct machine *machine = thread->maps->machine; const char *arch = perf_env__arch(machine->env); ts->kernel_start = machine__kernel_start(machine); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 590793cc5142..28b719388028 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../perf.h" #include <errno.h> #include <stdlib.h> #include <stdio.h> #include <string.h> #include <linux/kernel.h> #include <linux/zalloc.h> +#include "dso.h" #include "session.h" #include "thread.h" #include "thread-stack.h" @@ -19,21 +19,21 @@ #include <api/fs/fs.h> -int thread__init_map_groups(struct thread *thread, struct machine *machine) +int thread__init_maps(struct thread *thread, struct machine *machine) { pid_t pid = thread->pid_; if (pid == thread->tid || pid == -1) { - thread->mg = map_groups__new(machine); + thread->maps = maps__new(machine); } else { struct thread *leader = __machine__findnew_thread(machine, pid, pid); if (leader) { - thread->mg = map_groups__get(leader->mg); + thread->maps = maps__get(leader->maps); thread__put(leader); } } - return thread->mg ? 0 : -1; + return thread->maps ? 0 : -1; } struct thread *thread__new(pid_t pid, pid_t tid) @@ -86,9 +86,9 @@ void thread__delete(struct thread *thread) thread_stack__free(thread); - if (thread->mg) { - map_groups__put(thread->mg); - thread->mg = NULL; + if (thread->maps) { + maps__put(thread->maps); + thread->maps = NULL; } down_write(&thread->namespaces_lock); list_for_each_entry_safe(namespaces, tmp_namespaces, @@ -105,7 +105,6 @@ void thread__delete(struct thread *thread) } up_write(&thread->comm_lock); - unwind__finish_access(thread); nsinfo__zput(thread->nsinfo); srccode_state_free(&thread->srccode_state); @@ -170,7 +169,7 @@ struct namespaces *thread__namespaces(struct thread *thread) } static int __thread__set_namespaces(struct thread *thread, u64 timestamp, - struct namespaces_event *event) + struct perf_record_namespaces *event) { struct namespaces *new, *curr = __thread__namespaces(thread); @@ -194,7 +193,7 @@ static int __thread__set_namespaces(struct thread *thread, u64 timestamp, } int thread__set_namespaces(struct thread *thread, u64 timestamp, - struct namespaces_event *event) + struct perf_record_namespaces *event) { int ret; @@ -252,7 +251,7 @@ static int ____thread__set_comm(struct thread *thread, const char *str, list_add(&new->list, &thread->comm_list); if (exec) - unwind__flush_access(thread); + unwind__flush_access(thread->maps); } thread->comm_set = true; @@ -325,19 +324,19 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(thread->mg, fp); + maps__fprintf(thread->maps, fp); } int thread__insert_map(struct thread *thread, struct map *map) { int ret; - ret = unwind__prepare_access(thread, map, NULL); + ret = unwind__prepare_access(thread->maps, map, NULL); if (ret) return ret; - map_groups__fixup_overlappings(thread->mg, map, stderr); - map_groups__insert(thread->mg, map); + maps__fixup_overlappings(thread->maps, map, stderr); + maps__insert(thread->maps, map); return 0; } @@ -346,13 +345,13 @@ static int __thread__prepare_access(struct thread *thread) { bool initialized = false; int err = 0; - struct maps *maps = &thread->mg->maps; + struct maps *maps = thread->maps; struct map *map; down_read(&maps->lock); - for (map = maps__first(maps); map; map = map__next(map)) { - err = unwind__prepare_access(thread, map, &initialized); + maps__for_each_entry(maps, map) { + err = unwind__prepare_access(thread->maps, map, &initialized); if (err || initialized) break; } @@ -372,21 +371,19 @@ static int thread__prepare_access(struct thread *thread) return err; } -static int thread__clone_map_groups(struct thread *thread, - struct thread *parent, - bool do_maps_clone) +static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone) { /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) return thread__prepare_access(thread); - if (thread->mg == parent->mg) { + if (thread->maps == parent->maps) { pr_debug("broken map groups on thread %d/%d parent %d/%d\n", thread->pid_, thread->tid, parent->pid_, parent->tid); return 0; } /* But this one is new process, copy maps. */ - return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0; + return do_maps_clone ? maps__clone(thread, parent->maps) : 0; } int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone) @@ -402,7 +399,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo } thread->ppid = parent->tid; - return thread__clone_map_groups(thread, parent, do_maps_clone); + return thread__clone_maps(thread, parent, do_maps_clone); } void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index e97ef6977eb9..20b96b5d1f15 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -16,7 +16,7 @@ struct addr_location; struct map; -struct namespaces_event; +struct perf_record_namespaces; struct thread_stack; struct unwind_libunwind_ops; @@ -25,7 +25,7 @@ struct thread { struct rb_node rb_node; struct list_head node; }; - struct map_groups *mg; + struct maps *maps; pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; @@ -44,10 +44,6 @@ struct thread { struct thread_stack *ts; struct nsinfo *nsinfo; struct srccode_state srccode_state; -#ifdef HAVE_LIBUNWIND_SUPPORT - void *addr_space; - struct unwind_libunwind_ops *unwind_libunwind_ops; -#endif bool filter; int filter_entry_depth; }; @@ -57,7 +53,7 @@ struct namespaces; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); -int thread__init_map_groups(struct thread *thread, struct machine *machine); +int thread__init_maps(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); struct thread *thread__get(struct thread *thread); @@ -78,7 +74,7 @@ static inline void thread__exited(struct thread *thread) struct namespaces *thread__namespaces(struct thread *thread); int thread__set_namespaces(struct thread *thread, u64 timestamp, - struct namespaces_event *event); + struct perf_record_namespaces *event); int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, bool exec); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 5b3511f2b6b1..c9bfe4696943 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -28,34 +28,11 @@ static int filter(const struct dirent *dir) return 1; } -static void thread_map__reset(struct thread_map *map, int start, int nr) -{ - size_t size = (nr - start) * sizeof(map->map[0]); - - memset(&map->map[start], 0, size); - map->err_thread = -1; -} +#define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr) -static struct thread_map *thread_map__realloc(struct thread_map *map, int nr) +struct perf_thread_map *thread_map__new_by_pid(pid_t pid) { - size_t size = sizeof(*map) + sizeof(map->map[0]) * nr; - int start = map ? map->nr : 0; - - map = realloc(map, size); - /* - * We only realloc to add more items, let's reset new items. - */ - if (map) - thread_map__reset(map, start, nr); - - return map; -} - -#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr) - -struct thread_map *thread_map__new_by_pid(pid_t pid) -{ - struct thread_map *threads; + struct perf_thread_map *threads; char name[256]; int items; struct dirent **namelist = NULL; @@ -69,7 +46,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) threads = thread_map__alloc(items); if (threads != NULL) { for (i = 0; i < items; i++) - thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; refcount_set(&threads->refcnt, 1); } @@ -81,12 +58,12 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) return threads; } -struct thread_map *thread_map__new_by_tid(pid_t tid) +struct perf_thread_map *thread_map__new_by_tid(pid_t tid) { - struct thread_map *threads = thread_map__alloc(1); + struct perf_thread_map *threads = thread_map__alloc(1); if (threads != NULL) { - thread_map__set_pid(threads, 0, tid); + perf_thread_map__set_pid(threads, 0, tid); threads->nr = 1; refcount_set(&threads->refcnt, 1); } @@ -94,13 +71,13 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) return threads; } -static struct thread_map *__thread_map__new_all_cpus(uid_t uid) +static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid) { DIR *proc; int max_threads = 32, items, i; char path[NAME_MAX + 1 + 6]; struct dirent *dirent, **namelist = NULL; - struct thread_map *threads = thread_map__alloc(max_threads); + struct perf_thread_map *threads = thread_map__alloc(max_threads); if (threads == NULL) goto out; @@ -140,9 +117,9 @@ static struct thread_map *__thread_map__new_all_cpus(uid_t uid) } if (grow) { - struct thread_map *tmp; + struct perf_thread_map *tmp; - tmp = thread_map__realloc(threads, max_threads); + tmp = perf_thread_map__realloc(threads, max_threads); if (tmp == NULL) goto out_free_namelist; @@ -150,8 +127,8 @@ static struct thread_map *__thread_map__new_all_cpus(uid_t uid) } for (i = 0; i < items; i++) { - thread_map__set_pid(threads, threads->nr + i, - atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, threads->nr + i, + atoi(namelist[i]->d_name)); } for (i = 0; i < items; i++) @@ -180,17 +157,17 @@ out_free_closedir: goto out_closedir; } -struct thread_map *thread_map__new_all_cpus(void) +struct perf_thread_map *thread_map__new_all_cpus(void) { return __thread_map__new_all_cpus(UINT_MAX); } -struct thread_map *thread_map__new_by_uid(uid_t uid) +struct perf_thread_map *thread_map__new_by_uid(uid_t uid) { return __thread_map__new_all_cpus(uid); } -struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) { if (pid != -1) return thread_map__new_by_pid(pid); @@ -201,9 +178,9 @@ struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) return thread_map__new_by_tid(tid); } -static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) +static struct perf_thread_map *thread_map__new_by_pid_str(const char *pid_str) { - struct thread_map *threads = NULL, *nt; + struct perf_thread_map *threads = NULL, *nt; char name[256]; int items, total_tasks = 0; struct dirent **namelist = NULL; @@ -233,14 +210,14 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) goto out_free_threads; total_tasks += items; - nt = thread_map__realloc(threads, total_tasks); + nt = perf_thread_map__realloc(threads, total_tasks); if (nt == NULL) goto out_free_namelist; threads = nt; for (i = 0; i < items; i++) { - thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name)); zfree(&namelist[i]); } threads->nr = total_tasks; @@ -263,21 +240,9 @@ out_free_threads: goto out; } -struct thread_map *thread_map__new_dummy(void) -{ - struct thread_map *threads = thread_map__alloc(1); - - if (threads != NULL) { - thread_map__set_pid(threads, 0, -1); - threads->nr = 1; - refcount_set(&threads->refcnt, 1); - } - return threads; -} - -struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) { - struct thread_map *threads = NULL, *nt; + struct perf_thread_map *threads = NULL, *nt; int ntasks = 0; pid_t tid, prev_tid = INT_MAX; char *end_ptr; @@ -287,7 +252,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) /* perf-stat expects threads to be generated even if tid not given */ if (!tid_str) - return thread_map__new_dummy(); + return perf_thread_map__new_dummy(); slist = strlist__new(tid_str, &slist_config); if (!slist) @@ -304,13 +269,13 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) continue; ntasks++; - nt = thread_map__realloc(threads, ntasks); + nt = perf_thread_map__realloc(threads, ntasks); if (nt == NULL) goto out_free_threads; threads = nt; - thread_map__set_pid(threads, ntasks - 1, tid); + perf_thread_map__set_pid(threads, ntasks - 1, tid); threads->nr = ntasks; } out: @@ -324,7 +289,7 @@ out_free_threads: goto out; } -struct thread_map *thread_map__new_str(const char *pid, const char *tid, +struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid, bool all_threads) { if (pid) @@ -339,39 +304,13 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid, return thread_map__new_by_tid_str(tid); } -static void thread_map__delete(struct thread_map *threads) -{ - if (threads) { - int i; - - WARN_ONCE(refcount_read(&threads->refcnt) != 0, - "thread map refcnt unbalanced\n"); - for (i = 0; i < threads->nr; i++) - free(thread_map__comm(threads, i)); - free(threads); - } -} - -struct thread_map *thread_map__get(struct thread_map *map) -{ - if (map) - refcount_inc(&map->refcnt); - return map; -} - -void thread_map__put(struct thread_map *map) -{ - if (map && refcount_dec_and_test(&map->refcnt)) - thread_map__delete(map); -} - -size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) +size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp) { int i; size_t printed = fprintf(fp, "%d thread%s: ", threads->nr, threads->nr > 1 ? "s" : ""); for (i = 0; i < threads->nr; ++i) - printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i)); + printed += fprintf(fp, "%s%d", i ? ", " : "", perf_thread_map__pid(threads, i)); return printed + fprintf(fp, "\n"); } @@ -400,9 +339,9 @@ static int get_comm(char **comm, pid_t pid) return err; } -static void comm_init(struct thread_map *map, int i) +static void comm_init(struct perf_thread_map *map, int i) { - pid_t pid = thread_map__pid(map, i); + pid_t pid = perf_thread_map__pid(map, i); char *comm = NULL; /* dummy pid comm initialization */ @@ -421,7 +360,7 @@ static void comm_init(struct thread_map *map, int i) map->map[i].comm = comm; } -void thread_map__read_comms(struct thread_map *threads) +void thread_map__read_comms(struct perf_thread_map *threads) { int i; @@ -429,24 +368,24 @@ void thread_map__read_comms(struct thread_map *threads) comm_init(threads, i); } -static void thread_map__copy_event(struct thread_map *threads, - struct thread_map_event *event) +static void thread_map__copy_event(struct perf_thread_map *threads, + struct perf_record_thread_map *event) { unsigned i; threads->nr = (int) event->nr; for (i = 0; i < event->nr; i++) { - thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid); + perf_thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid); threads->map[i].comm = strndup(event->entries[i].comm, 16); } refcount_set(&threads->refcnt, 1); } -struct thread_map *thread_map__new_event(struct thread_map_event *event) +struct perf_thread_map *thread_map__new_event(struct perf_record_thread_map *event) { - struct thread_map *threads; + struct perf_thread_map *threads; threads = thread_map__alloc(event->nr); if (threads) @@ -455,7 +394,7 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event) return threads; } -bool thread_map__has(struct thread_map *threads, pid_t pid) +bool thread_map__has(struct perf_thread_map *threads, pid_t pid) { int i; @@ -467,7 +406,7 @@ bool thread_map__has(struct thread_map *threads, pid_t pid) return false; } -int thread_map__remove(struct thread_map *threads, int idx) +int thread_map__remove(struct perf_thread_map *threads, int idx) { int i; diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 2f689c90a8c6..3bb860a32b8e 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -5,61 +5,27 @@ #include <sys/types.h> #include <stdio.h> #include <linux/refcount.h> +#include <internal/threadmap.h> +#include <perf/threadmap.h> -struct thread_map_data { - pid_t pid; - char *comm; -}; +struct perf_record_thread_map; -struct thread_map { - refcount_t refcnt; - int nr; - int err_thread; - struct thread_map_data map[]; -}; +struct perf_thread_map *thread_map__new_dummy(void); +struct perf_thread_map *thread_map__new_by_pid(pid_t pid); +struct perf_thread_map *thread_map__new_by_tid(pid_t tid); +struct perf_thread_map *thread_map__new_by_uid(uid_t uid); +struct perf_thread_map *thread_map__new_all_cpus(void); +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); +struct perf_thread_map *thread_map__new_event(struct perf_record_thread_map *event); -struct thread_map_event; - -struct thread_map *thread_map__new_dummy(void); -struct thread_map *thread_map__new_by_pid(pid_t pid); -struct thread_map *thread_map__new_by_tid(pid_t tid); -struct thread_map *thread_map__new_by_uid(uid_t uid); -struct thread_map *thread_map__new_all_cpus(void); -struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); -struct thread_map *thread_map__new_event(struct thread_map_event *event); - -struct thread_map *thread_map__get(struct thread_map *map); -void thread_map__put(struct thread_map *map); - -struct thread_map *thread_map__new_str(const char *pid, +struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid, bool all_threads); -struct thread_map *thread_map__new_by_tid_str(const char *tid_str); - -size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); - -static inline int thread_map__nr(struct thread_map *threads) -{ - return threads ? threads->nr : 1; -} - -static inline pid_t thread_map__pid(struct thread_map *map, int thread) -{ - return map->map[thread].pid; -} - -static inline void -thread_map__set_pid(struct thread_map *map, int thread, pid_t pid) -{ - map->map[thread].pid = pid; -} +struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str); -static inline char *thread_map__comm(struct thread_map *map, int thread) -{ - return map->map[thread].comm; -} +size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp); -void thread_map__read_comms(struct thread_map *threads); -bool thread_map__has(struct thread_map *threads, pid_t pid); -int thread_map__remove(struct thread_map *threads, int idx); +void thread_map__read_comms(struct perf_thread_map *threads); +bool thread_map__has(struct perf_thread_map *threads, pid_t pid); +int thread_map__remove(struct perf_thread_map *threads, int idx); #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index c2abc259b51d..302443921681 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -10,7 +10,6 @@ #include <math.h> #include <linux/ctype.h> -#include "perf.h" #include "debug.h" #include "time-utils.h" #include "session.h" @@ -459,10 +458,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, return true; } -int perf_time__parse_for_ranges(const char *time_str, +int perf_time__parse_for_ranges_reltime(const char *time_str, struct perf_session *session, struct perf_time_interval **ranges, - int *range_size, int *range_num) + int *range_size, int *range_num, + bool reltime) { bool has_percent = strchr(time_str, '%'); struct perf_time_interval *ptime_range; @@ -472,7 +472,7 @@ int perf_time__parse_for_ranges(const char *time_str, if (!ptime_range) return -ENOMEM; - if (has_percent) { + if (has_percent || reltime) { if (session->evlist->first_sample_time == 0 && session->evlist->last_sample_time == 0) { pr_err("HINT: no first/last sample time found in perf data.\n" @@ -480,7 +480,9 @@ int perf_time__parse_for_ranges(const char *time_str, "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n"); goto error; } + } + if (has_percent) { num = perf_time__percent_parse_str( ptime_range, size, time_str, @@ -493,6 +495,15 @@ int perf_time__parse_for_ranges(const char *time_str, if (num < 0) goto error_invalid; + if (reltime) { + int i; + + for (i = 0; i < num; i++) { + ptime_range[i].start += session->evlist->first_sample_time; + ptime_range[i].end += session->evlist->first_sample_time; + } + } + *range_size = size; *range_num = num; *ranges = ptime_range; @@ -505,6 +516,15 @@ error: return ret; } +int perf_time__parse_for_ranges(const char *time_str, + struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num) +{ + return perf_time__parse_for_ranges_reltime(time_str, session, ranges, + range_size, range_num, false); +} + int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) { u64 sec = timestamp / NSEC_PER_SEC; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index 72a42ea1d513..1142b0bddd5e 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -3,6 +3,7 @@ #define _TIME_UTILS_H_ #include <stddef.h> +#include <time.h> #include <linux/types.h> struct perf_time_interval { @@ -25,6 +26,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf, struct perf_session; +int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session, + struct perf_time_interval **ranges, + int *range_size, int *range_num, + bool reltime); + int perf_time__parse_for_ranges(const char *str, struct perf_session *session, struct perf_time_interval **ranges, int *range_size, int *range_num); @@ -34,4 +40,12 @@ int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz); int fetch_current_timestamp(char *buf, size_t sz); +static inline unsigned long long rdclock(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ULL + ts.tv_nsec; +} + #endif diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 9096a6e3de59..2abbf668b8de 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -8,8 +8,8 @@ struct perf_session; union perf_event; -struct perf_evlist; -struct perf_evsel; +struct evlist; +struct evsel; struct perf_sample; struct perf_tool; struct machine; @@ -17,14 +17,14 @@ struct ordered_events; typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, struct machine *machine); + struct evsel *evsel, struct machine *machine); typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); typedef int (*event_attr_op)(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); typedef int (*event_op2)(struct perf_session *session, union perf_event *event); typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event); @@ -56,7 +56,7 @@ struct perf_tool { throttle, unthrottle, ksymbol, - bpf_event; + bpf; event_attr_op attr; event_attr_op event_update; diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 251bbf124fb0..3dce2de9d005 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -5,13 +5,13 @@ * Refactored from builtin-top.c, see that files for further copyright notes. */ -#include "cpumap.h" #include "event.h" #include "evlist.h" #include "evsel.h" #include "parse-events.h" #include "symbol.h" #include "top.h" +#include "../perf.h" #include <inttypes.h> #define SNPRINTF(buf, size, fmt, args...) \ @@ -70,10 +70,10 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) esamples_percent); } - if (top->evlist->nr_entries == 1) { - struct perf_evsel *first = perf_evlist__first(top->evlist); + if (top->evlist->core.nr_entries == 1) { + struct evsel *first = evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", - (uint64_t)first->attr.sample_period, + (uint64_t)first->core.attr.sample_period, opts->freq ? "Hz" : ""); } @@ -95,15 +95,15 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - top->evlist->cpus->nr > 1 ? "s" : "", + top->evlist->core.cpus->nr > 1 ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - top->evlist->cpus->nr, - top->evlist->cpus->nr > 1 ? "s" : ""); + top->evlist->core.cpus->nr, + top->evlist->core.cpus->nr > 1 ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 19f95eaf75c8..f117d4f4821e 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -3,21 +3,25 @@ #define __PERF_TOP_H 1 #include "tool.h" +#include "evswitch.h" #include "annotate.h" +#include "ordered-events.h" +#include "record.h" #include <linux/types.h> #include <stddef.h> #include <stdbool.h> #include <sys/ioctl.h> -struct perf_evlist; -struct perf_evsel; +struct evlist; +struct evsel; struct perf_session; struct perf_top { struct perf_tool tool; - struct perf_evlist *evlist; + struct evlist *evlist; struct record_opts record_opts; struct annotation_options annotation_opts; + struct evswitch evswitch; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -33,7 +37,7 @@ struct perf_top { bool vmlinux_warned; bool dump_symtab; struct hist_entry *sym_filter_entry; - struct perf_evsel *sym_evsel; + struct evsel *sym_evsel; struct perf_session *session; struct winsize winsize; int realtime_prio; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 4550015b9d5d..086e98ff42a3 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -2,7 +2,6 @@ /* * Copyright (C) 2008,2009, Steven Rostedt <srostedt@redhat.com> */ -#include "util.h" #include <dirent.h> #include <mntent.h> #include <stdio.h> @@ -19,8 +18,8 @@ #include <linux/list.h> #include <linux/kernel.h> #include <linux/zalloc.h> +#include <internal/lib.h> // page_size -#include "../perf.h" #include "trace-event.h" #include <api/fs/tracing_path.h> #include "evsel.h" @@ -405,11 +404,11 @@ static struct tracepoint_path * get_tracepoints_path(struct list_head *pattrs) { struct tracepoint_path path, *ppath = &path; - struct perf_evsel *pos; + struct evsel *pos; int nr_tracepoints = 0; - list_for_each_entry(pos, pattrs, node) { - if (pos->attr.type != PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, core.node) { + if (pos->core.attr.type != PERF_TYPE_TRACEPOINT) continue; ++nr_tracepoints; @@ -425,7 +424,7 @@ get_tracepoints_path(struct list_head *pattrs) } try_id: - ppath->next = tracepoint_id_to_path(pos->attr.config); + ppath->next = tracepoint_id_to_path(pos->core.attr.config); if (!ppath->next) { error: pr_debug("No memory to alloc tracepoints list\n"); @@ -441,10 +440,10 @@ next: bool have_tracepoints(struct list_head *pattrs) { - struct perf_evsel *pos; + struct evsel *pos; - list_for_each_entry(pos, pattrs, node) - if (pos->attr.type == PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, core.node) + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT) return true; return false; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index b3982e1bb4c5..9634f0ae57be 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -7,7 +7,6 @@ #include <string.h> #include <errno.h> -#include "../perf.h" #include "debug.h" #include "trace-event.h" @@ -110,7 +109,7 @@ void event_format__fprintf(struct tep_event *event, record.data = data; trace_seq_init(&s); - tep_event_info(&s, event, &record); + tep_print_event(event->tep, &s, &record, "%s", TEP_PRINT_INFO); trace_seq_do_fprintf(&s, fp); trace_seq_destroy(&s); } @@ -174,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent, return tep_parse_event(pevent, buf, size, sys); } -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event) -{ - static int idx; - int events_count; - struct tep_event *all_events; - - all_events = tep_get_first_event(pevent); - events_count = tep_get_events_count(pevent); - if (!pevent || !all_events || events_count < 1) - return NULL; - - if (!event) { - idx = 0; - return all_events; - } - - if (idx < events_count && event == (all_events + idx)) { - idx++; - if (idx == events_count) - return NULL; - return (all_events + idx); - } - - for (idx = 1; idx < events_count; idx++) { - if (event == (all_events + (idx - 1))) - return (all_events + idx); - } - return NULL; -} - struct flag { const char *name; unsigned long long value; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 13c1cf60d1bc..8593d3c200c6 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -15,8 +15,6 @@ #include <unistd.h> #include <errno.h> -#include "../perf.h" -#include "util.h" #include "trace-event.h" #include "debug.h" diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index ba58f69777a1..714581b0de65 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -10,7 +10,6 @@ #include <string.h> #include <errno.h> -#include "../perf.h" #include "debug.h" #include "trace-event.h" #include <linux/zalloc.h> @@ -29,7 +28,7 @@ static int stop_script_unsupported(void) static void process_event_unsupported(union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct addr_location *al __maybe_unused) { } diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 01b9d89bf5bf..b3ee651e3d91 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -14,7 +14,6 @@ #include <api/fs/fs.h> #include "trace-event.h" #include "machine.h" -#include "util.h" /* * global trace_event object used by trace_event__tp_format diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index c7002fe11673..72fdf2a3577c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -3,7 +3,6 @@ #define _PERF_UTIL_TRACE_EVENT_H #include <traceevent/event-parse.h> -#include <traceevent/trace-seq.h> #include "parse-events.h" struct machine; @@ -48,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event); unsigned long long read_size(struct tep_event *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); @@ -79,13 +76,13 @@ struct scripting_ops { int (*stop_script) (void); void (*process_event) (union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al); void (*process_switch)(union perf_event *event, struct perf_sample *sample, struct machine *machine); void (*process_stat)(struct perf_stat_config *config, - struct perf_evsel *evsel, u64 tstamp); + struct evsel *evsel, u64 tstamp); void (*process_stat_interval)(u64 tstamp); int (*generate_script) (struct tep_handle *pevent, const char *outfile); }; diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index 88223bc7c82b..33e997f9ccc8 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -2,7 +2,6 @@ #ifndef __TRIGGER_H_ #define __TRIGGER_H_ 1 -#include "util/debug.h" #include "asm/bug.h" /* diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index e0c3af34ac8d..3c5a632ee57c 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -4,13 +4,12 @@ #include <linux/types.h> -#include "event.h" - struct perf_tsc_conversion { u16 time_shift; u32 time_mult; u64 time_zero; }; + struct perf_event_mmap_page; int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, @@ -20,13 +19,4 @@ u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); u64 rdtsc(void); -struct perf_event_mmap_page; -struct perf_tool; -struct machine; - -int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, - struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); - -#endif +#endif // __PERF_TSC_H diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 28f71ca6ce1c..7a3dbc259cec 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -5,6 +5,7 @@ #include <inttypes.h> #include <errno.h> #include "debug.h" +#include "dso.h" #include "unwind.h" #include "unwind-libdw.h" #include "machine.h" @@ -16,7 +17,6 @@ #include "event.h" #include "perf_regs.h" #include "callchain.h" -#include "util.h" static char *debuginfo_path; @@ -80,9 +80,10 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; - e->map = al.map; - e->sym = al.sym; + e->ip = ip; + e->ms.maps = al.maps; + e->ms.map = al.map; + e->ms.sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", @@ -199,7 +200,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info *ui, ui_buf = { .sample = data, .thread = thread, - .machine = thread->mg->machine, + .machine = thread->maps->machine, .cb = cb, .arg = arg, .max_stack = max_stack, diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a788921b62..b4649f5a0c2f 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -37,7 +37,6 @@ #include "unwind.h" #include "map.h" #include "symbol.h" -#include "util.h" #include "debug.h" #include "asm/bug.h" #include "dso.h" @@ -576,9 +575,10 @@ static int entry(u64 ip, struct thread *thread, struct unwind_entry e; struct addr_location al; - e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); - e.ip = ip; - e.map = al.map; + e.ms.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); + e.ip = ip; + e.ms.map = al.map; + e.ms.maps = al.maps; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", @@ -616,26 +616,26 @@ static unw_accessors_t accessors = { .get_proc_name = get_proc_name, }; -static int _unwind__prepare_access(struct thread *thread) +static int _unwind__prepare_access(struct maps *maps) { - thread->addr_space = unw_create_addr_space(&accessors, 0); - if (!thread->addr_space) { + maps->addr_space = unw_create_addr_space(&accessors, 0); + if (!maps->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); + unw_set_caching_policy(maps->addr_space, UNW_CACHE_GLOBAL); return 0; } -static void _unwind__flush_access(struct thread *thread) +static void _unwind__flush_access(struct maps *maps) { - unw_flush_cache(thread->addr_space, 0, 0); + unw_flush_cache(maps->addr_space, 0, 0); } -static void _unwind__finish_access(struct thread *thread) +static void _unwind__finish_access(struct maps *maps) { - unw_destroy_addr_space(thread->addr_space); + unw_destroy_addr_space(maps->addr_space); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -660,7 +660,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, */ if (max_stack - 1 > 0) { WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); - addr_space = ui->thread->addr_space; + addr_space = ui->thread->maps->addr_space; if (addr_space == NULL) return -1; @@ -709,7 +709,7 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info ui = { .sample = data, .thread = thread, - .machine = thread->mg->machine, + .machine = thread->maps->machine, }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index c0811977d7d5..e89a5479b361 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "unwind.h" +#include "dso.h" #include "map.h" #include "thread.h" #include "session.h" @@ -11,14 +12,12 @@ struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops; -static void unwind__register_ops(struct thread *thread, - struct unwind_libunwind_ops *ops) +static void unwind__register_ops(struct maps *maps, struct unwind_libunwind_ops *ops) { - thread->unwind_libunwind_ops = ops; + maps->unwind_libunwind_ops = ops; } -int unwind__prepare_access(struct thread *thread, struct map *map, - bool *initialized) +int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized) { const char *arch; enum dso_type dso_type; @@ -28,7 +27,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map, if (!dwarf_callchain_users) return 0; - if (thread->addr_space) { + if (maps->addr_space) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); if (initialized) @@ -37,14 +36,14 @@ int unwind__prepare_access(struct thread *thread, struct map *map, } /* env->arch is NULL for live-mode (i.e. perf top) */ - if (!thread->mg->machine->env || !thread->mg->machine->env->arch) + if (!maps->machine->env || !maps->machine->env->arch) goto out_register; - dso_type = dso__type(map->dso, thread->mg->machine); + dso_type = dso__type(map->dso, maps->machine); if (dso_type == DSO__TYPE_UNKNOWN) return 0; - arch = perf_env__arch(thread->mg->machine->env); + arch = perf_env__arch(maps->machine->env); if (!strcmp(arch, "x86")) { if (dso_type != DSO__TYPE_64BIT) @@ -59,37 +58,31 @@ int unwind__prepare_access(struct thread *thread, struct map *map, return 0; } out_register: - unwind__register_ops(thread, ops); + unwind__register_ops(maps, ops); - err = thread->unwind_libunwind_ops->prepare_access(thread); + err = maps->unwind_libunwind_ops->prepare_access(maps); if (initialized) *initialized = err ? false : true; return err; } -void unwind__flush_access(struct thread *thread) +void unwind__flush_access(struct maps *maps) { - if (!dwarf_callchain_users) - return; - - if (thread->unwind_libunwind_ops) - thread->unwind_libunwind_ops->flush_access(thread); + if (maps->unwind_libunwind_ops) + maps->unwind_libunwind_ops->flush_access(maps); } -void unwind__finish_access(struct thread *thread) +void unwind__finish_access(struct maps *maps) { - if (!dwarf_callchain_users) - return; - - if (thread->unwind_libunwind_ops) - thread->unwind_libunwind_ops->finish_access(thread); + if (maps->unwind_libunwind_ops) + maps->unwind_libunwind_ops->finish_access(maps); } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack) { - if (thread->unwind_libunwind_ops) - return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + if (thread->maps->unwind_libunwind_ops) + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 8a44a1569a21..ab8ad469c8de 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -4,24 +4,23 @@ #include <linux/compiler.h> #include <linux/types.h> +#include "util/map_symbol.h" -struct map; +struct maps; struct perf_sample; -struct symbol; struct thread; struct unwind_entry { - struct map *map; - struct symbol *sym; - u64 ip; + struct map_symbol ms; + u64 ip; }; typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); struct unwind_libunwind_ops { - int (*prepare_access)(struct thread *thread); - void (*flush_access)(struct thread *thread); - void (*finish_access)(struct thread *thread); + int (*prepare_access)(struct maps *maps); + void (*flush_access)(struct maps *maps); + void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack); @@ -46,20 +45,19 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, #endif int LIBUNWIND__ARCH_REG_ID(int regnum); -int unwind__prepare_access(struct thread *thread, struct map *map, - bool *initialized); -void unwind__flush_access(struct thread *thread); -void unwind__finish_access(struct thread *thread); +int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized); +void unwind__flush_access(struct maps *maps); +void unwind__finish_access(struct maps *maps); #else -static inline int unwind__prepare_access(struct thread *thread __maybe_unused, +static inline int unwind__prepare_access(struct maps *maps __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} -static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} +static inline void unwind__flush_access(struct maps *maps __maybe_unused) {} +static inline void unwind__finish_access(struct maps *maps __maybe_unused) {} #endif #else static inline int @@ -72,14 +70,14 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, return 0; } -static inline int unwind__prepare_access(struct thread *thread __maybe_unused, +static inline int unwind__prepare_access(struct maps *maps __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} -static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} +static inline void unwind__flush_access(struct maps *maps __maybe_unused) {} +static inline void unwind__finish_access(struct maps *maps __maybe_unused) {} #endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 3949a60b00ae..196438ee4c9d 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -8,7 +8,6 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "util.h" -#include "debug.h" #include <stdio.h> #include <stdlib.h> #include <linux/compiler.h> diff --git a/tools/perf/util/util-cxx.h b/tools/perf/util/util-cxx.h deleted file mode 100644 index 80a99e458d4e..000000000000 --- a/tools/perf/util/util-cxx.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Support C++ source use utilities defined in util.h - */ - -#ifndef PERF_UTIL_UTIL_CXX_H -#define PERF_UTIL_UTIL_CXX_H - -#ifdef __cplusplus -extern "C" { -#endif - -/* - * Now 'new' is the only C++ keyword found in util.h: - * in tools/include/linux/rbtree.h - * - * Other keywords, like class and delete, should be - * redefined if necessary. - */ -#define new _new -#include "util.h" -#undef new - -#ifdef __cplusplus -} -#endif -#endif diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index a61535cf1bca..969ae560dad9 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,10 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../perf.h" #include "util.h" #include "debug.h" -#include "namespaces.h" +#include "event.h" #include <api/fs/fs.h> -#include <sys/mman.h> #include <sys/stat.h> #include <sys/utsname.h> #include <dirent.h> @@ -16,10 +14,12 @@ #include <string.h> #include <errno.h> #include <limits.h> +#include <linux/capability.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/time64.h> #include <unistd.h> +#include "cap.h" #include "strlist.h" #include "string2.h" @@ -39,28 +39,6 @@ void perf_set_multithreaded(void) perf_singlethreaded = false; } -unsigned int page_size; - -#ifdef _SC_LEVEL1_DCACHE_LINESIZE -#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) -#else -static void cache_line_size(int *cacheline_sizep) -{ - if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) - pr_debug("cannot determine cache line size"); -} -#endif - -int cacheline_size(void) -{ - static int size; - - if (!size) - cache_line_size(&size); - - return size; -} - int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; @@ -176,8 +154,10 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) continue; - if (!match_pat(d->d_name, pat)) - return -2; + if (!match_pat(d->d_name, pat)) { + ret = -2; + break; + } scnprintf(namebuf, sizeof(namebuf), "%s/%s", path, d->d_name); @@ -202,14 +182,31 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) return rmdir(path); } +static int rm_rf_kcore_dir(const char *path) +{ + char kcore_dir_path[PATH_MAX]; + const char *pat[] = { + "kcore", + "kallsyms", + "modules", + NULL, + }; + + snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path); + + return rm_rf_depth_pat(kcore_dir_path, 0, pat); +} + int rm_rf_perf_data(const char *path) { const char *pat[] = { - "header", + "data", "data.*", NULL, }; + rm_rf_kcore_dir(path); + return rm_rf_depth_pat(path, 0, pat); } @@ -252,178 +249,6 @@ out: return list; } -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, *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; - - to_fp = fopen(to, "w"); - if (to_fp == NULL) - goto out_fclose_from; - - while (getline(&line, &n, from_fp) > 0) - if (fputs(line, to_fp) == EOF) - goto out_fclose_to; - err = 0; -out_fclose_to: - fclose(to_fp); - free(line); -out_fclose_from: - fclose(from_fp); -out: - return err; -} - -int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) -{ - void *ptr; - loff_t pgoff; - - pgoff = off_in & ~(page_size - 1); - off_in -= pgoff; - - ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff); - if (ptr == MAP_FAILED) - return -1; - - while (size) { - ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out); - if (ret < 0 && errno == EINTR) - continue; - if (ret <= 0) - break; - - size -= ret; - off_in += ret; - off_out += ret; - } - munmap(ptr, off_in + size); - - return size ? -1 : 0; -} - -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; - char *tmp = NULL, *ptr = NULL; - struct nscookie nsc; - - 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) { - tmp = NULL; - goto out; - } - ptr = strrchr(tmp, '/'); - if (!ptr) - goto out; - ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1); - *ptr = '.'; - - tofd = mkstemp(tmp); - if (tofd < 0) - goto out; - - if (fchmod(tofd, mode)) - goto out_close_to; - - if (st.st_size == 0) { /* /proc? do it slowly... */ - err = slow_copyfile(from, tmp, nsi); - 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; - - err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size); - - close(fromfd); -out_close_to: - close(tofd); - if (!err) - err = link(tmp, to); - unlink(tmp); -out: - free(tmp); - 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); -} - -static ssize_t ion(bool is_read, int fd, void *buf, size_t n) -{ - void *buf_start = buf; - 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); - - if (ret < 0 && errno == EINTR) - continue; - if (ret <= 0) - return ret; - - left -= ret; - buf += ret; - } - - BUG_ON((size_t)(buf - buf_start) != n); - return n; -} - -/* - * Read exactly 'n' bytes or return an error. - */ -ssize_t readn(int fd, void *buf, size_t n) -{ - return ion(true, fd, buf, n); -} - -/* - * Write exactly 'n' bytes or return an error. - */ -ssize_t writen(int fd, const void *buf, size_t n) -{ - /* ion does not modify buf. */ - return ion(false, fd, (void *)buf, n); -} - size_t hex_width(u64 v) { size_t n = 1; @@ -443,6 +268,13 @@ int perf_event_paranoid(void) return value; } + +bool perf_event_paranoid_check(int max_level) +{ + return perf_cap__capable(CAP_SYS_ADMIN) || + perf_event_paranoid() <= max_level; +} + static int fetch_ubuntu_kernel_version(unsigned int *puint) { diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index dc7a469921e9..9969b8b46f7c 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -17,7 +17,6 @@ void usage(const char *err) __noreturn; void die(const char *err, ...) __noreturn __printf(1, 2); struct dirent; -struct nsinfo; struct strlist; int mkdir_p(char *path, mode_t mode); @@ -25,19 +24,9 @@ int rm_rf(const char *path); int rm_rf_perf_data(const char *path); struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); bool lsdir_no_dot_filter(const char *name, struct dirent *d); -int copyfile(const char *from, const char *to); -int copyfile_mode(const char *from, const char *to, mode_t mode); -int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); -int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); - -ssize_t readn(int fd, void *buf, size_t n); -ssize_t writen(int fd, const void *buf, size_t n); size_t hex_width(u64 v); -extern unsigned int page_size; -int __pure cacheline_size(void); - int sysctl__max_stack(void); int fetch_kernel_version(unsigned int *puint, diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index c59154e2d124..b9823f414f10 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -2,6 +2,7 @@ #include <inttypes.h> #include <stdio.h> #include <stdlib.h> +#include <string.h> #include <errno.h> #include <linux/zalloc.h> diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 7f427bab6c12..3cc91ad048ea 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -10,7 +10,8 @@ #include <linux/kernel.h> #include "vdso.h" -#include "util.h" +#include "dso.h" +#include <internal/lib.h> #include "map.h" #include "symbol.h" #include "machine.h" @@ -141,9 +142,9 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { enum dso_type dso_type = DSO__TYPE_UNKNOWN; - struct map *map = map_groups__first(thread->mg); + struct map *map; - for (; map ; map = map_groups__next(map)) { + maps__for_each_entry(thread->maps, map) { struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h deleted file mode 100644 index 7ffe562e7ae7..000000000000 --- a/tools/perf/util/xyarray.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PERF_XYARRAY_H_ -#define _PERF_XYARRAY_H_ 1 - -#include <sys/types.h> - -struct xyarray { - size_t row_size; - size_t entry_size; - size_t entries; - size_t max_x; - size_t max_y; - char contents[]; -}; - -struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size); -void xyarray__delete(struct xyarray *xy); -void xyarray__reset(struct xyarray *xy); - -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 512ad7c09b13..78d2297c1b67 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -1,16 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include <fcntl.h> #include <stdio.h> +#include <string.h> #include <unistd.h> #include <sys/stat.h> #include <sys/mman.h> #include <zlib.h> #include <linux/compiler.h> +#include <internal/lib.h> #include "util/compress.h" -#include "util/util.h" -#include "util/debug.h" - #define CHUNK_SIZE 16384 |
