diff options
Diffstat (limited to 'tools/perf/util')
68 files changed, 2378 insertions, 759 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index d2d318c59b37..1ce0adc8b3cb 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -14,6 +14,7 @@ libperf-y += find_next_bit.o libperf-y += help.o libperf-y += kallsyms.o libperf-y += levenshtein.o +libperf-y += llvm-utils.o libperf-y += parse-options.o libperf-y += parse-events.o libperf-y += path.o @@ -67,6 +68,7 @@ libperf-y += target.o libperf-y += rblist.o libperf-y += intlist.o libperf-y += vdso.o +libperf-y += counts.o libperf-y += stat.o libperf-y += stat-shadow.o libperf-y += record.o @@ -79,6 +81,7 @@ libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-y += parse-branch-options.o libperf-$(CONFIG_LIBELF) += symbol-elf.o +libperf-$(CONFIG_LIBELF) += probe-file.o libperf-$(CONFIG_LIBELF) += probe-event.o ifndef CONFIG_LIBELF diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 03b7bc70eb66..e0b614648044 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -473,17 +473,73 @@ int symbol__alloc_hist(struct symbol *sym) return 0; } +/* The cycles histogram is lazily allocated. */ +static int symbol__alloc_hist_cycles(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + const size_t size = symbol__size(sym); + + notes->src->cycles_hist = calloc(size, sizeof(struct cyc_hist)); + if (notes->src->cycles_hist == NULL) + return -1; + return 0; +} + void symbol__annotate_zero_histograms(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); pthread_mutex_lock(¬es->lock); - if (notes->src != NULL) + if (notes->src != NULL) { memset(notes->src->histograms, 0, notes->src->nr_histograms * notes->src->sizeof_sym_hist); + if (notes->src->cycles_hist) + memset(notes->src->cycles_hist, 0, + symbol__size(sym) * sizeof(struct cyc_hist)); + } pthread_mutex_unlock(¬es->lock); } +static int __symbol__account_cycles(struct annotation *notes, + u64 start, + unsigned offset, unsigned cycles, + unsigned have_start) +{ + struct cyc_hist *ch; + + ch = notes->src->cycles_hist; + /* + * For now we can only account one basic block per + * final jump. But multiple could be overlapping. + * Always account the longest one. So when + * a shorter one has been already seen throw it away. + * + * We separately always account the full cycles. + */ + ch[offset].num_aggr++; + ch[offset].cycles_aggr += cycles; + + if (!have_start && ch[offset].have_start) + return 0; + if (ch[offset].num) { + if (have_start && (!ch[offset].have_start || + ch[offset].start > start)) { + ch[offset].have_start = 0; + ch[offset].cycles = 0; + ch[offset].num = 0; + if (ch[offset].reset < 0xffff) + ch[offset].reset++; + } else if (have_start && + ch[offset].start < start) + return 0; + } + ch[offset].have_start = have_start; + ch[offset].start = start; + ch[offset].cycles += cycles; + ch[offset].num++; + return 0; +} + static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, struct annotation *notes, int evidx, u64 addr) { @@ -506,7 +562,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, return 0; } -static struct annotation *symbol__get_annotation(struct symbol *sym) +static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles) { struct annotation *notes = symbol__annotation(sym); @@ -514,6 +570,10 @@ static struct annotation *symbol__get_annotation(struct symbol *sym) if (symbol__alloc_hist(sym) < 0) return NULL; } + if (!notes->src->cycles_hist && cycles) { + if (symbol__alloc_hist_cycles(sym) < 0) + return NULL; + } return notes; } @@ -524,12 +584,73 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, if (sym == NULL) return 0; - notes = symbol__get_annotation(sym); + notes = symbol__get_annotation(sym, false); if (notes == NULL) return -ENOMEM; return __symbol__inc_addr_samples(sym, map, notes, evidx, addr); } +static int symbol__account_cycles(u64 addr, u64 start, + struct symbol *sym, unsigned cycles) +{ + struct annotation *notes; + unsigned offset; + + if (sym == NULL) + return 0; + notes = symbol__get_annotation(sym, true); + if (notes == NULL) + return -ENOMEM; + if (addr < sym->start || addr >= sym->end) + return -ERANGE; + + if (start) { + if (start < sym->start || start >= sym->end) + return -ERANGE; + if (start >= addr) + start = 0; + } + offset = addr - sym->start; + return __symbol__account_cycles(notes, + start ? start - sym->start : 0, + offset, cycles, + !!start); +} + +int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, + struct addr_map_symbol *start, + unsigned cycles) +{ + unsigned long saddr = 0; + int err; + + if (!cycles) + return 0; + + /* + * Only set start when IPC can be computed. We can only + * compute it when the basic block is completely in a single + * function. + * Special case the case when the jump is elsewhere, but + * it starts on the function start. + */ + if (start && + (start->sym == ams->sym || + (ams->sym && + start->addr == ams->sym->start + ams->map->start))) + saddr = start->al_addr; + if (saddr == 0) + pr_debug2("BB with bad start: addr %lx start %lx sym %lx saddr %lx\n", + ams->addr, + start ? start->addr : 0, + ams->sym ? ams->sym->start + ams->map->start : 0, + saddr); + err = symbol__account_cycles(ams->al_addr, saddr, ams->sym, cycles); + if (err) + pr_debug2("account_cycles failed %d\n", err); + return err; +} + int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx) { return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 7e78e6c27078..e9996092a093 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -59,6 +59,8 @@ struct disasm_line { char *name; struct ins *ins; int line_nr; + float ipc; + u64 cycles; struct ins_operands ops; }; @@ -79,6 +81,17 @@ struct sym_hist { u64 addr[0]; }; +struct cyc_hist { + u64 start; + u64 cycles; + u64 cycles_aggr; + u32 num; + u32 num_aggr; + u8 have_start; + /* 1 byte padding */ + u16 reset; +}; + struct source_line_samples { double percent; double percent_sum; @@ -97,6 +110,7 @@ struct source_line { * @histogram: Array of addr hit histograms per event being monitored * @lines: If 'print_lines' is specified, per source code line percentages * @source: source parsed from a disassembler like objdump -dS + * @cyc_hist: Average cycles per basic block * * lines is allocated, percentages calculated and all sorted by percentage * when the annotation is about to be presented, so the percentages are for @@ -109,6 +123,7 @@ struct annotated_source { struct source_line *lines; int nr_histograms; int sizeof_sym_hist; + struct cyc_hist *cycles_hist; struct sym_hist histograms[0]; }; @@ -130,6 +145,10 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); +int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, + struct addr_map_symbol *start, + unsigned cycles); + int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 83d9dd96fe08..a25b3609cef8 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -942,6 +942,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, struct itrace_synth_opts *synth_opts = opt->value; const char *p; char *endptr; + bool period_type_set = false; synth_opts->set = true; @@ -970,10 +971,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'i': synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS; + period_type_set = true; break; case 't': synth_opts->period_type = PERF_ITRACE_PERIOD_TICKS; + period_type_set = true; break; case 'm': synth_opts->period *= 1000; @@ -986,6 +989,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, goto out_err; synth_opts->period_type = PERF_ITRACE_PERIOD_NANOSECS; + period_type_set = true; break; case '\0': goto out; @@ -1039,7 +1043,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, } out: if (synth_opts->instructions) { - if (!synth_opts->period_type) + if (!period_type_set) synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; if (!synth_opts->period) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 1f6fc2323ef9..4a2c2f0ead41 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -124,7 +124,7 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size) char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) { - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + char build_id_hex[SBUILD_ID_SIZE]; if (!dso->has_build_id) return NULL; @@ -291,7 +291,7 @@ int build_id_cache__list_build_ids(const char *pathname, struct dirent *d; int ret = 0; - list = strlist__new(true, NULL); + list = strlist__new(NULL, NULL); dir_name = build_id_cache__dirname_from_path(pathname, false, false); if (!list || !dir_name) { ret = -ENOMEM; @@ -384,7 +384,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, const char *name, bool is_kallsyms, bool is_vdso) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; build_id__sprintf(build_id, build_id_size, sbuild_id); diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 85011222cc14..ce2f493f057a 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -1,7 +1,8 @@ #ifndef PERF_BUILD_ID_H_ #define PERF_BUILD_ID_H_ 1 -#define BUILD_ID_SIZE 20 +#define BUILD_ID_SIZE 20 +#define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" #include "strlist.h" diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 9f643ee77001..773fe13ce627 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,96 +25,9 @@ __thread struct callchain_cursor callchain_cursor; -#ifdef HAVE_DWARF_UNWIND_SUPPORT -static int get_stack_size(const char *str, unsigned long *_size) -{ - char *endptr; - unsigned long size; - unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - - size = strtoul(str, &endptr, 0); - - do { - if (*endptr) - break; - - size = round_up(size, sizeof(u64)); - if (!size || size > max_size) - break; - - *_size = size; - return 0; - - } while (0); - - pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", - max_size, str); - return -1; -} -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - -int parse_callchain_record_opt(const char *arg) +int parse_callchain_record_opt(const char *arg, struct callchain_param *param) { - char *tok, *name, *saveptr = NULL; - char *buf; - int ret = -1; - - /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); - if (!buf) - return -ENOMEM; - - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; - - do { - /* Framepointer style */ - if (!strncmp(name, "fp", sizeof("fp"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - callchain_param.record_mode = CALLCHAIN_FP; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph fp\n"); - break; - -#ifdef HAVE_DWARF_UNWIND_SUPPORT - /* Dwarf style */ - } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { - const unsigned long default_stack_dump_size = 8192; - - ret = 0; - callchain_param.record_mode = CALLCHAIN_DWARF; - callchain_param.dump_size = default_stack_dump_size; - - tok = strtok_r(NULL, ",", &saveptr); - if (tok) { - unsigned long size = 0; - - ret = get_stack_size(tok, &size); - callchain_param.dump_size = size; - } -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - } else if (!strncmp(name, "lbr", sizeof("lbr"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - callchain_param.record_mode = CALLCHAIN_LBR; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph lbr\n"); - break; - } else { - pr_err("callchain: Unknown --call-graph option " - "value: %s\n", arg); - break; - } - - } while (0); - - free(buf); - return ret; + return parse_callchain_record(arg, param); } static int parse_callchain_mode(const char *value) @@ -219,7 +132,7 @@ int perf_callchain_config(const char *var, const char *value) var += sizeof("call-graph.") - 1; if (!strcmp(var, "record-mode")) - return parse_callchain_record_opt(value); + return parse_callchain_record_opt(value, &callchain_param); #ifdef HAVE_DWARF_UNWIND_SUPPORT if (!strcmp(var, "dump-size")) { unsigned long size = 0; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 679c2c6d8ade..acee2b3cd801 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -177,7 +177,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * bool hide_unresolved); extern const char record_callchain_help[]; -int parse_callchain_record_opt(const char *arg); +extern int parse_callchain_record(const char *arg, struct callchain_param *param); +int parse_callchain_record_opt(const char *arg, struct callchain_param *param); int parse_callchain_report_opt(const char *arg); int perf_callchain_config(const char *var, const char *value); diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index 68888c29b04a..3bee6773ddb0 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -4,7 +4,7 @@ unsigned long perf_event_open_cloexec_flag(void); #ifdef __GLIBC_PREREQ -#if !__GLIBC_PREREQ(2, 6) +#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__) extern int sched_getcpu(void) __THROW; #endif #endif diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 55355b3d4f85..9b9565416f90 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -67,8 +67,9 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color, return r; } +/* Colors are not included in return value */ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, - va_list args, const char *trail) + va_list args) { int r = 0; @@ -83,12 +84,10 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, } if (perf_use_color_default && *color) - r += fprintf(fp, "%s", color); + fprintf(fp, "%s", color); r += vfprintf(fp, fmt, args); if (perf_use_color_default && *color) - r += fprintf(fp, "%s", PERF_COLOR_RESET); - if (trail) - r += fprintf(fp, "%s", trail); + fprintf(fp, "%s", PERF_COLOR_RESET); return r; } @@ -100,7 +99,7 @@ int color_vsnprintf(char *bf, size_t size, const char *color, int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args) { - return __color_vfprintf(fp, color, fmt, args, NULL); + return __color_vfprintf(fp, color, fmt, args); } int color_snprintf(char *bf, size_t size, const char *color, @@ -126,16 +125,6 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) return r; } -int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...) -{ - va_list args; - int r; - va_start(args, fmt); - r = __color_vfprintf(fp, color, fmt, args, "\n"); - va_end(args); - return r; -} - /* * This function splits the buffer by newlines and colors the lines individually. * diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 38146f922c54..a93997f16dec 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -35,7 +35,6 @@ int color_vsnprintf(char *bf, size_t size, const char *color, int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args); int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...); -int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); int value_color_snprintf(char *bf, size_t size, const char *fmt, double value); int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index e18f653cd7db..2e452ac1353d 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -12,6 +12,7 @@ #include "cache.h" #include "exec_cmd.h" #include "util/hist.h" /* perf_hist_config */ +#include "util/llvm-utils.h" /* perf_llvm_config */ #define MAXNAME (256) @@ -408,6 +409,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "call-graph.")) return perf_callchain_config(var, value); + if (!prefixcmp(var, "llvm.")) + return perf_llvm_config(var, value); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c new file mode 100644 index 000000000000..e3fde313deb2 --- /dev/null +++ b/tools/perf/util/counts.c @@ -0,0 +1,52 @@ +#include <stdlib.h> +#include "evsel.h" +#include "counts.h" + +struct perf_counts *perf_counts__new(int ncpus, int nthreads) +{ + struct perf_counts *counts = zalloc(sizeof(*counts)); + + if (counts) { + struct xyarray *values; + + values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); + if (!values) { + free(counts); + return NULL; + } + + counts->values = values; + } + + return counts; +} + +void perf_counts__delete(struct perf_counts *counts) +{ + if (counts) { + xyarray__delete(counts->values); + free(counts); + } +} + +static void perf_counts__reset(struct perf_counts *counts) +{ + xyarray__reset(counts->values); +} + +void perf_evsel__reset_counts(struct perf_evsel *evsel) +{ + perf_counts__reset(evsel->counts); +} + +int perf_evsel__alloc_counts(struct perf_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) +{ + perf_counts__delete(evsel->counts); + evsel->counts = NULL; +} diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h new file mode 100644 index 000000000000..34d8baaf558a --- /dev/null +++ b/tools/perf/util/counts.h @@ -0,0 +1,37 @@ +#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]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct xyarray *values; +}; + + +static inline struct perf_counts_values* +perf_counts(struct perf_counts *counts, int cpu, int thread) +{ + return xyarray__entry(counts->values, cpu, thread); +} + +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); + +#endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 2da5581ec74d..86d9c7302598 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -36,6 +36,11 @@ static int _eprintf(int level, int var, const char *fmt, va_list args) return ret; } +int veprintf(int level, int var, const char *fmt, va_list args) +{ + return _eprintf(level, var, fmt, args); +} + int eprintf(int level, int var, const char *fmt, ...) { va_list args; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index caac2fdc6105..8b9a088c32ab 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -50,6 +50,7 @@ void pr_stat(const char *fmt, ...); int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); +int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 2fe98bb0e95b..c73276db6d6f 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -137,6 +137,10 @@ struct dso { struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; + struct { + u64 addr; + struct symbol *symbol; + } last_find_result[MAP__NR_TYPES]; void *a2l; char *symsrc_filename; unsigned int a2l_fails; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 57f3ef41c2bc..445f455dd377 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -734,15 +734,18 @@ 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; + const char *fname, *decf = NULL; int lineno, ret = 0; + int decl = 0, inl; Dwarf_Die die_mem, *cu_die; size_t nlines, i; /* Get the CU die */ - if (dwarf_tag(rt_die) != DW_TAG_compile_unit) + if (dwarf_tag(rt_die) != DW_TAG_compile_unit) { cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL); - else + dwarf_decl_line(rt_die, &decl); + decf = dwarf_decl_file(rt_die); + } else cu_die = rt_die; if (!cu_die) { pr_debug2("Failed to get CU from given DIE.\n"); @@ -773,9 +776,14 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) * The line is included in given function, and * no inline block includes it. */ - if (!dwarf_haspc(rt_die, addr) || - die_find_inlinefunc(rt_die, addr, &die_mem)) + if (!dwarf_haspc(rt_die, addr)) continue; + if (die_find_inlinefunc(rt_die, addr, &die_mem)) { + dwarf_decl_line(&die_mem, &inl); + if (inl != decl || + decf != dwarf_decl_file(&die_mem)) + continue; + } /* Get source line */ fname = dwarf_linesrc(line, NULL, NULL); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 67a977e5d0ab..7ff61274ed57 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -26,6 +26,8 @@ static const char *perf_event__names[] = { [PERF_RECORD_AUX] = "AUX", [PERF_RECORD_ITRACE_START] = "ITRACE_START", [PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES", + [PERF_RECORD_SWITCH] = "SWITCH", + [PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -749,6 +751,14 @@ int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused, return machine__process_lost_samples_event(machine, event, sample); } +int perf_event__process_switch(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_switch_event(machine, event); +} + size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n", @@ -827,6 +837,20 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) event->itrace_start.pid, event->itrace_start.tid); } +size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) +{ + bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; + const char *in_out = out ? "OUT" : "IN "; + + if (event->header.type == PERF_RECORD_SWITCH) + return fprintf(fp, " %s\n", in_out); + + return fprintf(fp, " %s %s pid/tid: %5u/%-5u\n", + in_out, out ? "next" : "prev", + event->context_switch.next_prev_pid, + event->context_switch.next_prev_tid); +} + size_t perf_event__fprintf(union perf_event *event, FILE *fp) { size_t ret = fprintf(fp, "PERF_RECORD_%s", @@ -852,6 +876,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_ITRACE_START: ret += perf_event__fprintf_itrace_start(event, fp); break; + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + ret += perf_event__fprintf_switch(event, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index c53f36384b64..f729df5e25e6 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -134,7 +134,8 @@ struct branch_flags { u64 predicted:1; u64 in_tx:1; u64 abort:1; - u64 reserved:60; + u64 cycles:16; + u64 reserved:44; }; struct branch_entry { @@ -348,6 +349,12 @@ struct itrace_start_event { u32 pid, tid; }; +struct context_switch_event { + struct perf_event_header header; + u32 next_prev_pid; + u32 next_prev_tid; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -369,6 +376,7 @@ union perf_event { struct auxtrace_error_event auxtrace_error; struct aux_event aux; struct itrace_start_event itrace_start; + struct context_switch_event context_switch; }; void perf_event__print_totals(void); @@ -418,6 +426,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_switch(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -480,6 +492,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp); size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); u64 kallsyms__get_function_start(const char *kallsyms_filename, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6cfdee68e763..373f65b02545 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1102,7 +1102,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, } static int perf_evlist__propagate_maps(struct perf_evlist *evlist, - struct target *target) + bool has_user_cpus) { struct perf_evsel *evsel; @@ -1111,15 +1111,16 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (evsel->cpus && target->cpu_list) + if (evsel->cpus && has_user_cpus) cpu_map__put(evsel->cpus); - if (!evsel->cpus || target->cpu_list) + if (!evsel->cpus || has_user_cpus) evsel->cpus = cpu_map__get(evlist->cpus); evsel->threads = thread_map__get(evlist->threads); - if (!evsel->cpus || !evsel->threads) + if ((evlist->cpus && !evsel->cpus) || + (evlist->threads && !evsel->threads)) return -ENOMEM; } @@ -1142,7 +1143,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) if (evlist->cpus == NULL) goto out_delete_threads; - return perf_evlist__propagate_maps(evlist, target); + return perf_evlist__propagate_maps(evlist, !!target->cpu_list); out_delete_threads: thread_map__put(evlist->threads); @@ -1150,6 +1151,23 @@ out_delete_threads: return -1; } +int perf_evlist__set_maps(struct perf_evlist *evlist, + struct cpu_map *cpus, + struct thread_map *threads) +{ + if (evlist->cpus) + cpu_map__put(evlist->cpus); + + evlist->cpus = cpus; + + if (evlist->threads) + thread_map__put(evlist->threads); + + evlist->threads = threads; + + return perf_evlist__propagate_maps(evlist, false); +} + int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) { struct perf_evsel *evsel; @@ -1161,7 +1179,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e if (evsel->filter == NULL) continue; - err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter); + err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter); if (err) { *err_evsel = evsel; break; @@ -1175,11 +1193,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) { struct perf_evsel *evsel; int err = 0; - const int ncpus = cpu_map__nr(evlist->cpus), - nthreads = thread_map__nr(evlist->threads); evlist__for_each(evlist, evsel) { - err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter); + err = perf_evsel__set_filter(evsel, filter); if (err) break; } @@ -1257,6 +1273,16 @@ u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) return __perf_evlist__combined_sample_type(evlist); } +u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + u64 branch_type = 0; + + evlist__for_each(evlist, evsel) + branch_type |= evsel->attr.branch_sample_type; + return branch_type; +} + bool perf_evlist__valid_read_format(struct perf_evlist *evlist) { struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 037633c1da9d..397757063da1 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -114,6 +114,7 @@ void perf_evlist__close(struct perf_evlist *evlist); void perf_evlist__set_id_pos(struct perf_evlist *evlist); bool perf_can_sample_identifier(void); +bool perf_can_record_switch_events(void); void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts); int record_opts__config(struct record_opts *opts); @@ -152,14 +153,9 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist, void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); -static inline void perf_evlist__set_maps(struct perf_evlist *evlist, - struct cpu_map *cpus, - struct thread_map *threads) -{ - evlist->cpus = cpus; - evlist->threads = threads; -} - +int 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); @@ -169,6 +165,7 @@ void perf_evlist__set_leader(struct perf_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); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 2936b3080722..b096ef7a240c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -207,9 +207,11 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->unit = ""; evsel->scale = 1.0; 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); perf_evsel__calc_id_pos(evsel); + evsel->cmdline_group_boundary = false; } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -543,14 +545,15 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) static void perf_evsel__config_callgraph(struct perf_evsel *evsel, - struct record_opts *opts) + struct record_opts *opts, + struct callchain_param *param) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - if (callchain_param.record_mode == CALLCHAIN_LBR) { + if (param->record_mode == CALLCHAIN_LBR) { if (!opts->branch_stack) { if (attr->exclude_user) { pr_warning("LBR callstack option is only available " @@ -566,12 +569,12 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel, "Falling back to framepointers.\n"); } - if (callchain_param.record_mode == CALLCHAIN_DWARF) { + if (param->record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = callchain_param.dump_size; + attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user = 1; } else { pr_info("Cannot use DWARF unwind for function trace event," @@ -585,6 +588,97 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel, } } +static void +perf_evsel__reset_callgraph(struct perf_evsel *evsel, + struct callchain_param *param) +{ + struct perf_event_attr *attr = &evsel->attr; + + perf_evsel__reset_sample_bit(evsel, CALLCHAIN); + if (param->record_mode == CALLCHAIN_LBR) { + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); + attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_CALL_STACK); + } + if (param->record_mode == CALLCHAIN_DWARF) { + perf_evsel__reset_sample_bit(evsel, REGS_USER); + perf_evsel__reset_sample_bit(evsel, STACK_USER); + } +} + +static void apply_config_terms(struct perf_evsel *evsel, + struct record_opts *opts) +{ + struct perf_evsel_config_term *term; + struct list_head *config_terms = &evsel->config_terms; + struct perf_event_attr *attr = &evsel->attr; + struct callchain_param param; + u32 dump_size = 0; + char *callgraph_buf = NULL; + + /* callgraph default */ + param.record_mode = callchain_param.record_mode; + + list_for_each_entry(term, config_terms, list) { + switch (term->type) { + case PERF_EVSEL__CONFIG_TERM_PERIOD: + attr->sample_period = term->val.period; + attr->freq = 0; + break; + case PERF_EVSEL__CONFIG_TERM_FREQ: + attr->sample_freq = term->val.freq; + attr->freq = 1; + break; + case PERF_EVSEL__CONFIG_TERM_TIME: + if (term->val.time) + perf_evsel__set_sample_bit(evsel, TIME); + else + perf_evsel__reset_sample_bit(evsel, TIME); + break; + case PERF_EVSEL__CONFIG_TERM_CALLGRAPH: + callgraph_buf = term->val.callgraph; + break; + case PERF_EVSEL__CONFIG_TERM_STACK_USER: + dump_size = term->val.stack_user; + break; + default: + break; + } + } + + /* User explicitly set per-event callgraph, clear the old setting and reset. */ + if ((callgraph_buf != NULL) || (dump_size > 0)) { + + /* parse callgraph parameters */ + if (callgraph_buf != NULL) { + if (!strcmp(callgraph_buf, "no")) { + param.enabled = false; + param.record_mode = CALLCHAIN_NONE; + } else { + param.enabled = true; + if (parse_callchain_record(callgraph_buf, ¶m)) { + pr_err("per-event callgraph setting for %s failed. " + "Apply callgraph global setting for it\n", + evsel->name); + return; + } + } + } + if (dump_size > 0) { + dump_size = round_up(dump_size, sizeof(u64)); + param.dump_size = dump_size; + } + + /* If global callgraph set, clear it */ + if (callchain_param.enabled) + perf_evsel__reset_callgraph(evsel, &callchain_param); + + /* set perf-event callgraph */ + if (param.enabled) + perf_evsel__config_callgraph(evsel, opts, ¶m); + } +} + /* * The enable_on_exec/disabled value strategy: * @@ -689,7 +783,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) evsel->attr.exclude_callchain_user = 1; if (callchain_param.enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel, opts); + perf_evsel__config_callgraph(evsel, opts, &callchain_param); if (opts->sample_intr_regs) { attr->sample_regs_intr = PERF_REGS_MASK; @@ -707,7 +801,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) */ if (opts->sample_time && (!perf_missing_features.sample_id_all && - (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu))) + (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu || + opts->sample_time_set))) perf_evsel__set_sample_bit(evsel, TIME); if (opts->raw_samples && !evsel->no_aux_samples) { @@ -736,6 +831,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; + if (opts->record_switch_events) + attr->context_switch = track; + if (opts->sample_transaction) perf_evsel__set_sample_bit(evsel, TRANSACTION); @@ -772,6 +870,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->use_clockid = 1; attr->clockid = opts->clockid; } + + /* + * Apply event specific term settings, + * it overloads any global configuration. + */ + apply_config_terms(evsel, opts); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -815,14 +919,44 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea return 0; } -int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter) +int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter) { return perf_evsel__run_ioctl(evsel, ncpus, nthreads, PERF_EVENT_IOC_SET_FILTER, (void *)filter); } +int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) +{ + char *new_filter = strdup(filter); + + if (new_filter != NULL) { + free(evsel->filter); + evsel->filter = new_filter; + return 0; + } + + return -1; +} + +int perf_evsel__append_filter(struct perf_evsel *evsel, + const char *op, const char *filter) +{ + char *new_filter; + + if (evsel->filter == NULL) + return perf_evsel__set_filter(evsel, filter); + + if (asprintf(&new_filter,"(%s) %s (%s)", evsel->filter, op, filter) > 0) { + free(evsel->filter); + evsel->filter = new_filter; + return 0; + } + + return -1; +} + int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) { return perf_evsel__run_ioctl(evsel, ncpus, nthreads, @@ -865,6 +999,16 @@ static void perf_evsel__free_id(struct perf_evsel *evsel) zfree(&evsel->id); } +static void perf_evsel__free_config_terms(struct perf_evsel *evsel) +{ + struct perf_evsel_config_term *term, *h; + + list_for_each_entry_safe(term, h, &evsel->config_terms, list) { + list_del(&term->list); + free(term); + } +} + void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; @@ -884,6 +1028,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) assert(list_empty(&evsel->node)); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); + perf_evsel__free_config_terms(evsel); close_cgroup(evsel->cgrp); cpu_map__put(evsel->cpus); thread_map__put(evsel->threads); @@ -1095,6 +1240,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(mmap2, p_unsigned); PRINT_ATTRf(comm_exec, p_unsigned); PRINT_ATTRf(use_clockid, p_unsigned); + PRINT_ATTRf(context_switch, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); @@ -2075,8 +2221,13 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += perf_event_attr__fprintf(fp, &evsel->attr, __print_attr__fprintf, &first); } else if (details->freq) { - printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, - (u64)evsel->attr.sample_freq); + const char *term = "sample_freq"; + + if (!evsel->attr.freq) + term = "sample_period"; + + printed += comma_fprintf(fp, &first, " %s=%" PRIu64, + term, (u64)evsel->attr.sample_freq); } out: fputc('\n', fp); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4a7ed5656cf0..93ac6b128149 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -9,7 +9,7 @@ #include "xyarray.h" #include "symbol.h" #include "cpumap.h" -#include "stat.h" +#include "counts.h" struct perf_evsel; @@ -31,6 +31,33 @@ struct perf_sample_id { struct cgroup_sel; +/* + * 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 { + 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_MAX, +}; + +struct perf_evsel_config_term { + struct list_head list; + int type; + union { + u64 period; + u64 freq; + bool time; + char *callgraph; + u64 stack_user; + } val; +}; + /** struct perf_evsel - event selector * * @name - Can be set to retain the original event name passed by the user, @@ -86,6 +113,8 @@ struct perf_evsel { unsigned long *per_pkg_mask; struct perf_evsel *leader; char *group_name; + bool cmdline_group_boundary; + struct list_head config_terms; }; union u64_swap { @@ -182,8 +211,11 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, void perf_evsel__set_sample_id(struct perf_evsel *evsel, bool use_sample_identifier); -int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter); +int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter); +int perf_evsel__append_filter(struct perf_evsel *evsel, + const char *op, const char *filter); +int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter); int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__open_per_cpu(struct perf_evsel *evsel, diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 03ace57a800c..179b2bdd157d 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -923,17 +923,13 @@ static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { int nr, i; - char *str; nr = ph->env.nr_cmdline; - str = ph->env.cmdline; fprintf(fp, "# cmdline : "); - for (i = 0; i < nr; i++) { - fprintf(fp, "%s ", str); - str += strlen(str) + 1; - } + for (i = 0; i < nr; i++) + fprintf(fp, "%s ", ph->env.cmdline_argv[i]); fputc('\n', fp); } @@ -1541,14 +1537,13 @@ process_event_desc(struct perf_file_section *section __maybe_unused, return 0; } -static int process_cmdline(struct perf_file_section *section __maybe_unused, +static int process_cmdline(struct perf_file_section *section, struct perf_header *ph, int fd, void *data __maybe_unused) { ssize_t ret; - char *str; - u32 nr, i; - struct strbuf sb; + char *str, *cmdline = NULL, **argv = NULL; + u32 nr, i, len = 0; ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) @@ -1558,22 +1553,32 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused, nr = bswap_32(nr); ph->env.nr_cmdline = nr; - strbuf_init(&sb, 128); + + cmdline = zalloc(section->size + nr + 1); + if (!cmdline) + return -1; + + argv = zalloc(sizeof(char *) * (nr + 1)); + if (!argv) + goto error; for (i = 0; i < nr; i++) { str = do_read_string(fd, ph); if (!str) goto error; - /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + argv[i] = cmdline + len; + memcpy(argv[i], str, strlen(str) + 1); + len += strlen(str) + 1; free(str); } - ph->env.cmdline = strbuf_detach(&sb, NULL); + ph->env.cmdline = cmdline; + ph->env.cmdline_argv = (const char **) argv; return 0; error: - strbuf_release(&sb); + free(argv); + free(cmdline); return -1; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d4d57962c591..9b53b6525ce8 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -84,6 +84,7 @@ struct perf_session_env { int nr_pmu_mappings; int nr_groups; char *cmdline; + const char **cmdline_argv; char *sibling_cores; char *sibling_threads; char *numa_nodes; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6f28d53d4e46..08b6cd945f1e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -151,6 +151,12 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + if (h->srcline) + hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline)); + + if (h->srcfile) + hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile)); + if (h->transaction) hists__new_col_len(hists, HISTC_TRANSACTION, hist_entry__transaction_len()); @@ -618,7 +624,8 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * and not events sampled. Thus we use a pseudo period of 1. */ he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, - 1, 1, 0, true); + 1, bi->flags.cycles ? bi->flags.cycles : 1, + 0, true); if (he == NULL) return -ENOMEM; @@ -760,6 +767,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, struct hist_entry **he_cache = iter->priv; struct hist_entry *he; struct hist_entry he_tmp = { + .hists = evsel__hists(evsel), .cpu = al->cpu, .thread = al->thread, .comm = thread__comm(al->thread), @@ -944,6 +952,8 @@ void hist_entry__delete(struct hist_entry *he) zfree(&he->stat_acc); free_srcline(he->srcline); + if (he->srcfile && he->srcfile[0]) + free(he->srcfile); free_callchain(he->callchain); free(he); } @@ -1099,13 +1109,14 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h) static void __hists__insert_output_entry(struct rb_root *entries, struct hist_entry *he, - u64 min_callchain_hits) + u64 min_callchain_hits, + bool use_callchain) { struct rb_node **p = &entries->rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; - if (symbol_conf.use_callchain) + if (use_callchain) callchain_param.sort(&he->sorted_chain, he->callchain, min_callchain_hits, &callchain_param); @@ -1129,6 +1140,13 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) struct rb_node *next; struct hist_entry *n; u64 min_callchain_hits; + struct perf_evsel *evsel = hists_to_evsel(hists); + bool use_callchain; + + if (evsel && !symbol_conf.show_ref_callgraph) + use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + else + use_callchain = symbol_conf.use_callchain; min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); @@ -1147,7 +1165,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); - __hists__insert_output_entry(&hists->entries, n, min_callchain_hits); + __hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain); hists__inc_stats(hists, n); if (!n->filtered) @@ -1414,6 +1432,39 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } +void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, + struct perf_sample *sample, bool nonany_branch_mode) +{ + struct branch_info *bi; + + /* If we have branch cycles always annotate them. */ + if (bs && bs->nr && bs->entries[0].flags.cycles) { + int i; + + bi = sample__resolve_bstack(sample, al); + if (bi) { + struct addr_map_symbol *prev = NULL; + + /* + * Ignore errors, still want to process the + * other entries. + * + * For non standard branch modes always + * force no IPC (prev == NULL) + * + * Note that perf stores branches reversed from + * program order! + */ + for (i = bs->nr - 1; i >= 0; i--) { + addr_map_symbol__account_cycles(&bi[i].from, + nonany_branch_mode ? NULL : prev, + bi[i].flags.cycles); + prev = &bi[i].to; + } + free(bi); + } + } +} size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 5ed8d9c22981..bc528d54e457 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -30,6 +30,7 @@ enum hist_column { HISTC_PARENT, HISTC_CPU, HISTC_SRCLINE, + HISTC_SRCFILE, HISTC_MISPREDICT, HISTC_IN_TX, HISTC_ABORT, @@ -47,6 +48,7 @@ enum hist_column { HISTC_MEM_SNOOP, HISTC_MEM_DCACHELINE, HISTC_TRANSACTION, + HISTC_CYCLES, HISTC_NR_COLS, /* Last entry */ }; @@ -349,6 +351,9 @@ static inline int script_browse(const char *script_opt __maybe_unused) unsigned int hists__sort_list_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 option; int parse_filter_percentage(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused); diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c new file mode 100644 index 000000000000..4f6a4780bd5f --- /dev/null +++ b/tools/perf/util/llvm-utils.c @@ -0,0 +1,408 @@ +/* + * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015, Huawei Inc. + */ + +#include <stdio.h> +#include <sys/utsname.h> +#include "util.h" +#include "debug.h" +#include "llvm-utils.h" +#include "cache.h" + +#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ + "$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS " \ + "$KERNEL_INC_OPTIONS -Wno-unused-value " \ + "-Wno-pointer-sign -working-directory " \ + "$WORKING_DIR -c \"$CLANG_SOURCE\" -target bpf -O2 -o -" + +struct llvm_param llvm_param = { + .clang_path = "clang", + .clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE, + .clang_opt = NULL, + .kbuild_dir = NULL, + .kbuild_opts = NULL, + .user_set_param = false, +}; + +int perf_llvm_config(const char *var, const char *value) +{ + if (prefixcmp(var, "llvm.")) + return 0; + var += sizeof("llvm.") - 1; + + if (!strcmp(var, "clang-path")) + llvm_param.clang_path = strdup(value); + else if (!strcmp(var, "clang-bpf-cmd-template")) + llvm_param.clang_bpf_cmd_template = strdup(value); + else if (!strcmp(var, "clang-opt")) + llvm_param.clang_opt = strdup(value); + else if (!strcmp(var, "kbuild-dir")) + llvm_param.kbuild_dir = strdup(value); + else if (!strcmp(var, "kbuild-opts")) + llvm_param.kbuild_opts = strdup(value); + else + return -1; + llvm_param.user_set_param = true; + return 0; +} + +static int +search_program(const char *def, const char *name, + char *output) +{ + char *env, *path, *tmp = NULL; + char buf[PATH_MAX]; + int ret; + + output[0] = '\0'; + if (def && def[0] != '\0') { + if (def[0] == '/') { + if (access(def, F_OK) == 0) { + strlcpy(output, def, PATH_MAX); + return 0; + } + } else if (def[0] != '\0') + name = def; + } + + env = getenv("PATH"); + if (!env) + return -1; + env = strdup(env); + if (!env) + return -1; + + ret = -ENOENT; + path = strtok_r(env, ":", &tmp); + while (path) { + scnprintf(buf, sizeof(buf), "%s/%s", path, name); + if (access(buf, F_OK) == 0) { + strlcpy(output, buf, PATH_MAX); + ret = 0; + break; + } + path = strtok_r(NULL, ":", &tmp); + } + + free(env); + return ret; +} + +#define READ_SIZE 4096 +static int +read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz) +{ + int err = 0; + void *buf = NULL; + FILE *file = NULL; + size_t read_sz = 0, buf_sz = 0; + + file = popen(cmd, "r"); + if (!file) { + pr_err("ERROR: unable to popen cmd: %s\n", + strerror(errno)); + return -EINVAL; + } + + while (!feof(file) && !ferror(file)) { + /* + * Make buf_sz always have obe byte extra space so we + * can put '\0' there. + */ + if (buf_sz - read_sz < READ_SIZE + 1) { + void *new_buf; + + buf_sz = read_sz + READ_SIZE + 1; + new_buf = realloc(buf, buf_sz); + + if (!new_buf) { + pr_err("ERROR: failed to realloc memory\n"); + err = -ENOMEM; + goto errout; + } + + buf = new_buf; + } + read_sz += fread(buf + read_sz, 1, READ_SIZE, file); + } + + if (buf_sz - read_sz < 1) { + pr_err("ERROR: internal error\n"); + err = -EINVAL; + goto errout; + } + + if (ferror(file)) { + pr_err("ERROR: error occurred when reading from pipe: %s\n", + strerror(errno)); + err = -EIO; + goto errout; + } + + err = WEXITSTATUS(pclose(file)); + file = NULL; + if (err) { + err = -EINVAL; + goto errout; + } + + /* + * If buf is string, give it terminal '\0' to make our life + * easier. If buf is not string, that '\0' is out of space + * indicated by read_sz so caller won't even notice it. + */ + ((char *)buf)[read_sz] = '\0'; + + if (!p_buf) + free(buf); + else + *p_buf = buf; + + if (p_read_sz) + *p_read_sz = read_sz; + return 0; + +errout: + if (file) + pclose(file); + free(buf); + if (p_buf) + *p_buf = NULL; + if (p_read_sz) + *p_read_sz = 0; + return err; +} + +static inline void +force_set_env(const char *var, const char *value) +{ + if (value) { + setenv(var, value, 1); + pr_debug("set env: %s=%s\n", var, value); + } else { + unsetenv(var); + pr_debug("unset env: %s\n", var); + } +} + +static void +version_notice(void) +{ + pr_err( +" \tLLVM 3.7 or newer is required. Which can be found from http://llvm.org\n" +" \tYou may want to try git trunk:\n" +" \t\tgit clone http://llvm.org/git/llvm.git\n" +" \t\t and\n" +" \t\tgit clone http://llvm.org/git/clang.git\n\n" +" \tOr fetch the latest clang/llvm 3.7 from pre-built llvm packages for\n" +" \tdebian/ubuntu:\n" +" \t\thttp://llvm.org/apt\n\n" +" \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n" +" \toption in [llvm] section of ~/.perfconfig to:\n\n" +" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n" +" \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n" +" \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n" +" \t(Replace /path/to/llc with path to your llc)\n\n" +); +} + +static int detect_kbuild_dir(char **kbuild_dir) +{ + const char *test_dir = llvm_param.kbuild_dir; + const char *prefix_dir = ""; + const char *suffix_dir = ""; + + char *autoconf_path; + struct utsname utsname; + + int err; + + if (!test_dir) { + err = uname(&utsname); + if (err) { + pr_warning("uname failed: %s\n", strerror(errno)); + return -EINVAL; + } + + test_dir = utsname.release; + prefix_dir = "/lib/modules/"; + suffix_dir = "/build"; + } + + err = asprintf(&autoconf_path, "%s%s%s/include/generated/autoconf.h", + prefix_dir, test_dir, suffix_dir); + if (err < 0) + return -ENOMEM; + + if (access(autoconf_path, R_OK) == 0) { + free(autoconf_path); + + err = asprintf(kbuild_dir, "%s%s%s", prefix_dir, test_dir, + suffix_dir); + if (err < 0) + return -ENOMEM; + return 0; + } + free(autoconf_path); + return -ENOENT; +} + +static const char *kinc_fetch_script = +"#!/usr/bin/env sh\n" +"if ! test -d \"$KBUILD_DIR\"\n" +"then\n" +" exit -1\n" +"fi\n" +"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n" +"then\n" +" exit -1\n" +"fi\n" +"TMPDIR=`mktemp -d`\n" +"if test -z \"$TMPDIR\"\n" +"then\n" +" exit -1\n" +"fi\n" +"cat << EOF > $TMPDIR/Makefile\n" +"obj-y := dummy.o\n" +"\\$(obj)/%.o: \\$(src)/%.c\n" +"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" +"EOF\n" +"touch $TMPDIR/dummy.c\n" +"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" +"RET=$?\n" +"rm -rf $TMPDIR\n" +"exit $RET\n"; + +static inline void +get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) +{ + int err; + + if (!kbuild_dir || !kbuild_include_opts) + return; + + *kbuild_dir = NULL; + *kbuild_include_opts = NULL; + + if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) { + pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n"); + pr_debug("Skip kbuild options detection.\n"); + return; + } + + err = detect_kbuild_dir(kbuild_dir); + if (err) { + pr_warning( +"WARNING:\tunable to get correct kernel building directory.\n" +"Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n" +" \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n" +" \tdetection.\n\n"); + return; + } + + pr_debug("Kernel build dir is set to %s\n", *kbuild_dir); + force_set_env("KBUILD_DIR", *kbuild_dir); + force_set_env("KBUILD_OPTS", llvm_param.kbuild_opts); + err = read_from_pipe(kinc_fetch_script, + (void **)kbuild_include_opts, + NULL); + if (err) { + pr_warning( +"WARNING:\tunable to get kernel include directories from '%s'\n" +"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n" +" \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n" +" \toption in [llvm] to \"\" to suppress this detection.\n\n", + *kbuild_dir); + + free(*kbuild_dir); + *kbuild_dir = NULL; + return; + } + + pr_debug("include option is set to %s\n", *kbuild_include_opts); +} + +int llvm__compile_bpf(const char *path, void **p_obj_buf, + size_t *p_obj_buf_sz) +{ + int err; + char clang_path[PATH_MAX]; + const char *clang_opt = llvm_param.clang_opt; + const char *template = llvm_param.clang_bpf_cmd_template; + char *kbuild_dir = NULL, *kbuild_include_opts = NULL; + void *obj_buf = NULL; + size_t obj_buf_sz; + + if (!template) + template = CLANG_BPF_CMD_DEFAULT_TEMPLATE; + + err = search_program(llvm_param.clang_path, + "clang", clang_path); + if (err) { + pr_err( +"ERROR:\tunable to find clang.\n" +"Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n" +" \tand 'clang-path' option in [llvm] section of ~/.perfconfig.\n"); + version_notice(); + return -ENOENT; + } + + /* + * This is an optional work. Even it fail we can continue our + * work. Needn't to check error return. + */ + get_kbuild_opts(&kbuild_dir, &kbuild_include_opts); + + force_set_env("CLANG_EXEC", clang_path); + force_set_env("CLANG_OPTIONS", clang_opt); + force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts); + force_set_env("WORKING_DIR", kbuild_dir ? : "."); + + /* + * Since we may reset clang's working dir, path of source file + * should be transferred into absolute path, except we want + * stdin to be source file (testing). + */ + force_set_env("CLANG_SOURCE", + (path[0] == '-') ? path : + make_nonrelative_path(path)); + + pr_debug("llvm compiling command template: %s\n", template); + err = read_from_pipe(template, &obj_buf, &obj_buf_sz); + if (err) { + pr_err("ERROR:\tunable to compile %s\n", path); + pr_err("Hint:\tCheck error message shown above.\n"); + pr_err("Hint:\tYou can also pre-compile it into .o using:\n"); + pr_err(" \t\tclang -target bpf -O2 -c %s\n", path); + pr_err(" \twith proper -I and -D options.\n"); + goto errout; + } + + free(kbuild_dir); + free(kbuild_include_opts); + if (!p_obj_buf) + free(obj_buf); + else + *p_obj_buf = obj_buf; + + if (p_obj_buf_sz) + *p_obj_buf_sz = obj_buf_sz; + return 0; +errout: + free(kbuild_dir); + free(kbuild_include_opts); + free(obj_buf); + if (p_obj_buf) + *p_obj_buf = NULL; + if (p_obj_buf_sz) + *p_obj_buf_sz = 0; + return err; +} + +int llvm__search_clang(void) +{ + char clang_path[PATH_MAX]; + + return search_program(llvm_param.clang_path, "clang", clang_path); +} diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h new file mode 100644 index 000000000000..5b3cf1c229e2 --- /dev/null +++ b/tools/perf/util/llvm-utils.h @@ -0,0 +1,49 @@ +/* + * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015, Huawei Inc. + */ +#ifndef __LLVM_UTILS_H +#define __LLVM_UTILS_H + +#include "debug.h" + +struct llvm_param { + /* Path of clang executable */ + const char *clang_path; + /* + * Template of clang bpf compiling. 5 env variables + * can be used: + * $CLANG_EXEC: Path to clang. + * $CLANG_OPTIONS: Extra options to clang. + * $KERNEL_INC_OPTIONS: Kernel include directories. + * $WORKING_DIR: Kernel source directory. + * $CLANG_SOURCE: Source file to be compiled. + */ + const char *clang_bpf_cmd_template; + /* Will be filled in $CLANG_OPTIONS */ + const char *clang_opt; + /* Where to find kbuild system */ + const char *kbuild_dir; + /* + * Arguments passed to make, like 'ARCH=arm' if doing cross + * compiling. Should not be used for dynamic compiling. + */ + const char *kbuild_opts; + /* + * Default is false. If one of the above fields is set by user + * explicitly then user_set_llvm is set to true. This is used + * for perf test. If user doesn't set anything in .perfconfig + * and clang is not found, don't trigger llvm test. + */ + bool user_set_param; +}; + +extern struct llvm_param llvm_param; +extern int perf_llvm_config(const char *var, const char *value); + +extern int llvm__compile_bpf(const char *path, void **p_obj_buf, + size_t *p_obj_buf_sz); + +/* This function is for test__llvm() use only */ +extern int llvm__search_clang(void); +#endif diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index f1a4c833121e..6309f7ceb08f 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -250,7 +250,7 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid) static struct strlist *seen; if (!seen) - seen = strlist__new(true, NULL); + seen = strlist__new(NULL, NULL); if (!strlist__has_entry(seen, path)) { pr_err("Can't access file %s\n", path); @@ -550,6 +550,14 @@ int machine__process_itrace_start_event(struct machine *machine __maybe_unused, return 0; } +int machine__process_switch_event(struct machine *machine __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_switch(event, stdout); + return 0; +} + struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename) { @@ -1467,6 +1475,9 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_itrace_start_event(machine, event); break; case PERF_RECORD_LOST_SAMPLES: ret = machine__process_lost_samples_event(machine, event, sample); break; + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + ret = machine__process_switch_event(machine, event); break; default: ret = -1; break; @@ -2009,3 +2020,17 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { return dsos__findnew(&machine->dsos, filename); } + +char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp) +{ + struct machine *machine = vmachine; + struct map *map; + struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map, NULL); + + if (sym == NULL) + return NULL; + + *modp = __map__is_kmodule(map) ? (char *)map->dso->short_name : NULL; + *addrp = map->unmap_ip(map, sym->start); + return sym->name; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 887798e511e9..ea5cb4a621db 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -87,6 +87,8 @@ int machine__process_aux_event(struct machine *machine, union perf_event *event); int machine__process_itrace_start_event(struct machine *machine, union perf_event *event); +int machine__process_switch_event(struct machine *machine __maybe_unused, + union perf_event *event); int machine__process_mmap_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event, @@ -237,5 +239,9 @@ int machine__synthesize_threads(struct machine *machine, struct target *target, 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); +/* + * For use with libtraceevent's pevent_set_function_resolver() + */ +char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp); #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index b5a5e9c02437..ce37e95bc513 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -224,6 +224,20 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) 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 map->groups->machine->vmlinux_maps[map->type] == map; +} + static void map__exit(struct map *map) { BUG_ON(!RB_EMPTY_NODE(&map->rb_node)); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index d73e687b224e..57829e89b78b 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -256,4 +256,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); +bool __map__is_kernel(const struct map *map); + +static inline bool __map__is_kmodule(const struct map *map) +{ + return !__map__is_kernel(map); +} + #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 09f8d2357108..d826e6f515db 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -276,7 +276,8 @@ const char *event_type(int type) static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct cpu_map *cpus) + char *name, struct cpu_map *cpus, + struct list_head *config_terms) { struct perf_evsel *evsel; @@ -291,14 +292,19 @@ __add_event(struct list_head *list, int *idx, if (name) evsel->name = strdup(name); + + if (config_terms) + list_splice(config_terms, &evsel->config_terms); + list_add_tail(&evsel->node, list); return evsel; } static int add_event(struct list_head *list, int *idx, - struct perf_event_attr *attr, char *name) + struct perf_event_attr *attr, char *name, + struct list_head *config_terms) { - return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM; } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -377,7 +383,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, memset(&attr, 0, sizeof(attr)); attr.config = cache_type | (cache_op << 8) | (cache_result << 16); attr.type = PERF_TYPE_HW_CACHE; - return add_event(list, idx, &attr, name); + return add_event(list, idx, &attr, name, NULL); } static int add_tracepoint(struct list_head *list, int *idx, @@ -539,7 +545,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, attr.type = PERF_TYPE_BREAKPOINT; attr.sample_period = 1; - return add_event(list, idx, &attr, NULL); + return add_event(list, idx, &attr, NULL, NULL); } static int check_type_val(struct parse_events_term *term, @@ -590,7 +596,9 @@ do { \ break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: CHECK_TYPE_VAL(NUM); - attr->sample_period = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + CHECK_TYPE_VAL(NUM); break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: /* @@ -598,6 +606,20 @@ do { \ * attr->branch_sample_type = term->val.num; */ 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; + return -EINVAL; + } + break; + case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: + CHECK_TYPE_VAL(STR); + break; + case PARSE_EVENTS__TERM_TYPE_STACKSIZE: + CHECK_TYPE_VAL(NUM); + break; case PARSE_EVENTS__TERM_TYPE_NAME: CHECK_TYPE_VAL(STR); break; @@ -622,22 +644,71 @@ static int config_attr(struct perf_event_attr *attr, return 0; } +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 { \ + struct perf_evsel_config_term *__t; \ + \ + __t = zalloc(sizeof(*__t)); \ + if (!__t) \ + return -ENOMEM; \ + \ + INIT_LIST_HEAD(&__t->list); \ + __t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \ + __t->val.__name = __val; \ + list_add_tail(&__t->list, head_terms); \ +} while (0) + + struct parse_events_term *term; + + 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); + break; + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + ADD_CONFIG_TERM(FREQ, freq, term->val.num); + break; + case PARSE_EVENTS__TERM_TYPE_TIME: + ADD_CONFIG_TERM(TIME, time, term->val.num); + break; + case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: + ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str); + break; + case PARSE_EVENTS__TERM_TYPE_STACKSIZE: + ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num); + break; + default: + break; + } + } +#undef ADD_EVSEL_CONFIG + return 0; +} + int parse_events_add_numeric(struct parse_events_evlist *data, struct list_head *list, u32 type, u64 config, struct list_head *head_config) { struct perf_event_attr attr; + LIST_HEAD(config_terms); memset(&attr, 0, sizeof(attr)); attr.type = type; attr.config = config; - if (head_config && - config_attr(&attr, head_config, data->error)) - return -EINVAL; + if (head_config) { + if (config_attr(&attr, head_config, data->error)) + return -EINVAL; + + if (get_config_terms(head_config, &config_terms)) + return -ENOMEM; + } - return add_event(list, &data->idx, &attr, NULL); + return add_event(list, &data->idx, &attr, NULL, &config_terms); } static int parse_events__is_name_term(struct parse_events_term *term) @@ -664,6 +735,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; + LIST_HEAD(config_terms); pmu = perf_pmu__find(name); if (!pmu) @@ -678,7 +750,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus); + evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus, NULL); return evsel ? 0 : -ENOMEM; } @@ -692,11 +764,15 @@ int parse_events_add_pmu(struct parse_events_evlist *data, if (config_attr(&attr, head_config, data->error)) return -EINVAL; + if (get_config_terms(head_config, &config_terms)) + return -ENOMEM; + if (perf_pmu__config(pmu, &attr, head_config, data->error)) return -EINVAL; evsel = __add_event(list, &data->idx, &attr, - pmu_event_name(head_config), pmu->cpus); + pmu_event_name(head_config), pmu->cpus, + &config_terms); if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; @@ -1065,8 +1141,13 @@ int parse_events(struct perf_evlist *evlist, const char *str, perf_pmu__parse_cleanup(); if (!ret) { int entries = data.idx - evlist->nr_entries; + struct perf_evsel *last; + perf_evlist__splice_list_tail(evlist, &data.list, entries); evlist->nr_groups += data.nr_groups; + last = perf_evlist__last(evlist); + last->cmdline_group_boundary = true; + return 0; } @@ -1105,7 +1186,7 @@ static void parse_events_print_error(struct parse_events_error *err, * Maximum error index indent, we will cut * the event string if it's bigger. */ - int max_err_idx = 10; + int max_err_idx = 13; /* * Let's be specific with the message when @@ -1162,30 +1243,93 @@ int parse_events_option(const struct option *opt, const char *str, return ret; } -int parse_filter(const struct option *opt, const char *str, - int unset __maybe_unused) +static int +foreach_evsel_in_last_glob(struct perf_evlist *evlist, + int (*func)(struct perf_evsel *evsel, + const void *arg), + const void *arg) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; struct perf_evsel *last = NULL; + int err; if (evlist->nr_entries > 0) last = perf_evlist__last(evlist); - if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { + do { + err = (*func)(last, arg); + if (err) + return -1; + if (!last) + return 0; + + if (last->node.prev == &evlist->entries) + return 0; + last = list_entry(last->node.prev, struct perf_evsel, node); + } while (!last->cmdline_group_boundary); + + return 0; +} + +static int set_filter(struct perf_evsel *evsel, const void *arg) +{ + const char *str = arg; + + if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, "--filter option should follow a -e tracepoint option\n"); return -1; } - last->filter = strdup(str); - if (last->filter == NULL) { - fprintf(stderr, "not enough memory to hold filter string\n"); + if (perf_evsel__append_filter(evsel, "&&", str) < 0) { + fprintf(stderr, + "not enough memory to hold filter string\n"); return -1; } return 0; } +int parse_filter(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct perf_evlist *evlist = *(struct perf_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, + const void *arg __maybe_unused) +{ + char new_filter[64]; + + if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) { + fprintf(stderr, + "--exclude-perf option should follow a -e tracepoint option\n"); + return -1; + } + + snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid()); + + if (perf_evsel__append_filter(evsel, "&&", new_filter) < 0) { + fprintf(stderr, + "not enough memory to hold filter string\n"); + return -1; + } + + return 0; +} + +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; + + return foreach_evsel_in_last_glob(evlist, add_exclude_perf_filter, + NULL); +} + static const char * const event_type_descriptors[] = { "Hardware event", "Software event", diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 131f29b2f132..a09b0e210997 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -34,6 +34,7 @@ extern int parse_events(struct perf_evlist *evlist, const char *str, struct parse_events_error *error); extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); +extern int exclude_perf(const struct option *opt, const char *arg, int unset); #define EVENTS_HELP_MAX (128*1024) @@ -61,7 +62,11 @@ enum { PARSE_EVENTS__TERM_TYPE_CONFIG2, PARSE_EVENTS__TERM_TYPE_NAME, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, + PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, + PARSE_EVENTS__TERM_TYPE_TIME, + PARSE_EVENTS__TERM_TYPE_CALLGRAPH, + PARSE_EVENTS__TERM_TYPE_STACKSIZE, }; struct parse_events_term { diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 13cef3c65565..936d566f48d8 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -182,7 +182,11 @@ config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); } branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); } +call-graph { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); } +stack-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7bcb8c315615..84cad054d6f7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -542,7 +542,7 @@ struct perf_pmu *perf_pmu__find(const char *name) } static struct perf_pmu_format * -pmu_find_format(struct list_head *formats, char *name) +pmu_find_format(struct list_head *formats, const char *name) { struct perf_pmu_format *format; @@ -553,6 +553,21 @@ pmu_find_format(struct list_head *formats, char *name) return NULL; } +__u64 perf_pmu__format_bits(struct list_head *formats, const char *name) +{ + struct perf_pmu_format *format = pmu_find_format(formats, name); + __u64 bits = 0; + int fbit; + + if (!format) + return 0; + + for_each_set_bit(fbit, format->bits, PERF_PMU_FORMAT_BITS) + bits |= 1ULL << fbit; + + return bits; +} + /* * Sets value based on the format definition (format parameter) * and unformated value (value parameter). @@ -574,6 +589,18 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, } } +static __u64 pmu_format_max_value(const unsigned long *format) +{ + int w; + + w = bitmap_weight(format, PERF_PMU_FORMAT_BITS); + if (!w) + return 0; + if (w < 64) + return (1ULL << w) - 1; + return -1; +} + /* * Term is a string term, and might be a param-term. Try to look up it's value * in the remaining terms. @@ -607,7 +634,9 @@ static char *formats_error_string(struct list_head *formats) { struct perf_pmu_format *format; char *err, *str; - static const char *static_terms = "config,config1,config2,name,period,branch_type\n"; + static const char *static_terms = "config,config1,config2,name," + "period,freq,branch_type,time," + "call-graph,stack-size\n"; unsigned i = 0; if (!asprintf(&str, "valid terms:")) @@ -647,7 +676,7 @@ static int pmu_config_term(struct list_head *formats, { struct perf_pmu_format *format; __u64 *vp; - __u64 val; + __u64 val, max_val; /* * If this is a parameter we've already used for parameterized-eval, @@ -713,6 +742,22 @@ static int pmu_config_term(struct list_head *formats, } else return -EINVAL; + 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"); + return -EINVAL; + } + /* + * Assume we don't care if !err, in which case the value will be + * silently truncated. + */ + } + pmu_format_value(format->bits, val, vp, zero); return 0; } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 7b9c8cf8ae3e..5d7e84466bee 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -54,6 +54,7 @@ int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, 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__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, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 381f23a443c7..fe4941a94a25 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -45,6 +45,7 @@ #include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" +#include "probe-file.h" #include "session.h" #define MAX_CMDLEN 256 @@ -55,11 +56,7 @@ struct probe_conf probe_conf; #define semantic_error(msg ...) pr_err("Semantic error :" msg) -/* If there is no space to write, returns -E2BIG. */ -static int e_snprintf(char *str, size_t size, const char *format, ...) - __attribute__((format(printf, 3, 4))); - -static int e_snprintf(char *str, size_t size, const char *format, ...) +int e_snprintf(char *str, size_t size, const char *format, ...) { int ret; va_list ap; @@ -72,7 +69,6 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) } static char *synthesize_perf_probe_point(struct perf_probe_point *pp); -static void clear_probe_trace_event(struct probe_trace_event *tev); static struct machine *host_machine; /* Initialize symbol maps and path of vmlinux/modules */ @@ -1467,8 +1463,7 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) } /* Parse probe_events event into struct probe_point */ -static int parse_probe_trace_command(const char *cmd, - struct probe_trace_event *tev) +int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) { struct probe_trace_point *tp = &tev->point; char pr; @@ -1951,7 +1946,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev) memset(pev, 0, sizeof(*pev)); } -static void clear_probe_trace_event(struct probe_trace_event *tev) +void clear_probe_trace_event(struct probe_trace_event *tev) { struct probe_trace_arg_ref *ref, *next; int i; @@ -1976,119 +1971,6 @@ static void clear_probe_trace_event(struct probe_trace_event *tev) memset(tev, 0, sizeof(*tev)); } -static void print_open_warning(int err, bool is_kprobe) -{ - char sbuf[STRERR_BUFSIZE]; - - if (err == -ENOENT) { - const char *config; - - if (!is_kprobe) - config = "CONFIG_UPROBE_EVENTS"; - else - config = "CONFIG_KPROBE_EVENTS"; - - pr_warning("%cprobe_events file does not exist" - " - please rebuild kernel with %s.\n", - is_kprobe ? 'k' : 'u', config); - } else if (err == -ENOTSUP) - pr_warning("Tracefs or debugfs is not mounted.\n"); - else - pr_warning("Failed to open %cprobe_events: %s\n", - is_kprobe ? 'k' : 'u', - strerror_r(-err, sbuf, sizeof(sbuf))); -} - -static void print_both_open_warning(int kerr, int uerr) -{ - /* Both kprobes and uprobes are disabled, warn it. */ - if (kerr == -ENOTSUP && uerr == -ENOTSUP) - pr_warning("Tracefs or debugfs is not mounted.\n"); - else if (kerr == -ENOENT && uerr == -ENOENT) - pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " - "or/and CONFIG_UPROBE_EVENTS.\n"); - else { - char sbuf[STRERR_BUFSIZE]; - pr_warning("Failed to open kprobe events: %s.\n", - strerror_r(-kerr, sbuf, sizeof(sbuf))); - pr_warning("Failed to open uprobe events: %s.\n", - strerror_r(-uerr, sbuf, sizeof(sbuf))); - } -} - -static int open_probe_events(const char *trace_file, bool readwrite) -{ - char buf[PATH_MAX]; - const char *__debugfs; - const char *tracing_dir = ""; - int ret; - - __debugfs = tracefs_find_mountpoint(); - if (__debugfs == NULL) { - tracing_dir = "tracing/"; - - __debugfs = debugfs_find_mountpoint(); - if (__debugfs == NULL) - return -ENOTSUP; - } - - ret = e_snprintf(buf, PATH_MAX, "%s/%s%s", - __debugfs, tracing_dir, trace_file); - if (ret >= 0) { - pr_debug("Opening %s write=%d\n", buf, readwrite); - if (readwrite && !probe_event_dry_run) - ret = open(buf, O_RDWR | O_APPEND, 0); - else - ret = open(buf, O_RDONLY, 0); - - if (ret < 0) - ret = -errno; - } - return ret; -} - -static int open_kprobe_events(bool readwrite) -{ - return open_probe_events("kprobe_events", readwrite); -} - -static int open_uprobe_events(bool readwrite) -{ - return open_probe_events("uprobe_events", readwrite); -} - -/* Get raw string list of current kprobe_events or uprobe_events */ -static struct strlist *get_probe_trace_command_rawlist(int fd) -{ - int ret, idx; - FILE *fp; - char buf[MAX_CMDLEN]; - char *p; - struct strlist *sl; - - sl = strlist__new(true, NULL); - - fp = fdopen(dup(fd), "r"); - while (!feof(fp)) { - p = fgets(buf, MAX_CMDLEN, fp); - if (!p) - break; - - idx = strlen(p) - 1; - if (p[idx] == '\n') - p[idx] = '\0'; - ret = strlist__add(sl, buf); - if (ret < 0) { - pr_debug("strlist__add failed (%d)\n", ret); - strlist__delete(sl); - return NULL; - } - } - fclose(fp); - - return sl; -} - struct kprobe_blacklist_node { struct list_head list; unsigned long start; @@ -2284,7 +2166,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe, memset(&tev, 0, sizeof(tev)); memset(&pev, 0, sizeof(pev)); - rawlist = get_probe_trace_command_rawlist(fd); + rawlist = probe_file__get_rawlist(fd); if (!rawlist) return -ENOMEM; @@ -2325,89 +2207,20 @@ int show_perf_probe_events(struct strfilter *filter) if (ret < 0) return ret; - kp_fd = open_kprobe_events(false); - if (kp_fd >= 0) { - ret = __show_perf_probe_events(kp_fd, true, filter); - close(kp_fd); - if (ret < 0) - goto out; - } - - up_fd = open_uprobe_events(false); - if (kp_fd < 0 && up_fd < 0) { - print_both_open_warning(kp_fd, up_fd); - ret = kp_fd; - goto out; - } + ret = probe_file__open_both(&kp_fd, &up_fd, 0); + if (ret < 0) + return ret; - if (up_fd >= 0) { + if (kp_fd >= 0) + ret = __show_perf_probe_events(kp_fd, true, filter); + if (up_fd >= 0 && ret >= 0) ret = __show_perf_probe_events(up_fd, false, filter); + if (kp_fd > 0) + close(kp_fd); + if (up_fd > 0) close(up_fd); - } -out: exit_symbol_maps(); - return ret; -} - -/* Get current perf-probe event names */ -static struct strlist *get_probe_trace_event_names(int fd, bool include_group) -{ - char buf[128]; - struct strlist *sl, *rawlist; - struct str_node *ent; - struct probe_trace_event tev; - int ret = 0; - - memset(&tev, 0, sizeof(tev)); - rawlist = get_probe_trace_command_rawlist(fd); - if (!rawlist) - return NULL; - sl = strlist__new(true, NULL); - strlist__for_each(ent, rawlist) { - ret = parse_probe_trace_command(ent->s, &tev); - if (ret < 0) - break; - if (include_group) { - ret = e_snprintf(buf, 128, "%s:%s", tev.group, - tev.event); - if (ret >= 0) - ret = strlist__add(sl, buf); - } else - ret = strlist__add(sl, tev.event); - clear_probe_trace_event(&tev); - if (ret < 0) - break; - } - strlist__delete(rawlist); - - if (ret < 0) { - strlist__delete(sl); - return NULL; - } - return sl; -} - -static int write_probe_trace_event(int fd, struct probe_trace_event *tev) -{ - int ret = 0; - char *buf = synthesize_probe_trace_command(tev); - char sbuf[STRERR_BUFSIZE]; - - if (!buf) { - pr_debug("Failed to synthesize probe trace event.\n"); - return -EINVAL; - } - pr_debug("Writing event: %s\n", buf); - if (!probe_event_dry_run) { - ret = write(fd, buf, strlen(buf)); - if (ret <= 0) { - ret = -errno; - pr_warning("Failed to write event: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); - } - } - free(buf); return ret; } @@ -2478,36 +2291,67 @@ out: free(buf); } +/* Set new name from original perf_probe_event and namelist */ +static int probe_trace_event__set_name(struct probe_trace_event *tev, + struct perf_probe_event *pev, + struct strlist *namelist, + bool allow_suffix) +{ + const char *event, *group; + char buf[64]; + int ret; + + if (pev->event) + event = pev->event; + else + if (pev->point.function && !strisglob(pev->point.function)) + event = pev->point.function; + else + event = tev->point.realname; + if (pev->group) + group = pev->group; + else + group = PERFPROBE_GROUP; + + /* Get an unused new event name */ + ret = get_new_event_name(buf, 64, event, + namelist, allow_suffix); + if (ret < 0) + return ret; + + event = buf; + + tev->event = strdup(event); + tev->group = strdup(group); + if (tev->event == NULL || tev->group == NULL) + return -ENOMEM; + + /* Add added event name to namelist */ + strlist__add(namelist, event); + return 0; +} + static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs, bool allow_suffix) { int i, fd, ret; struct probe_trace_event *tev = NULL; - char buf[64]; const char *event = NULL, *group = NULL; struct strlist *namelist; - bool safename; - - if (pev->uprobes) - fd = open_uprobe_events(true); - else - fd = open_kprobe_events(true); - if (fd < 0) { - print_open_warning(fd, !pev->uprobes); + fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0)); + if (fd < 0) return fd; - } /* Get current event names */ - namelist = get_probe_trace_event_names(fd, false); + namelist = probe_file__get_namelist(fd); if (!namelist) { pr_debug("Failed to get current event list.\n"); ret = -ENOMEM; goto close_out; } - safename = (pev->point.function && !strisglob(pev->point.function)); ret = 0; pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { @@ -2516,36 +2360,15 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (!tev->point.symbol) continue; - if (pev->event) - event = pev->event; - else - if (safename) - event = pev->point.function; - else - event = tev->point.realname; - if (pev->group) - group = pev->group; - else - group = PERFPROBE_GROUP; - - /* Get an unused new event name */ - ret = get_new_event_name(buf, 64, event, - namelist, allow_suffix); + /* Set new name for tev (and update namelist) */ + ret = probe_trace_event__set_name(tev, pev, namelist, + allow_suffix); if (ret < 0) break; - event = buf; - tev->event = strdup(event); - tev->group = strdup(group); - if (tev->event == NULL || tev->group == NULL) { - ret = -ENOMEM; - break; - } - ret = write_probe_trace_event(fd, tev); + ret = probe_file__add_event(fd, tev); if (ret < 0) break; - /* Add added event name to namelist */ - strlist__add(namelist, event); /* We use tev's name for showing new events */ show_perf_probe_event(tev->group, tev->event, pev, @@ -2838,68 +2661,9 @@ end: return ret; } -static int __del_trace_probe_event(int fd, struct str_node *ent) -{ - char *p; - char buf[128]; - int ret; - - /* Convert from perf-probe event to trace-probe event */ - ret = e_snprintf(buf, 128, "-:%s", ent->s); - if (ret < 0) - goto error; - - p = strchr(buf + 2, ':'); - if (!p) { - pr_debug("Internal error: %s should have ':' but not.\n", - ent->s); - ret = -ENOTSUP; - goto error; - } - *p = '/'; - - pr_debug("Writing event: %s\n", buf); - ret = write(fd, buf, strlen(buf)); - if (ret < 0) { - ret = -errno; - goto error; - } - - pr_info("Removed event: %s\n", ent->s); - return 0; -error: - pr_warning("Failed to delete event: %s\n", - strerror_r(-ret, buf, sizeof(buf))); - return ret; -} - -static int del_trace_probe_events(int fd, struct strfilter *filter, - struct strlist *namelist) -{ - struct str_node *ent; - const char *p; - int ret = -ENOENT; - - if (!namelist) - return -ENOENT; - - strlist__for_each(ent, namelist) { - p = strchr(ent->s, ':'); - if ((p && strfilter__compare(filter, p + 1)) || - strfilter__compare(filter, ent->s)) { - ret = __del_trace_probe_event(fd, ent); - if (ret < 0) - break; - } - } - - return ret; -} - int del_perf_probe_events(struct strfilter *filter) { int ret, ret2, ufd = -1, kfd = -1; - struct strlist *namelist = NULL, *unamelist = NULL; char *str = strfilter__string(filter); if (!str) @@ -2908,25 +2672,15 @@ int del_perf_probe_events(struct strfilter *filter) pr_debug("Delete filter: \'%s\'\n", str); /* Get current event names */ - kfd = open_kprobe_events(true); - if (kfd >= 0) - namelist = get_probe_trace_event_names(kfd, true); - - ufd = open_uprobe_events(true); - if (ufd >= 0) - unamelist = get_probe_trace_event_names(ufd, true); - - if (kfd < 0 && ufd < 0) { - print_both_open_warning(kfd, ufd); - ret = kfd; - goto error; - } + ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW); + if (ret < 0) + goto out; - ret = del_trace_probe_events(kfd, filter, namelist); + ret = probe_file__del_events(kfd, filter); if (ret < 0 && ret != -ENOENT) goto error; - ret2 = del_trace_probe_events(ufd, filter, unamelist); + ret2 = probe_file__del_events(ufd, filter); if (ret2 < 0 && ret2 != -ENOENT) { ret = ret2; goto error; @@ -2937,15 +2691,11 @@ int del_perf_probe_events(struct strfilter *filter) ret = 0; error: - if (kfd >= 0) { - strlist__delete(namelist); + if (kfd >= 0) close(kfd); - } - - if (ufd >= 0) { - strlist__delete(unamelist); + if (ufd >= 0) close(ufd); - } +out: free(str); return ret; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 31db6ee7db54..83ee95e9743b 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -106,9 +106,13 @@ struct variable_list { struct strlist *vars; /* Available variables */ }; +struct map; + /* Command string to events */ extern int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev); +extern int parse_probe_trace_command(const char *cmd, + struct probe_trace_event *tev); /* Events to command string */ extern char *synthesize_perf_probe_command(struct perf_probe_event *pev); @@ -121,6 +125,7 @@ extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); /* Release event contents */ extern void clear_perf_probe_event(struct perf_probe_event *pev); +extern void clear_probe_trace_event(struct probe_trace_event *tev); /* Command string to line-range */ extern int parse_line_range_desc(const char *cmd, struct line_range *lr); @@ -144,6 +149,10 @@ bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map); +/* If there is no space to write, returns -E2BIG. */ +int e_snprintf(char *str, size_t size, const char *format, ...) + __attribute__((format(printf, 3, 4))); + /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c new file mode 100644 index 000000000000..bbb243717ec8 --- /dev/null +++ b/tools/perf/util/probe-file.c @@ -0,0 +1,301 @@ +/* + * probe-file.c : operate ftrace k/uprobe events files + * + * Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#include "util.h" +#include "event.h" +#include "strlist.h" +#include "debug.h" +#include "cache.h" +#include "color.h" +#include "symbol.h" +#include "thread.h" +#include <api/fs/debugfs.h> +#include <api/fs/tracefs.h> +#include "probe-event.h" +#include "probe-file.h" +#include "session.h" + +#define MAX_CMDLEN 256 + +static void print_open_warning(int err, bool uprobe) +{ + char sbuf[STRERR_BUFSIZE]; + + if (err == -ENOENT) { + const char *config; + + if (uprobe) + config = "CONFIG_UPROBE_EVENTS"; + else + config = "CONFIG_KPROBE_EVENTS"; + + pr_warning("%cprobe_events file does not exist" + " - please rebuild kernel with %s.\n", + uprobe ? 'u' : 'k', config); + } else if (err == -ENOTSUP) + pr_warning("Tracefs or debugfs is not mounted.\n"); + else + pr_warning("Failed to open %cprobe_events: %s\n", + uprobe ? 'u' : 'k', + strerror_r(-err, sbuf, sizeof(sbuf))); +} + +static void print_both_open_warning(int kerr, int uerr) +{ + /* Both kprobes and uprobes are disabled, warn it. */ + if (kerr == -ENOTSUP && uerr == -ENOTSUP) + pr_warning("Tracefs or debugfs is not mounted.\n"); + else if (kerr == -ENOENT && uerr == -ENOENT) + pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " + "or/and CONFIG_UPROBE_EVENTS.\n"); + else { + char sbuf[STRERR_BUFSIZE]; + pr_warning("Failed to open kprobe events: %s.\n", + strerror_r(-kerr, sbuf, sizeof(sbuf))); + pr_warning("Failed to open uprobe events: %s.\n", + strerror_r(-uerr, sbuf, sizeof(sbuf))); + } +} + +static int open_probe_events(const char *trace_file, bool readwrite) +{ + char buf[PATH_MAX]; + const char *__debugfs; + const char *tracing_dir = ""; + int ret; + + __debugfs = tracefs_find_mountpoint(); + if (__debugfs == NULL) { + tracing_dir = "tracing/"; + + __debugfs = debugfs_find_mountpoint(); + if (__debugfs == NULL) + return -ENOTSUP; + } + + ret = e_snprintf(buf, PATH_MAX, "%s/%s%s", + __debugfs, tracing_dir, trace_file); + if (ret >= 0) { + pr_debug("Opening %s write=%d\n", buf, readwrite); + if (readwrite && !probe_event_dry_run) + ret = open(buf, O_RDWR | O_APPEND, 0); + else + ret = open(buf, O_RDONLY, 0); + + if (ret < 0) + ret = -errno; + } + return ret; +} + +static int open_kprobe_events(bool readwrite) +{ + return open_probe_events("kprobe_events", readwrite); +} + +static int open_uprobe_events(bool readwrite) +{ + return open_probe_events("uprobe_events", readwrite); +} + +int probe_file__open(int flag) +{ + int fd; + + if (flag & PF_FL_UPROBE) + fd = open_uprobe_events(flag & PF_FL_RW); + else + fd = open_kprobe_events(flag & PF_FL_RW); + if (fd < 0) + print_open_warning(fd, flag & PF_FL_UPROBE); + + return fd; +} + +int probe_file__open_both(int *kfd, int *ufd, int flag) +{ + if (!kfd || !ufd) + return -EINVAL; + + *kfd = open_kprobe_events(flag & PF_FL_RW); + *ufd = open_uprobe_events(flag & PF_FL_RW); + if (*kfd < 0 && *ufd < 0) { + print_both_open_warning(*kfd, *ufd); + return *kfd; + } + + return 0; +} + +/* Get raw string list of current kprobe_events or uprobe_events */ +struct strlist *probe_file__get_rawlist(int fd) +{ + int ret, idx; + FILE *fp; + char buf[MAX_CMDLEN]; + char *p; + struct strlist *sl; + + sl = strlist__new(NULL, NULL); + + fp = fdopen(dup(fd), "r"); + while (!feof(fp)) { + p = fgets(buf, MAX_CMDLEN, fp); + if (!p) + break; + + idx = strlen(p) - 1; + if (p[idx] == '\n') + p[idx] = '\0'; + ret = strlist__add(sl, buf); + if (ret < 0) { + pr_debug("strlist__add failed (%d)\n", ret); + strlist__delete(sl); + return NULL; + } + } + fclose(fp); + + return sl; +} + +static struct strlist *__probe_file__get_namelist(int fd, bool include_group) +{ + char buf[128]; + struct strlist *sl, *rawlist; + struct str_node *ent; + struct probe_trace_event tev; + int ret = 0; + + memset(&tev, 0, sizeof(tev)); + rawlist = probe_file__get_rawlist(fd); + if (!rawlist) + return NULL; + sl = strlist__new(NULL, NULL); + strlist__for_each(ent, rawlist) { + ret = parse_probe_trace_command(ent->s, &tev); + if (ret < 0) + break; + if (include_group) { + ret = e_snprintf(buf, 128, "%s:%s", tev.group, + tev.event); + if (ret >= 0) + ret = strlist__add(sl, buf); + } else + ret = strlist__add(sl, tev.event); + clear_probe_trace_event(&tev); + if (ret < 0) + break; + } + strlist__delete(rawlist); + + if (ret < 0) { + strlist__delete(sl); + return NULL; + } + return sl; +} + +/* Get current perf-probe event names */ +struct strlist *probe_file__get_namelist(int fd) +{ + return __probe_file__get_namelist(fd, false); +} + +int probe_file__add_event(int fd, struct probe_trace_event *tev) +{ + int ret = 0; + char *buf = synthesize_probe_trace_command(tev); + char sbuf[STRERR_BUFSIZE]; + + if (!buf) { + pr_debug("Failed to synthesize probe trace event.\n"); + return -EINVAL; + } + + pr_debug("Writing event: %s\n", buf); + if (!probe_event_dry_run) { + ret = write(fd, buf, strlen(buf)); + if (ret <= 0) { + ret = -errno; + pr_warning("Failed to write event: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); + } + } + free(buf); + + return ret; +} + +static int __del_trace_probe_event(int fd, struct str_node *ent) +{ + char *p; + char buf[128]; + int ret; + + /* Convert from perf-probe event to trace-probe event */ + ret = e_snprintf(buf, 128, "-:%s", ent->s); + if (ret < 0) + goto error; + + p = strchr(buf + 2, ':'); + if (!p) { + pr_debug("Internal error: %s should have ':' but not.\n", + ent->s); + ret = -ENOTSUP; + goto error; + } + *p = '/'; + + pr_debug("Writing event: %s\n", buf); + ret = write(fd, buf, strlen(buf)); + if (ret < 0) { + ret = -errno; + goto error; + } + + pr_info("Removed event: %s\n", ent->s); + return 0; +error: + pr_warning("Failed to delete event: %s\n", + strerror_r(-ret, buf, sizeof(buf))); + return ret; +} + +int probe_file__del_events(int fd, struct strfilter *filter) +{ + struct strlist *namelist; + struct str_node *ent; + const char *p; + int ret = -ENOENT; + + namelist = __probe_file__get_namelist(fd, true); + if (!namelist) + return -ENOENT; + + strlist__for_each(ent, namelist) { + p = strchr(ent->s, ':'); + if ((p && strfilter__compare(filter, p + 1)) || + strfilter__compare(filter, ent->s)) { + ret = __del_trace_probe_event(fd, ent); + if (ret < 0) + break; + } + } + strlist__delete(namelist); + + return ret; +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h new file mode 100644 index 000000000000..ada94a242a17 --- /dev/null +++ b/tools/perf/util/probe-file.h @@ -0,0 +1,18 @@ +#ifndef __PROBE_FILE_H +#define __PROBE_FILE_H + +#include "strlist.h" +#include "strfilter.h" +#include "probe-event.h" + +#define PF_FL_UPROBE 1 +#define PF_FL_RW 2 + +int probe_file__open(int flag); +int probe_file__open_both(int *kfd, int *ufd, int flag); +struct strlist *probe_file__get_namelist(int fd); +struct strlist *probe_file__get_rawlist(int fd); +int probe_file__add_event(int fd, struct probe_trace_event *tev); +int probe_file__del_events(int fd, struct strfilter *filter); + +#endif diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2da65a710893..7b80f8cb62b9 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1355,7 +1355,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) vl->point.offset); /* Find local variables */ - vl->vars = strlist__new(true, NULL); + vl->vars = strlist__new(NULL, NULL); if (vl->vars == NULL) return -ENOMEM; af->child = true; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 0766d98c5da5..51be28b1bca2 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -16,7 +16,7 @@ util/util.c util/xyarray.c util/cgroup.c util/rblist.c -util/stat.c +util/counts.c util/strlist.c util/trace-event.c ../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 626422eda727..6324fe6b161e 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -941,76 +941,84 @@ static int pyrf_evlist__setup_types(void) return PyType_Ready(&pyrf_evlist__type); } +#define PERF_CONST(name) { #name, PERF_##name } + static struct { const char *name; int value; } perf__constants[] = { - { "TYPE_HARDWARE", PERF_TYPE_HARDWARE }, - { "TYPE_SOFTWARE", PERF_TYPE_SOFTWARE }, - { "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT }, - { "TYPE_HW_CACHE", PERF_TYPE_HW_CACHE }, - { "TYPE_RAW", PERF_TYPE_RAW }, - { "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT }, - - { "COUNT_HW_CPU_CYCLES", PERF_COUNT_HW_CPU_CYCLES }, - { "COUNT_HW_INSTRUCTIONS", PERF_COUNT_HW_INSTRUCTIONS }, - { "COUNT_HW_CACHE_REFERENCES", PERF_COUNT_HW_CACHE_REFERENCES }, - { "COUNT_HW_CACHE_MISSES", PERF_COUNT_HW_CACHE_MISSES }, - { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, - { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, - { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, - { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, - { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, - { "COUNT_HW_CACHE_DTLB", PERF_COUNT_HW_CACHE_DTLB }, - { "COUNT_HW_CACHE_ITLB", PERF_COUNT_HW_CACHE_ITLB }, - { "COUNT_HW_CACHE_BPU", PERF_COUNT_HW_CACHE_BPU }, - { "COUNT_HW_CACHE_OP_READ", PERF_COUNT_HW_CACHE_OP_READ }, - { "COUNT_HW_CACHE_OP_WRITE", PERF_COUNT_HW_CACHE_OP_WRITE }, - { "COUNT_HW_CACHE_OP_PREFETCH", PERF_COUNT_HW_CACHE_OP_PREFETCH }, - { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS }, - { "COUNT_HW_CACHE_RESULT_MISS", PERF_COUNT_HW_CACHE_RESULT_MISS }, - - { "COUNT_HW_STALLED_CYCLES_FRONTEND", PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, - { "COUNT_HW_STALLED_CYCLES_BACKEND", PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, - - { "COUNT_SW_CPU_CLOCK", PERF_COUNT_SW_CPU_CLOCK }, - { "COUNT_SW_TASK_CLOCK", PERF_COUNT_SW_TASK_CLOCK }, - { "COUNT_SW_PAGE_FAULTS", PERF_COUNT_SW_PAGE_FAULTS }, - { "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES }, - { "COUNT_SW_CPU_MIGRATIONS", PERF_COUNT_SW_CPU_MIGRATIONS }, - { "COUNT_SW_PAGE_FAULTS_MIN", PERF_COUNT_SW_PAGE_FAULTS_MIN }, - { "COUNT_SW_PAGE_FAULTS_MAJ", PERF_COUNT_SW_PAGE_FAULTS_MAJ }, - { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS }, - { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS }, - { "COUNT_SW_DUMMY", PERF_COUNT_SW_DUMMY }, - - { "SAMPLE_IP", PERF_SAMPLE_IP }, - { "SAMPLE_TID", PERF_SAMPLE_TID }, - { "SAMPLE_TIME", PERF_SAMPLE_TIME }, - { "SAMPLE_ADDR", PERF_SAMPLE_ADDR }, - { "SAMPLE_READ", PERF_SAMPLE_READ }, - { "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN }, - { "SAMPLE_ID", PERF_SAMPLE_ID }, - { "SAMPLE_CPU", PERF_SAMPLE_CPU }, - { "SAMPLE_PERIOD", PERF_SAMPLE_PERIOD }, - { "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID }, - { "SAMPLE_RAW", PERF_SAMPLE_RAW }, - - { "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED }, - { "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING }, - { "FORMAT_ID", PERF_FORMAT_ID }, - { "FORMAT_GROUP", PERF_FORMAT_GROUP }, - - { "RECORD_MMAP", PERF_RECORD_MMAP }, - { "RECORD_LOST", PERF_RECORD_LOST }, - { "RECORD_COMM", PERF_RECORD_COMM }, - { "RECORD_EXIT", PERF_RECORD_EXIT }, - { "RECORD_THROTTLE", PERF_RECORD_THROTTLE }, - { "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE }, - { "RECORD_FORK", PERF_RECORD_FORK }, - { "RECORD_READ", PERF_RECORD_READ }, - { "RECORD_SAMPLE", PERF_RECORD_SAMPLE }, + PERF_CONST(TYPE_HARDWARE), + PERF_CONST(TYPE_SOFTWARE), + PERF_CONST(TYPE_TRACEPOINT), + PERF_CONST(TYPE_HW_CACHE), + PERF_CONST(TYPE_RAW), + PERF_CONST(TYPE_BREAKPOINT), + + PERF_CONST(COUNT_HW_CPU_CYCLES), + PERF_CONST(COUNT_HW_INSTRUCTIONS), + PERF_CONST(COUNT_HW_CACHE_REFERENCES), + PERF_CONST(COUNT_HW_CACHE_MISSES), + PERF_CONST(COUNT_HW_BRANCH_INSTRUCTIONS), + PERF_CONST(COUNT_HW_BRANCH_MISSES), + PERF_CONST(COUNT_HW_BUS_CYCLES), + PERF_CONST(COUNT_HW_CACHE_L1D), + PERF_CONST(COUNT_HW_CACHE_L1I), + PERF_CONST(COUNT_HW_CACHE_LL), + PERF_CONST(COUNT_HW_CACHE_DTLB), + PERF_CONST(COUNT_HW_CACHE_ITLB), + PERF_CONST(COUNT_HW_CACHE_BPU), + PERF_CONST(COUNT_HW_CACHE_OP_READ), + PERF_CONST(COUNT_HW_CACHE_OP_WRITE), + PERF_CONST(COUNT_HW_CACHE_OP_PREFETCH), + PERF_CONST(COUNT_HW_CACHE_RESULT_ACCESS), + PERF_CONST(COUNT_HW_CACHE_RESULT_MISS), + + PERF_CONST(COUNT_HW_STALLED_CYCLES_FRONTEND), + PERF_CONST(COUNT_HW_STALLED_CYCLES_BACKEND), + + PERF_CONST(COUNT_SW_CPU_CLOCK), + PERF_CONST(COUNT_SW_TASK_CLOCK), + PERF_CONST(COUNT_SW_PAGE_FAULTS), + PERF_CONST(COUNT_SW_CONTEXT_SWITCHES), + PERF_CONST(COUNT_SW_CPU_MIGRATIONS), + PERF_CONST(COUNT_SW_PAGE_FAULTS_MIN), + PERF_CONST(COUNT_SW_PAGE_FAULTS_MAJ), + PERF_CONST(COUNT_SW_ALIGNMENT_FAULTS), + PERF_CONST(COUNT_SW_EMULATION_FAULTS), + PERF_CONST(COUNT_SW_DUMMY), + + PERF_CONST(SAMPLE_IP), + PERF_CONST(SAMPLE_TID), + PERF_CONST(SAMPLE_TIME), + PERF_CONST(SAMPLE_ADDR), + PERF_CONST(SAMPLE_READ), + PERF_CONST(SAMPLE_CALLCHAIN), + PERF_CONST(SAMPLE_ID), + PERF_CONST(SAMPLE_CPU), + PERF_CONST(SAMPLE_PERIOD), + PERF_CONST(SAMPLE_STREAM_ID), + PERF_CONST(SAMPLE_RAW), + + PERF_CONST(FORMAT_TOTAL_TIME_ENABLED), + PERF_CONST(FORMAT_TOTAL_TIME_RUNNING), + PERF_CONST(FORMAT_ID), + PERF_CONST(FORMAT_GROUP), + + PERF_CONST(RECORD_MMAP), + PERF_CONST(RECORD_LOST), + PERF_CONST(RECORD_COMM), + PERF_CONST(RECORD_EXIT), + PERF_CONST(RECORD_THROTTLE), + PERF_CONST(RECORD_UNTHROTTLE), + PERF_CONST(RECORD_FORK), + PERF_CONST(RECORD_READ), + PERF_CONST(RECORD_SAMPLE), + PERF_CONST(RECORD_MMAP2), + PERF_CONST(RECORD_AUX), + PERF_CONST(RECORD_ITRACE_START), + PERF_CONST(RECORD_LOST_SAMPLES), + PERF_CONST(RECORD_SWITCH), + PERF_CONST(RECORD_SWITCH_CPU_WIDE), { .name = NULL, }, }; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 1f7becbe5e18..0d228a29526d 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -85,6 +85,11 @@ static void perf_probe_comm_exec(struct perf_evsel *evsel) evsel->attr.comm_exec = 1; } +static void perf_probe_context_switch(struct perf_evsel *evsel) +{ + evsel->attr.context_switch = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); @@ -95,6 +100,11 @@ static bool perf_can_comm_exec(void) return perf_probe_api(perf_probe_comm_exec); } +bool perf_can_record_switch_events(void) +{ + return perf_probe_api(perf_probe_context_switch); +} + void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) { struct perf_evsel *evsel; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ed9dc2555ec7..18722e774a69 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -170,7 +170,7 @@ static void perf_session__delete_threads(struct perf_session *session) machine__delete_threads(&session->machines.host); } -static void perf_session_env__delete(struct perf_session_env *env) +static void perf_session_env__exit(struct perf_session_env *env) { zfree(&env->hostname); zfree(&env->os_release); @@ -180,6 +180,7 @@ static void perf_session_env__delete(struct perf_session_env *env) zfree(&env->cpuid); zfree(&env->cmdline); + zfree(&env->cmdline_argv); zfree(&env->sibling_cores); zfree(&env->sibling_threads); zfree(&env->numa_nodes); @@ -192,7 +193,7 @@ void perf_session__delete(struct perf_session *session) auxtrace_index__free(&session->auxtrace_index); perf_session__destroy_kernel_maps(session); perf_session__delete_threads(session); - perf_session_env__delete(&session->header.env); + perf_session_env__exit(&session->header.env); machines__exit(&session->machines); if (session->file) perf_data_file__close(session->file); @@ -332,6 +333,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->aux = perf_event__process_aux; if (tool->itrace_start == NULL) tool->itrace_start = perf_event__process_itrace_start; + if (tool->context_switch == NULL) + tool->context_switch = perf_event__process_switch; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -470,6 +473,19 @@ static void perf_event__itrace_start_swap(union perf_event *event, swap_sample_id_all(event, &event->itrace_start + 1); } +static void perf_event__switch_swap(union perf_event *event, bool sample_id_all) +{ + if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) { + event->context_switch.next_prev_pid = + bswap_32(event->context_switch.next_prev_pid); + event->context_switch.next_prev_tid = + bswap_32(event->context_switch.next_prev_tid); + } + + if (sample_id_all) + swap_sample_id_all(event, &event->context_switch + 1); +} + static void perf_event__throttle_swap(union perf_event *event, bool sample_id_all) { @@ -632,6 +648,8 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_AUX] = perf_event__aux_swap, [PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap, [PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap, + [PERF_RECORD_SWITCH] = perf_event__switch_swap, + [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -766,10 +784,18 @@ static void branch_stack__printf(struct perf_sample *sample) printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); - for (i = 0; i < sample->branch_stack->nr; i++) - printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n", - i, sample->branch_stack->entries[i].from, - sample->branch_stack->entries[i].to); + 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, + e->flags.cycles, + e->flags.mispred ? "M" : " ", + e->flags.predicted ? "P" : " ", + e->flags.abort ? "A" : " ", + e->flags.in_tx ? "T" : " ", + (unsigned)e->flags.reserved); + } } static void regs_dump__printf(u64 mask, u64 *regs) @@ -1093,6 +1119,9 @@ static int machines__deliver_event(struct machines *machines, return tool->aux(tool, event, sample, machine); case PERF_RECORD_ITRACE_START: return tool->itrace_start(tool, event, sample, machine); + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + return tool->context_switch(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 4c65a143a34c..7e3871606df3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -9,7 +9,7 @@ regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; -const char default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to"; +const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; @@ -319,6 +319,59 @@ struct sort_entry sort_srcline = { .se_width_idx = HISTC_SRCLINE, }; +/* --sort srcfile */ + +static char no_srcfile[1]; + +static char *get_srcfile(struct hist_entry *e) +{ + char *sf, *p; + struct map *map = e->ms.map; + + sf = get_srcline(map->dso, map__rip_2objdump(map, e->ip), + e->ms.sym, true); + if (!strcmp(sf, SRCLINE_UNKNOWN)) + return no_srcfile; + p = strchr(sf, ':'); + if (p && *sf) { + *p = 0; + return sf; + } + free(sf); + return no_srcfile; +} + +static int64_t +sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->srcfile) { + if (!left->ms.map) + left->srcfile = no_srcfile; + else + left->srcfile = get_srcfile(left); + } + if (!right->srcfile) { + if (!right->ms.map) + right->srcfile = no_srcfile; + else + right->srcfile = get_srcfile(right); + } + return strcmp(right->srcfile, left->srcfile); +} + +static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile); +} + +struct sort_entry sort_srcfile = { + .se_header = "Source File", + .se_cmp = sort__srcfile_cmp, + .se_snprintf = hist_entry__srcfile_snprintf, + .se_width_idx = HISTC_SRCFILE, +}; + /* --sort parent */ static int64_t @@ -526,6 +579,29 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, out); } +static int64_t +sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->branch_info->flags.cycles - + right->branch_info->flags.cycles; +} + +static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + if (he->branch_info->flags.cycles == 0) + return repsep_snprintf(bf, size, "%-*s", width, "-"); + return repsep_snprintf(bf, size, "%-*hd", width, + he->branch_info->flags.cycles); +} + +struct sort_entry sort_cycles = { + .se_header = "Basic Block Cycles", + .se_cmp = sort__cycles_cmp, + .se_snprintf = hist_entry__cycles_snprintf, + .se_width_idx = HISTC_CYCLES, +}; + /* --sort daddr_sym */ static int64_t sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) @@ -1173,6 +1249,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_SRCLINE, "srcline", sort_srcline), + DIM(SORT_SRCFILE, "srcfile", sort_srcfile), DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), @@ -1190,6 +1267,7 @@ static struct sort_dimension bstack_sort_dimensions[] = { DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), DIM(SORT_IN_TX, "in_tx", sort_in_tx), DIM(SORT_ABORT, "abort", sort_abort), + DIM(SORT_CYCLES, "cycles", sort_cycles), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index e97cd476d336..3c2a399f8f5b 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -114,6 +114,7 @@ struct hist_entry { }; }; char *srcline; + char *srcfile; struct symbol *parent; struct rb_root sorted_chain; struct branch_info *branch_info; @@ -172,6 +173,7 @@ enum sort_type { SORT_PARENT, SORT_CPU, SORT_SRCLINE, + SORT_SRCFILE, SORT_LOCAL_WEIGHT, SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, @@ -185,6 +187,7 @@ enum sort_type { SORT_MISPREDICT, SORT_ABORT, SORT_IN_TX, + SORT_CYCLES, /* memory mode specific sort keys */ __SORT_MEMORY_MODE, diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index c93fb0c5bd0b..fc08248f08ca 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -10,6 +10,8 @@ #include "symbol.h" +bool srcline_full_filename; + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -277,7 +279,9 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, if (!addr2line(dso_name, addr, &file, &line, dso)) goto out; - if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) { + if (asprintf(&srcline, "%s:%u", + srcline_full_filename ? file : basename(file), + line) < 0) { free(file); goto out; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index f2a0d1521e26..415c359de465 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,55 +97,6 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -struct perf_counts *perf_counts__new(int ncpus, int nthreads) -{ - struct perf_counts *counts = zalloc(sizeof(*counts)); - - if (counts) { - struct xyarray *values; - - values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); - if (!values) { - free(counts); - return NULL; - } - - counts->values = values; - } - - return counts; -} - -void perf_counts__delete(struct perf_counts *counts) -{ - if (counts) { - xyarray__delete(counts->values); - free(counts); - } -} - -static void perf_counts__reset(struct perf_counts *counts) -{ - xyarray__reset(counts->values); -} - -void perf_evsel__reset_counts(struct perf_evsel *evsel) -{ - perf_counts__reset(evsel->counts); -} - -int perf_evsel__alloc_counts(struct perf_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) -{ - perf_counts__delete(evsel->counts); - evsel->counts = NULL; -} - void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; @@ -238,3 +189,142 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist) perf_evsel__reset_counts(evsel); } } + +static void zero_per_pkg(struct perf_evsel *counter) +{ + if (counter->per_pkg_mask) + memset(counter->per_pkg_mask, 0, MAX_NR_CPUS); +} + +static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) +{ + unsigned long *mask = counter->per_pkg_mask; + struct cpu_map *cpus = perf_evsel__cpus(counter); + int s; + + *skip = false; + + if (!counter->per_pkg) + return 0; + + if (cpu_map__empty(cpus)) + return 0; + + if (!mask) { + mask = zalloc(MAX_NR_CPUS); + if (!mask) + return -ENOMEM; + + counter->per_pkg_mask = mask; + } + + s = cpu_map__get_socket(cpus, cpu); + if (s < 0) + return -1; + + *skip = test_and_set_bit(s, mask) == 1; + return 0; +} + +static int +process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel, + int cpu, int thread, + struct perf_counts_values *count) +{ + struct perf_counts_values *aggr = &evsel->counts->aggr; + static struct perf_counts_values zero; + bool skip = false; + + if (check_per_pkg(evsel, cpu, &skip)) { + pr_err("failed to read per-pkg counter\n"); + return -1; + } + + if (skip) + count = &zero; + + switch (config->aggr_mode) { + case AGGR_THREAD: + case AGGR_CORE: + case AGGR_SOCKET: + case AGGR_NONE: + if (!evsel->snapshot) + perf_evsel__compute_deltas(evsel, cpu, thread, count); + perf_counts_values__scale(count, config->scale, NULL); + if (config->aggr_mode == AGGR_NONE) + perf_stat__update_shadow_stats(evsel, count->values, cpu); + break; + case AGGR_GLOBAL: + aggr->val += count->val; + if (config->scale) { + aggr->ena += count->ena; + aggr->run += count->run; + } + default: + break; + } + + return 0; +} + +static int process_counter_maps(struct perf_stat_config *config, + struct perf_evsel *counter) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; + + if (counter->system_wide) + nthreads = 1; + + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + if (process_counter_values(config, counter, cpu, thread, + perf_counts(counter->counts, cpu, thread))) + return -1; + } + } + + return 0; +} + +int perf_stat_process_counter(struct perf_stat_config *config, + struct perf_evsel *counter) +{ + struct perf_counts_values *aggr = &counter->counts->aggr; + struct perf_stat *ps = counter->priv; + u64 *count = counter->counts->aggr.values; + int i, ret; + + aggr->val = aggr->ena = aggr->run = 0; + init_stats(ps->res_stats); + + if (counter->per_pkg) + zero_per_pkg(counter); + + ret = process_counter_maps(config, counter); + if (ret) + return ret; + + if (config->aggr_mode != AGGR_GLOBAL) + return 0; + + if (!counter->snapshot) + perf_evsel__compute_deltas(counter, -1, -1, aggr); + perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled); + + for (i = 0; i < 3; i++) + update_stats(&ps->res_stats[i], count[i]); + + if (verbose) { + fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + perf_evsel__name(counter), count[0], count[1], count[2]); + } + + /* + * Save the full runtime - to allow normalization during printout: + */ + perf_stat__update_shadow_stats(counter, count, 0); + + return 0; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 1cfbe0a980ac..62448c8175d3 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -33,29 +33,13 @@ enum aggr_mode { AGGR_THREAD, }; -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; +struct perf_stat_config { + enum aggr_mode aggr_mode; + bool scale; + FILE *output; + unsigned int interval; }; -struct perf_counts { - s8 scaled; - struct perf_counts_values aggr; - struct xyarray *values; -}; - -static inline struct perf_counts_values* -perf_counts(struct perf_counts *counts, int cpu, int thread) -{ - return xyarray__entry(counts->values, cpu, thread); -} - void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); @@ -89,13 +73,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -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_stat_priv(struct perf_evsel *evsel); int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); void perf_evsel__free_stat_priv(struct perf_evsel *evsel); @@ -109,4 +86,7 @@ int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw); 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_stat_process_counter(struct perf_stat_config *config, + struct perf_evsel *counter); #endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 6afd6106ceb5..fc8781de62db 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -357,3 +357,42 @@ void *memdup(const void *src, size_t len) return p; } + +char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints) +{ + /* + * FIXME: replace this with an expression using log10() when we + * find a suitable implementation, maybe the one in the dvb drivers... + * + * "%s == %d || " = log10(MAXINT) * 2 + 8 chars for the operators + */ + size_t size = nints * 28 + 1; /* \0 */ + size_t i, printed = 0; + char *expr = malloc(size); + + if (expr) { + const char *or_and = "||", *eq_neq = "=="; + char *e = expr; + + if (!in) { + or_and = "&&"; + eq_neq = "!="; + } + + for (i = 0; i < nints; ++i) { + if (printed == size) + goto out_err_overflow; + + if (i > 0) + printed += snprintf(e + printed, size - printed, " %s ", or_and); + printed += scnprintf(e + printed, size - printed, + "%s %s %d", var, eq_neq, ints[i]); + } + } + + return expr; + +out_err_overflow: + free(expr); + return NULL; +} diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 71f9d102b96f..bdf98f6f27bb 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -72,7 +72,7 @@ int strlist__load(struct strlist *slist, const char *filename) FILE *fp = fopen(filename, "r"); if (fp == NULL) - return errno; + return -errno; while (fgets(entry, sizeof(entry), fp) != NULL) { const size_t len = strlen(entry); @@ -108,43 +108,70 @@ struct str_node *strlist__find(struct strlist *slist, const char *entry) return snode; } -static int strlist__parse_list_entry(struct strlist *slist, const char *s) +static int strlist__parse_list_entry(struct strlist *slist, const char *s, + const char *subst_dir) { + int err; + char *subst = NULL; + if (strncmp(s, "file://", 7) == 0) return strlist__load(slist, s + 7); - return strlist__add(slist, s); + if (subst_dir) { + err = -ENOMEM; + if (asprintf(&subst, "%s/%s", subst_dir, s) < 0) + goto out; + + if (access(subst, F_OK) == 0) { + err = strlist__load(slist, subst); + goto out; + } + } + + err = strlist__add(slist, s); +out: + free(subst); + return err; } -int strlist__parse_list(struct strlist *slist, const char *s) +static int strlist__parse_list(struct strlist *slist, const char *s, const char *subst_dir) { char *sep; int err; while ((sep = strchr(s, ',')) != NULL) { *sep = '\0'; - err = strlist__parse_list_entry(slist, s); + err = strlist__parse_list_entry(slist, s, subst_dir); *sep = ','; if (err != 0) return err; s = sep + 1; } - return *s ? strlist__parse_list_entry(slist, s) : 0; + return *s ? strlist__parse_list_entry(slist, s, subst_dir) : 0; } -struct strlist *strlist__new(bool dupstr, const char *list) +struct strlist *strlist__new(const char *list, const struct strlist_config *config) { struct strlist *slist = malloc(sizeof(*slist)); if (slist != NULL) { + bool dupstr = true; + const char *dirname = NULL; + + if (config) { + dupstr = !config->dont_dupstr; + dirname = config->dirname; + } + rblist__init(&slist->rblist); slist->rblist.node_cmp = strlist__node_cmp; slist->rblist.node_new = strlist__node_new; slist->rblist.node_delete = strlist__node_delete; slist->dupstr = dupstr; - if (list && strlist__parse_list(slist, list) != 0) + + if (list && strlist__parse_list(slist, list, dirname) != 0) goto out_error; } diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 5c7f87069d9c..297565aa7535 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -16,7 +16,12 @@ struct strlist { bool dupstr; }; -struct strlist *strlist__new(bool dupstr, const char *slist); +struct strlist_config { + bool dont_dupstr; + const char *dirname; +}; + +struct strlist *strlist__new(const char *slist, const struct strlist_config *config); void strlist__delete(struct strlist *slist); void strlist__remove(struct strlist *slist, struct str_node *sn); @@ -74,6 +79,4 @@ static inline struct str_node *strlist__next(struct str_node *sn) #define strlist__for_each_safe(pos, n, slist) \ for (pos = strlist__first(slist), n = strlist__next(pos); pos;\ pos = n, n = strlist__next(n)) - -int strlist__parse_list(struct strlist *slist, const char *s); #endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 65f7e389ae09..b0ad810f04dd 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, #endif #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT -static int elf_getphdrnum(Elf *elf, size_t *dst) +int elf_getphdrnum(Elf *elf, size_t *dst) { GElf_Ehdr gehdr; GElf_Ehdr *ehdr; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 60f11414bb5c..725640fd7cd8 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -444,7 +444,12 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { - return symbols__find(&dso->symbols[type], addr); + if (dso->last_find_result[type].addr != addr) { + dso->last_find_result[type].addr = addr; + dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); + } + + return dso->last_find_result[type].symbol; } struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) @@ -1906,7 +1911,7 @@ int setup_list(struct strlist **list, const char *list_str, if (list_str == NULL) return 0; - *list = strlist__new(true, list_str); + *list = strlist__new(list_str, NULL); if (!*list) { pr_err("problems parsing %s list\n", list_name); return -1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index b98ce51af142..a4cde92afbad 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -106,7 +106,8 @@ struct symbol_conf { filter_relative, show_hist_headers, branch_callstack, - has_filter; + has_filter, + show_ref_callgraph; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 292ae2c90e06..6ec3c5ca438f 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -195,7 +195,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) pid_t pid, prev_pid = INT_MAX; char *end_ptr; struct str_node *pos; - struct strlist *slist = strlist__new(false, pid_str); + struct strlist_config slist_config = { .dont_dupstr = true, }; + struct strlist *slist = strlist__new(pid_str, &slist_config); if (!slist) return NULL; @@ -265,13 +266,14 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) pid_t tid, prev_tid = INT_MAX; char *end_ptr; struct str_node *pos; + struct strlist_config slist_config = { .dont_dupstr = true, }; struct strlist *slist; /* perf-stat expects threads to be generated even if tid not given */ if (!tid_str) return thread_map__new_dummy(); - slist = strlist__new(false, tid_str); + slist = strlist__new(tid_str, &slist_config); if (!slist) return NULL; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index c307dd438286..cab8cc24831b 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -46,6 +46,7 @@ struct perf_tool { lost_samples, aux, itrace_start, + context_switch, throttle, unthrottle; event_attr_op attr; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index eb72716017ac..22245986e59e 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -341,20 +341,14 @@ out: static int record_proc_kallsyms(void) { - unsigned int size; - const char *path = "/proc/kallsyms"; - struct stat st; - int ret, err = 0; - - ret = stat(path, &st); - if (ret < 0) { - /* not found */ - size = 0; - if (write(output_fd, &size, 4) != 4) - err = -EIO; - return err; - } - return record_file(path, 4); + unsigned long long size = 0; + /* + * Just to keep older perf.data file parsers happy, record a zero + * sized kallsyms file, i.e. do the same thing that was done when + * /proc/kallsyms (or something specified via --kallsyms, in a + * different path) couldn't be read. + */ + return write(output_fd, &size, 4) != 4 ? -EIO : 0; } static int record_ftrace_printk(void) diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index d4957418657e..8ff7d620d942 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -135,36 +135,6 @@ void event_format__print(struct event_format *event, return event_format__fprintf(event, cpu, data, size, stdout); } -void parse_proc_kallsyms(struct pevent *pevent, - char *file, unsigned int size __maybe_unused) -{ - unsigned long long addr; - char *func; - char *line; - char *next = NULL; - char *addr_str; - char *mod; - char *fmt = NULL; - - line = strtok_r(file, "\n", &next); - while (line) { - mod = NULL; - addr_str = strtok_r(line, " ", &fmt); - addr = strtoull(addr_str, NULL, 16); - /* skip character */ - strtok_r(NULL, " ", &fmt); - func = strtok_r(NULL, "\t", &fmt); - mod = strtok_r(NULL, "]", &fmt); - /* truncate the extra '[' */ - if (mod) - mod = mod + 1; - - pevent_register_function(pevent, func, addr, mod); - - line = strtok_r(NULL, "\n", &next); - } -} - void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size __maybe_unused) { diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 54d9e9b548a8..b67a0ccf5ab9 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -162,25 +162,23 @@ out: static int read_proc_kallsyms(struct pevent *pevent) { unsigned int size; - char *buf; size = read4(pevent); if (!size) return 0; - - buf = malloc(size + 1); - if (buf == NULL) - return -1; - - if (do_read(buf, size) < 0) { - free(buf); - return -1; - } - buf[size] = '\0'; - - parse_proc_kallsyms(pevent, buf, size); - - free(buf); + /* + * Just skip it, now that we configure libtraceevent to use the + * tools/perf/ symbol resolver. + * + * We need to skip it so that we can continue parsing old perf.data + * files, that contains this /proc/kallsyms payload. + * + * Newer perf.data files will have just the 4-bytes zeros "kallsyms + * payload", so that older tools can continue reading it and interpret + * it as "no kallsyms payload is present". + */ + lseek(input_fd, size, SEEK_CUR); + trace_data_size += size; return 0; } diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 6322d37164c5..b90e646c7a91 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <traceevent/event-parse.h> #include "trace-event.h" +#include "machine.h" #include "util.h" /* @@ -19,6 +20,7 @@ * there. */ static struct trace_event tevent; +static bool tevent_initialized; int trace_event__init(struct trace_event *t) { @@ -32,6 +34,31 @@ int trace_event__init(struct trace_event *t) return pevent ? 0 : -1; } +static int trace_event__init2(void) +{ + int be = traceevent_host_bigendian(); + struct pevent *pevent; + + if (trace_event__init(&tevent)) + return -1; + + pevent = tevent.pevent; + pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); + pevent_set_file_bigendian(pevent, be); + pevent_set_host_bigendian(pevent, be); + tevent_initialized = true; + return 0; +} + +int trace_event__register_resolver(struct machine *machine, + pevent_func_resolver_t *func) +{ + if (!tevent_initialized && trace_event__init2()) + return -1; + + return pevent_set_function_resolver(tevent.pevent, func, machine); +} + void trace_event__cleanup(struct trace_event *t) { traceevent_unload_plugins(t->plugin_list, t->pevent); @@ -62,21 +89,8 @@ tp_format(const char *sys, const char *name) struct event_format* trace_event__tp_format(const char *sys, const char *name) { - static bool initialized; - - if (!initialized) { - int be = traceevent_host_bigendian(); - struct pevent *pevent; - - if (trace_event__init(&tevent)) - return NULL; - - pevent = tevent.pevent; - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, be); - pevent_set_host_bigendian(pevent, be); - initialized = true; - } + if (!tevent_initialized && trace_event__init2()) + return NULL; return tp_format(sys, name); } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index d5168f0be4ec..da6cc4cc2a4f 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -18,6 +18,8 @@ struct trace_event { int trace_event__init(struct trace_event *t); void trace_event__cleanup(struct trace_event *t); +int trace_event__register_resolver(struct machine *machine, + pevent_func_resolver_t *func); struct event_format* trace_event__tp_format(const char *sys, const char *name); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index edc2d633b332..f7adf1203df1 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -566,6 +566,96 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) return (unsigned long) -1; } +int get_stack_size(const char *str, unsigned long *_size) +{ + char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); + + size = strtoul(str, &endptr, 0); + + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; + return 0; + + } while (0); + + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); + return -1; +} + +int parse_callchain_record(const char *arg, struct callchain_param *param) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph fp\n"); + break; + +#ifdef HAVE_DWARF_UNWIND_SUPPORT + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; + + ret = 0; + param->record_mode = CALLCHAIN_DWARF; + param->dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; + + ret = get_stack_size(tok, &size); + param->dump_size = size; + } +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + return ret; +} + int filename__read_str(const char *filename, char **buf, size_t *sizep) { size_t size = 0, alloc_size = 0; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 8bce58b47a82..88a891562a47 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -318,6 +318,7 @@ static inline int path__join3(char *bf, size_t size, struct dso; struct symbol; +extern bool srcline_full_filename; char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym); void free_srcline(char *srcline); @@ -339,4 +340,18 @@ int gzip_decompress_to_file(const char *input, int output_fd); int lzma_decompress_to_file(const char *input, int output_fd); #endif +char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints); + +static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, true, nints, ints); +} + +static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, false, nints, ints); +} + +int get_stack_size(const char *str, unsigned long *_size); + #endif /* GIT_COMPAT_UTIL_H */ |