diff options
Diffstat (limited to 'tools/perf/builtin-script.c')
| -rw-r--r-- | tools/perf/builtin-script.c | 1480 |
1 files changed, 866 insertions, 614 deletions
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 69394ac0a20d..62e43d3c5ad7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -32,14 +32,19 @@ #include "util/time-utils.h" #include "util/path.h" #include "util/event.h" +#include "util/mem-info.h" +#include "util/metricgroup.h" #include "ui/ui.h" #include "print_binary.h" +#include "print_insn.h" #include "archinsn.h" #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <linux/unaligned.h> #include <sys/utsname.h> #include "asm/bug.h" #include "util/mem-events.h" @@ -48,6 +53,7 @@ #include <errno.h> #include <inttypes.h> #include <signal.h> +#include <stdio.h> #include <sys/param.h> #include <sys/types.h> #include <sys/stat.h> @@ -59,11 +65,13 @@ #include "util/dlfilter.h" #include "util/record.h" #include "util/util.h" +#include "util/cgroup.h" +#include "util/annotate.h" #include "perf.h" #include <linux/ctype.h> #ifdef HAVE_LIBTRACEEVENT -#include <traceevent/event-parse.h> +#include <event-parse.h> #endif static char const *script_name; @@ -81,15 +89,12 @@ static bool system_wide; static bool print_flags; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); -static struct perf_stat_config stat_config; static int max_blocks; static bool native_arch; static struct dlfilter *dlfilter; static int dlargc; static char **dlargv; -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; - enum perf_output_field { PERF_OUTPUT_COMM = 1ULL << 0, PERF_OUTPUT_TID = 1ULL << 1, @@ -130,6 +135,12 @@ enum perf_output_field { PERF_OUTPUT_BRSTACKINSNLEN = 1ULL << 36, PERF_OUTPUT_MACHINE_PID = 1ULL << 37, PERF_OUTPUT_VCPU = 1ULL << 38, + PERF_OUTPUT_CGROUP = 1ULL << 39, + PERF_OUTPUT_RETIRE_LAT = 1ULL << 40, + PERF_OUTPUT_DSOFF = 1ULL << 41, + PERF_OUTPUT_DISASM = 1ULL << 42, + PERF_OUTPUT_BRSTACKDISASM = 1ULL << 43, + PERF_OUTPUT_BRCNTR = 1ULL << 44, }; struct perf_script { @@ -171,6 +182,7 @@ struct output_option { {.str = "ip", .field = PERF_OUTPUT_IP}, {.str = "sym", .field = PERF_OUTPUT_SYM}, {.str = "dso", .field = PERF_OUTPUT_DSO}, + {.str = "dsoff", .field = PERF_OUTPUT_DSOFF}, {.str = "addr", .field = PERF_OUTPUT_ADDR}, {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET}, {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, @@ -184,6 +196,7 @@ struct output_option { {.str = "bpf-output", .field = PERF_OUTPUT_BPF_OUTPUT}, {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT}, {.str = "insn", .field = PERF_OUTPUT_INSN}, + {.str = "disasm", .field = PERF_OUTPUT_DISASM}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF}, @@ -200,6 +213,10 @@ struct output_option { {.str = "brstackinsnlen", .field = PERF_OUTPUT_BRSTACKINSNLEN}, {.str = "machine_pid", .field = PERF_OUTPUT_MACHINE_PID}, {.str = "vcpu", .field = PERF_OUTPUT_VCPU}, + {.str = "cgroup", .field = PERF_OUTPUT_CGROUP}, + {.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT}, + {.str = "brstackdisasm", .field = PERF_OUTPUT_BRSTACKDISASM}, + {.str = "brcntr", .field = PERF_OUTPUT_BRCNTR}, }; enum { @@ -208,6 +225,10 @@ enum { OUTPUT_TYPE_MAX }; +// We need to refactor the evsel->priv use in 'perf script' to allow for +// using that area, that is being used only in some cases. +#define OUTPUT_TYPE_UNSET -1 + /* default set to maintain compatibility with current format */ static struct { bool user_set; @@ -275,7 +296,7 @@ static struct { PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE | - PERF_OUTPUT_INS_LAT, + PERF_OUTPUT_INS_LAT | PERF_OUTPUT_RETIRE_LAT, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -321,16 +342,8 @@ struct evsel_script { char *filename; FILE *fp; u64 samples; - /* For metric output */ - u64 val; - int gnum; }; -static inline struct evsel_script *evsel_script(struct evsel *evsel) -{ - return (struct evsel_script *)evsel->priv; -} - static struct evsel_script *evsel_script__new(struct evsel *evsel, struct perf_data *data) { struct evsel_script *es = zalloc(sizeof(*es)); @@ -381,6 +394,24 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } +static inline int evsel__output_type(struct evsel *evsel) +{ + int type = evsel->script_output_type; + + if (type == OUTPUT_TYPE_UNSET) { + type = output_type(evsel->core.attr.type); + if (type == OUTPUT_TYPE_OTHER) { + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu && pmu->is_core) + type = PERF_TYPE_RAW; + } + evsel->script_output_type = type; + } + + return type; +} + static bool output_set_by_user(void) { int j; @@ -405,13 +436,13 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[evsel__output_type(evsel)].fields & PERF_OUTPUT_##x) static int evsel__do_check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, enum perf_output_field field, bool allow_user_set) { struct perf_event_attr *attr = &evsel->core.attr; - int type = output_type(attr->type); + int type = evsel__output_type(evsel); const char *evname; if (attr->sample_type & sample_type) @@ -445,7 +476,6 @@ static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char * static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) { - struct perf_event_attr *attr = &evsel->core.attr; bool allow_user_set; if (evsel__is_dummy_event(evsel)) @@ -500,12 +530,19 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) && !allow_user_set && + if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM)) + && !allow_user_set && !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) { pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" "Hint: run 'perf record -b ...'\n"); return -EINVAL; } + if (PRINT_FIELD(BRCNTR) && + !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_COUNTERS)) { + pr_err("Display of branch counter requested but it's not enabled\n" + "Hint: run 'perf record -j any,counter ...'\n"); + return -EINVAL; + } if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) && evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID)) return -EINVAL; @@ -542,12 +579,22 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_INS_LAT)) return -EINVAL; + if (PRINT_FIELD(CGROUP) && + evsel__check_stype(evsel, PERF_SAMPLE_CGROUP, "CGROUP", PERF_OUTPUT_CGROUP)) { + pr_err("Hint: run 'perf record --all-cgroups ...'\n"); + return -EINVAL; + } + + if (PRINT_FIELD(RETIRE_LAT) && + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_RETIRE_LAT)) + return -EINVAL; + return 0; } -static void set_print_ip_opts(struct perf_event_attr *attr) +static void evsel__set_print_ip_opts(struct evsel *evsel) { - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -559,6 +606,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr) if (PRINT_FIELD(DSO)) output[type].print_ip_opts |= EVSEL__PRINT_DSO; + if (PRINT_FIELD(DSOFF)) + output[type].print_ip_opts |= EVSEL__PRINT_DSOFF; + if (PRINT_FIELD(SYMOFFSET)) output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; @@ -574,7 +624,7 @@ static struct evsel *find_first_output_type(struct evlist *evlist, evlist__for_each_entry(evlist, evsel) { if (evsel__is_dummy_event(evsel)) continue; - if (output_type(evsel->core.attr.type) == (int)type) + if (evsel__output_type(evsel) == (int)type) return evsel; } return NULL; @@ -612,7 +662,11 @@ static int perf_session__check_output_opt(struct perf_session *session) if (evsel == NULL) continue; - set_print_ip_opts(&evsel->core.attr); + /* 'dsoff' implys 'dso' field */ + if (output[j].fields & PERF_OUTPUT_DSOFF) + output[j].fields |= PERF_OUTPUT_DSO; + + evsel__set_print_ip_opts(evsel); tod |= output[j].fields & PERF_OUTPUT_TOD; } @@ -622,7 +676,7 @@ static int perf_session__check_output_opt(struct perf_session *session) evlist__for_each_entry(session->evlist, evsel) { not_pipe = true; - if (evsel__has_callchain(evsel)) { + if (evsel__has_callchain(evsel) || evsel__is_offcpu_event(evsel)) { use_callchain = true; break; } @@ -648,13 +702,13 @@ static int perf_session__check_output_opt(struct perf_session *session) output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); goto out; } } } - if (tod && !session->header.env.clock.enabled) { + if (tod && !perf_session__env(session)->clock.enabled) { pr_err("Can't provide 'tod' time, missing clock data. " "Please record with -k/--clockid option.\n"); return -1; @@ -699,7 +753,7 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen, if (buflen < 64 || !script) return buf; - env = &script->session->header.env; + env = perf_session__env(script->session); if (!env->clock.enabled) { scnprintf(buf, buflen, "disabled"); return buf; @@ -735,14 +789,20 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen, static int perf_sample__fprintf_iregs(struct perf_sample *sample, struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->intr_regs, + if (!sample->intr_regs) + return 0; + + return perf_sample__fprintf_regs(perf_sample__intr_regs(sample), attr->sample_regs_intr, arch, fp); } static int perf_sample__fprintf_uregs(struct perf_sample *sample, struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->user_regs, + if (!sample->user_regs) + return 0; + + return perf_sample__fprintf_regs(perf_sample__user_regs(sample), attr->sample_regs_user, arch, fp); } @@ -752,12 +812,24 @@ static int perf_sample__fprintf_start(struct perf_script *script, struct evsel *evsel, u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; unsigned long secs; unsigned long long nsecs; int printed = 0; char tstr[128]; + /* + * Print the branch counter's abbreviation list, + * if the branch counter is available. + */ + if (PRINT_FIELD(BRCNTR) && !verbose) { + char *buf; + + if (!annotation_br_cntr_abbr_list(&buf, evsel, true)) { + printed += fprintf(stdout, "%s", buf); + free(buf); + } + } + if (PRINT_FIELD(MACHINE_PID) && sample->machine_pid) printed += fprintf(fp, "VM:%5d ", sample->machine_pid); @@ -777,11 +849,11 @@ static int perf_sample__fprintf_start(struct perf_script *script, } if (PRINT_FIELD(PID) && PRINT_FIELD(TID)) - printed += fprintf(fp, "%5d/%-5d ", sample->pid, sample->tid); + printed += fprintf(fp, "%7d/%-7d ", sample->pid, sample->tid); else if (PRINT_FIELD(PID)) - printed += fprintf(fp, "%5d ", sample->pid); + printed += fprintf(fp, "%7d ", sample->pid); else if (PRINT_FIELD(TID)) - printed += fprintf(fp, "%5d ", sample->tid); + printed += fprintf(fp, "%7d ", sample->tid); if (PRINT_FIELD(CPU)) { if (latency_format) @@ -869,32 +941,38 @@ static int perf_sample__fprintf_start(struct perf_script *script, return printed; } -static inline char -mispred_str(struct branch_entry *br) +static inline size_t +bstack_event_str(struct branch_entry *br, char *buf, size_t sz) { - if (!(br->flags.mispred || br->flags.predicted)) - return '-'; + if (!(br->flags.mispred || br->flags.predicted || br->flags.not_taken)) + return snprintf(buf, sz, "-"); - return br->flags.predicted ? 'P' : 'M'; + return snprintf(buf, sz, "%s%s", + br->flags.predicted ? "P" : "M", + br->flags.not_taken ? "N" : ""); } static int print_bstack_flags(FILE *fp, struct branch_entry *br) { - return fprintf(fp, "/%c/%c/%c/%d/%s ", - mispred_str(br), + char events[16] = { 0 }; + size_t pos; + + pos = bstack_event_str(br, events, sizeof(events)); + return fprintf(fp, "/%s/%c/%c/%d/%s/%s ", + pos < 0 ? "-" : events, br->flags.in_tx ? 'X' : '-', br->flags.abort ? 'A' : '-', br->flags.cycles, - get_branch_type(br)); + get_branch_type(br), + br->flags.spec ? branch_spec_desc(br->flags.spec) : "-"); } static int perf_sample__fprintf_brstack(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -905,26 +983,22 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, from = entries[i].from; to = entries[i].to; + printed += fprintf(fp, " 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + struct addr_location alf, alt; + + addr_location__init(&alf); + addr_location__init(&alt); thread__find_map_fb(thread, sample->cpumode, from, &alf); thread__find_map_fb(thread, sample->cpumode, to, &alt); - } - - printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } - printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); + printed += fprintf(fp, "/0x%"PRIx64, to); + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); + addr_location__exit(&alt); + addr_location__exit(&alf); + } else + printed += fprintf(fp, "/0x%"PRIx64, to); printed += print_bstack_flags(fp, entries + i); } @@ -934,11 +1008,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -946,9 +1019,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + addr_location__init(&alf); + addr_location__init(&alt); from = entries[i].from; to = entries[i].to; @@ -956,19 +1030,15 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, thread__find_symbol_fb(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "%c", '/'); printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); + addr_location__exit(&alt); + addr_location__exit(&alf); } return printed; @@ -976,11 +1046,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); - struct addr_location alf, alt; u64 i, from, to; int printed = 0; @@ -988,33 +1057,30 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + addr_location__init(&alf); + addr_location__init(&alt); from = entries[i].from; to = entries[i].to; if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && - !alf.map->dso->adjust_symbols) - from = map__map_ip(alf.map, from); + !dso__adjust_symbols(map__dso(alf.map))) + from = map__dso_map_ip(alf.map, from); if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && - !alt.map->dso->adjust_symbols) - to = map__map_ip(alt.map, to); + !dso__adjust_symbols(map__dso(alt.map))) + to = map__dso_map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); + addr_location__exit(&alt); + addr_location__exit(&alf); } return printed; @@ -1028,6 +1094,8 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, long offset, len; struct addr_location al; bool kernel; + struct dso *dso; + int ret = 0; if (!start || !end) return 0; @@ -1049,7 +1117,6 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return -ENXIO; } - memset(&al, 0, sizeof(al)); if (end - start > MAXBB - MAXINSN) { if (last) pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); @@ -1058,27 +1125,31 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { + addr_location__init(&al); + if (!thread__find_map(thread, *cpumode, start, &al) || (dso = map__dso(al.map)) == NULL) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } - if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) { + if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } /* Load maps to ensure dso->is_64_bit has been updated */ map__load(al.map); - offset = al.map->map_ip(al.map, start); - len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer, + offset = map__map_ip(al.map, start); + len = dso__data_read_offset(dso, machine, offset, (u8 *)buffer, end - start + MAXINSN); - *is64bit = al.map->dso->is_64_bit; + *is64bit = dso__is_64_bit(dso); if (len <= 0) pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", start, end); - return len; + ret = len; +out: + addr_location__exit(&al); + return ret; } static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srccode_state *state) @@ -1088,10 +1159,11 @@ static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srcc unsigned line; int len; char *srccode; + struct dso *dso; - if (!map || !map->dso) + if (!map || (dso = map__dso(map)) == NULL) return 0; - srcfile = get_srcline_split(map->dso, + srcfile = get_srcline_split(dso, map__rip_2objdump(map, addr), &line); if (!srcfile) @@ -1128,29 +1200,91 @@ static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) struct addr_location al; int ret = 0; - memset(&al, 0, sizeof(al)); + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if (!al.map) - return 0; + goto out; ret = map__fprintf_srccode(al.map, al.addr, stdout, - &thread->srccode_state); + thread__srccode_state(thread)); if (ret) ret += printf("\n"); +out: + addr_location__exit(&al); return ret; } +static int any_dump_insn(struct evsel *evsel __maybe_unused, + struct perf_insn *x, uint64_t ip, + u8 *inbuf, int inlen, int *lenp, + FILE *fp) +{ + if (PRINT_FIELD(BRSTACKDISASM)) { + int printed = fprintf_insn_asm(x->machine, x->thread, x->cpumode, x->is64bit, + (uint8_t *)inbuf, inlen, ip, lenp, + PRINT_INSN_IMM_HEX, fp); + + if (printed > 0) + return printed; + } + return fprintf(fp, "%s", dump_insn(x, ip, inbuf, inlen, lenp)); +} + +static int add_padding(FILE *fp, int printed, int padding) +{ + if (printed >= 0 && printed < padding) + printed += fprintf(fp, "%*s", padding - printed, ""); + return printed; +} + static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, int insn, FILE *fp, int *total_cycles, - struct perf_event_attr *attr) + struct evsel *evsel, + struct thread *thread, + u64 br_cntr) { int ilen = 0; - int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip, - dump_insn(x, ip, inbuf, len, &ilen)); + int printed = fprintf(fp, "\t%016" PRIx64 "\t", ip); + + printed += add_padding(fp, any_dump_insn(evsel, x, ip, inbuf, len, &ilen, fp), 30); + printed += fprintf(fp, "\t"); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "ilen: %d\t", ilen); + if (PRINT_FIELD(SRCLINE)) { + struct addr_location al; + + addr_location__init(&al); + thread__find_map(thread, x->cpumode, ip, &al); + printed += map__fprintf_srcline(al.map, al.addr, " srcline: ", fp); + printed += fprintf(fp, "\t"); + addr_location__exit(&al); + } + + if (PRINT_FIELD(BRCNTR)) { + struct evsel *pos = evsel__leader(evsel); + unsigned int i = 0, j, num, mask, width; + + perf_env__find_br_cntr_info(evsel__env(evsel), NULL, &width); + mask = (1L << width) - 1; + printed += fprintf(fp, "br_cntr: "); + evlist__for_each_entry_from(evsel->evlist, pos) { + if (!(pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) + continue; + if (evsel__leader(pos) != evsel__leader(evsel)) + break; + + num = (br_cntr >> (i++ * width)) & mask; + if (!verbose) { + for (j = 0; j < num; j++) + printed += fprintf(fp, "%s", pos->abbr_name); + } else + printed += fprintf(fp, "%s %d ", pos->name, num); + } + printed += fprintf(fp, "\t"); + } + printed += fprintf(fp, "#%s%s%s%s", en->flags.predicted ? " PRED" : "", en->flags.mispred ? " MISPRED" : "", @@ -1162,22 +1296,22 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, if (insn) printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles); } + return printed + fprintf(fp, "\n"); } static int ip__fprintf_sym(uint64_t addr, struct thread *thread, u8 cpumode, int cpu, struct symbol **lastsym, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; - int off, printed = 0; - - memset(&al, 0, sizeof(al)); + int off, printed = 0, ret = 0; + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) - return 0; + goto out; al.cpu = cpu; al.sym = NULL; @@ -1185,12 +1319,12 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, al.sym = map__find_symbol(al.map, al.addr); if (!al.sym) - return 0; + goto out; if (al.addr < al.sym->end) off = al.addr - al.sym->start; else - off = al.addr - al.map->start - al.sym->start; + off = al.addr - map__start(al.map) - al.sym->start; printed += fprintf(fp, "\t%s", al.sym->name); if (off) printed += fprintf(fp, "%+d", off); @@ -1200,10 +1334,14 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, printed += fprintf(fp, "\n"); *lastsym = al.sym; - return printed; + ret = printed; +out: + addr_location__exit(&al); + return ret; } static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, + struct evsel *evsel, struct thread *thread, struct perf_event_attr *attr, struct machine *machine, FILE *fp) @@ -1217,6 +1355,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, unsigned off; struct symbol *lastsym = NULL; int total_cycles = 0; + u64 br_cntr = 0; if (!(br && br->nr)) return 0; @@ -1225,8 +1364,12 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, nr = max_blocks + 1; x.thread = thread; + x.machine = machine; x.cpu = sample->cpu; + if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr) + br_cntr = sample->branch_stack_cntr[nr - 1]; + printed += fprintf(fp, "%c", '\n'); /* Handle first from jump, of which we don't know the entry. */ @@ -1235,10 +1378,10 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, machine, thread, &x.is64bit, &x.cpumode, false); if (len > 0) { printed += ip__fprintf_sym(entries[nr - 1].from, thread, - x.cpumode, x.cpu, &lastsym, attr, fp); + x.cpumode, x.cpu, &lastsym, evsel, fp); printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1], &x, buffer, len, 0, fp, &total_cycles, - attr); + evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); } @@ -1266,17 +1409,19 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, for (off = 0; off < (unsigned)len; off += ilen) { uint64_t ip = start + off; - printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (ip == end) { + if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr) + br_cntr = sample->branch_stack_cntr[i]; printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp, - &total_cycles, attr); + &total_cycles, evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); break; } else { ilen = 0; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s", ip, - dump_insn(&x, ip, buffer + off, len - off, &ilen)); + printed += fprintf(fp, "\t%016" PRIx64 "\t", ip); + printed += any_dump_insn(evsel, &x, ip, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1301,12 +1446,12 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, goto out; /* - * Print final block upto sample + * Print final block up to sample * * Due to pipeline delays the LBRs might be missing a branch * or two, which can result in very large or negative blocks * between final branch and sample. When this happens just - * continue walking after the last TO until we hit a branch. + * continue walking after the last TO. */ start = entries[0].to; end = sample->ip; @@ -1315,7 +1460,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, end = start + 128; } len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); - printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (len <= 0) { /* Print at least last IP if basic block did not work */ len = grab_bb(buffer, sample->ip, sample->ip, @@ -1323,8 +1468,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, if (len <= 0) goto out; ilen = 0; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s", sample->ip, - dump_insn(&x, sample->ip, buffer, len, &ilen)); + printed += fprintf(fp, "\t%016" PRIx64 "\t", sample->ip); + printed += any_dump_insn(evsel, &x, sample->ip, buffer, len, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1334,14 +1479,16 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, } for (off = 0; off <= end - start; off += ilen) { ilen = 0; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s", start + off, - dump_insn(&x, start + off, buffer + off, len - off, &ilen)); + printed += fprintf(fp, "\t%016" PRIx64 "\t", start + off); + printed += any_dump_insn(evsel, &x, start + off, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); if (ilen == 0) break; - if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { + if ((attr->branch_sample_type == 0 || attr->branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + && arch_is_uncond_branch(buffer + off, len - off, x.is64bit) + && start + off != sample->ip) { /* * Hit a missing branch. Just stop. */ @@ -1357,12 +1504,13 @@ out: static int perf_sample__fprintf_addr(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int printed = fprintf(fp, "%16" PRIx64, sample->addr); - if (!sample_addr_correlates_sym(attr)) + addr_location__init(&al); + if (!sample_addr_correlates_sym(&evsel->core.attr)) goto out; thread__resolve(thread, &al, sample); @@ -1375,12 +1523,10 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample, printed += symbol__fprintf_symname(al.sym, fp); } - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(al.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(al.map, PRINT_FIELD(DSOFF), al.addr, fp); out: + addr_location__exit(&al); return printed; } @@ -1391,11 +1537,10 @@ static const char *resolve_branch_sym(struct perf_sample *sample, struct addr_location *addr_al, u64 *ip) { - struct perf_event_attr *attr = &evsel->core.attr; const char *name = NULL; if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { - if (sample_addr_correlates_sym(attr)) { + if (sample_addr_correlates_sym(&evsel->core.attr)) { if (!addr_al->thread) thread__resolve(thread, addr_al, sample); if (addr_al->sym) @@ -1421,7 +1566,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, struct addr_location *addr_al, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; @@ -1433,7 +1577,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, * The 'return' has already been popped off the stack so the depth has * to be adjusted to match the 'call'. */ - if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN) + if (thread__ts(thread) && sample->flags & PERF_IP_FLAG_RETURN) depth += 1; name = resolve_branch_sym(sample, evsel, thread, al, addr_al, &ip); @@ -1465,45 +1609,35 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, return len + dlen; } -__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} - -void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine) -{ - if (sample->insn_len == 0 && native_arch) - arch_fetch_insn(sample, thread, machine); -} - static int perf_sample__fprintf_insn(struct perf_sample *sample, + struct evsel *evsel, struct perf_event_attr *attr, struct thread *thread, - struct machine *machine, FILE *fp) + struct machine *machine, FILE *fp, + struct addr_location *al) { int printed = 0; - script_fetch_insn(sample, thread, machine); + script_fetch_insn(sample, thread, machine, native_arch); if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); if (PRINT_FIELD(INSN) && sample->insn_len) { - int i; - - printed += fprintf(fp, " insn:"); - for (i = 0; i < sample->insn_len; i++) - printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]); + printed += fprintf(fp, " insn: "); + printed += sample__fprintf_insn_raw(sample, fp); + } + if (PRINT_FIELD(DISASM) && sample->insn_len) { + printed += fprintf(fp, "\t\t"); + printed += sample__fprintf_insn_asm(sample, thread, machine, fp, al); } - if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) - printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp); + if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM)) + printed += perf_sample__fprintf_brstackinsn(sample, evsel, thread, attr, machine, fp); return printed; } static int perf_sample__fprintf_ipc(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { unsigned int ipc; @@ -1524,7 +1658,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, struct machine *machine, FILE *fp) { struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); bool print_srcline_last = false; int printed = 0; @@ -1536,11 +1670,13 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; - if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; - + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) + cursor = NULL; + } if (cursor == NULL) { printed += fprintf(fp, " "); if (print_opts & EVSEL__PRINT_SRCLINE) { @@ -1559,19 +1695,19 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && !output[type].user_set)) { printed += fprintf(fp, " => "); - printed += perf_sample__fprintf_addr(sample, thread, attr, fp); + printed += perf_sample__fprintf_addr(sample, thread, evsel, fp); } - printed += perf_sample__fprintf_ipc(sample, attr, fp); + printed += perf_sample__fprintf_ipc(sample, evsel, fp); if (print_srcline_last) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); - printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp); + printed += perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al); printed += fprintf(fp, "\n"); if (PRINT_FIELD(SRCCODE)) { int ret = map__fprintf_srccode(al->map, al->addr, stdout, - &thread->srccode_state); + thread__srccode_state(thread)); if (ret) { printed += ret; printed += printf("\n"); @@ -1580,92 +1716,17 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, return printed; } -static struct { - u32 flags; - const char *name; -} sample_flags[] = { - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, - {PERF_IP_FLAG_BRANCH, "jmp"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, "hw int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, - {0, NULL} -}; - -static const char *sample_flags_to_name(u32 flags) -{ - int i; - - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; - } - - return NULL; -} - -int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) -{ - u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | - PERF_IP_FLAG_INTR_TOGGLE; - const char *chars = PERF_IP_FLAG_CHARS; - const size_t n = strlen(PERF_IP_FLAG_CHARS); - const char *name = NULL; - size_t i, pos = 0; - char xs[16] = {0}; - - if (flags & xf) - snprintf(xs, sizeof(xs), "(%s%s%s)", - flags & PERF_IP_FLAG_IN_TX ? "x" : "", - flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", - flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); - - name = sample_flags_to_name(flags & ~xf); - if (name) - return snprintf(str, sz, "%-15s%6s", name, xs); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return snprintf(str, sz, "tr strt %-7s%6s", name, xs); - } - - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); - if (name) - return snprintf(str, sz, "tr end %-7s%6s", name, xs); - } - - for (i = 0; i < n; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = chars[i]; - } - for (; i < 32; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = '?'; - } - if (pos < sz) - str[pos] = 0; - - return pos; -} - static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { char str[SAMPLE_FLAGS_BUF_SIZE]; + int ret; - perf_sample__sprintf_flags(flags, str, sizeof(str)); - return fprintf(fp, " %-21s ", str); + ret = perf_sample__sprintf_flags(flags, str, sizeof(str)); + if (ret < 0) + return fprintf(fp, " raw flags:0x%-*x ", + SAMPLE_FLAGS_STR_ALIGNED_SIZE - 12, flags); + + return fprintf(fp, " %-*s ", SAMPLE_FLAGS_STR_ALIGNED_SIZE, str); } struct printer_data { @@ -1890,7 +1951,7 @@ static int perf_sample__fprintf_synth_evt(struct perf_sample *sample, FILE *fp) struct perf_synth_intel_evt *data = perf_sample__synth_ptr(sample); const char *cfe[32] = {NULL, "INTR", "IRET", "SMI", "RSM", "SIPI", "INIT", "VMENTRY", "VMEXIT", "VMEXIT_INTR", - "SHUTDOWN"}; + "SHUTDOWN", NULL, "UINTR", "UIRET"}; const char *evd[64] = {"PFA", "VMXQ", "VMXR"}; const char *s; int len, i; @@ -1934,6 +1995,25 @@ static int perf_sample__fprintf_synth_iflag_chg(struct perf_sample *sample, FILE return len + perf_sample__fprintf_pt_spacing(len, fp); } +static int perf_sample__fprintf_synth_vpadtl(struct perf_sample *data, FILE *fp) +{ + struct powerpc_vpadtl_entry *dtl = (struct powerpc_vpadtl_entry *)data->raw_data; + int len; + + len = fprintf(fp, "timebase: %" PRIu64 " dispatch_reason:%s, preempt_reason:%s,\n" + "enqueue_to_dispatch_time:%d, ready_to_enqueue_time:%d," + "waiting_to_ready_time:%d, processor_id: %d", + get_unaligned_be64(&dtl->timebase), + dispatch_reasons[dtl->dispatch_reason], + preempt_reasons[dtl->preempt_reason], + be32_to_cpu(dtl->enqueue_to_dispatch_time), + be32_to_cpu(dtl->ready_to_enqueue_time), + be32_to_cpu(dtl->waiting_to_ready_time), + be16_to_cpu(dtl->processor_id)); + + return len; +} + static int perf_sample__fprintf_synth(struct perf_sample *sample, struct evsel *evsel, FILE *fp) { @@ -1956,6 +2036,8 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, return perf_sample__fprintf_synth_evt(sample, fp); case PERF_SYNTH_INTEL_IFLAG_CHG: return perf_sample__fprintf_synth_iflag_chg(sample, fp); + case PERF_SYNTH_POWERPC_VPA_DTL: + return perf_sample__fprintf_synth_vpadtl(sample, fp); default: break; } @@ -1979,13 +2061,18 @@ static int evlist__max_name_len(struct evlist *evlist) static int data_src__fprintf(u64 data_src, FILE *fp) { - struct mem_info mi = { .data_src.val = data_src }; + struct mem_info *mi = mem_info__new(); char decode[100]; char out[100]; static int maxlen; int len; - perf_script__meminfo_scnprintf(decode, 100, &mi); + if (!mi) + return -ENOMEM; + + mem_info__data_src(mi)->val = data_src; + perf_script__meminfo_scnprintf(decode, 100, mi); + mem_info__put(mi); len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode); if (maxlen < len) @@ -2002,11 +2089,11 @@ struct metric_ctx { }; static void script_print_metric(struct perf_stat_config *config __maybe_unused, - void *ctx, const char *color, - const char *fmt, - const char *unit, double val) + void *ctx, enum metric_threshold_classify thresh, + const char *fmt, const char *unit, double val) { struct metric_ctx *mctx = ctx; + const char *color = metric_threshold_classify__color(thresh); if (!fmt) return; @@ -2030,13 +2117,161 @@ static void script_new_line(struct perf_stat_config *config __maybe_unused, fputs("\tmetric: ", mctx->fp); } -static void perf_sample__fprint_metric(struct perf_script *script, - struct thread *thread, +struct script_find_metrics_args { + struct evlist *evlist; + bool system_wide; +}; + +static struct evsel *map_metric_evsel_to_script_evsel(struct evlist *script_evlist, + struct evsel *metric_evsel) +{ + struct evsel *script_evsel; + + evlist__for_each_entry(script_evlist, script_evsel) { + /* Skip if perf_event_attr differ. */ + if (metric_evsel->core.attr.type != script_evsel->core.attr.type) + continue; + if (metric_evsel->core.attr.config != script_evsel->core.attr.config) + continue; + /* Skip if the script event has a metric_id that doesn't match. */ + if (script_evsel->metric_id && + strcmp(evsel__metric_id(metric_evsel), evsel__metric_id(script_evsel))) { + pr_debug("Skipping matching evsel due to differing metric ids '%s' vs '%s'\n", + evsel__metric_id(metric_evsel), evsel__metric_id(script_evsel)); + continue; + } + return script_evsel; + } + return NULL; +} + +static int script_find_metrics(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *data) +{ + struct script_find_metrics_args *args = data; + struct evlist *script_evlist = args->evlist; + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + int ret = metricgroup__parse_groups(metric_evlist, + /*pmu=*/"all", + pm->metric_name, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + /*user_requested_cpu_list=*/NULL, + args->system_wide, + /*hardware_aware_grouping=*/false); + + if (ret) { + /* Metric parsing failed but continue the search. */ + goto out; + } + + /* + * Check the script_evlist has an entry for each metric_evlist entry. If + * the script evsel was already set up avoid changing data that may + * break it. + */ + evlist__for_each_entry(metric_evlist, metric_evsel) { + struct evsel *script_evsel = + map_metric_evsel_to_script_evsel(script_evlist, metric_evsel); + struct evsel *new_metric_leader; + + if (!script_evsel) { + pr_debug("Skipping metric '%s' as evsel '%s' / '%s' is missing\n", + pm->metric_name, evsel__name(metric_evsel), + evsel__metric_id(metric_evsel)); + goto out; + } + + if (script_evsel->metric_leader == NULL) + continue; + + if (metric_evsel->metric_leader == metric_evsel) { + new_metric_leader = script_evsel; + } else { + new_metric_leader = + map_metric_evsel_to_script_evsel(script_evlist, + metric_evsel->metric_leader); + } + /* Mismatching evsel leaders. */ + if (script_evsel->metric_leader != new_metric_leader) { + pr_debug("Skipping metric '%s' due to mismatching evsel metric leaders '%s' vs '%s'\n", + pm->metric_name, evsel__metric_id(metric_evsel), + evsel__metric_id(script_evsel)); + goto out; + } + } + /* + * Metric events match those in the script evlist, copy metric evsel + * data into the script evlist. + */ + evlist__for_each_entry(metric_evlist, metric_evsel) { + struct evsel *script_evsel = + map_metric_evsel_to_script_evsel(script_evlist, metric_evsel); + struct metric_event *metric_me = metricgroup__lookup(&metric_evlist->metric_events, + metric_evsel, + /*create=*/false); + + if (script_evsel->metric_id == NULL) { + script_evsel->metric_id = metric_evsel->metric_id; + metric_evsel->metric_id = NULL; + } + + if (script_evsel->metric_leader == NULL) { + if (metric_evsel->metric_leader == metric_evsel) { + script_evsel->metric_leader = script_evsel; + } else { + script_evsel->metric_leader = + map_metric_evsel_to_script_evsel(script_evlist, + metric_evsel->metric_leader); + } + } + + if (metric_me) { + struct metric_expr *expr; + struct metric_event *script_me = + metricgroup__lookup(&script_evlist->metric_events, + script_evsel, + /*create=*/true); + + if (!script_me) { + /* + * As the metric_expr is created, the only + * failure is a lack of memory. + */ + goto out; + } + list_splice_init(&metric_me->head, &script_me->head); + list_for_each_entry(expr, &script_me->head, nd) { + for (int i = 0; expr->metric_events[i]; i++) { + expr->metric_events[i] = + map_metric_evsel_to_script_evsel(script_evlist, + expr->metric_events[i]); + } + } + } + } + pr_debug("Found metric '%s' whose evsels match those of in the perf data\n", + pm->metric_name); + evlist__delete(metric_evlist); +out: + return 0; +} + +static struct aggr_cpu_id script_aggr_cpu_id_get(struct perf_stat_config *config __maybe_unused, + struct perf_cpu cpu) +{ + return aggr_cpu_id__global(cpu, /*data=*/NULL); +} + +static void perf_sample__fprint_metric(struct thread *thread, struct evsel *evsel, struct perf_sample *sample, FILE *fp) { - struct evsel *leader = evsel__leader(evsel); + static bool init_metrics; struct perf_stat_output_ctx ctx = { .print_metric = script_print_metric, .new_line = script_new_line, @@ -2048,29 +2283,84 @@ static void perf_sample__fprint_metric(struct perf_script *script, }, .force_header = false, }; - struct evsel *ev2; - u64 val; + struct perf_counts_values *count, *old_count; + int cpu_map_idx, thread_map_idx, aggr_idx; + struct evsel *pos; + + if (!init_metrics) { + /* One time initialization of stat_config and metric data. */ + struct script_find_metrics_args args = { + .evlist = evsel->evlist, + .system_wide = perf_thread_map__pid(evsel->core.threads, /*idx=*/0) == -1, + + }; + if (!stat_config.output) + stat_config.output = stdout; + + if (!stat_config.aggr_map) { + /* TODO: currently only global aggregation is supported. */ + assert(stat_config.aggr_mode == AGGR_GLOBAL); + stat_config.aggr_get_id = script_aggr_cpu_id_get; + stat_config.aggr_map = + cpu_aggr_map__new(evsel->evlist->core.user_requested_cpus, + aggr_cpu_id__global, /*data=*/NULL, + /*needs_sort=*/false); + } + + metricgroup__for_each_metric(pmu_metrics_table__find(), script_find_metrics, &args); + init_metrics = true; + } + + if (!evsel->stats) { + if (evlist__alloc_stats(&stat_config, evsel->evlist, /*alloc_raw=*/true) < 0) + return; + } + if (!evsel->stats->aggr) { + if (evlist__alloc_aggr_stats(evsel->evlist, stat_config.aggr_map->nr) < 0) + return; + } - if (!evsel->stats) - evlist__alloc_stats(&stat_config, script->session->evlist, /*alloc_raw=*/false); - if (evsel_script(leader)->gnum++ == 0) - perf_stat__reset_shadow_stats(); - val = sample->period * evsel->scale; - perf_stat__update_shadow_stats(evsel, - val, - sample->cpu, - &rt_stat); - evsel_script(evsel)->val = val; - if (evsel_script(leader)->gnum == leader->core.nr_members) { - for_each_group_member (ev2, leader) { - perf_stat__print_shadow_stats(&stat_config, ev2, - evsel_script(ev2)->val, - sample->cpu, - &ctx, - NULL, - &rt_stat); + /* Update the evsel's count using the sample's data. */ + cpu_map_idx = perf_cpu_map__idx(evsel->core.cpus, (struct perf_cpu){sample->cpu}); + if (cpu_map_idx < 0) { + /* Missing CPU, check for any CPU. */ + if (perf_cpu_map__cpu(evsel->core.cpus, /*idx=*/0).cpu == -1 || + sample->cpu == (u32)-1) { + /* Place the counts in the which ever CPU is first in the map. */ + cpu_map_idx = 0; + } else { + pr_info("Missing CPU map entry for CPU %d\n", sample->cpu); + return; + } + } + thread_map_idx = perf_thread_map__idx(evsel->core.threads, sample->tid); + if (thread_map_idx < 0) { + /* Missing thread, check for any thread. */ + if (perf_thread_map__pid(evsel->core.threads, /*idx=*/0) == -1 || + sample->tid == (u32)-1) { + /* Place the counts in the which ever thread is first in the map. */ + thread_map_idx = 0; + } else { + pr_info("Missing thread map entry for thread %d\n", sample->tid); + return; + } + } + count = perf_counts(evsel->counts, cpu_map_idx, thread_map_idx); + old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread_map_idx); + count->val = old_count->val + sample->period; + count->run = old_count->run + 1; + count->ena = old_count->ena + 1; + + /* Update the aggregated stats. */ + perf_stat_process_counter(&stat_config, evsel); + + /* Display all metrics. */ + evlist__for_each_entry(evsel->evlist, pos) { + cpu_aggr_map__for_each_idx(aggr_idx, stat_config.aggr_map) { + perf_stat__print_shadow_stats(&stat_config, pos, + aggr_idx, + &ctx); } - evsel_script(leader)->gnum = 0; } } @@ -2085,9 +2375,9 @@ static bool show_event(struct perf_sample *sample, if (!symbol_conf.graph_function) return true; - if (thread->filter) { - if (depth <= thread->filter_entry_depth) { - thread->filter = false; + if (thread__filter(thread)) { + if (depth <= thread__filter_entry_depth(thread)) { + thread__set_filter(thread, false); return false; } return true; @@ -2104,8 +2394,8 @@ static bool show_event(struct perf_sample *sample, while (*s) { unsigned len = strcspn(s, ","); if (nlen == len && !strncmp(name, s, len)) { - thread->filter = true; - thread->filter_entry_depth = depth; + thread__set_filter(thread, true); + thread__set_filter_entry_depth(thread, depth); return true; } s += len; @@ -2124,7 +2414,7 @@ static void process_event(struct perf_script *script, { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); struct evsel_script *es = evsel->priv; FILE *fp = es->fp; char str[PAGE_SIZE_NAME_LEN]; @@ -2159,15 +2449,20 @@ static void process_event(struct perf_script *script, } #ifdef HAVE_LIBTRACEEVENT if (PRINT_FIELD(TRACE) && sample->raw_data) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, fp); + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format) { + event_format__fprintf(tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + fp); + } } #endif if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) perf_sample__fprintf_synth(sample, evsel, fp); if (PRINT_FIELD(ADDR)) - perf_sample__fprintf_addr(sample, thread, attr, fp); + perf_sample__fprintf_addr(sample, thread, evsel, fp); if (PRINT_FIELD(DATA_SRC)) data_src__fprintf(sample->data_src, fp); @@ -2178,17 +2473,33 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(INS_LAT)) fprintf(fp, "%16" PRIu16, sample->ins_lat); + if (PRINT_FIELD(RETIRE_LAT)) + fprintf(fp, "%16" PRIu16, sample->weight3); + + if (PRINT_FIELD(CGROUP)) { + const char *cgrp_name; + struct cgroup *cgrp = cgroup__find(machine->env, + sample->cgroup); + if (cgrp != NULL) + cgrp_name = cgrp->name; + else + cgrp_name = "unknown"; + fprintf(fp, " %s", cgrp_name); + } + if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL; if (script->stitch_lbr) - al->thread->lbr_stitch_enable = true; - - if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; - + thread__set_lbr_stitch_enable(al->thread, true); + + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) + cursor = NULL; + } fputc(cursor ? '\n' : ' ', fp); sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, symbol_conf.bt_stop_list, fp); @@ -2201,15 +2512,15 @@ static void process_event(struct perf_script *script, perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) - perf_sample__fprintf_brstack(sample, thread, attr, fp); + perf_sample__fprintf_brstack(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKSYM)) - perf_sample__fprintf_brstacksym(sample, thread, attr, fp); + perf_sample__fprintf_brstacksym(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKOFF)) - perf_sample__fprintf_brstackoff(sample, thread, attr, fp); + perf_sample__fprintf_brstackoff(sample, thread, evsel, fp); - if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) + if (evsel__is_bpf_output(evsel) && !evsel__is_offcpu_event(evsel) && PRINT_FIELD(BPF_OUTPUT)) perf_sample__fprintf_bpf_output(sample, fp); - perf_sample__fprintf_insn(sample, attr, thread, machine, fp); + perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al); if (PRINT_FIELD(PHYS_ADDR)) fprintf(fp, "%16" PRIx64, sample->phys_addr); @@ -2220,18 +2531,18 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(CODE_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); - perf_sample__fprintf_ipc(sample, attr, fp); + perf_sample__fprintf_ipc(sample, evsel, fp); fprintf(fp, "\n"); if (PRINT_FIELD(SRCCODE)) { if (map__fprintf_srccode(al->map, al->addr, stdout, - &thread->srccode_state)) + thread__srccode_state(thread))) printf("\n"); } if (PRINT_FIELD(METRIC)) - perf_sample__fprint_metric(script, thread, evsel, sample, fp); + perf_sample__fprint_metric(thread, evsel, sample, fp); if (verbose > 0) fflush(fp); @@ -2288,8 +2599,8 @@ static void setup_scripting(void) { #ifdef HAVE_LIBTRACEEVENT setup_perl_scripting(); - setup_python_scripting(); #endif + setup_python_scripting(); } static int flush_scripting(void) @@ -2311,7 +2622,7 @@ static bool filter_cpu(struct perf_sample *sample) return false; } -static int process_sample_event(struct perf_tool *tool, +static int process_sample_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct evsel *evsel, @@ -2323,8 +2634,8 @@ static int process_sample_event(struct perf_tool *tool, int ret = 0; /* Set thread to NULL to indicate addr_al and al are not initialized */ - addr_al.thread = NULL; - al.thread = NULL; + addr_location__init(&al); + addr_location__init(&addr_al); ret = dlfilter__filter_event_early(dlfilter, event, sample, evsel, machine, &al, &addr_al); if (ret) { @@ -2390,12 +2701,103 @@ static int process_sample_event(struct perf_tool *tool, } out_put: - if (al.thread) - addr_location__put(&al); + addr_location__exit(&addr_al); + addr_location__exit(&al); return ret; } -static int process_attr(struct perf_tool *tool, union perf_event *event, +static int process_deferred_sample_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct evsel *evsel, + struct machine *machine) +{ + struct perf_script *scr = container_of(tool, struct perf_script, tool); + struct perf_event_attr *attr = &evsel->core.attr; + struct evsel_script *es = evsel->priv; + unsigned int type = output_type(attr->type); + struct addr_location al; + FILE *fp = es->fp; + int ret = 0; + + if (output[type].fields == 0) + return 0; + + /* Set thread to NULL to indicate addr_al and al are not initialized */ + addr_location__init(&al); + + if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num, + sample->time)) { + goto out_put; + } + + if (debug_mode) { + if (sample->time < last_timestamp) { + pr_err("Samples misordered, previous: %" PRIu64 + " this: %" PRIu64 "\n", last_timestamp, + sample->time); + nr_unordered++; + } + last_timestamp = sample->time; + goto out_put; + } + + if (filter_cpu(sample)) + goto out_put; + + if (machine__resolve(machine, &al, sample) < 0) { + pr_err("problem processing %d event, skipping it.\n", + event->header.type); + ret = -1; + goto out_put; + } + + if (al.filtered) + goto out_put; + + if (!show_event(sample, evsel, al.thread, &al, NULL)) + goto out_put; + + if (evswitch__discard(&scr->evswitch, evsel)) + goto out_put; + + perf_sample__fprintf_start(scr, sample, al.thread, evsel, + PERF_RECORD_CALLCHAIN_DEFERRED, fp); + fprintf(fp, "DEFERRED CALLCHAIN [cookie: %llx]", + (unsigned long long)event->callchain_deferred.cookie); + + if (PRINT_FIELD(IP)) { + struct callchain_cursor *cursor = NULL; + + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al.thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) { + pr_info("cannot resolve deferred callchains\n"); + cursor = NULL; + } + } + + fputc(cursor ? '\n' : ' ', fp); + sample__fprintf_sym(sample, &al, 0, output[type].print_ip_opts, + cursor, symbol_conf.bt_stop_list, fp); + } + + fprintf(fp, "\n"); + + if (verbose > 0) + fflush(fp); + +out_put: + addr_location__exit(&al); + return ret; +} + +// Used when scr->per_event_dump is not set +static struct evsel_script es_stdout; + +static int process_attr(const struct perf_tool *tool, union perf_event *event, struct evlist **pevlist) { struct perf_script *scr = container_of(tool, struct perf_script, tool); @@ -2403,7 +2805,6 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, struct evsel *evsel, *pos; u64 sample_type; int err; - static struct evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) @@ -2415,12 +2816,11 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, if (!evsel->priv) { if (scr->per_event_dump) { evsel->priv = evsel_script__new(evsel, scr->session->data); - } else { - es = zalloc(sizeof(*es)); - if (!es) + if (!evsel->priv) return -ENOMEM; - es->fp = stdout; - evsel->priv = es; + } else { // Replicate what is done in perf_script__setup_per_event_dump() + es_stdout.fp = stdout; + evsel->priv = &es_stdout; } } @@ -2444,7 +2844,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, * on events sample_type. */ sample_type = evlist__combined_sample_type(evlist); - callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); + callchain_param_setup(sample_type, perf_env__arch(perf_session__env(scr->session))); /* Enable fields for callchain entries */ if (symbol_conf.use_callchain && @@ -2452,18 +2852,18 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, sample_type & PERF_SAMPLE_BRANCH_STACK || (sample_type & PERF_SAMPLE_REGS_USER && sample_type & PERF_SAMPLE_STACK_USER))) { - int type = output_type(evsel->core.attr.type); + int type = evsel__output_type(evsel); if (!(output[type].user_unset_fields & PERF_OUTPUT_IP)) output[type].fields |= PERF_OUTPUT_IP; if (!(output[type].user_unset_fields & PERF_OUTPUT_SYM)) output[type].fields |= PERF_OUTPUT_SYM; } - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); return 0; } -static int print_event_with_time(struct perf_tool *tool, +static int print_event_with_time(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine, @@ -2499,14 +2899,14 @@ static int print_event_with_time(struct perf_tool *tool, return 0; } -static int print_event(struct perf_tool *tool, union perf_event *event, +static int print_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine, pid_t pid, pid_t tid) { return print_event_with_time(tool, event, sample, machine, pid, tid, 0); } -static int process_comm_event(struct perf_tool *tool, +static int process_comm_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2518,7 +2918,7 @@ static int process_comm_event(struct perf_tool *tool, event->comm.tid); } -static int process_namespaces_event(struct perf_tool *tool, +static int process_namespaces_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2530,7 +2930,7 @@ static int process_namespaces_event(struct perf_tool *tool, event->namespaces.tid); } -static int process_cgroup_event(struct perf_tool *tool, +static int process_cgroup_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2542,7 +2942,7 @@ static int process_cgroup_event(struct perf_tool *tool, sample->tid); } -static int process_fork_event(struct perf_tool *tool, +static int process_fork_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2554,7 +2954,7 @@ static int process_fork_event(struct perf_tool *tool, event->fork.pid, event->fork.tid, event->fork.time); } -static int process_exit_event(struct perf_tool *tool, +static int process_exit_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2567,7 +2967,7 @@ static int process_exit_event(struct perf_tool *tool, return perf_event__process_exit(tool, event, sample, machine); } -static int process_mmap_event(struct perf_tool *tool, +static int process_mmap_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2579,7 +2979,7 @@ static int process_mmap_event(struct perf_tool *tool, event->mmap.tid); } -static int process_mmap2_event(struct perf_tool *tool, +static int process_mmap2_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2591,7 +2991,7 @@ static int process_mmap2_event(struct perf_tool *tool, event->mmap2.tid); } -static int process_switch_event(struct perf_tool *tool, +static int process_switch_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2611,7 +3011,8 @@ static int process_switch_event(struct perf_tool *tool, sample->tid); } -static int process_auxtrace_error(struct perf_session *session, +static int process_auxtrace_error(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event) { if (scripting_ops && scripting_ops->process_auxtrace_error) { @@ -2619,11 +3020,11 @@ static int process_auxtrace_error(struct perf_session *session, return 0; } - return perf_event__process_auxtrace_error(session, event); + return perf_event__process_auxtrace_error(tool, session, event); } static int -process_lost_event(struct perf_tool *tool, +process_lost_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2633,7 +3034,7 @@ process_lost_event(struct perf_tool *tool, } static int -process_throttle_event(struct perf_tool *tool __maybe_unused, +process_throttle_event(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2644,7 +3045,7 @@ process_throttle_event(struct perf_tool *tool __maybe_unused, } static int -process_finished_round_event(struct perf_tool *tool __maybe_unused, +process_finished_round_event(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct ordered_events *oe __maybe_unused) @@ -2654,7 +3055,7 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused, } static int -process_bpf_events(struct perf_tool *tool __maybe_unused, +process_bpf_events(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2666,7 +3067,16 @@ process_bpf_events(struct perf_tool *tool __maybe_unused, sample->tid); } -static int process_text_poke_events(struct perf_tool *tool, +static int +process_bpf_metadata_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, + union perf_event *event) +{ + perf_event__fprintf(event, NULL, stdout); + return 0; +} + +static int process_text_poke_events(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) @@ -2726,7 +3136,6 @@ out_err_fclose: static int perf_script__setup_per_event_dump(struct perf_script *script) { struct evsel *evsel; - static struct evsel_script es_stdout; if (script->per_event_dump) return perf_script__fopen_per_event_dump(script); @@ -2764,8 +3173,6 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); - perf_stat__init_shadow_stats(); - /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; @@ -2791,8 +3198,9 @@ static int __cmd_script(struct perf_script *script) script->tool.finished_round = process_finished_round_event; } if (script->show_bpf_events) { - script->tool.ksymbol = process_bpf_events; - script->tool.bpf = process_bpf_events; + script->tool.ksymbol = process_bpf_events; + script->tool.bpf = process_bpf_events; + script->tool.bpf_metadata = process_bpf_metadata_event; } if (script->show_text_poke_events) { script->tool.ksymbol = process_bpf_events; @@ -2815,79 +3223,18 @@ static int __cmd_script(struct perf_script *script) return ret; } -struct script_spec { - struct list_head node; - struct scripting_ops *ops; - char spec[]; -}; - -static LIST_HEAD(script_specs); - -static struct script_spec *script_spec__new(const char *spec, - struct scripting_ops *ops) -{ - struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); - - if (s != NULL) { - strcpy(s->spec, spec); - s->ops = ops; - } - - return s; -} - -static void script_spec__add(struct script_spec *s) -{ - list_add_tail(&s->node, &script_specs); -} - -static struct script_spec *script_spec__find(const char *spec) -{ - struct script_spec *s; - - list_for_each_entry(s, &script_specs, node) - if (strcasecmp(s->spec, spec) == 0) - return s; - return NULL; -} - -int script_spec_register(const char *spec, struct scripting_ops *ops) +static int list_available_languages_cb(struct scripting_ops *ops, const char *spec) { - struct script_spec *s; - - s = script_spec__find(spec); - if (s) - return -1; - - s = script_spec__new(spec, ops); - if (!s) - return -1; - else - script_spec__add(s); - + fprintf(stderr, " %-42s [%s]\n", spec, ops->name); return 0; } -static struct scripting_ops *script_spec__lookup(const char *spec) -{ - struct script_spec *s = script_spec__find(spec); - if (!s) - return NULL; - - return s->ops; -} - static void list_available_languages(void) { - struct script_spec *s; - fprintf(stderr, "\n"); fprintf(stderr, "Scripting language extensions (used in " "perf script -s [spec:]script.[spec]):\n\n"); - - list_for_each_entry(s, &script_specs, node) - fprintf(stderr, " %-42s [%s]\n", s->spec, s->ops->name); - + script_spec__for_each(&list_available_languages_cb); fprintf(stderr, "\n"); } @@ -3076,6 +3423,13 @@ parse: rc = -EINVAL; goto out; } +#ifndef HAVE_LIBCAPSTONE_SUPPORT + if (change != REMOVE && strcmp(tok, "disasm") == 0) { + fprintf(stderr, "Field \"disasm\" requires perf to be built with libcapstone support.\n"); + rc = -EINVAL; + goto out; + } +#endif if (type == -1) { /* add user option to all events types for @@ -3286,14 +3640,21 @@ static int list_available_scripts(const struct option *opt __maybe_unused, int unset __maybe_unused) { struct dirent *script_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN]; + char *buf, *scripts_path, *script_path, *lang_path, *first_half; DIR *scripts_dir, *lang_dir; - char script_path[MAXPATHLEN]; - char lang_path[MAXPATHLEN]; struct script_desc *desc; - char first_half[BUFSIZ]; char *script_root; + buf = malloc(3 * MAXPATHLEN + BUFSIZ); + if (!buf) { + pr_err("malloc failed\n"); + exit(-1); + } + scripts_path = buf; + script_path = buf + MAXPATHLEN; + lang_path = buf + 2 * MAXPATHLEN; + first_half = buf + 3 * MAXPATHLEN; + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); @@ -3302,6 +3663,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, "open(%s) failed.\n" "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", scripts_path); + free(buf); exit(-1); } @@ -3332,6 +3694,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, desc->half_liner ? desc->half_liner : ""); } + free(buf); exit(0); } @@ -3363,144 +3726,6 @@ static void free_dlarg(void) free(dlargv); } -/* - * Some scripts specify the required events in their "xxx-record" file, - * this function will check if the events in perf.data match those - * mentioned in the "xxx-record". - * - * Fixme: All existing "xxx-record" are all in good formats "-e event ", - * which is covered well now. And new parsing code should be added to - * cover the future complex formats like event groups etc. - */ -static int check_ev_match(char *dir_name, char *scriptname, - struct perf_session *session) -{ - char filename[MAXPATHLEN], evname[128]; - char line[BUFSIZ], *p; - struct evsel *pos; - int match, len; - FILE *fp; - - scnprintf(filename, MAXPATHLEN, "%s/bin/%s-record", dir_name, scriptname); - - fp = fopen(filename, "r"); - if (!fp) - return -1; - - while (fgets(line, sizeof(line), fp)) { - p = skip_spaces(line); - if (*p == '#') - continue; - - while (strlen(p)) { - p = strstr(p, "-e"); - if (!p) - break; - - p += 2; - p = skip_spaces(p); - len = strcspn(p, " \t"); - if (!len) - break; - - snprintf(evname, len + 1, "%s", p); - - match = 0; - evlist__for_each_entry(session->evlist, pos) { - if (!strcmp(evsel__name(pos), evname)) { - match = 1; - break; - } - } - - if (!match) { - fclose(fp); - return -1; - } - } - } - - fclose(fp); - return 0; -} - -/* - * Return -1 if none is found, otherwise the actual scripts number. - * - * Currently the only user of this function is the script browser, which - * will list all statically runnable scripts, select one, execute it and - * show the output in a perf browser. - */ -int find_scripts(char **scripts_array, char **scripts_path_array, int num, - int pathlen) -{ - struct dirent *script_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; - DIR *scripts_dir, *lang_dir; - struct perf_session *session; - struct perf_data data = { - .path = input_name, - .mode = PERF_DATA_MODE_READ, - }; - char *temp; - int i = 0; - - session = perf_session__new(&data, NULL); - if (IS_ERR(session)) - return PTR_ERR(session); - - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); - - scripts_dir = opendir(scripts_path); - if (!scripts_dir) { - perf_session__delete(session); - return -1; - } - - for_each_lang(scripts_path, scripts_dir, lang_dirent) { - scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent->d_name); -#ifndef HAVE_LIBPERL_SUPPORT - if (strstr(lang_path, "perl")) - continue; -#endif -#ifndef HAVE_LIBPYTHON_SUPPORT - if (strstr(lang_path, "python")) - continue; -#endif - - lang_dir = opendir(lang_path); - if (!lang_dir) - continue; - - for_each_script(lang_path, lang_dir, script_dirent) { - /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent->d_name, "top.")) - continue; - if (i >= num) - break; - snprintf(scripts_path_array[i], pathlen, "%s/%s", - lang_path, - script_dirent->d_name); - temp = strchr(script_dirent->d_name, '.'); - snprintf(scripts_array[i], - (temp - script_dirent->d_name) + 1, - "%s", script_dirent->d_name); - - if (check_ev_match(lang_path, - scripts_array[i], session)) - continue; - - i++; - } - closedir(lang_dir); - } - - closedir(scripts_dir); - perf_session__delete(session); - return i; -} - static char *get_script_path(const char *script_root, const char *suffix) { struct dirent *script_dirent, *lang_dirent; @@ -3603,7 +3828,8 @@ static void script__setup_sample_type(struct perf_script *script) } } -static int process_stat_round_event(struct perf_session *session, +static int process_stat_round_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { struct perf_record_stat_round *round = &event->stat_round; @@ -3618,10 +3844,18 @@ static int process_stat_round_event(struct perf_session *session, return 0; } -static int process_stat_config_event(struct perf_session *session __maybe_unused, +static int process_stat_config_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } @@ -3645,10 +3879,10 @@ static int set_maps(struct perf_script *script) } static -int process_thread_map_event(struct perf_session *session, +int process_thread_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, union perf_event *event) { - struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (dump_trace) @@ -3667,10 +3901,10 @@ int process_thread_map_event(struct perf_session *session, } static -int process_cpu_map_event(struct perf_session *session, +int process_cpu_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, union perf_event *event) { - struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (dump_trace) @@ -3688,7 +3922,8 @@ int process_cpu_map_event(struct perf_session *session, return set_maps(script); } -static int process_feature_event(struct perf_session *session, +static int process_feature_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { if (event->feat.feat_id < HEADER_LAST_FEATURE) @@ -3696,13 +3931,11 @@ static int process_feature_event(struct perf_session *session, return 0; } -#ifdef HAVE_AUXTRACE_SUPPORT -static int perf_script__process_auxtrace_info(struct perf_session *session, +static int perf_script__process_auxtrace_info(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event) { - struct perf_tool *tool = session->tool; - - int ret = perf_event__process_auxtrace_info(session, event); + int ret = perf_event__process_auxtrace_info(tool, session, event); if (ret == 0) { struct perf_script *script = container_of(tool, struct perf_script, tool); @@ -3712,16 +3945,27 @@ static int perf_script__process_auxtrace_info(struct perf_session *session, return ret; } -#else -#define perf_script__process_auxtrace_info 0 -#endif static int parse_insn_trace(const struct option *opt __maybe_unused, - const char *str __maybe_unused, - int unset __maybe_unused) + const char *str, int unset __maybe_unused) { - parse_output_fields(NULL, "+insn,-event,-period", 0); - itrace_parse_synth_opts(opt, "i0ns", 0); + const char *fields = "+insn,-event,-period"; + int ret; + + if (str) { + if (strcmp(str, "disasm") == 0) + fields = "+disasm,-event,-period"; + else if (strlen(str) != 0 && strcmp(str, "raw") != 0) { + fprintf(stderr, "Only accept raw|disasm\n"); + return -EINVAL; + } + } + + ret = parse_output_fields(NULL, fields, 0); + if (ret < 0) + return ret; + + itrace_parse_synth_opts(opt, "i0nse", 0); symbol_conf.nanosecs = true; return 0; } @@ -3765,6 +4009,7 @@ int cmd_script(int argc, const char **argv) bool header_only = false; bool script_started = false; bool unsorted_dump = false; + bool merge_deferred_callchains = true; char *rec_script_path = NULL; char *rep_script_path = NULL; struct perf_session *session; @@ -3777,38 +4022,7 @@ int cmd_script(int argc, const char **argv) const char *dlfilter_file = NULL; const char **__argv; int i, j, err = 0; - struct perf_script script = { - .tool = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .mmap2 = perf_event__process_mmap2, - .comm = perf_event__process_comm, - .namespaces = perf_event__process_namespaces, - .cgroup = perf_event__process_cgroup, - .exit = perf_event__process_exit, - .fork = perf_event__process_fork, - .attr = process_attr, - .event_update = perf_event__process_event_update, -#ifdef HAVE_LIBTRACEEVENT - .tracing_data = perf_event__process_tracing_data, -#endif - .feature = process_feature_event, - .build_id = perf_event__process_build_id, - .id_index = perf_event__process_id_index, - .auxtrace_info = perf_script__process_auxtrace_info, - .auxtrace = perf_event__process_auxtrace, - .auxtrace_error = perf_event__process_auxtrace_error, - .stat = perf_event__process_stat_event, - .stat_round = process_stat_round_event, - .stat_config = process_stat_config_event, - .thread_map = process_thread_map_event, - .cpu_map = process_cpu_map_event, - .throttle = process_throttle_event, - .unthrottle = process_throttle_event, - .ordered_events = true, - .ordering_requires_timestamps = true, - }, - }; + struct perf_script script = {}; struct perf_data data = { .mode = PERF_DATA_MODE_READ, }; @@ -3851,12 +4065,13 @@ int cmd_script(int argc, const char **argv) "comma separated output fields prepend with 'type:'. " "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " - "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," + "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff," "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,data_src,weight,bpf-output,brstackinsn," - "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth," + "brstackinsnlen,brstackdisasm,brstackoff,callindent,insn,disasm,insnlen,synth," "phys_addr,metric,misc,srccode,ipc,tod,data_page_size," - "code_page_size,ins_lat", + "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat," + "brcntr", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -3866,7 +4081,7 @@ int cmd_script(int argc, const char **argv) "only consider these symbols"), OPT_INTEGER(0, "addr-range", &symbol_conf.addr_range, "Use with -S to list traced records within address range"), - OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL, + OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, "raw|disasm", "Decode instructions from itrace", parse_insn_trace), OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL, "Run xed disassembler on output", parse_xed), @@ -3929,6 +4144,8 @@ int cmd_script(int argc, const char **argv) "Enable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), + OPT_STRING(0, "addr2line", &symbol_conf.addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_STRING(0, "time", &script.time_str, "str", "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, @@ -3946,6 +4163,8 @@ int cmd_script(int argc, const char **argv) "Guest code can be found in hypervisor process"), OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr, "Enable LBR callgraph stitching approach"), + OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains, + "Enable merge deferred user callchains"), OPTS_EVSWITCH(&script.evswitch), OPT_END() }; @@ -3958,6 +4177,7 @@ int cmd_script(int argc, const char **argv) "perf script [<options>] <top-script> [script-args]", NULL }; + struct perf_env *env; perf_set_singlethreaded(); @@ -3980,10 +4200,8 @@ int cmd_script(int argc, const char **argv) data.path = input_name; data.force = symbol_conf.force; - if (unsorted_dump) { + if (unsorted_dump) dump_trace = true; - script.tool.ordered_events = false; - } if (symbol__validate_sym_arguments()) return -1; @@ -4174,10 +4392,41 @@ script_found: use_browser = 0; } + perf_tool__init(&script.tool, !unsorted_dump); + script.tool.sample = process_sample_event; + script.tool.callchain_deferred = process_deferred_sample_event; + script.tool.mmap = perf_event__process_mmap; + script.tool.mmap2 = perf_event__process_mmap2; + script.tool.comm = perf_event__process_comm; + script.tool.namespaces = perf_event__process_namespaces; + script.tool.cgroup = perf_event__process_cgroup; + script.tool.exit = perf_event__process_exit; + script.tool.fork = perf_event__process_fork; + script.tool.attr = process_attr; + script.tool.event_update = perf_event__process_event_update; +#ifdef HAVE_LIBTRACEEVENT + script.tool.tracing_data = perf_event__process_tracing_data; +#endif + script.tool.feature = process_feature_event; + script.tool.build_id = perf_event__process_build_id; + script.tool.id_index = perf_event__process_id_index; + script.tool.auxtrace_info = perf_script__process_auxtrace_info; + script.tool.auxtrace = perf_event__process_auxtrace; + script.tool.auxtrace_error = perf_event__process_auxtrace_error; + script.tool.stat = perf_event__process_stat_event; + script.tool.stat_round = process_stat_round_event; + script.tool.stat_config = process_stat_config_event; + script.tool.thread_map = process_thread_map_event; + script.tool.cpu_map = process_cpu_map_event; + script.tool.throttle = process_throttle_event; + script.tool.unthrottle = process_throttle_event; + script.tool.ordering_requires_timestamps = true; + script.tool.merge_deferred_callchains = merge_deferred_callchains; session = perf_session__new(&data, &script.tool); if (IS_ERR(session)) return PTR_ERR(session); + env = perf_session__env(session); if (header || header_only) { script.tool.show_feat_hdr = SHOW_FEAT_HEADER; perf_session__fprintf_info(session, stdout, show_full_info); @@ -4187,17 +4436,17 @@ script_found: if (show_full_info) script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; - if (symbol__init(&session->header.env) < 0) + if (symbol__init(env) < 0) goto out_delete; uname(&uts); if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; - } else if (session->header.env.arch) { - if (!strcmp(uts.machine, session->header.env.arch)) + } else if (env->arch) { + if (!strcmp(uts.machine, env->arch)) native_arch = true; else if (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386")) + !strcmp(env->arch, "i386")) native_arch = true; } @@ -4318,6 +4567,9 @@ script_found: flush_scripting(); + if (verbose > 2 || debug_kmaps) + perf_session__dump_kmaps(session); + out_delete: if (script.ptime_range) { itrace_synth_opts__clear_time_range(&itrace_synth_opts); |