diff options
Diffstat (limited to 'tools/perf/builtin-script.c')
| -rw-r--r-- | tools/perf/builtin-script.c | 4064 |
1 files changed, 3556 insertions, 508 deletions
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 92d4658f56fb..62e43d3c5ad7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1,46 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 #include "builtin.h" -#include "perf.h" -#include "util/cache.h" +#include "util/counts.h" #include "util/debug.h" -#include "util/exec_cmd.h" +#include "util/dso.h" +#include <subcmd/exec-cmd.h> #include "util/header.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> +#include "util/perf_regs.h" #include "util/session.h" #include "util/tool.h" +#include "util/map.h" +#include "util/srcline.h" #include "util/symbol.h" #include "util/thread.h" #include "util/trace-event.h" -#include "util/util.h" +#include "util/env.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_fprintf.h" +#include "util/evswitch.h" #include "util/sort.h" +#include "util/data.h" +#include "util/auxtrace.h" +#include "util/cpumap.h" +#include "util/thread_map.h" +#include "util/stat.h" +#include "util/color.h" +#include "util/string2.h" +#include "util/thread-stack.h" +#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" +#include "util/dump-insn.h" +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <signal.h> +#include <stdio.h> +#include <sys/param.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <subcmd/pager.h> +#include <perf/evlist.h> +#include <linux/err.h> +#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 <event-parse.h> +#endif static char const *script_name; static char const *generate_script_lang; +static bool reltime; +static bool deltatime; +static u64 initial_time; +static u64 previous_time; static bool debug_mode; static u64 last_timestamp; static u64 nr_unordered; -extern const struct option record_options[]; static bool no_callchain; +static bool latency_format; static bool system_wide; +static bool print_flags; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +static int max_blocks; +static bool native_arch; +static struct dlfilter *dlfilter; +static int dlargc; +static char **dlargv; enum perf_output_field { - PERF_OUTPUT_COMM = 1U << 0, - PERF_OUTPUT_TID = 1U << 1, - PERF_OUTPUT_PID = 1U << 2, - PERF_OUTPUT_TIME = 1U << 3, - PERF_OUTPUT_CPU = 1U << 4, - PERF_OUTPUT_EVNAME = 1U << 5, - PERF_OUTPUT_TRACE = 1U << 6, - PERF_OUTPUT_IP = 1U << 7, - PERF_OUTPUT_SYM = 1U << 8, - PERF_OUTPUT_DSO = 1U << 9, - PERF_OUTPUT_ADDR = 1U << 10, - PERF_OUTPUT_SYMOFFSET = 1U << 11, + PERF_OUTPUT_COMM = 1ULL << 0, + PERF_OUTPUT_TID = 1ULL << 1, + PERF_OUTPUT_PID = 1ULL << 2, + PERF_OUTPUT_TIME = 1ULL << 3, + PERF_OUTPUT_CPU = 1ULL << 4, + PERF_OUTPUT_EVNAME = 1ULL << 5, + PERF_OUTPUT_TRACE = 1ULL << 6, + PERF_OUTPUT_IP = 1ULL << 7, + PERF_OUTPUT_SYM = 1ULL << 8, + PERF_OUTPUT_DSO = 1ULL << 9, + PERF_OUTPUT_ADDR = 1ULL << 10, + PERF_OUTPUT_SYMOFFSET = 1ULL << 11, + PERF_OUTPUT_SRCLINE = 1ULL << 12, + PERF_OUTPUT_PERIOD = 1ULL << 13, + PERF_OUTPUT_IREGS = 1ULL << 14, + PERF_OUTPUT_BRSTACK = 1ULL << 15, + PERF_OUTPUT_BRSTACKSYM = 1ULL << 16, + PERF_OUTPUT_DATA_SRC = 1ULL << 17, + PERF_OUTPUT_WEIGHT = 1ULL << 18, + PERF_OUTPUT_BPF_OUTPUT = 1ULL << 19, + PERF_OUTPUT_CALLINDENT = 1ULL << 20, + PERF_OUTPUT_INSN = 1ULL << 21, + PERF_OUTPUT_INSNLEN = 1ULL << 22, + PERF_OUTPUT_BRSTACKINSN = 1ULL << 23, + PERF_OUTPUT_BRSTACKOFF = 1ULL << 24, + PERF_OUTPUT_SYNTH = 1ULL << 25, + PERF_OUTPUT_PHYS_ADDR = 1ULL << 26, + PERF_OUTPUT_UREGS = 1ULL << 27, + PERF_OUTPUT_METRIC = 1ULL << 28, + PERF_OUTPUT_MISC = 1ULL << 29, + PERF_OUTPUT_SRCCODE = 1ULL << 30, + PERF_OUTPUT_IPC = 1ULL << 31, + PERF_OUTPUT_TOD = 1ULL << 32, + PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, + PERF_OUTPUT_CODE_PAGE_SIZE = 1ULL << 34, + PERF_OUTPUT_INS_LAT = 1ULL << 35, + 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 { + struct perf_tool tool; + struct perf_session *session; + bool show_task_events; + bool show_mmap_events; + bool show_switch_events; + bool show_namespace_events; + bool show_lost_events; + bool show_round_events; + bool show_bpf_events; + bool show_cgroup_events; + bool show_text_poke_events; + bool allocated; + bool per_event_dump; + bool stitch_lbr; + struct evswitch evswitch; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; + int name_width; + const char *time_str; + struct perf_time_interval *ptime_range; + int range_size; + int range_num; }; struct output_option { @@ -57,17 +182,63 @@ 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}, + {.str = "period", .field = PERF_OUTPUT_PERIOD}, + {.str = "iregs", .field = PERF_OUTPUT_IREGS}, + {.str = "uregs", .field = PERF_OUTPUT_UREGS}, + {.str = "brstack", .field = PERF_OUTPUT_BRSTACK}, + {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM}, + {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC}, + {.str = "weight", .field = PERF_OUTPUT_WEIGHT}, + {.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}, + {.str = "synth", .field = PERF_OUTPUT_SYNTH}, + {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR}, + {.str = "metric", .field = PERF_OUTPUT_METRIC}, + {.str = "misc", .field = PERF_OUTPUT_MISC}, + {.str = "srccode", .field = PERF_OUTPUT_SRCCODE}, + {.str = "ipc", .field = PERF_OUTPUT_IPC}, + {.str = "tod", .field = PERF_OUTPUT_TOD}, + {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, + {.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE}, + {.str = "ins_lat", .field = PERF_OUTPUT_INS_LAT}, + {.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 { + OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_OTHER, + 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; bool wildcard_set; + unsigned int print_ip_opts; u64 fields; u64 invalid_fields; -} output[PERF_TYPE_MAX] = { + u64 user_set_fields; + u64 user_unset_fields; +} output[OUTPUT_TYPE_MAX] = { [PERF_TYPE_HARDWARE] = { .user_set = false, @@ -75,9 +246,10 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, - .invalid_fields = PERF_OUTPUT_TRACE, + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, [PERF_TYPE_SOFTWARE] = { @@ -86,7 +258,9 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_BPF_OUTPUT, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -96,7 +270,19 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | - PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE, + PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE + }, + + [PERF_TYPE_HW_CACHE] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, [PERF_TYPE_RAW] = { @@ -105,16 +291,131 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + 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_RETIRE_LAT, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, - .invalid_fields = PERF_OUTPUT_TRACE, + [PERF_TYPE_BREAKPOINT] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, + + [OUTPUT_TYPE_SYNTH] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_OTHER] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, +}; + +struct evsel_script { + char *filename; + FILE *fp; + u64 samples; }; +static struct evsel_script *evsel_script__new(struct evsel *evsel, struct perf_data *data) +{ + struct evsel_script *es = zalloc(sizeof(*es)); + + if (es != NULL) { + if (asprintf(&es->filename, "%s.%s.dump", data->file.path, evsel__name(evsel)) < 0) + goto out_free; + es->fp = fopen(es->filename, "w"); + if (es->fp == NULL) + goto out_free_filename; + } + + return es; +out_free_filename: + zfree(&es->filename); +out_free: + free(es); + return NULL; +} + +static void evsel_script__delete(struct evsel_script *es) +{ + zfree(&es->filename); + fclose(es->fp); + es->fp = NULL; + free(es); +} + +static int evsel_script__fprintf(struct evsel_script *es, FILE *fp) +{ + struct stat st; + + fstat(fileno(es->fp), &st); + return fprintf(fp, "[ perf script: Wrote %.3f MB %s (%" PRIu64 " samples) ]\n", + st.st_size / 1024.0 / 1024.0, es->filename, es->samples); +} + +static inline int output_type(unsigned int type) +{ + switch (type) { + case PERF_TYPE_SYNTH: + return OUTPUT_TYPE_SYNTH; + default: + if (type < PERF_TYPE_MAX) + return 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; - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].user_set) return true; } @@ -135,21 +436,22 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[evsel__output_type(evsel)].fields & PERF_OUTPUT_##x) -static int perf_evsel__check_stype(struct perf_evsel *evsel, - u64 sample_type, const char *sample_msg, - enum perf_output_field field) +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->attr; - int type = attr->type; + struct perf_event_attr *attr = &evsel->core.attr; + int type = evsel__output_type(evsel); const char *evname; if (attr->sample_type & sample_type) return 0; - if (output[type].user_set) { - evname = perf_evsel__name(evsel); + if (output[type].user_set_fields & field) { + if (allow_user_set) + return 0; + evname = evsel__name(evsel); pr_err("Samples for '%s' event do not have %s attribute set. " "Cannot print '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -158,7 +460,7 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel, /* user did not ask for it explicitly so remove from the default list */ output[type].fields &= ~field; - evname = perf_evsel__name(evsel); + evname = evsel__name(evsel); pr_debug("Samples for '%s' event do not have %s attribute set. " "Skipping '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -166,33 +468,50 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel, return 0; } -static int perf_evsel__check_attr(struct perf_evsel *evsel, - struct perf_session *session) +static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, + enum perf_output_field field) +{ + return evsel__do_check_stype(evsel, sample_type, sample_msg, field, false); +} + +static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) { - struct perf_event_attr *attr = &evsel->attr; + bool allow_user_set; + + if (evsel__is_dummy_event(evsel)) + return 0; + + if (perf_header__has_feat(&session->header, HEADER_STAT)) + return 0; + + allow_user_set = perf_header__has_feat(&session->header, + HEADER_AUXTRACE); if (PRINT_FIELD(TRACE) && - !perf_session__has_traces(session, "record -R")) + !perf_session__has_traces(session, "record -R")) return -EINVAL; if (PRINT_FIELD(IP)) { - if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", - PERF_OUTPUT_IP)) + if (evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", PERF_OUTPUT_IP)) return -EINVAL; - - if (!no_callchain && - !(attr->sample_type & PERF_SAMPLE_CALLCHAIN)) - symbol_conf.use_callchain = false; } if (PRINT_FIELD(ADDR) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", - PERF_OUTPUT_ADDR)) + evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", PERF_OUTPUT_ADDR, allow_user_set)) + return -EINVAL; + + if (PRINT_FIELD(DATA_SRC) && + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; - if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { + if (PRINT_FIELD(WEIGHT) && + evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set)) + return -EINVAL; + + if (PRINT_FIELD(SYM) && + !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of symbols requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " + "sample address\navailable. Hence, no addresses to convert " "to symbols.\n"); return -EINVAL; } @@ -201,290 +520,2133 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { - pr_err("Display of DSO requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " - "to DSO.\n"); + if (PRINT_FIELD(DSO) && + !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + pr_err("Display of DSO requested but no address to convert.\n"); + return -EINVAL; + } + if ((PRINT_FIELD(SRCLINE) || PRINT_FIELD(SRCCODE)) && !PRINT_FIELD(IP)) { + pr_err("Display of source line number requested but sample IP is not\n" + "selected. Hence, no address to lookup the source line number.\n"); + return -EINVAL; + } + 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)) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", - PERF_OUTPUT_TID|PERF_OUTPUT_PID)) + evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID)) return -EINVAL; if (PRINT_FIELD(TIME) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME", - PERF_OUTPUT_TIME)) + evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME", PERF_OUTPUT_TIME)) return -EINVAL; if (PRINT_FIELD(CPU) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU", - PERF_OUTPUT_CPU)) + evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU", PERF_OUTPUT_CPU, allow_user_set)) + return -EINVAL; + + if (PRINT_FIELD(IREGS) && + evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set)) + return -EINVAL; + + if (PRINT_FIELD(UREGS) && + evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS", PERF_OUTPUT_UREGS)) + return -EINVAL; + + if (PRINT_FIELD(PHYS_ADDR) && + evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR, allow_user_set)) + return -EINVAL; + + if (PRINT_FIELD(DATA_PAGE_SIZE) && + evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE)) + return -EINVAL; + + if (PRINT_FIELD(CODE_PAGE_SIZE) && + evsel__check_stype(evsel, PERF_SAMPLE_CODE_PAGE_SIZE, "CODE_PAGE_SIZE", PERF_OUTPUT_CODE_PAGE_SIZE)) + return -EINVAL; + + if (PRINT_FIELD(INS_LAT) && + 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 evsel__set_print_ip_opts(struct evsel *evsel) +{ + unsigned int type = evsel__output_type(evsel); + + output[type].print_ip_opts = 0; + if (PRINT_FIELD(IP)) + output[type].print_ip_opts |= EVSEL__PRINT_IP; + + if (PRINT_FIELD(SYM)) + output[type].print_ip_opts |= EVSEL__PRINT_SYM; + + 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; + + if (PRINT_FIELD(SRCLINE)) + output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; +} + +static struct evsel *find_first_output_type(struct evlist *evlist, + unsigned int type) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_dummy_event(evsel)) + continue; + if (evsel__output_type(evsel) == (int)type) + return evsel; + } + return NULL; +} + /* * verify all user requested events exist and the samples * have the expected data */ static int perf_session__check_output_opt(struct perf_session *session) { - int j; - struct perf_evsel *evsel; + bool tod = false; + unsigned int j; + struct evsel *evsel; - for (j = 0; j < PERF_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, j); + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { + evsel = find_first_output_type(session->evlist, j); /* * even if fields is set to 0 (ie., show nothing) event must * exist if user explicitly includes it on the command line */ - if (!evsel && output[j].user_set && !output[j].wildcard_set) { + if (!evsel && output[j].user_set && !output[j].wildcard_set && + j != OUTPUT_TYPE_SYNTH) { pr_err("%s events do not exist. " - "Remove corresponding -f option to proceed.\n", + "Remove corresponding -F option to proceed.\n", event_type(j)); return -1; } if (evsel && output[j].fields && - perf_evsel__check_attr(evsel, session)) + evsel__check_attr(evsel, session)) return -1; + + if (evsel == NULL) + continue; + + /* '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; + } + + if (!no_callchain) { + bool use_callchain = false; + bool not_pipe = false; + + evlist__for_each_entry(session->evlist, evsel) { + not_pipe = true; + if (evsel__has_callchain(evsel) || evsel__is_offcpu_event(evsel)) { + use_callchain = true; + break; + } + } + if (not_pipe && !use_callchain) + symbol_conf.use_callchain = false; } + /* + * set default for tracepoints to print symbols only + * if callchains are present + */ + if (symbol_conf.use_callchain && + !output[PERF_TYPE_TRACEPOINT].user_set) { + j = PERF_TYPE_TRACEPOINT; + + evlist__for_each_entry(session->evlist, evsel) { + if (evsel->core.attr.type != j) + continue; + + if (evsel__has_callchain(evsel)) { + output[j].fields |= PERF_OUTPUT_IP; + output[j].fields |= PERF_OUTPUT_SYM; + output[j].fields |= PERF_OUTPUT_SYMOFFSET; + output[j].fields |= PERF_OUTPUT_DSO; + evsel__set_print_ip_opts(evsel); + goto out; + } + } + } + + 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; + } +out: return 0; } -static void print_sample_start(struct perf_sample *sample, - struct thread *thread, - struct perf_evsel *evsel) +static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch, + FILE *fp) +{ + unsigned i = 0, r; + int printed = 0; + + if (!regs || !regs->regs) + return 0; + + printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi); + + for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { + u64 val = regs->regs[i++]; + printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val); + } + + return printed; +} + +#define DEFAULT_TOD_FMT "%F %H:%M:%S" + +static char* +tod_scnprintf(struct perf_script *script, char *buf, int buflen, + u64 timestamp) +{ + u64 tod_ns, clockid_ns; + struct perf_env *env; + unsigned long nsec; + struct tm ltime; + char date[64]; + time_t sec; + + buf[0] = '\0'; + if (buflen < 64 || !script) + return buf; + + env = perf_session__env(script->session); + if (!env->clock.enabled) { + scnprintf(buf, buflen, "disabled"); + return buf; + } + + clockid_ns = env->clock.clockid_ns; + tod_ns = env->clock.tod_ns; + + if (timestamp > clockid_ns) + tod_ns += timestamp - clockid_ns; + else + tod_ns -= clockid_ns - timestamp; + + sec = (time_t) (tod_ns / NSEC_PER_SEC); + nsec = tod_ns - sec * NSEC_PER_SEC; + + if (localtime_r(&sec, <ime) == NULL) { + scnprintf(buf, buflen, "failed"); + } else { + strftime(date, sizeof(date), DEFAULT_TOD_FMT, <ime); + + if (symbol_conf.nanosecs) { + snprintf(buf, buflen, "%s.%09lu", date, nsec); + } else { + snprintf(buf, buflen, "%s.%06lu", + date, nsec / NSEC_PER_USEC); + } + } + + return buf; +} + +static int perf_sample__fprintf_iregs(struct perf_sample *sample, + struct perf_event_attr *attr, const char *arch, FILE *fp) +{ + 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) +{ + if (!sample->user_regs) + return 0; + + return perf_sample__fprintf_regs(perf_sample__user_regs(sample), + attr->sample_regs_user, arch, fp); +} + +static int perf_sample__fprintf_start(struct perf_script *script, + struct perf_sample *sample, + struct thread *thread, + struct evsel *evsel, + u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; - const char *evname = NULL; unsigned long secs; - unsigned long usecs; 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); + + /* Print VCPU only for guest events i.e. with machine_pid */ + if (PRINT_FIELD(VCPU) && sample->machine_pid) + printed += fprintf(fp, "VCPU:%03d ", sample->vcpu); if (PRINT_FIELD(COMM)) { + const char *comm = thread ? thread__comm_str(thread) : ":-1"; + if (latency_format) - printf("%8.8s ", thread->comm); - else if (PRINT_FIELD(IP) && symbol_conf.use_callchain) - printf("%s ", thread->comm); + printed += fprintf(fp, "%8.8s ", comm); + else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) + printed += fprintf(fp, "%s ", comm); else - printf("%16s ", thread->comm); + printed += fprintf(fp, "%16s ", comm); } if (PRINT_FIELD(PID) && PRINT_FIELD(TID)) - printf("%5d/%-5d ", sample->pid, sample->tid); + printed += fprintf(fp, "%7d/%-7d ", sample->pid, sample->tid); else if (PRINT_FIELD(PID)) - printf("%5d ", sample->pid); + printed += fprintf(fp, "%7d ", sample->pid); else if (PRINT_FIELD(TID)) - printf("%5d ", sample->tid); + printed += fprintf(fp, "%7d ", sample->tid); if (PRINT_FIELD(CPU)) { if (latency_format) - printf("%3d ", sample->cpu); + printed += fprintf(fp, "%3d ", sample->cpu); else - printf("[%03d] ", sample->cpu); + printed += fprintf(fp, "[%03d] ", sample->cpu); + } + + if (PRINT_FIELD(MISC)) { + int ret = 0; + + #define has(m) \ + (sample->misc & PERF_RECORD_MISC_##m) == PERF_RECORD_MISC_##m + + if (has(KERNEL)) + ret += fprintf(fp, "K"); + if (has(USER)) + ret += fprintf(fp, "U"); + if (has(HYPERVISOR)) + ret += fprintf(fp, "H"); + if (has(GUEST_KERNEL)) + ret += fprintf(fp, "G"); + if (has(GUEST_USER)) + ret += fprintf(fp, "g"); + + switch (type) { + case PERF_RECORD_MMAP: + case PERF_RECORD_MMAP2: + if (has(MMAP_DATA)) + ret += fprintf(fp, "M"); + break; + case PERF_RECORD_COMM: + if (has(COMM_EXEC)) + ret += fprintf(fp, "E"); + break; + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + if (has(SWITCH_OUT)) { + ret += fprintf(fp, "S"); + if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) + ret += fprintf(fp, "p"); + } + default: + break; + } + + #undef has + + ret += fprintf(fp, "%*s", 6 - ret, " "); + printed += ret; + } + + if (PRINT_FIELD(TOD)) { + tod_scnprintf(script, tstr, sizeof(tstr), sample->time); + printed += fprintf(fp, "%s ", tstr); } if (PRINT_FIELD(TIME)) { - nsecs = sample->time; - secs = nsecs / NSECS_PER_SEC; - nsecs -= secs * NSECS_PER_SEC; - usecs = nsecs / NSECS_PER_USEC; - printf("%5lu.%06lu: ", secs, usecs); + u64 t = sample->time; + if (reltime) { + if (!initial_time) + initial_time = sample->time; + t = sample->time - initial_time; + } else if (deltatime) { + if (previous_time) + t = sample->time - previous_time; + else { + t = 0; + } + previous_time = sample->time; + } + nsecs = t; + secs = nsecs / NSEC_PER_SEC; + nsecs -= secs * NSEC_PER_SEC; + + if (symbol_conf.nanosecs) + printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs); + else { + char sample_time[32]; + timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time)); + printed += fprintf(fp, "%12s: ", sample_time); + } } - if (PRINT_FIELD(EVNAME)) { - evname = perf_evsel__name(evsel); - printf("%s: ", evname ? evname : "[unknown]"); + return printed; +} + +static inline size_t +bstack_event_str(struct branch_entry *br, char *buf, size_t sz) +{ + if (!(br->flags.mispred || br->flags.predicted || br->flags.not_taken)) + return snprintf(buf, sz, "-"); + + 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) +{ + 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), + br->flags.spec ? branch_spec_desc(br->flags.spec) : "-"); +} + +static int perf_sample__fprintf_brstack(struct perf_sample *sample, + struct thread *thread, + struct evsel *evsel, FILE *fp) +{ + struct branch_stack *br = sample->branch_stack; + struct branch_entry *entries = perf_sample__branch_entries(sample); + u64 i, from, to; + int printed = 0; + + if (!(br && br->nr)) + return 0; + + for (i = 0; i < br->nr; i++) { + from = entries[i].from; + to = entries[i].to; + + printed += fprintf(fp, " 0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + 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 += 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); } + + return printed; } -static bool is_bts_event(struct perf_event_attr *attr) +static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, + struct thread *thread, + struct evsel *evsel, FILE *fp) { - return ((attr->type == PERF_TYPE_HARDWARE) && - (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && - (attr->sample_period == 1)); + struct branch_stack *br = sample->branch_stack; + struct branch_entry *entries = perf_sample__branch_entries(sample); + u64 i, from, to; + int printed = 0; + + if (!(br && br->nr)) + return 0; + + for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; + + addr_location__init(&alf); + addr_location__init(&alt); + from = entries[i].from; + to = entries[i].to; + + thread__find_symbol_fb(thread, sample->cpumode, from, &alf); + thread__find_symbol_fb(thread, sample->cpumode, to, &alt); + + printed += symbol__fprintf_symname_offs(alf.sym, &alf, 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 += 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; } -static bool sample_addr_correlates_sym(struct perf_event_attr *attr) +static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, + struct thread *thread, + struct evsel *evsel, FILE *fp) { - if ((attr->type == PERF_TYPE_SOFTWARE) && - ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))) - return true; + struct branch_stack *br = sample->branch_stack; + struct branch_entry *entries = perf_sample__branch_entries(sample); + u64 i, from, to; + int printed = 0; - if (is_bts_event(attr)) - return true; + if (!(br && br->nr)) + return 0; - return false; + for (i = 0; i < br->nr; i++) { + struct addr_location alf, 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) && + !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) && + !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 += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); + printed += fprintf(fp, "/0x%"PRIx64, to); + 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; } +#define MAXBB 16384UL -static void print_sample_addr(union perf_event *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread, - struct perf_event_attr *attr) +static int grab_bb(u8 *buffer, u64 start, u64 end, + struct machine *machine, struct thread *thread, + bool *is64bit, u8 *cpumode, bool last) { + long offset, len; struct addr_location al; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + bool kernel; + struct dso *dso; + int ret = 0; - printf("%16" PRIx64, sample->addr); + if (!start || !end) + return 0; - if (!sample_addr_correlates_sym(attr)) - return; + kernel = machine__kernel_ip(machine, start); + if (kernel) + *cpumode = PERF_RECORD_MISC_KERNEL; + else + *cpumode = PERF_RECORD_MISC_USER; - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->addr, &al); + /* + * Block overlaps between kernel and user. + * This can happen due to ring filtering + * On Intel CPUs the entry into the kernel is filtered, + * but the exit is not. Let the caller patch it up. + */ + if (kernel != machine__kernel_ip(machine, end)) { + pr_debug("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", start, end); + return -ENXIO; + } + + if (end - start > MAXBB - MAXINSN) { + if (last) + pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); + else + pr_debug("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start); + return 0; + } + + 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); + goto out; + } + if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR) { + pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); + goto out; + } + + /* Load maps to ensure dso->is_64_bit has been updated */ + map__load(al.map); + + offset = map__map_ip(al.map, start); + len = dso__data_read_offset(dso, machine, offset, (u8 *)buffer, + end - start + MAXINSN); + + *is64bit = dso__is_64_bit(dso); + if (len <= 0) + pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", + start, end); + 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) +{ + char *srcfile; + int ret = 0; + unsigned line; + int len; + char *srccode; + struct dso *dso; + + if (!map || (dso = map__dso(map)) == NULL) + return 0; + srcfile = get_srcline_split(dso, + map__rip_2objdump(map, addr), + &line); + if (!srcfile) + return 0; + + /* Avoid redundant printing */ + if (state && + state->srcfile && + !strcmp(state->srcfile, srcfile) && + state->line == line) { + free(srcfile); + return 0; + } + + srccode = find_sourceline(srcfile, line, &len); + if (!srccode) + goto out_free_line; + + ret = fprintf(fp, "|%-8d %.*s", line, len, srccode); + + if (state) { + state->srcfile = srcfile; + state->line = line; + } + return ret; + +out_free_line: + free(srcfile); + return ret; +} + +static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) +{ + struct addr_location al; + int ret = 0; + + addr_location__init(&al); + thread__find_map(thread, cpumode, addr, &al); if (!al.map) - thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, - sample->addr, &al); + goto out; + ret = map__fprintf_srccode(al.map, al.addr, stdout, + thread__srccode_state(thread)); + if (ret) + ret += printf("\n"); +out: + addr_location__exit(&al); + return ret; +} - al.cpu = sample->cpu; - al.sym = NULL; +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 evsel *evsel, + struct thread *thread, + u64 br_cntr) +{ + int ilen = 0; + 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" : "", + en->flags.in_tx ? " INTX" : "", + en->flags.abort ? " ABORT" : ""); + if (en->flags.cycles) { + *total_cycles += en->flags.cycles; + printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles); + 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 evsel *evsel, FILE *fp) +{ + struct addr_location 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) + goto out; + + al.cpu = cpu; + al.sym = NULL; if (al.map) - al.sym = map__find_symbol(al.map, al.addr, NULL); + al.sym = map__find_symbol(al.map, al.addr); + + if (!al.sym) + goto out; + + if (al.addr < al.sym->end) + off = al.addr - al.sym->start; + else + 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); + printed += fprintf(fp, ":"); + if (PRINT_FIELD(SRCLINE)) + printed += map__fprintf_srcline(al.map, al.addr, "\t", fp); + printed += fprintf(fp, "\n"); + *lastsym = al.sym; + + 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) +{ + struct branch_stack *br = sample->branch_stack; + struct branch_entry *entries = perf_sample__branch_entries(sample); + u64 start, end; + int i, insn, len, nr, ilen, printed = 0; + struct perf_insn x; + u8 buffer[MAXBB]; + unsigned off; + struct symbol *lastsym = NULL; + int total_cycles = 0; + u64 br_cntr = 0; + + if (!(br && br->nr)) + return 0; + nr = br->nr; + if (max_blocks && nr > max_blocks + 1) + 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. */ + len = grab_bb(buffer, entries[nr-1].from, + entries[nr-1].from, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len > 0) { + printed += ip__fprintf_sym(entries[nr - 1].from, thread, + 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, + evsel, thread, br_cntr); + if (PRINT_FIELD(SRCCODE)) + printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); + } + + /* Print all blocks */ + for (i = nr - 2; i >= 0; i--) { + if (entries[i].from || entries[i].to) + pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i, + entries[i].from, + entries[i].to); + start = entries[i + 1].to; + end = entries[i].from; + + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + /* Patch up missing kernel transfers due to ring filters */ + if (len == -ENXIO && i > 0) { + end = entries[--i].from; + pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end); + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + } + if (len <= 0) + continue; + + insn = 0; + for (off = 0; off < (unsigned)len; off += ilen) { + uint64_t ip = start + off; + + 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, 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", 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"); + if (ilen == 0) + break; + if (PRINT_FIELD(SRCCODE)) + print_srccode(thread, x.cpumode, ip); + insn++; + } + } + if (off != end - start) + printed += fprintf(fp, "\tmismatch of LBR data and executable\n"); + } + + /* + * Hit the branch? In this case we are already done, and the target + * has not been executed yet. + */ + if (entries[0].from == sample->ip) + goto out; + if (entries[0].flags.abort) + goto out; + + /* + * 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. + */ + start = entries[0].to; + end = sample->ip; + if (end < start) { + /* Missing jump. Scan 128 bytes for the next branch */ + 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, evsel, fp); + if (len <= 0) { + /* Print at least last IP if basic block did not work */ + len = grab_bb(buffer, sample->ip, sample->ip, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len <= 0) + goto out; + ilen = 0; + 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"); + if (PRINT_FIELD(SRCCODE)) + print_srccode(thread, x.cpumode, sample->ip); + goto out; + } + for (off = 0; off <= end - start; off += ilen) { + ilen = 0; + 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 ((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. + */ + printed += fprintf(fp, "\t... not reaching sample ...\n"); + break; + } + if (PRINT_FIELD(SRCCODE)) + print_srccode(thread, x.cpumode, start + off); + } +out: + return printed; +} + +static int perf_sample__fprintf_addr(struct perf_sample *sample, + struct thread *thread, + struct evsel *evsel, FILE *fp) +{ + struct addr_location al; + int printed = fprintf(fp, "%16" PRIx64, sample->addr); + + addr_location__init(&al); + if (!sample_addr_correlates_sym(&evsel->core.attr)) + goto out; + + thread__resolve(thread, &al, sample); if (PRINT_FIELD(SYM)) { - printf(" "); + printed += fprintf(fp, " "); if (PRINT_FIELD(SYMOFFSET)) - symbol__fprintf_symname_offs(al.sym, &al, stdout); + printed += symbol__fprintf_symname_offs(al.sym, &al, fp); + else + printed += symbol__fprintf_symname(al.sym, 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; +} + +static const char *resolve_branch_sym(struct perf_sample *sample, + struct evsel *evsel, + struct thread *thread, + struct addr_location *al, + struct addr_location *addr_al, + u64 *ip) +{ + const char *name = NULL; + + if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { + if (sample_addr_correlates_sym(&evsel->core.attr)) { + if (!addr_al->thread) + thread__resolve(thread, addr_al, sample); + if (addr_al->sym) + name = addr_al->sym->name; + else + *ip = sample->addr; + } else { + *ip = sample->addr; + } + } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) { + if (al->sym) + name = al->sym->name; else - symbol__fprintf_symname(al.sym, stdout); + *ip = sample->ip; + } + return name; +} + +static int perf_sample__fprintf_callindent(struct perf_sample *sample, + struct evsel *evsel, + struct thread *thread, + struct addr_location *al, + struct addr_location *addr_al, + FILE *fp) +{ + size_t depth = thread_stack__depth(thread, sample->cpu); + const char *name = NULL; + static int spacing; + int len = 0; + int dlen = 0; + u64 ip = 0; + + /* + * The 'return' has already been popped off the stack so the depth has + * to be adjusted to match the 'call'. + */ + if (thread__ts(thread) && sample->flags & PERF_IP_FLAG_RETURN) + depth += 1; + + name = resolve_branch_sym(sample, evsel, thread, al, addr_al, &ip); + + if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) { + dlen += fprintf(fp, "("); + dlen += map__fprintf_dsoname(al->map, fp); + dlen += fprintf(fp, ")\t"); } - if (PRINT_FIELD(DSO)) { - printf(" ("); - map__fprintf_dsoname(al.map, stdout); - printf(")"); + if (name) + len = fprintf(fp, "%*s%s", (int)depth * 4, "", name); + else if (ip) + len = fprintf(fp, "%*s%16" PRIx64, (int)depth * 4, "", ip); + + if (len < 0) + return len; + + /* + * Try to keep the output length from changing frequently so that the + * output lines up more nicely. + */ + if (len > spacing || (len && len < spacing - 52)) + spacing = round_up(len + 4, 32); + + if (len < spacing) + len += fprintf(fp, "%*s", spacing - len, ""); + + return len + dlen; +} + +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 addr_location *al) +{ + int printed = 0; + + 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) { + 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) || 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 evsel *evsel, FILE *fp) +{ + unsigned int ipc; + + if (!PRINT_FIELD(IPC) || !sample->cyc_cnt || !sample->insn_cnt) + return 0; + + ipc = (sample->insn_cnt * 100) / sample->cyc_cnt; + + return fprintf(fp, " \t IPC: %u.%02u (%" PRIu64 "/%" PRIu64 ") ", + ipc / 100, ipc % 100, sample->insn_cnt, sample->cyc_cnt); } -static void print_sample_bts(union perf_event *event, - struct perf_sample *sample, - struct perf_evsel *evsel, - struct machine *machine, - struct thread *thread) +static int perf_sample__fprintf_bts(struct perf_sample *sample, + struct evsel *evsel, + struct thread *thread, + struct addr_location *al, + struct addr_location *addr_al, + struct machine *machine, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; + unsigned int type = evsel__output_type(evsel); + bool print_srcline_last = false; + int printed = 0; + + if (PRINT_FIELD(CALLINDENT)) + printed += perf_sample__fprintf_callindent(sample, evsel, thread, al, addr_al, fp); /* print branch_from information */ if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else - printf("\n"); - perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); - } + unsigned int print_opts = output[type].print_ip_opts; + 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)) + cursor = NULL; + } + if (cursor == NULL) { + printed += fprintf(fp, " "); + if (print_opts & EVSEL__PRINT_SRCLINE) { + print_srcline_last = true; + print_opts &= ~EVSEL__PRINT_SRCLINE; + } + } else + printed += fprintf(fp, "\n"); - printf(" => "); + printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, + symbol_conf.bt_stop_list, fp); + } /* print branch_to information */ - if (PRINT_FIELD(ADDR)) - print_sample_addr(event, sample, machine, thread, attr); + if (PRINT_FIELD(ADDR) || + ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && + !output[type].user_set)) { + printed += fprintf(fp, " => "); + printed += perf_sample__fprintf_addr(sample, thread, evsel, fp); + } + + printed += perf_sample__fprintf_ipc(sample, evsel, fp); - printf("\n"); + if (print_srcline_last) + printed += map__fprintf_srcline(al->map, al->addr, "\n ", 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)); + if (ret) { + printed += ret; + printed += printf("\n"); + } + } + return printed; } -static void process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al) +static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; - struct thread *thread = al->thread; + char str[SAMPLE_FLAGS_BUF_SIZE]; + int ret; + + 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 { + int line_no; + bool hit_nul; + bool is_printable; +}; + +static int sample__fprintf_bpf_output(enum binary_printer_ops op, + unsigned int val, + void *extra, FILE *fp) +{ + unsigned char ch = (unsigned char)val; + struct printer_data *printer_data = extra; + int printed = 0; + + switch (op) { + case BINARY_PRINT_DATA_BEGIN: + printed += fprintf(fp, "\n"); + break; + case BINARY_PRINT_LINE_BEGIN: + printed += fprintf(fp, "%17s", !printer_data->line_no ? "BPF output:" : + " "); + break; + case BINARY_PRINT_ADDR: + printed += fprintf(fp, " %04x:", val); + break; + case BINARY_PRINT_NUM_DATA: + printed += fprintf(fp, " %02x", val); + break; + case BINARY_PRINT_NUM_PAD: + printed += fprintf(fp, " "); + break; + case BINARY_PRINT_SEP: + printed += fprintf(fp, " "); + break; + case BINARY_PRINT_CHAR_DATA: + if (printer_data->hit_nul && ch) + printer_data->is_printable = false; + + if (!isprint(ch)) { + printed += fprintf(fp, "%c", '.'); + + if (!printer_data->is_printable) + break; + + if (ch == '\0') + printer_data->hit_nul = true; + else + printer_data->is_printable = false; + } else { + printed += fprintf(fp, "%c", ch); + } + break; + case BINARY_PRINT_CHAR_PAD: + printed += fprintf(fp, " "); + break; + case BINARY_PRINT_LINE_END: + printed += fprintf(fp, "\n"); + printer_data->line_no++; + break; + case BINARY_PRINT_DATA_END: + default: + break; + } + + return printed; +} + +static int perf_sample__fprintf_bpf_output(struct perf_sample *sample, FILE *fp) +{ + unsigned int nr_bytes = sample->raw_size; + struct printer_data printer_data = {0, false, true}; + int printed = binary__fprintf(sample->raw_data, nr_bytes, 8, + sample__fprintf_bpf_output, &printer_data, fp); + + if (printer_data.is_printable && printer_data.hit_nul) + printed += fprintf(fp, "%17s \"%s\"\n", "BPF string:", (char *)(sample->raw_data)); + + return printed; +} + +static int perf_sample__fprintf_spacing(int len, int spacing, FILE *fp) +{ + if (len > 0 && len < spacing) + return fprintf(fp, "%*s", spacing - len, ""); + + return 0; +} + +static int perf_sample__fprintf_pt_spacing(int len, FILE *fp) +{ + return perf_sample__fprintf_spacing(len, 34, fp); +} + +/* If a value contains only printable ASCII characters padded with NULLs */ +static bool ptw_is_prt(u64 val) +{ + char c; + u32 i; + + for (i = 0; i < sizeof(val); i++) { + c = ((char *)&val)[i]; + if (!c) + break; + if (!isprint(c) || !isascii(c)) + return false; + } + for (; i < sizeof(val); i++) { + c = ((char *)&val)[i]; + if (c) + return false; + } + return true; +} + +static int perf_sample__fprintf_synth_ptwrite(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample); + char str[sizeof(u64) + 1] = ""; + int len; + u64 val; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + val = le64_to_cpu(data->payload); + if (ptw_is_prt(val)) { + memcpy(str, &val, sizeof(val)); + str[sizeof(val)] = 0; + } + len = fprintf(fp, " IP: %u payload: %#" PRIx64 " %s ", + data->ip, val, str); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_mwait(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " hints: %#x extensions: %#x ", + data->hints, data->extensions); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_pwre(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " hw: %u cstate: %u sub-cstate: %u ", + data->hw, data->cstate, data->subcstate); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_exstop(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " IP: %u ", data->ip); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_pwrx(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " deepest cstate: %u last cstate: %u wake reason: %#x ", + data->deepest_cstate, data->last_cstate, + data->wake_reason); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample); + unsigned int percent, freq; + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + freq = (le32_to_cpu(data->freq) + 500) / 1000; + len = fprintf(fp, " cbr: %2u freq: %4u MHz ", data->cbr, freq); + if (data->max_nonturbo) { + percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10; + len += fprintf(fp, "(%3u%%) ", percent); + } + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_psb(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_psb *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " psb offs: %#" PRIx64, data->offset); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +/* Intel PT Event Trace */ +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", NULL, "UINTR", "UIRET"}; + const char *evd[64] = {"PFA", "VMXQ", "VMXR"}; + const char *s; + int len, i; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + s = cfe[data->type]; + if (s) { + len = fprintf(fp, " cfe: %s IP: %d vector: %u", + s, data->ip, data->vector); + } else { + len = fprintf(fp, " cfe: %u IP: %d vector: %u", + data->type, data->ip, data->vector); + } + for (i = 0; i < data->evd_cnt; i++) { + unsigned int et = data->evd[i].evd_type & 0x3f; + + s = evd[et]; + if (s) { + len += fprintf(fp, " %s: %#" PRIx64, + s, data->evd[i].payload); + } else { + len += fprintf(fp, " EVD_%u: %#" PRIx64, + et, data->evd[i].payload); + } + } + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + +static int perf_sample__fprintf_synth_iflag_chg(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_iflag_chg *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " IFLAG: %d->%d %s branch", !data->iflag, data->iflag, + data->via_branch ? "via" : "non"); + 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) +{ + switch (evsel->core.attr.config) { + case PERF_SYNTH_INTEL_PTWRITE: + return perf_sample__fprintf_synth_ptwrite(sample, fp); + case PERF_SYNTH_INTEL_MWAIT: + return perf_sample__fprintf_synth_mwait(sample, fp); + case PERF_SYNTH_INTEL_PWRE: + return perf_sample__fprintf_synth_pwre(sample, fp); + case PERF_SYNTH_INTEL_EXSTOP: + return perf_sample__fprintf_synth_exstop(sample, fp); + case PERF_SYNTH_INTEL_PWRX: + return perf_sample__fprintf_synth_pwrx(sample, fp); + case PERF_SYNTH_INTEL_CBR: + return perf_sample__fprintf_synth_cbr(sample, fp); + case PERF_SYNTH_INTEL_PSB: + return perf_sample__fprintf_synth_psb(sample, fp); + case PERF_SYNTH_INTEL_EVT: + 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; + } + + return 0; +} + +static int evlist__max_name_len(struct evlist *evlist) +{ + struct evsel *evsel; + int max = 0; + + evlist__for_each_entry(evlist, evsel) { + int len = strlen(evsel__name(evsel)); + + max = MAX(len, max); + } + + return max; +} + +static int data_src__fprintf(u64 data_src, FILE *fp) +{ + struct mem_info *mi = mem_info__new(); + char decode[100]; + char out[100]; + static int maxlen; + int len; + + 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) + maxlen = len; + + return fprintf(fp, "%-*s", maxlen, out); +} + +struct metric_ctx { + struct perf_sample *sample; + struct thread *thread; + struct evsel *evsel; + FILE *fp; +}; + +static void script_print_metric(struct perf_stat_config *config __maybe_unused, + 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; + perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel, + PERF_RECORD_SAMPLE, mctx->fp); + fputs("\tmetric: ", mctx->fp); + if (color) + color_fprintf(mctx->fp, color, fmt, val); + else + printf(fmt, val); + fprintf(mctx->fp, " %s\n", unit); +} + +static void script_new_line(struct perf_stat_config *config __maybe_unused, + void *ctx) +{ + struct metric_ctx *mctx = ctx; + + perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel, + PERF_RECORD_SAMPLE, mctx->fp); + fputs("\tmetric: ", mctx->fp); +} + +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 (output[attr->type].fields == 0) + 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) +{ + static bool init_metrics; + struct perf_stat_output_ctx ctx = { + .print_metric = script_print_metric, + .new_line = script_new_line, + .ctx = &(struct metric_ctx) { + .sample = sample, + .thread = thread, + .evsel = evsel, + .fp = fp, + }, + .force_header = false, + }; + 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; + } + + /* 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); + } + } +} + +static bool show_event(struct perf_sample *sample, + struct evsel *evsel, + struct thread *thread, + struct addr_location *al, + struct addr_location *addr_al) +{ + int depth = thread_stack__depth(thread, sample->cpu); + + if (!symbol_conf.graph_function) + return true; + + if (thread__filter(thread)) { + if (depth <= thread__filter_entry_depth(thread)) { + thread__set_filter(thread, false); + return false; + } + return true; + } else { + const char *s = symbol_conf.graph_function; + u64 ip; + const char *name = resolve_branch_sym(sample, evsel, thread, al, addr_al, + &ip); + unsigned nlen; + + if (!name) + return false; + nlen = strlen(name); + while (*s) { + unsigned len = strcspn(s, ","); + if (nlen == len && !strncmp(name, s, len)) { + thread__set_filter(thread, true); + thread__set_filter_entry_depth(thread, depth); + return true; + } + s += len; + if (*s == ',') + s++; + } + return false; + } +} + +static void process_event(struct perf_script *script, + struct perf_sample *sample, struct evsel *evsel, + struct addr_location *al, + struct addr_location *addr_al, + struct machine *machine) +{ + struct thread *thread = al->thread; + struct perf_event_attr *attr = &evsel->core.attr; + unsigned int type = evsel__output_type(evsel); + struct evsel_script *es = evsel->priv; + FILE *fp = es->fp; + char str[PAGE_SIZE_NAME_LEN]; + const char *arch = perf_env__arch(machine->env); + + if (output[type].fields == 0) return; - print_sample_start(sample, thread, evsel); + ++es->samples; + + perf_sample__fprintf_start(script, sample, thread, evsel, + PERF_RECORD_SAMPLE, fp); + + if (PRINT_FIELD(PERIOD)) + fprintf(fp, "%10" PRIu64 " ", sample->period); + + if (PRINT_FIELD(EVNAME)) { + const char *evname = evsel__name(evsel); + + if (!script->name_width) + script->name_width = evlist__max_name_len(script->session->evlist); + + fprintf(fp, "%*s: ", script->name_width, evname ?: "[unknown]"); + } + + if (print_flags) + perf_sample__fprintf_flags(sample->flags, fp); if (is_bts_event(attr)) { - print_sample_bts(event, sample, evsel, machine, thread); + perf_sample__fprintf_bts(sample, evsel, thread, al, addr_al, machine, fp); return; } +#ifdef HAVE_LIBTRACEEVENT + if (PRINT_FIELD(TRACE) && sample->raw_data) { + 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(TRACE)) - event_format__print(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) - print_sample_addr(event, sample, machine, thread, attr); + perf_sample__fprintf_addr(sample, thread, evsel, fp); - if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); + if (PRINT_FIELD(DATA_SRC)) + data_src__fprintf(sample->data_src, fp); + + if (PRINT_FIELD(WEIGHT)) + fprintf(fp, "%16" PRIu64, sample->weight); + + 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) + 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); + } + + if (PRINT_FIELD(IREGS)) + perf_sample__fprintf_iregs(sample, attr, arch, fp); + + if (PRINT_FIELD(UREGS)) + perf_sample__fprintf_uregs(sample, attr, arch, fp); + + if (PRINT_FIELD(BRSTACK)) + perf_sample__fprintf_brstack(sample, thread, evsel, fp); + else if (PRINT_FIELD(BRSTACKSYM)) + perf_sample__fprintf_brstacksym(sample, thread, evsel, fp); + else if (PRINT_FIELD(BRSTACKOFF)) + perf_sample__fprintf_brstackoff(sample, thread, evsel, fp); + + 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, evsel, attr, thread, machine, fp, al); + + if (PRINT_FIELD(PHYS_ADDR)) + fprintf(fp, "%16" PRIx64, sample->phys_addr); + + if (PRINT_FIELD(DATA_PAGE_SIZE)) + fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str)); + + if (PRINT_FIELD(CODE_PAGE_SIZE)) + fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); + + 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))) printf("\n"); - perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); } - printf("\n"); + if (PRINT_FIELD(METRIC)) + perf_sample__fprint_metric(thread, evsel, sample, fp); + + if (verbose > 0) + fflush(fp); } -static int default_start_script(const char *script __maybe_unused, - int argc __maybe_unused, - const char **argv __maybe_unused) +static struct scripting_ops *scripting_ops; + +static void __process_stat(struct evsel *counter, u64 tstamp) { - return 0; + int nthreads = perf_thread_map__nr(counter->core.threads); + int idx, thread; + struct perf_cpu cpu; + static int header_printed; + + if (!header_printed) { + printf("%3s %8s %15s %15s %15s %15s %s\n", + "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT"); + header_printed = 1; + } + + for (thread = 0; thread < nthreads; thread++) { + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { + struct perf_counts_values *counts; + + counts = perf_counts(counter->counts, idx, thread); + + printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", + cpu.cpu, + perf_thread_map__pid(counter->core.threads, thread), + counts->val, + counts->ena, + counts->run, + tstamp, + evsel__name(counter)); + } + } } -static int default_stop_script(void) +static void process_stat(struct evsel *counter, u64 tstamp) { - return 0; + if (scripting_ops && scripting_ops->process_stat) + scripting_ops->process_stat(&stat_config, counter, tstamp); + else + __process_stat(counter, tstamp); } -static int default_generate_script(struct pevent *pevent __maybe_unused, - const char *outfile __maybe_unused) +static void process_stat_interval(u64 tstamp) { - return 0; + if (scripting_ops && scripting_ops->process_stat_interval) + scripting_ops->process_stat_interval(tstamp); } -static struct scripting_ops default_scripting_ops = { - .start_script = default_start_script, - .stop_script = default_stop_script, - .process_event = process_event, - .generate_script = default_generate_script, -}; - -static struct scripting_ops *scripting_ops; - static void setup_scripting(void) { +#ifdef HAVE_LIBTRACEEVENT setup_perl_scripting(); +#endif setup_python_scripting(); +} - scripting_ops = &default_scripting_ops; +static int flush_scripting(void) +{ + return scripting_ops ? scripting_ops->flush_script() : 0; } static int cleanup_scripting(void) { pr_debug("\nperf script stopped\n"); - return scripting_ops->stop_script(); + return scripting_ops ? scripting_ops->stop_script() : 0; } -static int process_sample_event(struct perf_tool *tool __maybe_unused, +static bool filter_cpu(struct perf_sample *sample) +{ + if (cpu_list && sample->cpu != (u32)-1) + return !test_bit(sample->cpu, cpu_bitmap); + return false; +} + +static int process_sample_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { + struct perf_script *scr = container_of(tool, struct perf_script, tool); struct addr_location al; - struct thread *thread = machine__findnew_thread(machine, event->ip.tid); + struct addr_location addr_al; + int ret = 0; + + /* Set thread to NULL to indicate addr_al and al are not initialized */ + addr_location__init(&al); + addr_location__init(&addr_al); + + ret = dlfilter__filter_event_early(dlfilter, event, sample, evsel, machine, &al, &addr_al); + if (ret) { + if (ret > 0) + ret = 0; + goto out_put; + } - if (thread == NULL) { - pr_debug("problem processing %d event, skipping it.\n", - event->header.type); - return -1; + if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num, + sample->time)) { + goto out_put; } if (debug_mode) { @@ -495,151 +2657,616 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, nr_unordered++; } last_timestamp = sample->time; + goto out_put; + } + + if (filter_cpu(sample)) + goto out_put; + + if (!al.thread && 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, &addr_al)) + goto out_put; + + if (evswitch__discard(&scr->evswitch, evsel)) + goto out_put; + + ret = dlfilter__filter_event(dlfilter, event, sample, evsel, machine, &al, &addr_al); + if (ret) { + if (ret > 0) + ret = 0; + goto out_put; + } + + if (scripting_ops) { + struct addr_location *addr_al_ptr = NULL; + + if ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && + sample_addr_correlates_sym(&evsel->core.attr)) { + if (!addr_al.thread) + thread__resolve(al.thread, &addr_al, sample); + addr_al_ptr = &addr_al; + } + scripting_ops->process_event(event, sample, evsel, &al, addr_al_ptr); + } else { + process_event(scr, sample, evsel, &al, &addr_al, machine); + } + +out_put: + addr_location__exit(&addr_al); + addr_location__exit(&al); + return ret; +} + +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 (perf_event__preprocess_sample(event, machine, &al, sample, 0) < 0) { + 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); - return -1; + 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); + struct evlist *evlist; + struct evsel *evsel, *pos; + u64 sample_type; + int err; + + err = perf_event__process_attr(tool, event, pevlist); + if (err) + return err; + + evlist = *pevlist; + evsel = evlist__last(*pevlist); + + if (!evsel->priv) { + if (scr->per_event_dump) { + evsel->priv = evsel_script__new(evsel, scr->session->data); + if (!evsel->priv) + return -ENOMEM; + } else { // Replicate what is done in perf_script__setup_per_event_dump() + es_stdout.fp = stdout; + evsel->priv = &es_stdout; + } + } + + if (evsel->core.attr.type >= PERF_TYPE_MAX && + evsel->core.attr.type != PERF_TYPE_SYNTH) return 0; - if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + evlist__for_each_entry(evlist, pos) { + if (pos->core.attr.type == evsel->core.attr.type && pos != evsel) + return 0; + } + + if (evsel->core.attr.sample_type) { + err = evsel__check_attr(evsel, scr->session); + if (err) + return err; + } + + /* + * Check if we need to enable callchains based + * on events sample_type. + */ + sample_type = evlist__combined_sample_type(evlist); + callchain_param_setup(sample_type, perf_env__arch(perf_session__env(scr->session))); + + /* Enable fields for callchain entries */ + if (symbol_conf.use_callchain && + (sample_type & PERF_SAMPLE_CALLCHAIN || + sample_type & PERF_SAMPLE_BRANCH_STACK || + (sample_type & PERF_SAMPLE_REGS_USER && + sample_type & PERF_SAMPLE_STACK_USER))) { + 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; + } + evsel__set_print_ip_opts(evsel); + return 0; +} + +static int print_event_with_time(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + pid_t pid, pid_t tid, u64 timestamp) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct evsel *evsel = evlist__id2evsel(session->evlist, sample->id); + struct thread *thread = NULL; + + if (evsel && !evsel->core.attr.sample_id_all) { + sample->cpu = 0; + sample->time = timestamp; + sample->pid = pid; + sample->tid = tid; + } + + if (filter_cpu(sample)) return 0; - scripting_ops->process_event(event, sample, evsel, machine, &al); + if (tid != -1) + thread = machine__findnew_thread(machine, pid, tid); + + if (evsel) { + perf_sample__fprintf_start(script, sample, thread, evsel, + event->header.type, stdout); + } + + perf_event__fprintf(event, machine, stdout); + + thread__put(thread); - evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_tool perf_script = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_exit, - .fork = perf_event__process_fork, - .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, - .tracing_data = perf_event__process_tracing_data, - .build_id = perf_event__process_build_id, - .ordered_samples = true, - .ordering_requires_timestamps = true, -}; +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(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_comm(tool, event, sample, machine) < 0) + return -1; -extern volatile int session_done; + return print_event(tool, event, sample, machine, event->comm.pid, + event->comm.tid); +} -static void sig_handler(int sig __maybe_unused) +static int process_namespaces_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - session_done = 1; + if (perf_event__process_namespaces(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, event->namespaces.pid, + event->namespaces.tid); } -static int __cmd_script(struct perf_session *session) +static int process_cgroup_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - int ret; + if (perf_event__process_cgroup(tool, event, sample, machine) < 0) + return -1; - signal(SIGINT, sig_handler); + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} - ret = perf_session__process_events(session, &perf_script); +static int process_fork_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_fork(tool, event, sample, machine) < 0) + return -1; - if (debug_mode) - pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); + return print_event_with_time(tool, event, sample, machine, + event->fork.pid, event->fork.tid, + event->fork.time); +} +static int process_exit_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + /* Print before 'exit' deletes anything */ + if (print_event_with_time(tool, event, sample, machine, event->fork.pid, + event->fork.tid, event->fork.time)) + return -1; - return ret; + return perf_event__process_exit(tool, event, sample, machine); } -struct script_spec { - struct list_head node; - struct scripting_ops *ops; - char spec[0]; -}; +static int process_mmap_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_mmap(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, event->mmap.pid, + event->mmap.tid); +} -static LIST_HEAD(script_specs); +static int process_mmap2_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_mmap2(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, event->mmap2.pid, + event->mmap2.tid); +} -static struct script_spec *script_spec__new(const char *spec, - struct scripting_ops *ops) +static int process_switch_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (perf_event__process_switch(tool, event, sample, machine) < 0) + return -1; + + if (scripting_ops && scripting_ops->process_switch && !filter_cpu(sample)) + scripting_ops->process_switch(event, sample, machine); - if (s != NULL) { - strcpy(s->spec, spec); - s->ops = ops; + if (!script->show_switch_events) + return 0; + + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} + +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) { + scripting_ops->process_auxtrace_error(session, event); + return 0; } - return s; + return perf_event__process_auxtrace_error(tool, session, event); } -static void script_spec__add(struct script_spec *s) +static int +process_lost_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - list_add_tail(&s->node, &script_specs); + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } -static struct script_spec *script_spec__find(const char *spec) +static int +process_throttle_event(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct script_spec *s; + if (scripting_ops && scripting_ops->process_throttle) + scripting_ops->process_throttle(event, sample, machine); + return 0; +} - list_for_each_entry(s, &script_specs, node) - if (strcasecmp(s->spec, spec) == 0) - return s; - return NULL; +static int +process_finished_round_event(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct ordered_events *oe __maybe_unused) + +{ + perf_event__fprintf(event, NULL, stdout); + return 0; } -static struct script_spec *script_spec__findnew(const char *spec, - struct scripting_ops *ops) +static int +process_bpf_events(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct script_spec *s = script_spec__find(spec); + if (machine__process_ksymbol(machine, event, sample) < 0) + return -1; - if (s) - return s; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} - s = script_spec__new(spec, ops); - if (!s) - return NULL; +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; +} - script_spec__add(s); +static int process_text_poke_events(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_text_poke(tool, event, sample, machine) < 0) + return -1; - return s; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } -int script_spec_register(const char *spec, struct scripting_ops *ops) +static void sig_handler(int sig __maybe_unused) { - struct script_spec *s; + session_done = 1; +} - s = script_spec__find(spec); - if (s) - return -1; +static void perf_script__fclose_per_event_dump(struct perf_script *script) +{ + struct evlist *evlist = script->session->evlist; + struct evsel *evsel; - s = script_spec__findnew(spec, ops); - if (!s) - return -1; + evlist__for_each_entry(evlist, evsel) { + if (!evsel->priv) + break; + evsel_script__delete(evsel->priv); + evsel->priv = NULL; + } +} + +static int perf_script__fopen_per_event_dump(struct perf_script *script) +{ + struct evsel *evsel; + + evlist__for_each_entry(script->session->evlist, evsel) { + /* + * Already setup? I.e. we may be called twice in cases like + * Intel PT, one for the intel_pt// and dummy events, then + * for the evsels synthesized from the auxtrace info. + * + * Ses perf_script__process_auxtrace_info. + */ + if (evsel->priv != NULL) + continue; + + evsel->priv = evsel_script__new(evsel, script->session->data); + if (evsel->priv == NULL) + goto out_err_fclose; + } return 0; + +out_err_fclose: + perf_script__fclose_per_event_dump(script); + return -1; } -static struct scripting_ops *script_spec__lookup(const char *spec) +static int perf_script__setup_per_event_dump(struct perf_script *script) { - struct script_spec *s = script_spec__find(spec); - if (!s) - return NULL; + struct evsel *evsel; + + if (script->per_event_dump) + return perf_script__fopen_per_event_dump(script); + + es_stdout.fp = stdout; + + evlist__for_each_entry(script->session->evlist, evsel) + evsel->priv = &es_stdout; - return s->ops; + return 0; } -static void list_available_languages(void) +static void perf_script__exit_per_event_dump_stats(struct perf_script *script) +{ + struct evsel *evsel; + + evlist__for_each_entry(script->session->evlist, evsel) { + struct evsel_script *es = evsel->priv; + + evsel_script__fprintf(es, stdout); + evsel_script__delete(es); + evsel->priv = NULL; + } +} + +static void perf_script__exit(struct perf_script *script) +{ + perf_thread_map__put(script->threads); + perf_cpu_map__put(script->cpus); +} + +static int __cmd_script(struct perf_script *script) +{ + int ret; + + signal(SIGINT, sig_handler); + + /* override event processing functions */ + if (script->show_task_events) { + script->tool.comm = process_comm_event; + script->tool.fork = process_fork_event; + script->tool.exit = process_exit_event; + } + if (script->show_mmap_events) { + script->tool.mmap = process_mmap_event; + script->tool.mmap2 = process_mmap2_event; + } + if (script->show_switch_events || (scripting_ops && scripting_ops->process_switch)) + script->tool.context_switch = process_switch_event; + if (scripting_ops && scripting_ops->process_auxtrace_error) + script->tool.auxtrace_error = process_auxtrace_error; + if (script->show_namespace_events) + script->tool.namespaces = process_namespaces_event; + if (script->show_cgroup_events) + script->tool.cgroup = process_cgroup_event; + if (script->show_lost_events) + script->tool.lost = process_lost_event; + if (script->show_round_events) { + script->tool.ordered_events = false; + 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.bpf_metadata = process_bpf_metadata_event; + } + if (script->show_text_poke_events) { + script->tool.ksymbol = process_bpf_events; + script->tool.text_poke = process_text_poke_events; + } + + if (perf_script__setup_per_event_dump(script)) { + pr_err("Couldn't create the per event dump files\n"); + return -1; + } + + ret = perf_session__process_events(script->session); + + if (script->per_event_dump) + perf_script__exit_per_event_dump_stats(script); + + if (debug_mode) + pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); + + return ret; +} + +static int list_available_languages_cb(struct scripting_ops *ops, const char *spec) { - struct script_spec *s; + fprintf(stderr, " %-42s [%s]\n", spec, ops->name); + return 0; +} +static void list_available_languages(void) +{ fprintf(stderr, "\n"); fprintf(stderr, "Scripting language extensions (used in " "perf script -s [spec:]script.[spec]):\n\n"); + script_spec__for_each(&list_available_languages_cb); + fprintf(stderr, "\n"); +} - list_for_each_entry(s, &script_specs, node) - fprintf(stderr, " %-42s [%s]\n", s->spec, s->ops->name); +/* Find script file relative to current directory or exec path */ +static char *find_script(const char *script) +{ + char path[PATH_MAX]; - fprintf(stderr, "\n"); + if (!scripting_ops) { + const char *ext = strrchr(script, '.'); + + if (!ext) + return NULL; + + scripting_ops = script_spec__lookup(++ext); + if (!scripting_ops) + return NULL; + } + + if (access(script, R_OK)) { + char *exec_path = get_argv_exec_path(); + + if (!exec_path) + return NULL; + snprintf(path, sizeof(path), "%s/scripts/%s/%s", + exec_path, scripting_ops->dirname, script); + free(exec_path); + script = path; + if (access(script, R_OK)) + return NULL; + } + return strdup(script); } static int parse_scriptname(const struct option *opt __maybe_unused, @@ -683,7 +3310,9 @@ static int parse_scriptname(const struct option *opt __maybe_unused, } } - script_name = strdup(script); + script_name = find_script(script); + if (!script_name) + script_name = strdup(script); return 0; } @@ -691,12 +3320,13 @@ static int parse_scriptname(const struct option *opt __maybe_unused, static int parse_output_fields(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { - char *tok; + char *tok, *strtok_saveptr = NULL; int i, imax = ARRAY_SIZE(all_output_options); int j; int rc = 0; char *str = strdup(arg); int type = -1; + enum { DEFAULT, SET, ADD, REMOVE } change = DEFAULT; if (!str) return -ENOMEM; @@ -717,6 +3347,10 @@ static int parse_output_fields(const struct option *opt __maybe_unused, type = PERF_TYPE_TRACEPOINT; else if (!strcmp(str, "raw")) type = PERF_TYPE_RAW; + else if (!strcmp(str, "break")) + type = PERF_TYPE_BREAKPOINT; + else if (!strcmp(str, "synth")) + type = OUTPUT_TYPE_SYNTH; else { fprintf(stderr, "Invalid event type in field string.\n"); rc = -EINVAL; @@ -727,6 +3361,10 @@ static int parse_output_fields(const struct option *opt __maybe_unused, pr_warning("Overriding previous field request for %s events.\n", event_type(type)); + /* Don't override defaults for +- */ + if (strchr(tok, '+') || strchr(tok, '-')) + goto parse; + output[type].fields = 0; output[type].user_set = true; output[type].wildcard_set = false; @@ -740,38 +3378,80 @@ static int parse_output_fields(const struct option *opt __maybe_unused, goto out; } + /* Don't override defaults for +- */ + if (strchr(str, '+') || strchr(str, '-')) + goto parse; + if (output_set_by_user()) pr_warning("Overriding previous field request for all events.\n"); - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { output[j].fields = 0; output[j].user_set = true; output[j].wildcard_set = true; } } - tok = strtok(tok, ","); - while (tok) { +parse: + for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) { + if (*tok == '+') { + if (change == SET) + goto out_badmix; + change = ADD; + tok++; + } else if (*tok == '-') { + if (change == SET) + goto out_badmix; + change = REMOVE; + tok++; + } else { + if (change != SET && change != DEFAULT) + goto out_badmix; + change = SET; + } + for (i = 0; i < imax; ++i) { if (strcmp(tok, all_output_options[i].str) == 0) break; } + if (i == imax && strcmp(tok, "flags") == 0) { + print_flags = change != REMOVE; + continue; + } if (i == imax) { fprintf(stderr, "Invalid field requested.\n"); 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 * which it is valid */ - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].invalid_fields & all_output_options[i].field) { pr_warning("\'%s\' not valid for %s events. Ignoring.\n", all_output_options[i].str, event_type(j)); - } else - output[j].fields |= all_output_options[i].field; + } else { + if (change == REMOVE) { + output[j].fields &= ~all_output_options[i].field; + output[j].user_set_fields &= ~all_output_options[i].field; + output[j].user_unset_fields |= all_output_options[i].field; + } else { + output[j].fields |= all_output_options[i].field; + output[j].user_set_fields |= all_output_options[i].field; + output[j].user_unset_fields &= ~all_output_options[i].field; + } + output[j].user_set = true; + output[j].wildcard_set = true; + } } } else { if (output[type].invalid_fields & all_output_options[i].field) { @@ -781,10 +3461,13 @@ static int parse_output_fields(const struct option *opt __maybe_unused, rc = -EINVAL; goto out; } - output[type].fields |= all_output_options[i].field; + if (change == REMOVE) + output[type].fields &= ~all_output_options[i].field; + else + output[type].fields |= all_output_options[i].field; + output[type].user_set = true; + output[type].wildcard_set = true; } - - tok = strtok(NULL, ","); } if (type >= 0) { @@ -793,40 +3476,29 @@ static int parse_output_fields(const struct option *opt __maybe_unused, "Events will not be displayed.\n", event_type(type)); } } + goto out; +out_badmix: + fprintf(stderr, "Cannot mix +-field with overridden fields\n"); + rc = -EINVAL; out: free(str); return rc; } -/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */ -static int is_directory(const char *base_path, const struct dirent *dent) -{ - char path[PATH_MAX]; - struct stat st; - - sprintf(path, "%s/%s", base_path, dent->d_name); - if (stat(path, &st)) - return 0; - - return S_ISDIR(st.st_mode); -} - -#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\ - while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) && \ - lang_next) \ - if ((lang_dirent.d_type == DT_DIR || \ - (lang_dirent.d_type == DT_UNKNOWN && \ - is_directory(scripts_path, &lang_dirent))) && \ - (strcmp(lang_dirent.d_name, ".")) && \ - (strcmp(lang_dirent.d_name, ".."))) +#define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ + while ((lang_dirent = readdir(scripts_dir)) != NULL) \ + if ((lang_dirent->d_type == DT_DIR || \ + (lang_dirent->d_type == DT_UNKNOWN && \ + is_directory(scripts_path, lang_dirent))) && \ + (strcmp(lang_dirent->d_name, ".")) && \ + (strcmp(lang_dirent->d_name, ".."))) -#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\ - while (!readdir_r(lang_dir, &script_dirent, &script_next) && \ - script_next) \ - if (script_dirent.d_type != DT_DIR && \ - (script_dirent.d_type != DT_UNKNOWN || \ - !is_directory(lang_path, &script_dirent))) +#define for_each_script(lang_path, lang_dir, script_dirent) \ + while ((script_dirent = readdir(lang_dir)) != NULL) \ + if (script_dirent->d_type != DT_DIR && \ + (script_dirent->d_type != DT_UNKNOWN || \ + !is_directory(lang_path, script_dirent))) #define RECORD_SUFFIX "-record" @@ -853,9 +3525,9 @@ static struct script_desc *script_desc__new(const char *name) static void script_desc__delete(struct script_desc *s) { - free(s->name); - free(s->half_liner); - free(s->args); + zfree(&s->name); + zfree(&s->half_liner); + zfree(&s->args); free(s); } @@ -883,16 +3555,11 @@ static struct script_desc *script_desc__findnew(const char *name) s = script_desc__new(name); if (!s) - goto out_delete_desc; + return NULL; script_desc__add(s); return s; - -out_delete_desc: - script_desc__delete(s); - - return NULL; } static const char *ends_with(const char *str, const char *suffix) @@ -919,7 +3586,7 @@ static int read_script_info(struct script_desc *desc, const char *filename) return -1; while (fgets(line, sizeof(line), fp)) { - p = ltrim(line); + p = skip_spaces(line); if (strlen(p) == 0) continue; if (*p != '#') @@ -928,19 +3595,19 @@ static int read_script_info(struct script_desc *desc, const char *filename) if (strlen(p) && *p == '!') continue; - p = ltrim(p); + p = skip_spaces(p); if (strlen(p) && p[strlen(p) - 1] == '\n') p[strlen(p) - 1] = '\0'; if (!strncmp(p, "description:", strlen("description:"))) { p += strlen("description:"); - desc->half_liner = strdup(ltrim(p)); + desc->half_liner = strdup(skip_spaces(p)); continue; } if (!strncmp(p, "args:", strlen("args:"))) { p += strlen("args:"); - desc->args = strdup(ltrim(p)); + desc->args = strdup(skip_spaces(p)); continue; } } @@ -972,34 +3639,47 @@ static int list_available_scripts(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset __maybe_unused) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; - char scripts_path[MAXPATHLEN]; + struct dirent *script_dirent, *lang_dirent; + 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; - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + 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); - if (!scripts_dir) - return -1; + if (!scripts_dir) { + fprintf(stdout, + "open(%s) failed.\n" + "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", + scripts_path); + free(buf); + exit(-1); + } - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { - snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + for_each_lang(scripts_path, scripts_dir, lang_dirent) { + scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - script_root = get_script_root(&script_dirent, REPORT_SUFFIX); + for_each_script(lang_path, lang_dir, script_dirent) { + script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); - snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + scnprintf(script_path, MAXPATHLEN, "%s/%s", + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -1014,170 +3694,68 @@ static int list_available_scripts(const struct option *opt __maybe_unused, desc->half_liner ? desc->half_liner : ""); } + free(buf); exit(0); } -/* - * 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 complexing formats like event groups etc. - */ -static int check_ev_match(char *dir_name, char *scriptname, - struct perf_session *session) +static int add_dlarg(const struct option *opt __maybe_unused, + const char *s, int unset __maybe_unused) { - char filename[MAXPATHLEN], evname[128]; - char line[BUFSIZ], *p; - struct perf_evsel *pos; - int match, len; - FILE *fp; + char *arg = strdup(s); + void *a; - sprintf(filename, "%s/bin/%s-record", dir_name, scriptname); - - fp = fopen(filename, "r"); - if (!fp) + if (!arg) return -1; - while (fgets(line, sizeof(line), fp)) { - p = ltrim(line); - if (*p == '#') - continue; - - while (strlen(p)) { - p = strstr(p, "-e"); - if (!p) - break; - - p += 2; - p = ltrim(p); - len = strcspn(p, " \t"); - if (!len) - break; - - snprintf(evname, len + 1, "%s", p); - - match = 0; - list_for_each_entry(pos, - &session->evlist->entries, node) { - if (!strcmp(perf_evsel__name(pos), evname)) { - match = 1; - break; - } - } - - if (!match) { - fclose(fp); - return -1; - } - } + a = realloc(dlargv, sizeof(dlargv[0]) * (dlargc + 1)); + if (!a) { + free(arg); + return -1; } - fclose(fp); + dlargv = a; + dlargv[dlargc++] = arg; + 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) +static void free_dlarg(void) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; - char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; - DIR *scripts_dir, *lang_dir; - struct perf_session *session; - char *temp; - int i = 0; - - session = perf_session__new(input_name, O_RDONLY, 0, false, NULL); - if (!session) - return -1; - - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_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, lang_next) { - snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent.d_name); -#ifdef NO_LIBPERL - if (strstr(lang_path, "perl")) - continue; -#endif -#ifdef NO_LIBPYTHON - 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, script_next) { - /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent.d_name, "top.")) - continue; - sprintf(scripts_path_array[i], "%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; + while (dlargc--) + free(dlargv[dlargc]); + free(dlargv); } static char *get_script_path(const char *script_root, const char *suffix) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; char script_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; char lang_path[MAXPATHLEN]; char *__script_root; - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); if (!scripts_dir) return NULL; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { - snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + for_each_lang(scripts_path, scripts_dir, lang_dirent) { + scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - __script_root = get_script_root(&script_dirent, suffix); + for_each_script(lang_path, lang_dir, script_dirent) { + __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); - closedir(lang_dir); closedir(scripts_dir); - snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + scnprintf(script_path, MAXPATHLEN, "%s/%s", + lang_path, script_dirent->d_name); + closedir(lang_dir); return strdup(script_path); } free(__script_root); @@ -1191,7 +3769,7 @@ static char *get_script_path(const char *script_root, const char *suffix) static bool is_top_script(const char *script_path) { - return ends_with(script_path, "top") == NULL ? false : true; + return ends_with(script_path, "top") != NULL; } static int has_required_arg(char *script_path) @@ -1236,59 +3814,362 @@ static int have_cmd(int argc, const char **argv) return 0; } -int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) +static void script__setup_sample_type(struct perf_script *script) +{ + struct perf_session *session = script->session; + u64 sample_type = evlist__combined_sample_type(session->evlist); + + callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env)); + + if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { + pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" + "Please apply --call-graph lbr when recording.\n"); + script->stitch_lbr = false; + } +} + +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; + struct evsel *counter; + + evlist__for_each_entry(session->evlist, counter) { + perf_stat_process_counter(&stat_config, counter); + process_stat(counter, round->time); + } + + process_stat_interval(round->time); + return 0; +} + +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; +} + +static int set_maps(struct perf_script *script) +{ + struct evlist *evlist = script->session->evlist; + + if (!script->cpus || !script->threads) + return 0; + + if (WARN_ONCE(script->allocated, "stats double allocation\n")) + return -EINVAL; + + perf_evlist__set_maps(&evlist->core, script->cpus, script->threads); + + if (evlist__alloc_stats(&stat_config, evlist, /*alloc_raw=*/true)) + return -ENOMEM; + + script->allocated = true; + return 0; +} + +static +int process_thread_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, + union perf_event *event) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (dump_trace) + perf_event__fprintf_thread_map(event, stdout); + + if (script->threads) { + pr_warning("Extra thread map event, ignoring.\n"); + return 0; + } + + script->threads = thread_map__new_event(&event->thread_map); + if (!script->threads) + return -ENOMEM; + + return set_maps(script); +} + +static +int process_cpu_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, + union perf_event *event) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (dump_trace) + perf_event__fprintf_cpu_map(event, stdout); + + if (script->cpus) { + pr_warning("Extra cpu map event, ignoring.\n"); + return 0; + } + + script->cpus = cpu_map__new_data(&event->cpu_map.data); + if (!script->cpus) + return -ENOMEM; + + return set_maps(script); +} + +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) + return perf_event__process_feature(session, event); + return 0; +} + +static int perf_script__process_auxtrace_info(const struct perf_tool *tool, + struct perf_session *session, + union perf_event *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); + + ret = perf_script__setup_per_event_dump(script); + } + + return ret; +} + +static int parse_insn_trace(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) +{ + 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; +} + +static int parse_xed(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + if (isatty(1)) + force_pager("xed -F insn: -A -64 | less"); + else + force_pager("xed -F insn: -A -64"); + return 0; +} + +static int parse_call_trace(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0); + itrace_parse_synth_opts(opt, "cewp", 0); + symbol_conf.nanosecs = true; + symbol_conf.pad_output_len_dso = 50; + return 0; +} + +static int parse_callret_trace(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0); + itrace_parse_synth_opts(opt, "crewp", 0); + symbol_conf.nanosecs = true; + return 0; +} + +int cmd_script(int argc, const char **argv) { bool show_full_info = false; + bool header = false; + 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; + struct itrace_synth_opts itrace_synth_opts = { + .set = false, + .default_no_sample = true, + }; + struct utsname uts; char *script_path = NULL; + const char *dlfilter_file = NULL; const char **__argv; - int i, j, err; + int i, j, err = 0; + struct perf_script script = {}; + struct perf_data data = { + .mode = PERF_DATA_MODE_READ, + }; const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN(0, "dump-unsorted-raw-trace", &unsorted_dump, + "dump unsorted raw trace in ASCII"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('L', "Latency", &latency_format, "show latency attributes (irqs/preemption disabled, etc)"), OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts", list_available_scripts), + OPT_CALLBACK_NOOPT(0, "list-dlfilters", NULL, NULL, "list available dlfilters", + list_available_dlfilters), OPT_CALLBACK('s', "script", NULL, "name", "script file name (lang:script name, script name, or *)", parse_scriptname), OPT_STRING('g', "gen-script", &generate_script_lang, "lang", "generate perf-script.xx script in specified language"), + OPT_STRING(0, "dlfilter", &dlfilter_file, "file", "filter .so file name"), + OPT_CALLBACK(0, "dlarg", NULL, "argument", "filter argument", + add_dlarg), OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_BOOLEAN('d', "debug-mode", &debug_mode, "do various checks like samples ordering and lost events"), + OPT_BOOLEAN(0, "header", &header, "Show data header."), + OPT_BOOLEAN(0, "header-only", &header_only, "Show only data header."), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", "kallsyms pathname"), OPT_BOOLEAN('G', "hide-call-graph", &no_callchain, "When printing symbols do not display call chain"), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), - OPT_CALLBACK('f', "fields", NULL, "str", + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), + OPT_CALLBACK('F', "fields", NULL, "str", "comma separated output fields prepend with 'type:'. " - "Valid types: hw,sw,trace,raw. " - "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff", parse_output_fields), + "+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,dsoff," + "addr,symoff,srcline,period,iregs,uregs,brstack," + "brstacksym,flags,data_src,weight,bpf-output,brstackinsn," + "brstackinsnlen,brstackdisasm,brstackoff,callindent,insn,disasm,insnlen,synth," + "phys_addr,metric,misc,srccode,ipc,tod,data_page_size," + "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"), + OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", + "only consider symbols in these DSOs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "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, "raw|disasm", + "Decode instructions from itrace", parse_insn_trace), + OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL, + "Run xed disassembler on output", parse_xed), + OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL, + "Decode calls from itrace", parse_call_trace), + OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL, + "Decode calls and returns from itrace", parse_callret_trace), + OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]", + "Only print symbols and callees with --call-trace/--call-ret-trace"), + OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]", + "Stop display of callgraph at these symbols"), OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", "only display events for these comms"), + OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]", + "only consider symbols in these pids"), + OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", + "only consider symbols in these tids"), + OPT_UINTEGER(0, "max-stack", &scripting_max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), + OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"), + OPT_BOOLEAN(0, "deltatime", &deltatime, "Show time stamps relative to previous event"), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, "Show the path of [kernel.kallsyms]"), + OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events, + "Show the fork/comm/exit events"), + OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events, + "Show the mmap events"), + OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events, + "Show context switch events (if recorded)"), + OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, + "Show namespace events (if recorded)"), + OPT_BOOLEAN('\0', "show-cgroup-events", &script.show_cgroup_events, + "Show cgroup events (if recorded)"), + OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events, + "Show lost events (if recorded)"), + OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events, + "Show round events (if recorded)"), + OPT_BOOLEAN('\0', "show-bpf-events", &script.show_bpf_events, + "Show bpf related events (if recorded)"), + OPT_BOOLEAN('\0', "show-text-poke-events", &script.show_text_poke_events, + "Show text poke related events (if recorded)"), + OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump, + "Dump trace output to files named by the monitored events"), + OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), + OPT_INTEGER(0, "max-blocks", &max_blocks, + "Maximum number of code blocks to dump with brstackinsn"), + OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, + "Use 9 decimal places when displaying time"), + OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", + "Instruction Tracing options\n" ITRACE_HELP, + itrace_parse_synth_opts), + OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, + "Show full source file name path for source lines"), + OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, + "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, + "Show inline function"), + OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", + "guest mount directory under which every guest os" + " instance has a subdir"), + OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, + "file", "file saving guest os vmlinux"), + OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, + "file", "file saving guest os /proc/kallsyms"), + OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, + "file", "file saving guest os /proc/modules"), + OPT_BOOLEAN(0, "guest-code", &symbol_conf.guest_code, + "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() }; - const char * const script_usage[] = { + const char * const script_subcommands[] = { "record", "report", NULL }; + const char *script_usage[] = { "perf script [<options>]", "perf script [<options>] record <script> [<record-options>] <command>", "perf script [<options>] report <script> [script-args]", @@ -1296,19 +4177,42 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "perf script [<options>] <top-script> [script-args]", NULL }; + struct perf_env *env; + + perf_set_singlethreaded(); setup_scripting(); - argc = parse_options(argc, argv, options, script_usage, + argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { + if (symbol_conf.guestmount || + symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_kallsyms || + symbol_conf.default_guest_modules || + symbol_conf.guest_code) { + /* + * Enable guest sample processing. + */ + perf_guest = true; + } + + data.path = input_name; + data.force = symbol_conf.force; + + if (unsorted_dump) + dump_trace = true; + + if (symbol__validate_sym_arguments()) + return -1; + + if (argc > 1 && strlen(argv[0]) > 2 && strstarts("record", argv[0])) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) - return cmd_record(argc, argv, NULL); + return cmd_record(argc, argv); } - if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) { + if (argc > 1 && strlen(argv[0]) > 2 && strstarts("report", argv[0])) { rep_script_path = get_script_path(argv[1], REPORT_SUFFIX); if (!rep_script_path) { fprintf(stderr, @@ -1318,8 +4222,19 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) } } + if (reltime && deltatime) { + fprintf(stderr, + "reltime and deltatime - the two don't get along well. " + "Please limit to --reltime or --deltatime.\n"); + return -1; + } + + if ((itrace_synth_opts.callchain || itrace_synth_opts.add_callchain) && + itrace_synth_opts.callchain_sz > scripting_max_stack) + scripting_max_stack = itrace_synth_opts.callchain_sz; + /* make sure PERF_EXEC_PATH is set for scripts */ - perf_set_argv_exec_path(perf_exec_path()); + set_argv_exec_path(get_argv_exec_path()); if (argc && !script_name && !rec_script_path && !rep_script_path) { int live_pipe[2]; @@ -1330,9 +4245,15 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) rep_script_path = get_script_path(argv[0], REPORT_SUFFIX); if (!rec_script_path && !rep_script_path) { - fprintf(stderr, " Couldn't find script %s\n\n See perf" + script_name = find_script(argv[0]); + if (script_name) { + argc -= 1; + argv += 1; + goto script_found; + } + usage_with_options_msg(script_usage, options, + "Couldn't find script `%s'\n\n See perf" " script -l for available scripts.\n", argv[0]); - usage_with_options(script_usage, options); } if (is_top_script(argv[0])) { @@ -1343,10 +4264,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) rep_args = has_required_arg(rep_script_path); rec_args = (argc - 1) - rep_args; if (rec_args < 0) { - fprintf(stderr, " %s script requires options." + usage_with_options_msg(script_usage, options, + "`%s' script requires options." "\n\n See perf script -l for available " "scripts and options.\n", argv[0]); - usage_with_options(script_usage, options); } } @@ -1422,7 +4343,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) free(__argv); exit(-1); } - +script_found: if (rec_script_path) script_path = rec_script_path; if (rep_script_path) @@ -1460,29 +4381,106 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) exit(-1); } - if (symbol__init() < 0) - return -1; - if (!script_name) + if (dlfilter_file) { + dlfilter = dlfilter__new(dlfilter_file, dlargc, dlargv); + if (!dlfilter) + return -1; + } + + if (!script_name) { setup_pager(); + use_browser = 0; + } - session = perf_session__new(input_name, O_RDONLY, 0, false, - &perf_script); - if (session == NULL) - return -ENOMEM; + 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); + if (header_only) + goto out_delete; + } + if (show_full_info) + script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; + + 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 (env->arch) { + if (!strcmp(uts.machine, env->arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(env->arch, "i386")) + native_arch = true; + } + + script.session = session; + script__setup_sample_type(&script); + + if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) || + symbol_conf.graph_function) + itrace_synth_opts.thread_stack = true; + + session->itrace_synth_opts = &itrace_synth_opts; if (cpu_list) { - if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) - return -1; + err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (err < 0) + goto out_delete; + itrace_synth_opts.cpu_bitmap = cpu_bitmap; } - if (!script_name && !generate_script_lang) - perf_session__fprintf_info(session, stdout, show_full_info); - if (!no_callchain) symbol_conf.use_callchain = true; else symbol_conf.use_callchain = false; +#ifdef HAVE_LIBTRACEEVENT + if (session->tevent.pevent && + tep_set_function_resolver(session->tevent.pevent, + machine__resolve_kernel_addr, + &session->machines.host) < 0) { + pr_err("%s: failed to set libtraceevent function resolver\n", __func__); + err = -1; + goto out_delete; + } +#endif if (generate_script_lang) { struct stat perf_stat; int input; @@ -1490,53 +4488,103 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) if (output_set_by_user()) { fprintf(stderr, "custom fields not supported for generated scripts"); - return -1; + err = -EINVAL; + goto out_delete; } - input = open(session->filename, O_RDONLY); /* input_name */ + input = open(data.path, O_RDONLY); /* input_name */ if (input < 0) { + err = -errno; perror("failed to open file"); - return -1; + goto out_delete; } err = fstat(input, &perf_stat); if (err < 0) { perror("failed to stat file"); - return -1; + goto out_delete; } if (!perf_stat.st_size) { fprintf(stderr, "zero-sized file, nothing to do!\n"); - return 0; + goto out_delete; } scripting_ops = script_spec__lookup(generate_script_lang); if (!scripting_ops) { fprintf(stderr, "invalid language specifier"); - return -1; + err = -ENOENT; + goto out_delete; } - - err = scripting_ops->generate_script(session->pevent, +#ifdef HAVE_LIBTRACEEVENT + err = scripting_ops->generate_script(session->tevent.pevent, "perf-script"); - goto out; +#else + err = scripting_ops->generate_script(NULL, "perf-script"); +#endif + goto out_delete; } + err = dlfilter__start(dlfilter, session); + if (err) + goto out_delete; + if (script_name) { - err = scripting_ops->start_script(script_name, argc, argv); + err = scripting_ops->start_script(script_name, argc, argv, session); if (err) - goto out; + goto out_delete; pr_debug("perf script started with script %s\n\n", script_name); + script_started = true; } err = perf_session__check_output_opt(session); if (err < 0) - goto out; + goto out_delete; + + if (script.time_str) { + err = perf_time__parse_for_ranges_reltime(script.time_str, session, + &script.ptime_range, + &script.range_size, + &script.range_num, + reltime); + if (err < 0) + goto out_delete; + + itrace_synth_opts__set_time_range(&itrace_synth_opts, + script.ptime_range, + script.range_num); + } + + err = evswitch__init(&script.evswitch, session->evlist, stderr); + if (err) + goto out_delete; + + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + + err = __cmd_script(&script); - err = __cmd_script(session); + 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); + zfree(&script.ptime_range); + } + + zstd_fini(&(session->zstd_data)); + evlist__free_stats(session->evlist); perf_session__delete(session); - cleanup_scripting(); + perf_script__exit(&script); + + if (script_started) + cleanup_scripting(); + dlfilter__cleanup(dlfilter); + free_dlarg(); out: return err; } |
