diff options
Diffstat (limited to 'tools/perf/builtin-script.c')
| -rw-r--r-- | tools/perf/builtin-script.c | 2915 |
1 files changed, 1882 insertions, 1033 deletions
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d079f36d342d..62e43d3c5ad7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1,21 +1,25 @@ // 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/dso.h" #include <subcmd/exec-cmd.h> #include "util/header.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" @@ -27,11 +31,21 @@ #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" @@ -39,17 +53,33 @@ #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 "sane_ctype.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; @@ -57,46 +87,85 @@ static bool no_callchain; static bool latency_format; static bool system_wide; static bool print_flags; -static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); -static struct perf_stat_config stat_config; static int max_blocks; - -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; +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_SRCLINE = 1U << 12, - PERF_OUTPUT_PERIOD = 1U << 13, - PERF_OUTPUT_IREGS = 1U << 14, - PERF_OUTPUT_BRSTACK = 1U << 15, - PERF_OUTPUT_BRSTACKSYM = 1U << 16, - PERF_OUTPUT_DATA_SRC = 1U << 17, - PERF_OUTPUT_WEIGHT = 1U << 18, - PERF_OUTPUT_BPF_OUTPUT = 1U << 19, - PERF_OUTPUT_CALLINDENT = 1U << 20, - PERF_OUTPUT_INSN = 1U << 21, - PERF_OUTPUT_INSNLEN = 1U << 22, - PERF_OUTPUT_BRSTACKINSN = 1U << 23, - PERF_OUTPUT_BRSTACKOFF = 1U << 24, - PERF_OUTPUT_SYNTH = 1U << 25, - PERF_OUTPUT_PHYS_ADDR = 1U << 26, - PERF_OUTPUT_UREGS = 1U << 27, - PERF_OUTPUT_METRIC = 1U << 28, - PERF_OUTPUT_MISC = 1U << 29, - PERF_OUTPUT_SRCCODE = 1U << 30, + 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 { @@ -113,6 +182,7 @@ struct output_option { {.str = "ip", .field = PERF_OUTPUT_IP}, {.str = "sym", .field = PERF_OUTPUT_SYM}, {.str = "dso", .field = PERF_OUTPUT_DSO}, + {.str = "dsoff", .field = PERF_OUTPUT_DSOFF}, {.str = "addr", .field = PERF_OUTPUT_ADDR}, {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET}, {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, @@ -126,6 +196,7 @@ struct output_option { {.str = "bpf-output", .field = PERF_OUTPUT_BPF_OUTPUT}, {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT}, {.str = "insn", .field = PERF_OUTPUT_INSN}, + {.str = "disasm", .field = PERF_OUTPUT_DISASM}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF}, @@ -134,13 +205,30 @@ struct output_option { {.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; @@ -148,6 +236,8 @@ static struct { unsigned int print_ip_opts; u64 fields; u64 invalid_fields; + u64 user_set_fields; + u64 user_unset_fields; } output[OUTPUT_TYPE_MAX] = { [PERF_TYPE_HARDWARE] = { @@ -204,7 +294,9 @@ static struct { 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_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, }, @@ -232,29 +324,32 @@ static struct { .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 perf_evsel_script { +struct evsel_script { char *filename; FILE *fp; u64 samples; - /* For metric output */ - u64 val; - int gnum; }; -static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel) -{ - return (struct perf_evsel_script *)evsel->priv; -} - -static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel, - struct perf_data *data) +static struct evsel_script *evsel_script__new(struct evsel *evsel, struct perf_data *data) { - struct perf_evsel_script *es = zalloc(sizeof(*es)); + struct evsel_script *es = zalloc(sizeof(*es)); if (es != NULL) { - if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0) + 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) @@ -269,7 +364,7 @@ out_free: return NULL; } -static void perf_evsel_script__delete(struct perf_evsel_script *es) +static void evsel_script__delete(struct evsel_script *es) { zfree(&es->filename); fclose(es->fp); @@ -277,7 +372,7 @@ static void perf_evsel_script__delete(struct perf_evsel_script *es) free(es); } -static int perf_evsel_script__fprintf(struct perf_evsel_script *es, FILE *fp) +static int evsel_script__fprintf(struct evsel_script *es, FILE *fp) { struct stat st; @@ -292,18 +387,29 @@ static inline int output_type(unsigned int type) case PERF_TYPE_SYNTH: return OUTPUT_TYPE_SYNTH; default: - return type; + if (type < PERF_TYPE_MAX) + return type; } + + return OUTPUT_TYPE_OTHER; } -static inline unsigned int attr_type(unsigned int type) +static inline int evsel__output_type(struct evsel *evsel) { - switch (type) { - case OUTPUT_TYPE_SYNTH: - return PERF_TYPE_SYNTH; - default: - return type; + 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) @@ -330,24 +436,22 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[evsel__output_type(evsel)].fields & PERF_OUTPUT_##x) -static int perf_evsel__do_check_stype(struct perf_evsel *evsel, - u64 sample_type, const char *sample_msg, - enum perf_output_field field, - bool allow_user_set) +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 = output_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) { + if (output[type].user_set_fields & field) { if (allow_user_set) return 0; - evname = perf_evsel__name(evsel); + 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)); @@ -356,7 +460,7 @@ static int perf_evsel__do_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)); @@ -364,20 +468,19 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel, return 0; } -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__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, + enum perf_output_field field) { - return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field, - false); + return evsel__do_check_stype(evsel, sample_type, sample_msg, field, false); } -static int perf_evsel__check_attr(struct perf_evsel *evsel, - struct perf_session *session) +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; @@ -385,32 +488,28 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, 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 (PRINT_FIELD(ADDR) && - perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", - PERF_OUTPUT_ADDR, allow_user_set)) + evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", PERF_OUTPUT_ADDR, allow_user_set)) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", - PERF_OUTPUT_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(WEIGHT) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", - PERF_OUTPUT_WEIGHT)) + evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set)) return -EINVAL; if (PRINT_FIELD(SYM) && - !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of symbols requested but neither sample IP nor " "sample address\navailable. Hence, no addresses to convert " "to symbols.\n"); @@ -422,7 +521,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return -EINVAL; } if (PRINT_FIELD(DSO) && - !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + !(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; } @@ -431,49 +530,71 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if (PRINT_FIELD(BRSTACKINSN) && - !(perf_evlist__combined_branch_type(session->evlist) & - PERF_SAMPLE_BRANCH_ANY)) { + 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__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU", - PERF_OUTPUT_CPU, allow_user_set)) + evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU", PERF_OUTPUT_CPU, allow_user_set)) return -EINVAL; if (PRINT_FIELD(IREGS) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", - PERF_OUTPUT_IREGS)) + evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set)) return -EINVAL; if (PRINT_FIELD(UREGS) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS", - PERF_OUTPUT_UREGS)) + evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS", PERF_OUTPUT_UREGS)) return -EINVAL; if (PRINT_FIELD(PHYS_ADDR) && - perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", - PERF_OUTPUT_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 set_print_ip_opts(struct perf_event_attr *attr) +static void evsel__set_print_ip_opts(struct evsel *evsel) { - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -485,6 +606,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr) if (PRINT_FIELD(DSO)) output[type].print_ip_opts |= EVSEL__PRINT_DSO; + if (PRINT_FIELD(DSOFF)) + output[type].print_ip_opts |= EVSEL__PRINT_DSOFF; + if (PRINT_FIELD(SYMOFFSET)) output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; @@ -492,17 +616,32 @@ static void set_print_ip_opts(struct perf_event_attr *attr) 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) { + bool tod = false; unsigned int j; - struct perf_evsel *evsel; + struct evsel *evsel; for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, attr_type(j)); + evsel = find_first_output_type(session->evlist, j); /* * even if fields is set to 0 (ie., show nothing) event must @@ -517,13 +656,18 @@ static int perf_session__check_output_opt(struct perf_session *session) } if (evsel && output[j].fields && - perf_evsel__check_attr(evsel, session)) + evsel__check_attr(evsel, session)) return -1; if (evsel == NULL) continue; - set_print_ip_opts(&evsel->attr); + /* 'dsoff' implys 'dso' field */ + if (output[j].fields & PERF_OUTPUT_DSOFF) + output[j].fields |= PERF_OUTPUT_DSO; + + evsel__set_print_ip_opts(evsel); + tod |= output[j].fields & PERF_OUTPUT_TOD; } if (!no_callchain) { @@ -532,7 +676,7 @@ static int perf_session__check_output_opt(struct perf_session *session) evlist__for_each_entry(session->evlist, evsel) { not_pipe = true; - if (evsel__has_callchain(evsel)) { + if (evsel__has_callchain(evsel) || evsel__is_offcpu_event(evsel)) { use_callchain = true; break; } @@ -550,7 +694,7 @@ static int perf_session__check_output_opt(struct perf_session *session) j = PERF_TYPE_TRACEPOINT; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.type != j) + if (evsel->core.attr.type != j) continue; if (evsel__has_callchain(evsel)) { @@ -558,19 +702,23 @@ static int perf_session__check_output_opt(struct perf_session *session) output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->attr); + 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 int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, - FILE *fp -) +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; @@ -582,53 +730,130 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, 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), val); + printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val); } - fprintf(fp, "\n"); - 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, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->intr_regs, - attr->sample_regs_intr, 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, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->user_regs, - attr->sample_regs_user, 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_sample *sample, +static int perf_sample__fprintf_start(struct perf_script *script, + struct perf_sample *sample, struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; unsigned long secs; unsigned long long nsecs; int printed = 0; + char tstr[128]; + + /* + * Print the branch counter's abbreviation list, + * if the branch counter is available. + */ + if (PRINT_FIELD(BRCNTR) && !verbose) { + char *buf; + + if (!annotation_br_cntr_abbr_list(&buf, evsel, true)) { + printed += fprintf(stdout, "%s", buf); + free(buf); + } + } + + if (PRINT_FIELD(MACHINE_PID) && sample->machine_pid) + printed += fprintf(fp, "VM:%5d ", sample->machine_pid); + + /* 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) - printed += fprintf(fp, "%8.8s ", thread__comm_str(thread)); + printed += fprintf(fp, "%8.8s ", comm); else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) - printed += fprintf(fp, "%s ", thread__comm_str(thread)); + printed += fprintf(fp, "%s ", comm); else - printed += fprintf(fp, "%16s ", thread__comm_str(thread)); + printed += fprintf(fp, "%16s ", comm); } if (PRINT_FIELD(PID) && PRINT_FIELD(TID)) - printed += fprintf(fp, "%5d/%-5d ", sample->pid, sample->tid); + printed += fprintf(fp, "%7d/%-7d ", sample->pid, sample->tid); else if (PRINT_FIELD(PID)) - printed += fprintf(fp, "%5d ", sample->pid); + printed += fprintf(fp, "%7d ", sample->pid); else if (PRINT_FIELD(TID)) - printed += fprintf(fp, "%5d ", sample->tid); + printed += fprintf(fp, "%7d ", sample->tid); if (PRINT_FIELD(CPU)) { if (latency_format) @@ -681,16 +906,34 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, 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; + 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 (nanosecs) + if (symbol_conf.nanosecs) printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs); else { char sample_time[32]; - timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time)); + timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time)); printed += fprintf(fp, "%12s: ", sample_time); } } @@ -698,21 +941,38 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, return printed; } -static inline char -mispred_str(struct branch_entry *br) +static inline size_t +bstack_event_str(struct branch_entry *br, char *buf, size_t sz) { - if (!(br->flags.mispred || br->flags.predicted)) - return '-'; + if (!(br->flags.mispred || br->flags.predicted || br->flags.not_taken)) + return snprintf(buf, sz, "-"); + + return snprintf(buf, sz, "%s%s", + br->flags.predicted ? "P" : "M", + br->flags.not_taken ? "N" : ""); +} - return br->flags.predicted ? 'P' : 'M'; +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 perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; - struct addr_location alf, alt; + struct branch_entry *entries = perf_sample__branch_entries(sample); u64 i, from, to; int printed = 0; @@ -720,35 +980,27 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { - from = br->entries[i].from; - to = br->entries[i].to; + from = entries[i].from; + to = entries[i].to; + printed += fprintf(fp, " 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); + struct addr_location alf, alt; + + addr_location__init(&alf); + addr_location__init(&alt); thread__find_map_fb(thread, sample->cpumode, from, &alf); thread__find_map_fb(thread, sample->cpumode, to, &alt); - } - printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } - - printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); + printed += fprintf(fp, "/0x%"PRIx64, to); + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); + addr_location__exit(&alt); + addr_location__exit(&alf); + } else + printed += fprintf(fp, "/0x%"PRIx64, to); - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str( br->entries + i), - br->entries[i].flags.in_tx? 'X' : '-', - br->entries[i].flags.abort? 'A' : '-', - br->entries[i].flags.cycles); + printed += print_bstack_flags(fp, entries + i); } return printed; @@ -756,10 +1008,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; - struct addr_location alf, alt; + struct branch_entry *entries = perf_sample__branch_entries(sample); u64 i, from, to; int printed = 0; @@ -767,33 +1019,26 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); - from = br->entries[i].from; - to = br->entries[i].to; + 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 += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "%c", '/'); printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str( br->entries + i), - br->entries[i].flags.in_tx? 'X' : '-', - br->entries[i].flags.abort? 'A' : '-', - br->entries[i].flags.cycles); + 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; @@ -801,10 +1046,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; - struct addr_location alf, alt; + struct branch_entry *entries = perf_sample__branch_entries(sample); u64 i, from, to; int printed = 0; @@ -812,37 +1057,30 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, return 0; for (i = 0; i < br->nr; i++) { + struct addr_location alf, alt; - memset(&alf, 0, sizeof(alf)); - memset(&alt, 0, sizeof(alt)); - from = br->entries[i].from; - to = br->entries[i].to; + addr_location__init(&alf); + addr_location__init(&alt); + from = entries[i].from; + to = entries[i].to; if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && - !alf.map->dso->adjust_symbols) - from = map__map_ip(alf.map, from); + !dso__adjust_symbols(map__dso(alf.map))) + from = map__dso_map_ip(alf.map, from); if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && - !alt.map->dso->adjust_symbols) - to = map__map_ip(alt.map, to); + !dso__adjust_symbols(map__dso(alt.map))) + to = map__dso_map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str(br->entries + i), - br->entries[i].flags.in_tx ? 'X' : '-', - br->entries[i].flags.abort ? 'A' : '-', - br->entries[i].flags.cycles); + 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; @@ -856,6 +1094,8 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, long offset, len; struct addr_location al; bool kernel; + struct dso *dso; + int ret = 0; if (!start || !end) return 0; @@ -877,7 +1117,6 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return -ENXIO; } - memset(&al, 0, sizeof(al)); if (end - start > MAXBB - MAXINSN) { if (last) pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); @@ -886,27 +1125,74 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { + addr_location__init(&al); + if (!thread__find_map(thread, *cpumode, start, &al) || (dso = map__dso(al.map)) == NULL) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } - if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) { + if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); - return 0; + goto out; } /* Load maps to ensure dso->is_64_bit has been updated */ map__load(al.map); - offset = al.map->map_ip(al.map, start); - len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer, + offset = map__map_ip(al.map, start); + len = dso__data_read_offset(dso, machine, offset, (u8 *)buffer, end - start + MAXINSN); - *is64bit = al.map->dso->is_64_bit; + *is64bit = dso__is_64_bit(dso); if (len <= 0) pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", start, end); - return len; + ret = len; +out: + addr_location__exit(&al); + return ret; +} + +static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srccode_state *state) +{ + 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) @@ -914,23 +1200,92 @@ static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) struct addr_location al; int ret = 0; - memset(&al, 0, sizeof(al)); + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if (!al.map) - return 0; + goto out; ret = map__fprintf_srccode(al.map, al.addr, stdout, - &thread->srccode_state); + thread__srccode_state(thread)); if (ret) ret += printf("\n"); +out: + addr_location__exit(&al); return ret; } +static int any_dump_insn(struct evsel *evsel __maybe_unused, + struct perf_insn *x, uint64_t ip, + u8 *inbuf, int inlen, int *lenp, + FILE *fp) +{ + if (PRINT_FIELD(BRSTACKDISASM)) { + int printed = fprintf_insn_asm(x->machine, x->thread, x->cpumode, x->is64bit, + (uint8_t *)inbuf, inlen, ip, lenp, + PRINT_INSN_IMM_HEX, fp); + + if (printed > 0) + return printed; + } + return fprintf(fp, "%s", dump_insn(x, ip, inbuf, inlen, lenp)); +} + +static int add_padding(FILE *fp, int printed, int padding) +{ + if (printed >= 0 && printed < padding) + printed += fprintf(fp, "%*s", padding - printed, ""); + return printed; +} + static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, - int insn, FILE *fp, int *total_cycles) + int insn, FILE *fp, int *total_cycles, + struct evsel *evsel, + struct thread *thread, + u64 br_cntr) { - int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip, - dump_insn(x, ip, inbuf, len, NULL), + 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" : "", @@ -941,22 +1296,22 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, if (insn) printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles); } + return printed + fprintf(fp, "\n"); } static int ip__fprintf_sym(uint64_t addr, struct thread *thread, u8 cpumode, int cpu, struct symbol **lastsym, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; - int off, printed = 0; - - memset(&al, 0, sizeof(al)); + int off, printed = 0, ret = 0; + addr_location__init(&al); thread__find_map(thread, cpumode, addr, &al); if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) - return 0; + goto out; al.cpu = cpu; al.sym = NULL; @@ -964,12 +1319,12 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, al.sym = map__find_symbol(al.map, al.addr); if (!al.sym) - return 0; + goto out; if (al.addr < al.sym->end) off = al.addr - al.sym->start; else - off = al.addr - al.map->start - al.sym->start; + off = al.addr - map__start(al.map) - al.sym->start; printed += fprintf(fp, "\t%s", al.sym->name); if (off) printed += fprintf(fp, "%+d", off); @@ -979,15 +1334,20 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, printed += fprintf(fp, "\n"); *lastsym = al.sym; - return printed; + ret = printed; +out: + addr_location__exit(&al); + return ret; } static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, + struct evsel *evsel, struct thread *thread, struct perf_event_attr *attr, struct machine *machine, FILE *fp) { 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; @@ -995,6 +1355,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, unsigned off; struct symbol *lastsym = NULL; int total_cycles = 0; + u64 br_cntr = 0; if (!(br && br->nr)) return 0; @@ -1003,36 +1364,41 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, nr = max_blocks + 1; x.thread = thread; + x.machine = machine; x.cpu = sample->cpu; + if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr) + br_cntr = sample->branch_stack_cntr[nr - 1]; + printed += fprintf(fp, "%c", '\n'); /* Handle first from jump, of which we don't know the entry. */ - len = grab_bb(buffer, br->entries[nr-1].from, - br->entries[nr-1].from, + 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(br->entries[nr - 1].from, thread, - x.cpumode, x.cpu, &lastsym, attr, fp); - printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1], - &x, buffer, len, 0, fp, &total_cycles); + 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, br->entries[nr - 1].from); + printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); } /* Print all blocks */ for (i = nr - 2; i >= 0; i--) { - if (br->entries[i].from || br->entries[i].to) + if (entries[i].from || entries[i].to) pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i, - br->entries[i].from, - br->entries[i].to); - start = br->entries[i + 1].to; - end = br->entries[i].from; + 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 = br->entries[--i].from; + 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); } @@ -1040,19 +1406,25 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, continue; insn = 0; - for (off = 0;; off += ilen) { + for (off = 0; off < (unsigned)len; off += ilen) { uint64_t ip = start + off; - printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (ip == end) { - printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp, - &total_cycles); + 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 { - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip, - dump_insn(&x, ip, buffer + off, len - off, &ilen)); + 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)) @@ -1060,51 +1432,63 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 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 (br->entries[0].from == sample->ip) + if (entries[0].from == sample->ip) goto out; - if (br->entries[0].flags.abort) + if (entries[0].flags.abort) goto out; /* - * Print final block upto sample + * Print final block up to sample * * Due to pipeline delays the LBRs might be missing a branch * or two, which can result in very large or negative blocks * between final branch and sample. When this happens just - * continue walking after the last TO until we hit a branch. + * continue walking after the last TO. */ - start = br->entries[0].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, attr, fp); + printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (len <= 0) { /* Print at least last IP if basic block did not work */ len = grab_bb(buffer, sample->ip, sample->ip, machine, thread, &x.is64bit, &x.cpumode, false); if (len <= 0) goto out; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip, - dump_insn(&x, sample->ip, buffer, len, NULL)); + 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) { - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off, - dump_insn(&x, start + off, buffer + off, len - 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 (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { + if ((attr->branch_sample_type == 0 || attr->branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + && arch_is_uncond_branch(buffer + off, len - off, x.is64bit) + && start + off != sample->ip) { /* * Hit a missing branch. Just stop. */ @@ -1120,12 +1504,13 @@ out: static int perf_sample__fprintf_addr(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int printed = fprintf(fp, "%16" PRIx64, sample->addr); - if (!sample_addr_correlates_sym(attr)) + addr_location__init(&al); + if (!sample_addr_correlates_sym(&evsel->core.attr)) goto out; thread__resolve(thread, &al, sample); @@ -1138,30 +1523,28 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample, printed += symbol__fprintf_symname(al.sym, fp); } - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(al.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(al.map, PRINT_FIELD(DSOFF), al.addr, fp); out: + addr_location__exit(&al); return printed; } static const char *resolve_branch_sym(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct addr_location *al, + struct addr_location *addr_al, u64 *ip) { - struct addr_location addr_al; - struct perf_event_attr *attr = &evsel->attr; const char *name = NULL; if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { - if (sample_addr_correlates_sym(attr)) { - thread__resolve(thread, &addr_al, sample); - if (addr_al.sym) - name = addr_al.sym->name; + 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 { @@ -1177,11 +1560,12 @@ static const char *resolve_branch_sym(struct perf_sample *sample, } static int perf_sample__fprintf_callindent(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, - struct addr_location *al, FILE *fp) + struct addr_location *al, + struct addr_location *addr_al, + FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; @@ -1193,10 +1577,10 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, * The 'return' has already been popped off the stack so the depth has * to be adjusted to match the 'call'. */ - if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN) + if (thread__ts(thread) && sample->flags & PERF_IP_FLAG_RETURN) depth += 1; - name = resolve_branch_sym(sample, evsel, thread, al, &ip); + name = resolve_branch_sym(sample, evsel, thread, al, addr_al, &ip); if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) { dlen += fprintf(fp, "("); @@ -1226,51 +1610,73 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, } static int perf_sample__fprintf_insn(struct perf_sample *sample, + struct evsel *evsel, struct perf_event_attr *attr, struct thread *thread, - struct machine *machine, FILE *fp) + struct machine *machine, FILE *fp, + struct addr_location *al) { int printed = 0; + script_fetch_insn(sample, thread, machine, native_arch); + if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); - if (PRINT_FIELD(INSN)) { - int i; - - printed += fprintf(fp, " insn:"); - for (i = 0; i < sample->insn_len; i++) - printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]); + if (PRINT_FIELD(INSN) && sample->insn_len) { + printed += fprintf(fp, " insn: "); + printed += sample__fprintf_insn_raw(sample, fp); } - if (PRINT_FIELD(BRSTACKINSN)) - printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, 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 int perf_sample__fprintf_bts(struct perf_sample *sample, - struct perf_evsel *evsel, + 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; - unsigned int type = output_type(attr->type); + 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, fp); + printed += perf_sample__fprintf_callindent(sample, evsel, thread, al, addr_al, fp); /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; - if (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; - + if (symbol_conf.use_callchain && sample->callchain) { + cursor = get_tls_callchain_cursor(); + if (thread__resolve_callchain(al->thread, cursor, evsel, + sample, NULL, NULL, + scripting_max_stack)) + cursor = NULL; + } if (cursor == NULL) { printed += fprintf(fp, " "); if (print_opts & EVSEL__PRINT_SRCLINE) { @@ -1280,25 +1686,28 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, } else printed += fprintf(fp, "\n"); - printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp); + printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, + symbol_conf.bt_stop_list, fp); } /* print branch_to information */ if (PRINT_FIELD(ADDR) || - ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && + ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && !output[type].user_set)) { printed += fprintf(fp, " => "); - printed += perf_sample__fprintf_addr(sample, thread, attr, fp); + printed += perf_sample__fprintf_addr(sample, thread, evsel, fp); } + printed += perf_sample__fprintf_ipc(sample, evsel, fp); + if (print_srcline_last) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); - printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp); + printed += perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al); printed += fprintf(fp, "\n"); if (PRINT_FIELD(SRCCODE)) { int ret = map__fprintf_srccode(al->map, al->addr, stdout, - &thread->srccode_state); + thread__srccode_state(thread)); if (ret) { printed += ret; printed += printf("\n"); @@ -1307,74 +1716,17 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, return printed; } -static struct { - u32 flags; - const char *name; -} sample_flags[] = { - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, - {PERF_IP_FLAG_BRANCH, "jmp"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, "hw int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, - {0, NULL} -}; - -static const char *sample_flags_to_name(u32 flags) -{ - int i; - - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; - } - - return NULL; -} - static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { - const char *chars = PERF_IP_FLAG_CHARS; - const int n = strlen(PERF_IP_FLAG_CHARS); - bool in_tx = flags & PERF_IP_FLAG_IN_TX; - const char *name = NULL; - char str[33]; - int i, pos = 0; - - name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX); - if (name) - return fprintf(fp, " %-15s%4s ", name, in_tx ? "(x)" : ""); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return fprintf(fp, " tr strt %-7s%4s ", name, in_tx ? "(x)" : ""); - } - - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END)); - if (name) - return fprintf(fp, " tr end %-7s%4s ", name, in_tx ? "(x)" : ""); - } + char str[SAMPLE_FLAGS_BUF_SIZE]; + int ret; - for (i = 0; i < n; i++, flags >>= 1) { - if (flags & 1) - str[pos++] = chars[i]; - } - for (; i < 32; i++, flags >>= 1) { - if (flags & 1) - str[pos++] = '?'; - } - str[pos] = 0; + 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, " %-19s ", str); + return fprintf(fp, " %-*s ", SAMPLE_FLAGS_STR_ALIGNED_SIZE, str); } struct printer_data { @@ -1470,16 +1822,44 @@ 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; - len = fprintf(fp, " IP: %u payload: %#" PRIx64 " ", - data->ip, le64_to_cpu(data->payload)); + 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); } @@ -1553,10 +1933,91 @@ static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp) 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 perf_evsel *evsel, FILE *fp) + struct evsel *evsel, FILE *fp) { - switch (evsel->attr.config) { + switch (evsel->core.attr.config) { case PERF_SYNTH_INTEL_PTWRITE: return perf_sample__fprintf_synth_ptwrite(sample, fp); case PERF_SYNTH_INTEL_MWAIT: @@ -1569,6 +2030,14 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, 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; } @@ -1576,33 +2045,13 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, return 0; } -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 allocated; - bool per_event_dump; - struct cpu_map *cpus; - struct thread_map *threads; - int name_width; - const char *time_str; - struct perf_time_interval *ptime_range; - int range_size; - int range_num; -}; - -static int perf_evlist__max_name_len(struct perf_evlist *evlist) +static int evlist__max_name_len(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; int max = 0; evlist__for_each_entry(evlist, evsel) { - int len = strlen(perf_evsel__name(evsel)); + int len = strlen(evsel__name(evsel)); max = MAX(len, max); } @@ -1612,13 +2061,18 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist) static int data_src__fprintf(u64 data_src, FILE *fp) { - struct mem_info mi = { .data_src.val = data_src }; + struct mem_info *mi = mem_info__new(); char decode[100]; char out[100]; static int maxlen; int len; - perf_script__meminfo_scnprintf(decode, 100, &mi); + if (!mi) + return -ENOMEM; + + mem_info__data_src(mi)->val = data_src; + perf_script__meminfo_scnprintf(decode, 100, mi); + mem_info__put(mi); len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode); if (maxlen < len) @@ -1630,20 +2084,20 @@ static int data_src__fprintf(u64 data_src, FILE *fp) struct metric_ctx { struct perf_sample *sample; struct thread *thread; - struct perf_evsel *evsel; + struct evsel *evsel; FILE *fp; }; static void script_print_metric(struct perf_stat_config *config __maybe_unused, - void *ctx, const char *color, - const char *fmt, - const char *unit, double val) + void *ctx, enum metric_threshold_classify thresh, + const char *fmt, const char *unit, double val) { struct metric_ctx *mctx = ctx; + const char *color = metric_threshold_classify__color(thresh); if (!fmt) return; - perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel, + perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel, PERF_RECORD_SAMPLE, mctx->fp); fputs("\tmetric: ", mctx->fp); if (color) @@ -1658,17 +2112,166 @@ static void script_new_line(struct perf_stat_config *config __maybe_unused, { struct metric_ctx *mctx = ctx; - perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel, + perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel, PERF_RECORD_SAMPLE, mctx->fp); fputs("\tmetric: ", mctx->fp); } -static void perf_sample__fprint_metric(struct perf_script *script, - struct thread *thread, - struct perf_evsel *evsel, +struct script_find_metrics_args { + struct evlist *evlist; + bool system_wide; +}; + +static struct evsel *map_metric_evsel_to_script_evsel(struct evlist *script_evlist, + struct evsel *metric_evsel) +{ + struct evsel *script_evsel; + + evlist__for_each_entry(script_evlist, script_evsel) { + /* Skip if perf_event_attr differ. */ + if (metric_evsel->core.attr.type != script_evsel->core.attr.type) + continue; + if (metric_evsel->core.attr.config != script_evsel->core.attr.config) + continue; + /* Skip if the script event has a metric_id that doesn't match. */ + if (script_evsel->metric_id && + strcmp(evsel__metric_id(metric_evsel), evsel__metric_id(script_evsel))) { + pr_debug("Skipping matching evsel due to differing metric ids '%s' vs '%s'\n", + evsel__metric_id(metric_evsel), evsel__metric_id(script_evsel)); + continue; + } + return script_evsel; + } + return NULL; +} + +static int script_find_metrics(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *data) +{ + struct script_find_metrics_args *args = data; + struct evlist *script_evlist = args->evlist; + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + int ret = metricgroup__parse_groups(metric_evlist, + /*pmu=*/"all", + pm->metric_name, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + /*user_requested_cpu_list=*/NULL, + args->system_wide, + /*hardware_aware_grouping=*/false); + + if (ret) { + /* Metric parsing failed but continue the search. */ + goto out; + } + + /* + * Check the script_evlist has an entry for each metric_evlist entry. If + * the script evsel was already set up avoid changing data that may + * break it. + */ + evlist__for_each_entry(metric_evlist, metric_evsel) { + struct evsel *script_evsel = + map_metric_evsel_to_script_evsel(script_evlist, metric_evsel); + struct evsel *new_metric_leader; + + if (!script_evsel) { + pr_debug("Skipping metric '%s' as evsel '%s' / '%s' is missing\n", + pm->metric_name, evsel__name(metric_evsel), + evsel__metric_id(metric_evsel)); + goto out; + } + + if (script_evsel->metric_leader == NULL) + continue; + + if (metric_evsel->metric_leader == metric_evsel) { + new_metric_leader = script_evsel; + } else { + new_metric_leader = + map_metric_evsel_to_script_evsel(script_evlist, + metric_evsel->metric_leader); + } + /* Mismatching evsel leaders. */ + if (script_evsel->metric_leader != new_metric_leader) { + pr_debug("Skipping metric '%s' due to mismatching evsel metric leaders '%s' vs '%s'\n", + pm->metric_name, evsel__metric_id(metric_evsel), + evsel__metric_id(script_evsel)); + goto out; + } + } + /* + * Metric events match those in the script evlist, copy metric evsel + * data into the script evlist. + */ + evlist__for_each_entry(metric_evlist, metric_evsel) { + struct evsel *script_evsel = + map_metric_evsel_to_script_evsel(script_evlist, metric_evsel); + struct metric_event *metric_me = metricgroup__lookup(&metric_evlist->metric_events, + metric_evsel, + /*create=*/false); + + if (script_evsel->metric_id == NULL) { + script_evsel->metric_id = metric_evsel->metric_id; + metric_evsel->metric_id = NULL; + } + + if (script_evsel->metric_leader == NULL) { + if (metric_evsel->metric_leader == metric_evsel) { + script_evsel->metric_leader = script_evsel; + } else { + script_evsel->metric_leader = + map_metric_evsel_to_script_evsel(script_evlist, + metric_evsel->metric_leader); + } + } + + if (metric_me) { + struct metric_expr *expr; + struct metric_event *script_me = + metricgroup__lookup(&script_evlist->metric_events, + script_evsel, + /*create=*/true); + + if (!script_me) { + /* + * As the metric_expr is created, the only + * failure is a lack of memory. + */ + goto out; + } + list_splice_init(&metric_me->head, &script_me->head); + list_for_each_entry(expr, &script_me->head, nd) { + for (int i = 0; expr->metric_events[i]; i++) { + expr->metric_events[i] = + map_metric_evsel_to_script_evsel(script_evlist, + expr->metric_events[i]); + } + } + } + } + pr_debug("Found metric '%s' whose evsels match those of in the perf data\n", + pm->metric_name); + evlist__delete(metric_evlist); +out: + return 0; +} + +static struct aggr_cpu_id script_aggr_cpu_id_get(struct perf_stat_config *config __maybe_unused, + struct perf_cpu cpu) +{ + return aggr_cpu_id__global(cpu, /*data=*/NULL); +} + +static void perf_sample__fprint_metric(struct thread *thread, + struct evsel *evsel, struct perf_sample *sample, FILE *fp) { + static bool init_metrics; struct perf_stat_output_ctx ctx = { .print_metric = script_print_metric, .new_line = script_new_line, @@ -1680,57 +2283,108 @@ static void perf_sample__fprint_metric(struct perf_script *script, }, .force_header = false, }; - struct perf_evsel *ev2; - static bool init; - u64 val; + struct perf_counts_values *count, *old_count; + int cpu_map_idx, thread_map_idx, aggr_idx; + struct evsel *pos; + + if (!init_metrics) { + /* One time initialization of stat_config and metric data. */ + struct script_find_metrics_args args = { + .evlist = evsel->evlist, + .system_wide = perf_thread_map__pid(evsel->core.threads, /*idx=*/0) == -1, + + }; + if (!stat_config.output) + stat_config.output = stdout; + + if (!stat_config.aggr_map) { + /* TODO: currently only global aggregation is supported. */ + assert(stat_config.aggr_mode == AGGR_GLOBAL); + stat_config.aggr_get_id = script_aggr_cpu_id_get; + stat_config.aggr_map = + cpu_aggr_map__new(evsel->evlist->core.user_requested_cpus, + aggr_cpu_id__global, /*data=*/NULL, + /*needs_sort=*/false); + } + + metricgroup__for_each_metric(pmu_metrics_table__find(), script_find_metrics, &args); + init_metrics = true; + } - if (!init) { - perf_stat__init_shadow_stats(); - init = true; - } - if (!evsel->stats) - perf_evlist__alloc_stats(script->session->evlist, false); - if (evsel_script(evsel->leader)->gnum++ == 0) - perf_stat__reset_shadow_stats(); - val = sample->period * evsel->scale; - perf_stat__update_shadow_stats(evsel, - val, - sample->cpu, - &rt_stat); - evsel_script(evsel)->val = val; - if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) { - for_each_group_member (ev2, evsel->leader) { - perf_stat__print_shadow_stats(&stat_config, ev2, - evsel_script(ev2)->val, - sample->cpu, - &ctx, - NULL, - &rt_stat); - } - evsel_script(evsel->leader)->gnum = 0; + 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 perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, - struct addr_location *al) + 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) { - if (depth <= thread->filter_entry_depth) { - thread->filter = false; + if (thread__filter(thread)) { + if (depth <= thread__filter_entry_depth(thread)) { + thread__set_filter(thread, false); return false; } return true; } else { const char *s = symbol_conf.graph_function; u64 ip; - const char *name = resolve_branch_sym(sample, evsel, thread, al, + const char *name = resolve_branch_sym(sample, evsel, thread, al, addr_al, &ip); unsigned nlen; @@ -1740,8 +2394,8 @@ static bool show_event(struct perf_sample *sample, while (*s) { unsigned len = strcspn(s, ","); if (nlen == len && !strncmp(name, s, len)) { - thread->filter = true; - thread->filter_entry_depth = depth; + thread__set_filter(thread, true); + thread__set_filter_entry_depth(thread, depth); return true; } s += len; @@ -1753,35 +2407,35 @@ static bool show_event(struct perf_sample *sample, } static void process_event(struct perf_script *script, - struct perf_sample *sample, struct perf_evsel *evsel, + 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->attr; - unsigned int type = output_type(attr->type); - struct perf_evsel_script *es = evsel->priv; + 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; - if (!show_event(sample, evsel, thread, al)) - return; - ++es->samples; - perf_sample__fprintf_start(sample, thread, evsel, + 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 = perf_evsel__name(evsel); + const char *evname = evsel__name(evsel); if (!script->name_width) - script->name_width = perf_evlist__max_name_len(script->session->evlist); + script->name_width = evlist__max_name_len(script->session->evlist); fprintf(fp, "%*s: ", script->name_width, evname ?: "[unknown]"); } @@ -1790,20 +2444,25 @@ static void process_event(struct perf_script *script, perf_sample__fprintf_flags(sample->flags, fp); if (is_bts_event(attr)) { - perf_sample__fprintf_bts(sample, evsel, thread, al, machine, fp); + perf_sample__fprintf_bts(sample, evsel, thread, al, addr_al, machine, fp); return; } - - if (PRINT_FIELD(TRACE)) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, fp); +#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(ADDR)) - perf_sample__fprintf_addr(sample, thread, attr, fp); + perf_sample__fprintf_addr(sample, thread, evsel, fp); if (PRINT_FIELD(DATA_SRC)) data_src__fprintf(sample->data_src, fp); @@ -1811,64 +2470,93 @@ static void process_event(struct perf_script *script, 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 (symbol_conf.use_callchain && sample->callchain && - thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, scripting_max_stack) == 0) - cursor = &callchain_cursor; + if (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, 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, fp); + perf_sample__fprintf_iregs(sample, attr, arch, fp); if (PRINT_FIELD(UREGS)) - perf_sample__fprintf_uregs(sample, attr, fp); + perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) - perf_sample__fprintf_brstack(sample, thread, attr, fp); + perf_sample__fprintf_brstack(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKSYM)) - perf_sample__fprintf_brstacksym(sample, thread, attr, fp); + perf_sample__fprintf_brstacksym(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKOFF)) - perf_sample__fprintf_brstackoff(sample, thread, attr, fp); + perf_sample__fprintf_brstackoff(sample, thread, evsel, fp); - if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) + if (evsel__is_bpf_output(evsel) && !evsel__is_offcpu_event(evsel) && PRINT_FIELD(BPF_OUTPUT)) perf_sample__fprintf_bpf_output(sample, fp); - perf_sample__fprintf_insn(sample, attr, thread, machine, fp); + perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al); if (PRINT_FIELD(PHYS_ADDR)) fprintf(fp, "%16" PRIx64, sample->phys_addr); + + 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__srccode_state(thread))) printf("\n"); } if (PRINT_FIELD(METRIC)) - perf_sample__fprint_metric(script, thread, evsel, sample, fp); + perf_sample__fprint_metric(thread, evsel, sample, fp); - if (verbose) + if (verbose > 0) fflush(fp); } static struct scripting_ops *scripting_ops; -static void __process_stat(struct perf_evsel *counter, u64 tstamp) +static void __process_stat(struct evsel *counter, u64 tstamp) { - int nthreads = thread_map__nr(counter->threads); - int ncpus = perf_evsel__nr_cpus(counter); - int cpu, thread; + int nthreads = perf_thread_map__nr(counter->core.threads); + int idx, thread; + struct perf_cpu cpu; static int header_printed; - if (counter->system_wide) - nthreads = 1; - if (!header_printed) { printf("%3s %8s %15s %15s %15s %15s %s\n", "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT"); @@ -1876,24 +2564,24 @@ static void __process_stat(struct perf_evsel *counter, u64 tstamp) } for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { struct perf_counts_values *counts; - counts = perf_counts(counter->counts, cpu, thread); + counts = perf_counts(counter->counts, idx, thread); printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", - counter->cpus->map[cpu], - thread_map__pid(counter->threads, thread), + cpu.cpu, + perf_thread_map__pid(counter->core.threads, thread), counts->val, counts->ena, counts->run, tstamp, - perf_evsel__name(counter)); + evsel__name(counter)); } } } -static void process_stat(struct perf_evsel *counter, u64 tstamp) +static void process_stat(struct evsel *counter, u64 tstamp) { if (scripting_ops && scripting_ops->process_stat) scripting_ops->process_stat(&stat_config, counter, tstamp); @@ -1909,7 +2597,9 @@ static void process_stat_interval(u64 tstamp) static void setup_scripting(void) { +#ifdef HAVE_LIBTRACEEVENT setup_perl_scripting(); +#endif setup_python_scripting(); } @@ -1925,18 +2615,38 @@ static int cleanup_scripting(void) return scripting_ops ? scripting_ops->stop_script() : 0; } -static int process_sample_event(struct perf_tool *tool, +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 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 (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num, sample->time)) { - return 0; + goto out_put; } if (debug_mode) { @@ -1947,338 +2657,437 @@ static int process_sample_event(struct perf_tool *tool, 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 (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 (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + if (!show_event(sample, evsel, al.thread, &al, NULL)) goto out_put; - if (scripting_ops) - scripting_ops->process_event(event, sample, evsel, &al); - else - process_event(scr, sample, evsel, &al, machine); + 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__put(&al); - return 0; + addr_location__exit(&al); + return ret; } -static int process_attr(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist) +// 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 perf_evlist *evlist; - struct perf_evsel *evsel, *pos; + struct evlist *evlist; + struct evsel *evsel, *pos; + u64 sample_type; int err; - static struct perf_evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) return err; evlist = *pevlist; - evsel = perf_evlist__last(*pevlist); + evsel = evlist__last(*pevlist); if (!evsel->priv) { if (scr->per_event_dump) { - evsel->priv = perf_evsel_script__new(evsel, - scr->session->data); - } else { - es = zalloc(sizeof(*es)); - if (!es) + evsel->priv = evsel_script__new(evsel, scr->session->data); + if (!evsel->priv) return -ENOMEM; - es->fp = stdout; - evsel->priv = es; + } else { // Replicate what is done in perf_script__setup_per_event_dump() + es_stdout.fp = stdout; + evsel->priv = &es_stdout; } } - if (evsel->attr.type >= PERF_TYPE_MAX && - evsel->attr.type != PERF_TYPE_SYNTH) + if (evsel->core.attr.type >= PERF_TYPE_MAX && + evsel->core.attr.type != PERF_TYPE_SYNTH) return 0; evlist__for_each_entry(evlist, pos) { - if (pos->attr.type == evsel->attr.type && pos != evsel) + if (pos->core.attr.type == evsel->core.attr.type && pos != evsel) return 0; } - set_print_ip_opts(&evsel->attr); + if (evsel->core.attr.sample_type) { + err = evsel__check_attr(evsel, scr->session); + if (err) + return err; + } - if (evsel->attr.sample_type) - err = perf_evsel__check_attr(evsel, scr->session); + /* + * 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))); - return err; + /* 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 process_comm_event(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine) +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 thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - int ret = -1; + struct evsel *evsel = evlist__id2evsel(session->evlist, sample->id); + struct thread *thread = NULL; - thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid); - if (thread == NULL) { - pr_debug("problem processing COMM event, skipping it.\n"); - return -1; + if (evsel && !evsel->core.attr.sample_id_all) { + sample->cpu = 0; + sample->time = timestamp; + sample->pid = pid; + sample->tid = tid; } - if (perf_event__process_comm(tool, event, sample, machine) < 0) - goto out; + if (filter_cpu(sample)) + return 0; + + 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); - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->comm.tid; - sample->pid = event->comm.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_COMM, stdout); - perf_event__fprintf(event, stdout); - ret = 0; -out: thread__put(thread); - return ret; + + return 0; +} + +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; + + return print_event(tool, event, sample, machine, event->comm.pid, + event->comm.tid); } -static int process_namespaces_event(struct perf_tool *tool, +static int process_namespaces_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - int ret = -1; - - thread = machine__findnew_thread(machine, event->namespaces.pid, - event->namespaces.tid); - if (thread == NULL) { - pr_debug("problem processing NAMESPACES event, skipping it.\n"); + if (perf_event__process_namespaces(tool, event, sample, machine) < 0) return -1; - } - if (perf_event__process_namespaces(tool, event, sample, machine) < 0) - goto out; + return print_event(tool, event, sample, machine, event->namespaces.pid, + event->namespaces.tid); +} - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->namespaces.tid; - sample->pid = event->namespaces.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_NAMESPACES, stdout); - perf_event__fprintf(event, stdout); - ret = 0; -out: - thread__put(thread); - return ret; +static int process_cgroup_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_cgroup(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } -static int process_fork_event(struct perf_tool *tool, +static int process_fork_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_fork(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); - if (thread == NULL) { - pr_debug("problem processing FORK event, skipping it.\n"); - return -1; - } - - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = event->fork.time; - sample->tid = event->fork.tid; - sample->pid = event->fork.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_FORK, stdout); - perf_event__fprintf(event, stdout); - thread__put(thread); - - return 0; + return print_event_with_time(tool, event, sample, machine, + event->fork.pid, event->fork.tid, + event->fork.time); } -static int process_exit_event(struct perf_tool *tool, +static int process_exit_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - int err = 0; - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - - thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); - if (thread == NULL) { - pr_debug("problem processing EXIT event, skipping it.\n"); + /* 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; - } - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->fork.tid; - sample->pid = event->fork.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_EXIT, stdout); - perf_event__fprintf(event, stdout); - - if (perf_event__process_exit(tool, event, sample, machine) < 0) - err = -1; - - thread__put(thread); - return err; + return perf_event__process_exit(tool, event, sample, machine); } -static int process_mmap_event(struct perf_tool *tool, +static int process_mmap_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_mmap(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid); - if (thread == NULL) { - pr_debug("problem processing MMAP event, skipping it.\n"); - return -1; - } - - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->mmap.tid; - sample->pid = event->mmap.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP, stdout); - perf_event__fprintf(event, stdout); - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, event->mmap.pid, + event->mmap.tid); } -static int process_mmap2_event(struct perf_tool *tool, +static int process_mmap2_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_mmap2(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid); - if (thread == NULL) { - pr_debug("problem processing MMAP2 event, skipping it.\n"); - return -1; - } - - if (!evsel->attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->mmap2.tid; - sample->pid = event->mmap2.pid; - } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP2, stdout); - perf_event__fprintf(event, stdout); - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, event->mmap2.pid, + event->mmap2.tid); } -static int process_switch_event(struct perf_tool *tool, +static int process_switch_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_switch(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, sample->pid, - sample->tid); - if (thread == NULL) { - pr_debug("problem processing SWITCH event, skipping it.\n"); - return -1; + if (scripting_ops && scripting_ops->process_switch && !filter_cpu(sample)) + scripting_ops->process_switch(event, sample, machine); + + 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; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_SWITCH, stdout); - perf_event__fprintf(event, stdout); - thread__put(thread); - return 0; + return perf_event__process_auxtrace_error(tool, session, event); } static int -process_lost_event(struct perf_tool *tool, +process_lost_event(const struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - struct thread *thread; - - thread = machine__findnew_thread(machine, sample->pid, - sample->tid); - if (thread == NULL) - return -1; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_LOST, stdout); - perf_event__fprintf(event, stdout); - thread__put(thread); +static int +process_throttle_event(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (scripting_ops && scripting_ops->process_throttle) + scripting_ops->process_throttle(event, sample, machine); return 0; } static int -process_finished_round_event(struct perf_tool *tool __maybe_unused, +process_finished_round_event(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct ordered_events *oe __maybe_unused) { - perf_event__fprintf(event, stdout); + perf_event__fprintf(event, NULL, stdout); return 0; } +static int +process_bpf_events(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (machine__process_ksymbol(machine, event, sample) < 0) + return -1; + + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} + +static int +process_bpf_metadata_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, + union perf_event *event) +{ + perf_event__fprintf(event, NULL, stdout); + return 0; +} + +static int process_text_poke_events(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_text_poke(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); +} + static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -2286,33 +3095,33 @@ static void sig_handler(int sig __maybe_unused) static void perf_script__fclose_per_event_dump(struct perf_script *script) { - struct perf_evlist *evlist = script->session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = script->session->evlist; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (!evsel->priv) break; - perf_evsel_script__delete(evsel->priv); + evsel_script__delete(evsel->priv); evsel->priv = NULL; } } static int perf_script__fopen_per_event_dump(struct perf_script *script) { - struct perf_evsel *evsel; + 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 syntheized from the auxtrace info. + * for the evsels synthesized from the auxtrace info. * * Ses perf_script__process_auxtrace_info. */ if (evsel->priv != NULL) continue; - evsel->priv = perf_evsel_script__new(evsel, script->session->data); + evsel->priv = evsel_script__new(evsel, script->session->data); if (evsel->priv == NULL) goto out_err_fclose; } @@ -2326,8 +3135,7 @@ out_err_fclose: static int perf_script__setup_per_event_dump(struct perf_script *script) { - struct perf_evsel *evsel; - static struct perf_evsel_script es_stdout; + struct evsel *evsel; if (script->per_event_dump) return perf_script__fopen_per_event_dump(script); @@ -2342,17 +3150,23 @@ static int perf_script__setup_per_event_dump(struct perf_script *script) static void perf_script__exit_per_event_dump_stats(struct perf_script *script) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(script->session->evlist, evsel) { - struct perf_evsel_script *es = evsel->priv; + struct evsel_script *es = evsel->priv; - perf_evsel_script__fprintf(es, stdout); - perf_evsel_script__delete(es); + 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; @@ -2369,16 +3183,29 @@ static int __cmd_script(struct perf_script *script) script->tool.mmap = process_mmap_event; script->tool.mmap2 = process_mmap2_event; } - if (script->show_switch_events) + 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"); @@ -2396,80 +3223,50 @@ static int __cmd_script(struct perf_script *script) return ret; } -struct script_spec { - struct list_head node; - struct scripting_ops *ops; - char spec[0]; -}; - -static LIST_HEAD(script_specs); - -static struct script_spec *script_spec__new(const char *spec, - struct scripting_ops *ops) -{ - struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); - - if (s != NULL) { - strcpy(s->spec, spec); - s->ops = ops; - } - - return s; -} - -static void script_spec__add(struct script_spec *s) +static int list_available_languages_cb(struct scripting_ops *ops, const char *spec) { - list_add_tail(&s->node, &script_specs); -} - -static struct script_spec *script_spec__find(const char *spec) -{ - struct script_spec *s; - - list_for_each_entry(s, &script_specs, node) - if (strcasecmp(s->spec, spec) == 0) - return s; - return NULL; -} - -int script_spec_register(const char *spec, struct scripting_ops *ops) -{ - struct script_spec *s; - - s = script_spec__find(spec); - if (s) - return -1; - - s = script_spec__new(spec, ops); - if (!s) - return -1; - else - script_spec__add(s); - + fprintf(stderr, " %-42s [%s]\n", spec, ops->name); return 0; } -static struct scripting_ops *script_spec__lookup(const char *spec) -{ - struct script_spec *s = script_spec__find(spec); - if (!s) - return NULL; - - return s->ops; -} - static void list_available_languages(void) { - struct script_spec *s; - fprintf(stderr, "\n"); fprintf(stderr, "Scripting language extensions (used in " "perf script -s [spec:]script.[spec]):\n\n"); + 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, @@ -2513,7 +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; } @@ -2562,6 +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; @@ -2612,7 +3415,7 @@ parse: break; } if (i == imax && strcmp(tok, "flags") == 0) { - print_flags = change == REMOVE ? false : true; + print_flags = change != REMOVE; continue; } if (i == imax) { @@ -2620,6 +3423,13 @@ parse: rc = -EINVAL; goto out; } +#ifndef HAVE_LIBCAPSTONE_SUPPORT + if (change != REMOVE && strcmp(tok, "disasm") == 0) { + fprintf(stderr, "Field \"disasm\" requires perf to be built with libcapstone support.\n"); + rc = -EINVAL; + goto out; + } +#endif if (type == -1) { /* add user option to all events types for @@ -2630,10 +3440,15 @@ parse: pr_warning("\'%s\' not valid for %s events. Ignoring.\n", all_output_options[i].str, event_type(j)); } else { - if (change == REMOVE) + if (change == REMOVE) { output[j].fields &= ~all_output_options[i].field; - else + 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; } @@ -2646,6 +3461,10 @@ parse: rc = -EINVAL; goto out; } + 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; } @@ -2767,7 +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 != '#') @@ -2776,19 +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; } } @@ -2821,14 +3640,21 @@ static int list_available_scripts(const struct option *opt __maybe_unused, int unset __maybe_unused) { struct dirent *script_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN]; + char *buf, *scripts_path, *script_path, *lang_path, *first_half; DIR *scripts_dir, *lang_dir; - char script_path[MAXPATHLEN]; - char lang_path[MAXPATHLEN]; struct script_desc *desc; - char first_half[BUFSIZ]; char *script_root; + buf = malloc(3 * MAXPATHLEN + BUFSIZ); + if (!buf) { + pr_err("malloc failed\n"); + exit(-1); + } + scripts_path = buf; + script_path = buf + MAXPATHLEN; + lang_path = buf + 2 * MAXPATHLEN; + first_half = buf + 3 * MAXPATHLEN; + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); @@ -2837,6 +3663,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, "open(%s) failed.\n" "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", scripts_path); + free(buf); exit(-1); } @@ -2867,143 +3694,36 @@ 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; - scnprintf(filename, MAXPATHLEN, "%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; - evlist__for_each_entry(session->evlist, pos) { - 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_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; - DIR *scripts_dir, *lang_dir; - struct perf_session *session; - struct perf_data data = { - .file = { - .path = input_name, - }, - .mode = PERF_DATA_MODE_READ, - }; - char *temp; - int i = 0; - - session = perf_session__new(&data, false, NULL); - if (!session) - return -1; - - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); - - scripts_dir = opendir(scripts_path); - if (!scripts_dir) { - perf_session__delete(session); - return -1; - } - - for_each_lang(scripts_path, scripts_dir, lang_dirent) { - scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent->d_name); -#ifndef HAVE_LIBPERL_SUPPORT - if (strstr(lang_path, "perl")) - continue; -#endif -#ifndef HAVE_LIBPYTHON_SUPPORT - if (strstr(lang_path, "python")) - continue; -#endif - - lang_dir = opendir(lang_path); - if (!lang_dir) - continue; - - for_each_script(lang_path, lang_dir, script_dirent) { - /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent->d_name, "top.")) - continue; - 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) @@ -3032,10 +3752,10 @@ static char *get_script_path(const char *script_root, const char *suffix) __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); scnprintf(script_path, MAXPATHLEN, "%s/%s", lang_path, script_dirent->d_name); + closedir(lang_dir); return strdup(script_path); } free(__script_root); @@ -3049,7 +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) @@ -3097,25 +3817,23 @@ static int have_cmd(int argc, const char **argv) static void script__setup_sample_type(struct perf_script *script) { struct perf_session *session = script->session; - u64 sample_type = perf_evlist__combined_sample_type(session->evlist); - - if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { - if ((sample_type & PERF_SAMPLE_REGS_USER) && - (sample_type & PERF_SAMPLE_STACK_USER)) { - callchain_param.record_mode = CALLCHAIN_DWARF; - dwarf_callchain_users = true; - } else if (sample_type & PERF_SAMPLE_BRANCH_STACK) - callchain_param.record_mode = CALLCHAIN_LBR; - else - callchain_param.record_mode = CALLCHAIN_FP; + 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(struct perf_session *session, +static int process_stat_round_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { - struct stat_round_event *round = &event->stat_round; - struct perf_evsel *counter; + 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); @@ -3126,16 +3844,24 @@ static int process_stat_round_event(struct perf_session *session, return 0; } -static int process_stat_config_event(struct perf_session *session __maybe_unused, +static int process_stat_config_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } static int set_maps(struct perf_script *script) { - struct perf_evlist *evlist = script->session->evlist; + struct evlist *evlist = script->session->evlist; if (!script->cpus || !script->threads) return 0; @@ -3143,9 +3869,9 @@ static int set_maps(struct perf_script *script) if (WARN_ONCE(script->allocated, "stats double allocation\n")) return -EINVAL; - perf_evlist__set_maps(evlist, script->cpus, script->threads); + perf_evlist__set_maps(&evlist->core, script->cpus, script->threads); - if (perf_evlist__alloc_stats(evlist, true)) + if (evlist__alloc_stats(&stat_config, evlist, /*alloc_raw=*/true)) return -ENOMEM; script->allocated = true; @@ -3153,12 +3879,15 @@ static int set_maps(struct perf_script *script) } static -int process_thread_map_event(struct perf_session *session, +int process_thread_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, union perf_event *event) { - struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); + if (dump_trace) + perf_event__fprintf_thread_map(event, stdout); + if (script->threads) { pr_warning("Extra thread map event, ignoring.\n"); return 0; @@ -3172,12 +3901,15 @@ int process_thread_map_event(struct perf_session *session, } static -int process_cpu_map_event(struct perf_session *session, +int process_cpu_map_event(const struct perf_tool *tool, + struct perf_session *session __maybe_unused, union perf_event *event) { - struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); + if (dump_trace) + perf_event__fprintf_cpu_map(event, stdout); + if (script->cpus) { pr_warning("Extra cpu map event, ignoring.\n"); return 0; @@ -3190,7 +3922,8 @@ int process_cpu_map_event(struct perf_session *session, return set_maps(script); } -static int process_feature_event(struct perf_session *session, +static int process_feature_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { if (event->feat.feat_id < HEADER_LAST_FEATURE) @@ -3198,13 +3931,11 @@ static int process_feature_event(struct perf_session *session, return 0; } -#ifdef HAVE_AUXTRACE_SUPPORT -static int perf_script__process_auxtrace_info(struct perf_session *session, +static int perf_script__process_auxtrace_info(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event) { - struct perf_tool *tool = session->tool; - - int ret = perf_event__process_auxtrace_info(session, event); + int ret = perf_event__process_auxtrace_info(tool, session, event); if (ret == 0) { struct perf_script *script = container_of(tool, struct perf_script, tool); @@ -3214,17 +3945,28 @@ static int perf_script__process_auxtrace_info(struct perf_session *session, return ret; } -#else -#define perf_script__process_auxtrace_info 0 -#endif static int parse_insn_trace(const struct option *opt __maybe_unused, - const char *str __maybe_unused, - int unset __maybe_unused) + const char *str, int unset __maybe_unused) { - parse_output_fields(NULL, "+insn,-event,-period", 0); - itrace_parse_synth_opts(opt, "i0ns", 0); - nanosecs = true; + 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; } @@ -3232,7 +3974,10 @@ static int parse_xed(const struct option *opt __maybe_unused, const char *str __maybe_unused, int unset __maybe_unused) { - force_pager("xed -F insn: -A -64 | less"); + if (isatty(1)) + force_pager("xed -F insn: -A -64 | less"); + else + force_pager("xed -F insn: -A -64"); return 0; } @@ -3242,7 +3987,8 @@ static int parse_call_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0); itrace_parse_synth_opts(opt, "cewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; + symbol_conf.pad_output_len_dso = 50; return 0; } @@ -3252,7 +3998,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0); itrace_parse_synth_opts(opt, "crewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3262,6 +4008,8 @@ int cmd_script(int argc, const char **argv) 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; @@ -3269,53 +4017,36 @@ int cmd_script(int argc, const char **argv) .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 = 0; - struct perf_script script = { - .tool = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .mmap2 = perf_event__process_mmap2, - .comm = perf_event__process_comm, - .namespaces = perf_event__process_namespaces, - .exit = perf_event__process_exit, - .fork = perf_event__process_fork, - .attr = process_attr, - .event_update = perf_event__process_event_update, - .tracing_data = perf_event__process_tracing_data, - .feature = process_feature_event, - .build_id = perf_event__process_build_id, - .id_index = perf_event__process_id_index, - .auxtrace_info = perf_script__process_auxtrace_info, - .auxtrace = perf_event__process_auxtrace, - .auxtrace_error = perf_event__process_auxtrace_error, - .stat = perf_event__process_stat_event, - .stat_round = process_stat_round_event, - .stat_config = process_stat_config_event, - .thread_map = process_thread_map_event, - .cpu_map = process_cpu_map_event, - .ordered_events = true, - .ordering_requires_timestamps = true, - }, - }; + 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"), @@ -3334,21 +4065,28 @@ int cmd_script(int argc, const char **argv) "comma separated output fields prepend with 'type:'. " "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " - "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," + "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff," "addr,symoff,srcline,period,iregs,uregs,brstack," - "brstacksym,flags,bpf-output,brstackinsn,brstackoff," - "callindent,insn,insnlen,synth,phys_addr,metric,misc", + "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_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL, + 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 from itrace", parse_call_trace), + "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...]", @@ -3366,6 +4104,8 @@ int cmd_script(int argc, const char **argv) "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, @@ -3378,16 +4118,22 @@ int cmd_script(int argc, const char **argv) "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", &nanosecs, + 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, @@ -3398,10 +4144,28 @@ int cmd_script(int argc, const char **argv) "Enable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), + OPT_STRING(0, "addr2line", &symbol_conf.addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_STRING(0, "time", &script.time_str, "str", "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "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_subcommands[] = { "record", "report", NULL }; @@ -3413,6 +4177,7 @@ int cmd_script(int argc, const char **argv) "perf script [<options>] <top-script> [script-args]", NULL }; + struct perf_env *env; perf_set_singlethreaded(); @@ -3421,16 +4186,33 @@ int cmd_script(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, PARSE_OPT_STOP_AT_NON_OPTION); - data.file.path = input_name; - data.force = symbol_conf.force; + 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 (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { + 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); } - 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, @@ -3440,7 +4222,14 @@ int cmd_script(int argc, const char **argv) } } - if (itrace_synth_opts.callchain && + 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; @@ -3456,6 +4245,12 @@ int cmd_script(int argc, const char **argv) rep_script_path = get_script_path(argv[0], REPORT_SUFFIX); if (!rec_script_path && !rep_script_path) { + 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]); @@ -3548,7 +4343,7 @@ int cmd_script(int argc, const char **argv) free(__argv); exit(-1); } - +script_found: if (rec_script_path) script_path = rec_script_path; if (rep_script_path) @@ -3586,15 +4381,52 @@ int cmd_script(int argc, const char **argv) exit(-1); } + 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(&data, false, &script.tool); - if (session == NULL) - return -1; - + 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); @@ -3604,9 +4436,20 @@ int cmd_script(int argc, const char **argv) if (show_full_info) script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; - if (symbol__init(&session->header.env) < 0) + if (symbol__init(env) < 0) goto out_delete; + uname(&uts); + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ + native_arch = true; + } else if (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); @@ -3628,6 +4471,7 @@ int cmd_script(int argc, const char **argv) else symbol_conf.use_callchain = false; +#ifdef HAVE_LIBTRACEEVENT if (session->tevent.pevent && tep_set_function_resolver(session->tevent.pevent, machine__resolve_kernel_addr, @@ -3636,7 +4480,7 @@ int cmd_script(int argc, const char **argv) err = -1; goto out_delete; } - +#endif if (generate_script_lang) { struct stat perf_stat; int input; @@ -3648,7 +4492,7 @@ int cmd_script(int argc, const char **argv) goto out_delete; } - input = open(data.file.path, O_RDONLY); /* input_name */ + input = open(data.path, O_RDONLY); /* input_name */ if (input < 0) { err = -errno; perror("failed to open file"); @@ -3672,14 +4516,21 @@ int cmd_script(int argc, const char **argv) err = -ENOENT; goto out_delete; } - +#ifdef HAVE_LIBTRACEEVENT err = scripting_ops->generate_script(session->tevent.pevent, "perf-script"); +#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_delete; pr_debug("perf script started with script %s\n\n", script_name); @@ -3691,51 +4542,49 @@ int cmd_script(int argc, const char **argv) if (err < 0) goto out_delete; - script.ptime_range = perf_time__range_alloc(script.time_str, - &script.range_size); - if (!script.ptime_range) { - err = -ENOMEM; - goto out_delete; - } - - /* needs to be parsed after looking up reference time */ - if (perf_time__parse_str(script.ptime_range, script.time_str) != 0) { - if (session->evlist->first_sample_time == 0 && - session->evlist->last_sample_time == 0) { - pr_err("HINT: no first/last sample time found in perf data.\n" - "Please use latest perf binary to execute 'perf record'\n" - "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n"); - err = -EINVAL; + 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; - } - - script.range_num = perf_time__percent_parse_str( - script.ptime_range, script.range_size, - script.time_str, - session->evlist->first_sample_time, - session->evlist->last_sample_time); - if (script.range_num < 0) { - pr_err("Invalid time string\n"); - err = -EINVAL; - goto out_delete; - } - } else { - script.range_num = 1; + 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); flush_scripting(); + if (verbose > 2 || debug_kmaps) + perf_session__dump_kmaps(session); + out_delete: - zfree(&script.ptime_range); + if (script.ptime_range) { + itrace_synth_opts__clear_time_range(&itrace_synth_opts); + zfree(&script.ptime_range); + } - perf_evlist__free_stats(session->evlist); + zstd_fini(&(session->zstd_data)); + evlist__free_stats(session->evlist); perf_session__delete(session); + perf_script__exit(&script); if (script_started) cleanup_scripting(); + dlfilter__cleanup(dlfilter); + free_dlarg(); out: return err; } |