diff options
Diffstat (limited to 'tools/perf/util')
54 files changed, 2207 insertions, 428 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8d18380ecd10..cd5e41960e64 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -117,6 +117,7 @@ endif perf-y += parse-branch-options.o perf-y += dump-insn.o perf-y += parse-regs-options.o +perf-y += parse-sublevel-options.o perf-y += term.o perf-y += help-unknown-cmd.o perf-y += mem-events.o @@ -128,6 +129,7 @@ perf-y += expr-bison.o perf-y += expr.o perf-y += branch.o perf-y += mem2node.o +perf-y += clockid.o perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o @@ -191,36 +193,60 @@ CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))" # avoid compiler warnings in 32-bit mode CFLAGS_genelf_debug.o += -Wno-packed -$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c +$(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-flex.h: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(call rule_mkdir) - $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l + $(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/parse-events-flex.c \ + --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) $< -$(OUTPUT)util/parse-events-bison.c: util/parse-events.y +$(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/parse-events-bison.h: util/parse-events.y $(call rule_mkdir) - $(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ + $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \ + -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ -$(OUTPUT)util/expr-flex.c: util/expr.l $(OUTPUT)util/expr-bison.c +$(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-flex.h: util/expr.l $(OUTPUT)util/expr-bison.c $(call rule_mkdir) - $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) util/expr.l + $(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/expr-flex.c \ + --header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) $< -$(OUTPUT)util/expr-bison.c: util/expr.y +$(OUTPUT)util/expr-bison.c $(OUTPUT)util/expr-bison.h: util/expr.y $(call rule_mkdir) - $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr_ + $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \ + -o $(OUTPUT)util/expr-bison.c -p expr_ -$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c +$(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-flex.h: util/pmu.l $(OUTPUT)util/pmu-bison.c $(call rule_mkdir) - $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l + $(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/pmu-flex.c \ + --header-file=$(OUTPUT)util/pmu-flex.h $(PARSER_DEBUG_FLEX) $< -$(OUTPUT)util/pmu-bison.c: util/pmu.y +$(OUTPUT)util/pmu-bison.c $(OUTPUT)util/pmu-bison.h: util/pmu.y $(call rule_mkdir) - $(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_ - -CFLAGS_parse-events-flex.o += -w -CFLAGS_pmu-flex.o += -w -CFLAGS_expr-flex.o += -w -CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w -CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w -CFLAGS_expr-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w + $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) \ + -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ + +FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e 's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26) +ifeq ($(FLEX_GE_26),1) + flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations + CC_HASNT_MISLEADING_INDENTATION := $(shell echo "int main(void) { return 0 }" | $(CC) -Werror -Wno-misleading-indentation -o /dev/null -xc - 2>&1 | grep -q -- -Wno-misleading-indentation ; echo $$?) + ifeq ($(CC_HASNT_MISLEADING_INDENTATION), 1) + flex_flags += -Wno-misleading-indentation + endif +else + flex_flags := -w +endif +CFLAGS_parse-events-flex.o += $(flex_flags) +CFLAGS_pmu-flex.o += $(flex_flags) +CFLAGS_expr-flex.o += $(flex_flags) + +bison_flags := -DYYENABLE_NLS=0 +BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35) +ifeq ($(BISON_GE_35),1) + bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum +else + bison_flags += -w +endif +CFLAGS_parse-events-bison.o += $(bison_flags) +CFLAGS_pmu-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) +CFLAGS_expr-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 76bfb4a9d94e..0a1fcf787538 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1621,6 +1621,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil char *build_id_filename; char *build_id_path = NULL; char *pos; + int len; if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) @@ -1649,10 +1650,16 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil if (pos && strlen(pos) < SBUILD_ID_SIZE - 2) dirname(build_id_path); - if (dso__is_kcore(dso) || - readlink(build_id_path, linkname, sizeof(linkname)) < 0 || - strstr(linkname, DSO__NAME_KALLSYMS) || - access(filename, R_OK)) { + if (dso__is_kcore(dso)) + goto fallback; + + len = readlink(build_id_path, linkname, sizeof(linkname) - 1); + if (len < 0) + goto fallback; + + linkname[len] = '\0'; + if (strstr(linkname, DSO__NAME_KALLSYMS) || + access(filename, R_OK)) { fallback: /* * If we don't have build-ids or the build-id file isn't in the diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 25c639ac4ad4..42a85c86421d 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1349,6 +1349,47 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->initial_skip = 0; } +static int get_flag(const char **ptr, unsigned int *flags) +{ + while (1) { + char c = **ptr; + + if (c >= 'a' && c <= 'z') { + *flags |= 1 << (c - 'a'); + ++*ptr; + return 0; + } else if (c == ' ') { + ++*ptr; + continue; + } else { + return -1; + } + } +} + +static int get_flags(const char **ptr, unsigned int *plus_flags, unsigned int *minus_flags) +{ + while (1) { + switch (**ptr) { + case '+': + ++*ptr; + if (get_flag(ptr, plus_flags)) + return -1; + break; + case '-': + ++*ptr; + if (get_flag(ptr, minus_flags)) + return -1; + break; + case ' ': + ++*ptr; + break; + default: + return 0; + } + } +} + /* * Please check tools/perf/Documentation/perf-script.txt for information * about the options parsed here, which is introduced after this cset, @@ -1436,9 +1477,15 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, break; case 'e': synth_opts->errors = true; + if (get_flags(&p, &synth_opts->error_plus_flags, + &synth_opts->error_minus_flags)) + goto out_err; break; case 'd': synth_opts->log = true; + if (get_flags(&p, &synth_opts->log_plus_flags, + &synth_opts->log_minus_flags)) + goto out_err; break; case 'c': synth_opts->branches = true; @@ -1507,6 +1554,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'a': synth_opts->remote_access = true; break; + case 'q': + synth_opts->quick += 1; + break; case ' ': case ',': break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 142ccf7d34df..951d2d14cf24 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -55,6 +55,11 @@ enum itrace_period_type { PERF_ITRACE_PERIOD_NANOSECS, }; +#define AUXTRACE_ERR_FLG_OVERFLOW (1 << ('o' - 'a')) +#define AUXTRACE_ERR_FLG_DATA_LOST (1 << ('l' - 'a')) + +#define AUXTRACE_LOG_FLG_ALL_PERF_EVTS (1 << ('a' - 'a')) + /** * struct itrace_synth_opts - AUX area tracing synthesis options. * @set: indicates whether or not options have been set @@ -91,6 +96,11 @@ enum itrace_period_type { * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all * @ptime_range: time intervals to trace or NULL * @range_num: number of time intervals to trace + * @error_plus_flags: flags to affect what errors are reported + * @error_minus_flags: flags to affect what errors are reported + * @log_plus_flags: flags to affect what is logged + * @log_minus_flags: flags to affect what is logged + * @quick: quicker (less detailed) decoding */ struct itrace_synth_opts { bool set; @@ -124,6 +134,11 @@ struct itrace_synth_opts { unsigned long *cpu_bitmap; struct perf_time_interval *ptime_range; int range_num; + unsigned int error_plus_flags; + unsigned int error_minus_flags; + unsigned int log_plus_flags; + unsigned int log_minus_flags; + unsigned int quick; }; /** @@ -604,22 +619,32 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, struct evsel *evsel); #define ITRACE_HELP \ -" i: synthesize instructions events\n" \ +" i[period]: synthesize instructions events\n" \ " b: synthesize branches events (branch misses for Arm SPE)\n" \ " c: synthesize branches events (calls only)\n" \ " r: synthesize branches events (returns only)\n" \ " x: synthesize transactions events\n" \ " w: synthesize ptwrite events\n" \ " p: synthesize power events\n" \ -" e: synthesize error events\n" \ -" d: create a debug log\n" \ +" o: synthesize other events recorded due to the use\n" \ +" of aux-output (refer to perf record)\n" \ +" e[flags]: synthesize error events\n" \ +" each flag must be preceded by + or -\n" \ +" error flags are: o (overflow)\n" \ +" l (data lost)\n" \ +" d[flags]: create a debug log\n" \ +" each flag must be preceded by + or -\n" \ +" log flags are: a (all perf events)\n" \ " f: synthesize first level cache events\n" \ " m: synthesize last level cache events\n" \ " t: synthesize TLB events\n" \ " a: synthesize remote access events\n" \ " g[len]: synthesize a call chain (use with i or x)\n" \ +" G[len]: synthesize a call chain on existing event records\n" \ " l[len]: synthesize last branch entries (use with i or x)\n" \ +" L[len]: synthesize last branch entries on existing event records\n" \ " sNUMBER: skip initial number of events\n" \ +" q: quicker (less detailed) decoding\n" \ " PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \ " concatenate multiple options. Default is ibxwpe or cewp\n" diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index c076fc7fe025..31207b6e2066 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -31,6 +31,10 @@ #include "probe-file.h" #include "strlist.h" +#ifdef HAVE_DEBUGINFOD_SUPPORT +#include <elfutils/debuginfod.h> +#endif + #include <linux/ctype.h> #include <linux/zalloc.h> @@ -636,6 +640,21 @@ static char *build_id_cache__find_debug(const char *sbuild_id, if (realname && access(realname, R_OK)) zfree(&realname); nsinfo__mountns_exit(&nsc); + +#ifdef HAVE_DEBUGINFOD_SUPPORT + if (realname == NULL) { + debuginfod_client* c = debuginfod_begin(); + if (c != NULL) { + int fd = debuginfod_find_debuginfo(c, + (const unsigned char*)sbuild_id, 0, + &realname); + if (fd >= 0) + close(fd); /* retaining reference by realname */ + debuginfod_end(c); + } + } +#endif + out: free(debugfile); return realname; diff --git a/tools/perf/util/clockid.c b/tools/perf/util/clockid.c new file mode 100644 index 000000000000..74365a5d99c1 --- /dev/null +++ b/tools/perf/util/clockid.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <subcmd/parse-options.h> +#include <stdio.h> +#include <time.h> +#include <strings.h> +#include <linux/time64.h> +#include "debug.h" +#include "clockid.h" +#include "record.h" + +struct clockid_map { + const char *name; + int clockid; +}; + +#define CLOCKID_MAP(n, c) \ + { .name = n, .clockid = (c), } + +#define CLOCKID_END { .name = NULL, } + + +/* + * Add the missing ones, we need to build on many distros... + */ +#ifndef CLOCK_MONOTONIC_RAW +#define CLOCK_MONOTONIC_RAW 4 +#endif +#ifndef CLOCK_BOOTTIME +#define CLOCK_BOOTTIME 7 +#endif +#ifndef CLOCK_TAI +#define CLOCK_TAI 11 +#endif + +static const struct clockid_map clockids[] = { + /* available for all events, NMI safe */ + CLOCKID_MAP("monotonic", CLOCK_MONOTONIC), + CLOCKID_MAP("monotonic_raw", CLOCK_MONOTONIC_RAW), + + /* available for some events */ + CLOCKID_MAP("realtime", CLOCK_REALTIME), + CLOCKID_MAP("boottime", CLOCK_BOOTTIME), + CLOCKID_MAP("tai", CLOCK_TAI), + + /* available for the lazy */ + CLOCKID_MAP("mono", CLOCK_MONOTONIC), + CLOCKID_MAP("raw", CLOCK_MONOTONIC_RAW), + CLOCKID_MAP("real", CLOCK_REALTIME), + CLOCKID_MAP("boot", CLOCK_BOOTTIME), + + CLOCKID_END, +}; + +static int get_clockid_res(clockid_t clk_id, u64 *res_ns) +{ + struct timespec res; + + *res_ns = 0; + if (!clock_getres(clk_id, &res)) + *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC; + else + pr_warning("WARNING: Failed to determine specified clock resolution.\n"); + + return 0; +} + +int parse_clockid(const struct option *opt, const char *str, int unset) +{ + struct record_opts *opts = (struct record_opts *)opt->value; + const struct clockid_map *cm; + const char *ostr = str; + + if (unset) { + opts->use_clockid = 0; + return 0; + } + + /* no arg passed */ + if (!str) + return 0; + + /* no setting it twice */ + if (opts->use_clockid) + return -1; + + opts->use_clockid = true; + + /* if its a number, we're done */ + if (sscanf(str, "%d", &opts->clockid) == 1) + return get_clockid_res(opts->clockid, &opts->clockid_res_ns); + + /* allow a "CLOCK_" prefix to the name */ + if (!strncasecmp(str, "CLOCK_", 6)) + str += 6; + + for (cm = clockids; cm->name; cm++) { + if (!strcasecmp(str, cm->name)) { + opts->clockid = cm->clockid; + return get_clockid_res(opts->clockid, + &opts->clockid_res_ns); + } + } + + opts->use_clockid = false; + ui__warning("unknown clockid %s, check man page\n", ostr); + return -1; +} + +const char *clockid_name(clockid_t clk_id) +{ + const struct clockid_map *cm; + + for (cm = clockids; cm->name; cm++) { + if (cm->clockid == clk_id) + return cm->name; + } + return "(not found)"; +} diff --git a/tools/perf/util/clockid.h b/tools/perf/util/clockid.h new file mode 100644 index 000000000000..9b49b4711c76 --- /dev/null +++ b/tools/perf/util/clockid.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PERF_CLOCKID_H +#define __PERF_CLOCKID_H + +struct option; +int parse_clockid(const struct option *opt, const char *str, int unset); + +const char *clockid_name(clockid_t clk_id); + +#endif diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 5f36fc6a5578..27c5fef9ad54 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -31,6 +31,9 @@ #include "config.h" #include <linux/ctype.h> #include <linux/err.h> +#include <linux/time64.h> +#include "util.h" +#include "clockid.h" #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -1381,11 +1384,26 @@ do { \ return 0; } -static int ctf_writer__setup_clock(struct ctf_writer *cw) +static int ctf_writer__setup_clock(struct ctf_writer *cw, + struct perf_session *session, + bool tod) { struct bt_ctf_clock *clock = cw->clock; + const char *desc = "perf clock"; + int64_t offset = 0; - bt_ctf_clock_set_description(clock, "perf clock"); + if (tod) { + struct perf_env *env = &session->header.env; + + if (!env->clock.enabled) { + pr_err("Can't provide --tod time, missing clock data. " + "Please record with -k/--clockid option.\n"); + return -1; + } + + desc = clockid_name(env->clock.clockid); + offset = env->clock.tod_ns - env->clock.clockid_ns; + } #define SET(__n, __v) \ do { \ @@ -1394,8 +1412,8 @@ do { \ } while (0) SET(frequency, 1000000000); - SET(offset_s, 0); - SET(offset, 0); + SET(offset, offset); + SET(description, desc); SET(precision, 10); SET(is_absolute, 0); @@ -1481,7 +1499,8 @@ static void ctf_writer__cleanup(struct ctf_writer *cw) memset(cw, 0, sizeof(*cw)); } -static int ctf_writer__init(struct ctf_writer *cw, const char *path) +static int ctf_writer__init(struct ctf_writer *cw, const char *path, + struct perf_session *session, bool tod) { struct bt_ctf_writer *writer; struct bt_ctf_stream_class *stream_class; @@ -1505,7 +1524,7 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path) cw->clock = clock; - if (ctf_writer__setup_clock(cw)) { + if (ctf_writer__setup_clock(cw, session, tod)) { pr("Failed to setup CTF clock.\n"); goto err_cleanup; } @@ -1613,17 +1632,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, if (err) return err; - /* CTF writer */ - if (ctf_writer__init(cw, path)) - return -1; - err = -1; /* perf.data session */ session = perf_session__new(&data, 0, &c.tool); - if (IS_ERR(session)) { - err = PTR_ERR(session); - goto free_writer; - } + if (IS_ERR(session)) + return PTR_ERR(session); + + /* CTF writer */ + if (ctf_writer__init(cw, path, session, opts->tod)) + goto free_session; if (c.queue_size) { ordered_events__set_alloc_size(&session->ordered_events, @@ -1632,17 +1649,17 @@ int bt_convert__perf2ctf(const char *input, const char *path, /* CTF writer env/clock setup */ if (ctf_writer__setup_env(cw, session)) - goto free_session; + goto free_writer; /* CTF events setup */ if (setup_events(cw, session)) - goto free_session; + goto free_writer; if (opts->all && setup_non_sample_events(cw, session)) - goto free_session; + goto free_writer; if (setup_streams(cw, session)) - goto free_session; + goto free_writer; err = perf_session__process_events(session); if (!err) @@ -1670,10 +1687,10 @@ int bt_convert__perf2ctf(const char *input, const char *path, return err; -free_session: - perf_session__delete(session); free_writer: ctf_writer__cleanup(cw); +free_session: + perf_session__delete(session); pr_err("Error during conversion setup.\n"); return err; } diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h index af90b6076c06..feab5f114e37 100644 --- a/tools/perf/util/data-convert.h +++ b/tools/perf/util/data-convert.h @@ -5,6 +5,7 @@ struct perf_data_convert_opts { bool force; bool all; + bool tod; }; #endif /* __DATA_CONVERT_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index adb656745ecc..5cda5565777a 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -20,6 +20,7 @@ #include "target.h" #include "ui/helpline.h" #include "ui/ui.h" +#include "util/parse-sublevel-options.h" #include <linux/ctype.h> @@ -173,65 +174,37 @@ void trace_event(union perf_event *event) trace_event_printer, event); } -static struct debug_variable { - const char *name; - int *ptr; -} debug_variables[] = { - { .name = "verbose", .ptr = &verbose }, - { .name = "ordered-events", .ptr = &debug_ordered_events}, - { .name = "stderr", .ptr = &redirect_to_stderr}, - { .name = "data-convert", .ptr = &debug_data_convert }, - { .name = "perf-event-open", .ptr = &debug_peo_args }, +static struct sublevel_option debug_opts[] = { + { .name = "verbose", .value_ptr = &verbose }, + { .name = "ordered-events", .value_ptr = &debug_ordered_events}, + { .name = "stderr", .value_ptr = &redirect_to_stderr}, + { .name = "data-convert", .value_ptr = &debug_data_convert }, + { .name = "perf-event-open", .value_ptr = &debug_peo_args }, { .name = NULL, } }; int perf_debug_option(const char *str) { - struct debug_variable *var = &debug_variables[0]; - char *vstr, *s = strdup(str); - int v = 1; - - vstr = strchr(s, '='); - if (vstr) - *vstr++ = 0; - - while (var->name) { - if (!strcmp(s, var->name)) - break; - var++; - } - - if (!var->name) { - pr_err("Unknown debug variable name '%s'\n", s); - free(s); - return -1; - } + int ret; - if (vstr) { - v = atoi(vstr); - /* - * Allow only values in range (0, 10), - * otherwise set 0. - */ - v = (v < 0) || (v > 10) ? 0 : v; - } + ret = perf_parse_sublevel_options(str, debug_opts); + if (ret) + return ret; - if (quiet) - v = -1; + /* Allow only verbose value in range (0, 10), otherwise set 0. */ + verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose; - *var->ptr = v; - free(s); return 0; } int perf_quiet_option(void) { - struct debug_variable *var = &debug_variables[0]; + struct sublevel_option *opt = &debug_opts[0]; /* disable all debug messages */ - while (var->name) { - *var->ptr = -1; - var++; + while (opt->name) { + *opt->value_ptr = -1; + opt++; } return 0; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 99f0a39c3c59..5a3b4755f0b3 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -208,6 +208,7 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__JAVA_JIT: case DSO_BINARY_TYPE__BPF_PROG_INFO: case DSO_BINARY_TYPE__BPF_IMAGE: + case DSO_BINARY_TYPE__OOL: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; break; @@ -898,6 +899,8 @@ static struct dso_cache *dso_cache__populate(struct dso *dso, if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) *ret = bpf_read(dso, cache_offset, cache->data); + else if (dso->binary_type == DSO_BINARY_TYPE__OOL) + *ret = DSO__DATA_CACHE_SIZE; else *ret = file_read(dso, machine, cache_offset, cache->data); @@ -1262,7 +1265,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id) dso->has_build_id = 0; dso->has_srcline = 1; dso->a2l_fails = 1; - dso->kernel = DSO_TYPE_USER; + dso->kernel = DSO_SPACE__USER; dso->needs_swap = DSO_SWAP__UNSET; dso->comp = COMP_ID__NONE; RB_CLEAR_NODE(&dso->rb_node); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index d3d03274b0d1..8ad17f395a19 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -42,13 +42,14 @@ enum dso_binary_type { DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__BPF_PROG_INFO, DSO_BINARY_TYPE__BPF_IMAGE, + DSO_BINARY_TYPE__OOL, DSO_BINARY_TYPE__NOT_FOUND, }; -enum dso_kernel_type { - DSO_TYPE_USER = 0, - DSO_TYPE_KERNEL, - DSO_TYPE_GUEST_KERNEL +enum dso_space_type { + DSO_SPACE__USER = 0, + DSO_SPACE__KERNEL, + DSO_SPACE__KERNEL_GUEST }; enum dso_swap_type { @@ -159,7 +160,7 @@ struct dso { void *a2l; char *symsrc_filename; unsigned int a2l_fails; - enum dso_kernel_type kernel; + enum dso_space_type kernel; enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; enum dso_binary_type binary_type; diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 1ab2682d5d2b..a12972652006 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -77,7 +77,6 @@ struct perf_env { struct numa_node *numa_nodes; struct memory_node *memory_nodes; unsigned long long memory_bsize; - u64 clockid_res_ns; /* * bpf_info_lock protects bpf rbtrees. This is needed because the @@ -100,6 +99,19 @@ struct perf_env { /* For fast cpu to numa node lookup via perf_env__numa_node */ int *numa_map; int nr_numa_map; + + /* For real clock time reference. */ + struct { + u64 tod_ns; + u64 clockid_ns; + u64 clockid_res_ns; + int clockid; + /* + * enabled is valid for report mode, and is true if above + * values are set, it's set in process_clock_data + */ + bool enabled; + } clock; }; enum perf_compress_type { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f581550a3015..317a26571845 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -31,6 +31,7 @@ #include "stat.h" #include "session.h" #include "bpf-event.h" +#include "print_binary.h" #include "tool.h" #include "../perf.h" @@ -55,6 +56,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_KSYMBOL] = "KSYMBOL", [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", [PERF_RECORD_CGROUP] = "CGROUP", + [PERF_RECORD_TEXT_POKE] = "TEXT_POKE", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -267,6 +269,14 @@ int perf_event__process_bpf(struct perf_tool *tool __maybe_unused, return machine__process_bpf(machine, event, sample); } +int perf_event__process_text_poke(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_text_poke(machine, event, sample); +} + size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 "]: %c %s\n", @@ -413,7 +423,52 @@ size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp) event->bpf.type, event->bpf.flags, event->bpf.id); } -size_t perf_event__fprintf(union perf_event *event, FILE *fp) +static int text_poke_printer(enum binary_printer_ops op, unsigned int val, + void *extra, FILE *fp) +{ + bool old = *(bool *)extra; + + switch ((int)op) { + case BINARY_PRINT_LINE_BEGIN: + return fprintf(fp, " %s bytes:", old ? "Old" : "New"); + case BINARY_PRINT_NUM_DATA: + return fprintf(fp, " %02x", val); + case BINARY_PRINT_LINE_END: + return fprintf(fp, "\n"); + default: + return 0; + } +} + +size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine, FILE *fp) +{ + struct perf_record_text_poke_event *tp = &event->text_poke; + size_t ret; + bool old; + + ret = fprintf(fp, " %" PRI_lx64 " ", tp->addr); + if (machine) { + struct addr_location al; + + al.map = maps__find(&machine->kmaps, tp->addr); + if (al.map && map__load(al.map) >= 0) { + al.addr = al.map->map_ip(al.map, tp->addr); + al.sym = map__find_symbol(al.map, al.addr); + if (al.sym) + ret += symbol__fprintf_symname_offs(al.sym, &al, fp); + } + } + ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len); + old = true; + ret += binary__fprintf(tp->bytes, tp->old_len, 16, text_poke_printer, + &old, fp); + old = false; + ret += binary__fprintf(tp->bytes + tp->old_len, tp->new_len, 16, + text_poke_printer, &old, fp); + return ret; +} + +size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp) { size_t ret = fprintf(fp, "PERF_RECORD_%s", perf_event__name(event->header.type)); @@ -457,6 +512,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_BPF_EVENT: ret += perf_event__fprintf_bpf(event, fp); break; + case PERF_RECORD_TEXT_POKE: + ret += perf_event__fprintf_text_poke(event, machine, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6ae01c3c2ffa..b828b99176f4 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -351,6 +351,10 @@ int perf_event__process_bpf(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_text_poke(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -385,7 +389,8 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp); size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp); size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp); -size_t perf_event__fprintf(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine,FILE *fp); +size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp); int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ab48be4cf258..e3fa3bf7498a 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -63,6 +63,9 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, perf_evlist__set_maps(&evlist->core, cpus, threads); evlist->workload.pid = -1; evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; + evlist->ctl_fd.fd = -1; + evlist->ctl_fd.ack = -1; + evlist->ctl_fd.pos = -1; } struct evlist *evlist__new(void) @@ -79,7 +82,7 @@ struct evlist *perf_evlist__new_default(void) { struct evlist *evlist = evlist__new(); - if (evlist && perf_evlist__add_default(evlist)) { + if (evlist && evlist__add_default(evlist)) { evlist__delete(evlist); evlist = NULL; } @@ -91,7 +94,7 @@ struct evlist *perf_evlist__new_dummy(void) { struct evlist *evlist = evlist__new(); - if (evlist && perf_evlist__add_dummy(evlist)) { + if (evlist && evlist__add_dummy(evlist)) { evlist__delete(evlist); evlist = NULL; } @@ -231,7 +234,7 @@ void perf_evlist__set_leader(struct evlist *evlist) } } -int __perf_evlist__add_default(struct evlist *evlist, bool precise) +int __evlist__add_default(struct evlist *evlist, bool precise) { struct evsel *evsel = evsel__new_cycles(precise); @@ -242,7 +245,7 @@ int __perf_evlist__add_default(struct evlist *evlist, bool precise) return 0; } -int perf_evlist__add_dummy(struct evlist *evlist) +int evlist__add_dummy(struct evlist *evlist) { struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, @@ -258,8 +261,7 @@ int perf_evlist__add_dummy(struct evlist *evlist) return 0; } -static int evlist__add_attrs(struct evlist *evlist, - struct perf_event_attr *attrs, size_t nr_attrs) +static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { struct evsel *evsel, *n; LIST_HEAD(head); @@ -282,8 +284,7 @@ out_delete_partial_list: return -1; } -int __perf_evlist__add_default_attrs(struct evlist *evlist, - struct perf_event_attr *attrs, size_t nr_attrs) +int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { size_t i; @@ -322,8 +323,7 @@ perf_evlist__find_tracepoint_by_name(struct evlist *evlist, return NULL; } -int perf_evlist__add_newtp(struct evlist *evlist, - const char *sys, const char *name, void *handler) +int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler) { struct evsel *evsel = evsel__newtp(sys, name); @@ -500,7 +500,7 @@ int perf_evlist__enable_event_idx(struct evlist *evlist, int evlist__add_pollfd(struct evlist *evlist, int fd) { - return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN); + return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN, fdarray_flag__default); } int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) @@ -540,7 +540,7 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) if (sid) return container_of(sid->evsel, struct evsel, core); - if (!perf_evlist__sample_id_all(evlist)) + if (!evlist__sample_id_all(evlist)) return evlist__first(evlist); return NULL; @@ -1088,7 +1088,7 @@ int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) return perf_evlist__append_tp_filter_pids(evlist, 1, &pid); } -bool perf_evlist__valid_sample_type(struct evlist *evlist) +bool evlist__valid_sample_type(struct evlist *evlist) { struct evsel *pos; @@ -1107,7 +1107,7 @@ bool perf_evlist__valid_sample_type(struct evlist *evlist) return true; } -u64 __perf_evlist__combined_sample_type(struct evlist *evlist) +u64 __evlist__combined_sample_type(struct evlist *evlist) { struct evsel *evsel; @@ -1120,13 +1120,13 @@ u64 __perf_evlist__combined_sample_type(struct evlist *evlist) return evlist->combined_sample_type; } -u64 perf_evlist__combined_sample_type(struct evlist *evlist) +u64 evlist__combined_sample_type(struct evlist *evlist) { evlist->combined_sample_type = 0; - return __perf_evlist__combined_sample_type(evlist); + return __evlist__combined_sample_type(evlist); } -u64 perf_evlist__combined_branch_type(struct evlist *evlist) +u64 evlist__combined_branch_type(struct evlist *evlist) { struct evsel *evsel; u64 branch_type = 0; @@ -1191,7 +1191,7 @@ out: return size; } -bool perf_evlist__valid_sample_id_all(struct evlist *evlist) +bool evlist__valid_sample_id_all(struct evlist *evlist) { struct evsel *first = evlist__first(evlist), *pos = first; @@ -1203,7 +1203,7 @@ bool perf_evlist__valid_sample_id_all(struct evlist *evlist) return true; } -bool perf_evlist__sample_id_all(struct evlist *evlist) +bool evlist__sample_id_all(struct evlist *evlist) { struct evsel *first = evlist__first(evlist); return first->core.attr.sample_id_all; @@ -1464,8 +1464,7 @@ int perf_evlist__parse_sample_timestamp(struct evlist *evlist, return evsel__parse_sample_timestamp(evsel, event, timestamp); } -int perf_evlist__strerror_open(struct evlist *evlist, - int err, char *buf, size_t size) +int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size) { int printed, value; char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); @@ -1518,7 +1517,7 @@ out_default: return 0; } -int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) +int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) { char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0; @@ -1727,3 +1726,143 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, } return leader; } + +int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack) +{ + if (fd == -1) { + pr_debug("Control descriptor is not initialized\n"); + return 0; + } + + evlist->ctl_fd.pos = perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN, + fdarray_flag__nonfilterable); + if (evlist->ctl_fd.pos < 0) { + evlist->ctl_fd.pos = -1; + pr_err("Failed to add ctl fd entry: %m\n"); + return -1; + } + + evlist->ctl_fd.fd = fd; + evlist->ctl_fd.ack = ack; + + return 0; +} + +bool evlist__ctlfd_initialized(struct evlist *evlist) +{ + return evlist->ctl_fd.pos >= 0; +} + +int evlist__finalize_ctlfd(struct evlist *evlist) +{ + struct pollfd *entries = evlist->core.pollfd.entries; + + if (!evlist__ctlfd_initialized(evlist)) + return 0; + + entries[evlist->ctl_fd.pos].fd = -1; + entries[evlist->ctl_fd.pos].events = 0; + entries[evlist->ctl_fd.pos].revents = 0; + + evlist->ctl_fd.pos = -1; + evlist->ctl_fd.ack = -1; + evlist->ctl_fd.fd = -1; + + return 0; +} + +static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, + char *cmd_data, size_t data_size) +{ + int err; + char c; + size_t bytes_read = 0; + + memset(cmd_data, 0, data_size); + data_size--; + + do { + err = read(evlist->ctl_fd.fd, &c, 1); + if (err > 0) { + if (c == '\n' || c == '\0') + break; + cmd_data[bytes_read++] = c; + if (bytes_read == data_size) + break; + } else { + if (err == -1) + pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd); + break; + } + } while (1); + + pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data, + bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0"); + + if (err > 0) { + if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG, + (sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_ENABLE; + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG, + (sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_DISABLE; + } + } + + return err; +} + +static int evlist__ctlfd_ack(struct evlist *evlist) +{ + int err; + + if (evlist->ctl_fd.ack == -1) + return 0; + + err = write(evlist->ctl_fd.ack, EVLIST_CTL_CMD_ACK_TAG, + sizeof(EVLIST_CTL_CMD_ACK_TAG)); + if (err == -1) + pr_err("failed to write to ctl_ack_fd %d: %m\n", evlist->ctl_fd.ack); + + return err; +} + +int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) +{ + int err = 0; + char cmd_data[EVLIST_CTL_CMD_MAX_LEN]; + int ctlfd_pos = evlist->ctl_fd.pos; + struct pollfd *entries = evlist->core.pollfd.entries; + + if (!evlist__ctlfd_initialized(evlist) || !entries[ctlfd_pos].revents) + return 0; + + if (entries[ctlfd_pos].revents & POLLIN) { + err = evlist__ctlfd_recv(evlist, cmd, cmd_data, + EVLIST_CTL_CMD_MAX_LEN); + if (err > 0) { + switch (*cmd) { + case EVLIST_CTL_CMD_ENABLE: + evlist__enable(evlist); + break; + case EVLIST_CTL_CMD_DISABLE: + evlist__disable(evlist); + break; + case EVLIST_CTL_CMD_ACK: + case EVLIST_CTL_CMD_UNSUPPORTED: + default: + pr_debug("ctlfd: unsupported %d\n", *cmd); + break; + } + if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED)) + evlist__ctlfd_ack(evlist); + } + } + + if (entries[ctlfd_pos].revents & (POLLHUP | POLLERR)) + evlist__finalize_ctlfd(evlist); + else + entries[ctlfd_pos].revents = 0; + + return err; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a8081dfc19cf..c73f7f7f120b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -74,6 +74,11 @@ struct evlist { pthread_t th; volatile int done; } thread; + struct { + int fd; /* control file descriptor */ + int ack; /* ack file descriptor for control commands */ + int pos; /* index at evlist core object to check signals */ + } ctl_fd; }; struct evsel_str_handler { @@ -92,20 +97,20 @@ void evlist__delete(struct evlist *evlist); void evlist__add(struct evlist *evlist, struct evsel *entry); void evlist__remove(struct evlist *evlist, struct evsel *evsel); -int __perf_evlist__add_default(struct evlist *evlist, bool precise); +int __evlist__add_default(struct evlist *evlist, bool precise); -static inline int perf_evlist__add_default(struct evlist *evlist) +static inline int evlist__add_default(struct evlist *evlist) { - return __perf_evlist__add_default(evlist, true); + return __evlist__add_default(evlist, true); } -int __perf_evlist__add_default_attrs(struct evlist *evlist, +int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); -#define perf_evlist__add_default_attrs(evlist, array) \ - __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) +#define evlist__add_default_attrs(evlist, array) \ + __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) -int perf_evlist__add_dummy(struct evlist *evlist); +int evlist__add_dummy(struct evlist *evlist); int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, @@ -116,8 +121,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target); void perf_evlist__stop_sb_thread(struct evlist *evlist); -int perf_evlist__add_newtp(struct evlist *evlist, - const char *sys, const char *name, void *handler); +int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); int __evlist__set_tracepoints_handlers(struct evlist *evlist, const struct evsel_str_handler *assocs, @@ -219,10 +223,10 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct evlist *evlist); -u64 __perf_evlist__combined_sample_type(struct evlist *evlist); -u64 perf_evlist__combined_sample_type(struct evlist *evlist); -u64 perf_evlist__combined_branch_type(struct evlist *evlist); -bool perf_evlist__sample_id_all(struct evlist *evlist); +u64 __evlist__combined_sample_type(struct evlist *evlist); +u64 evlist__combined_sample_type(struct evlist *evlist); +u64 evlist__combined_branch_type(struct evlist *evlist); +bool evlist__sample_id_all(struct evlist *evlist); u16 perf_evlist__id_hdr_size(struct evlist *evlist); int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, @@ -232,8 +236,8 @@ int perf_evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp); -bool perf_evlist__valid_sample_type(struct evlist *evlist); -bool perf_evlist__valid_sample_id_all(struct evlist *evlist); +bool evlist__valid_sample_type(struct evlist *evlist); +bool evlist__valid_sample_id_all(struct evlist *evlist); bool perf_evlist__valid_read_format(struct evlist *evlist); void perf_evlist__splice_list_tail(struct evlist *evlist, @@ -258,8 +262,8 @@ static inline struct evsel *evlist__last(struct evlist *evlist) return container_of(evsel, struct evsel, core); } -int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); -int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); +int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); +int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); bool perf_evlist__can_select_event(struct evlist *evlist, const char *str); void perf_evlist__to_front(struct evlist *evlist, @@ -356,4 +360,25 @@ void perf_evlist__force_leader(struct evlist *evlist); struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, struct evsel *evsel, bool close); +#define EVLIST_CTL_CMD_ENABLE_TAG "enable" +#define EVLIST_CTL_CMD_DISABLE_TAG "disable" +#define EVLIST_CTL_CMD_ACK_TAG "ack\n" + +#define EVLIST_CTL_CMD_MAX_LEN 64 + +enum evlist_ctl_cmd { + EVLIST_CTL_CMD_UNSUPPORTED = 0, + EVLIST_CTL_CMD_ENABLE, + EVLIST_CTL_CMD_DISABLE, + EVLIST_CTL_CMD_ACK +}; + +int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack); +int evlist__finalize_ctlfd(struct evlist *evlist); +bool evlist__ctlfd_initialized(struct evlist *evlist); +int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd); + +#define EVLIST_ENABLED_MSG "Events enabled\n" +#define EVLIST_DISABLED_MSG "Events disabled\n" + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ef802f6d40c1..fd865002cbbd 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1014,12 +1014,14 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (callchain && callchain->enabled && !evsel->no_aux_samples) evsel__config_callchain(evsel, opts, callchain); - if (opts->sample_intr_regs && !evsel->no_aux_samples) { + if (opts->sample_intr_regs && !evsel->no_aux_samples && + !evsel__is_dummy_event(evsel)) { attr->sample_regs_intr = opts->sample_intr_regs; evsel__set_sample_bit(evsel, REGS_INTR); } - if (opts->sample_user_regs && !evsel->no_aux_samples) { + if (opts->sample_user_regs && !evsel->no_aux_samples && + !evsel__is_dummy_event(evsel)) { attr->sample_regs_user |= opts->sample_user_regs; evsel__set_sample_bit(evsel, REGS_USER); } @@ -1064,7 +1066,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; - attr->ksymbol = track && !perf_missing_features.ksymbol; + /* + * ksymbol is tracked separately with text poke because it needs to be + * system wide and enabled immediately. + */ + if (!opts->text_poke) + attr->ksymbol = track && !perf_missing_features.ksymbol; attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf; if (opts->record_namespaces) @@ -2495,8 +2502,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg + printed, size - printed, "Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open\n" - "access to performance monitoring and observability operations for users\n" - "without CAP_PERFMON or CAP_SYS_ADMIN Linux capability.\n" + "access to performance monitoring and observability operations for processes\n" + "without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability.\n" + "More information can be found at 'Perf events and tool security' document:\n" + "https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html\n" "perf_event_paranoid setting is %d:\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" @@ -2528,6 +2537,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: + if (evsel->core.attr.aux_output) + return scnprintf(msg, size, + "%s: PMU Hardware doesn't support 'aux_output' feature", + evsel__name(evsel)); if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index f64ab91c432b..53482ef53c41 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -1,10 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdbool.h> #include <assert.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include "metricgroup.h" +#include "debug.h" #include "expr.h" #include "expr-bison.h" #include "expr-flex.h" #include <linux/kernel.h> +#include <linux/zalloc.h> +#include <ctype.h> #ifdef PARSER_DEBUG extern int expr_debug; @@ -30,35 +37,144 @@ static bool key_equal(const void *key1, const void *key2, } /* Caller must make sure id is allocated */ -int expr__add_id(struct expr_parse_ctx *ctx, const char *name, double val) +int expr__add_id(struct expr_parse_ctx *ctx, const char *id) { - double *val_ptr = NULL, *old_val = NULL; + struct expr_id_data *data_ptr = NULL, *old_data = NULL; char *old_key = NULL; int ret; - if (val != 0.0) { - val_ptr = malloc(sizeof(double)); - if (!val_ptr) - return -ENOMEM; - *val_ptr = val; + data_ptr = malloc(sizeof(*data_ptr)); + if (!data_ptr) + return -ENOMEM; + + data_ptr->parent = ctx->parent; + + ret = hashmap__set(&ctx->ids, id, data_ptr, + (const void **)&old_key, (void **)&old_data); + if (ret) + free(data_ptr); + free(old_key); + free(old_data); + return ret; +} + +/* Caller must make sure id is allocated */ +int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) +{ + struct expr_id_data *data_ptr = NULL, *old_data = NULL; + char *old_key = NULL; + int ret; + + data_ptr = malloc(sizeof(*data_ptr)); + if (!data_ptr) + return -ENOMEM; + data_ptr->val = val; + data_ptr->is_ref = false; + + ret = hashmap__set(&ctx->ids, id, data_ptr, + (const void **)&old_key, (void **)&old_data); + if (ret) + free(data_ptr); + free(old_key); + free(old_data); + return ret; +} + +int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) +{ + struct expr_id_data *data_ptr = NULL, *old_data = NULL; + char *old_key = NULL; + char *name, *p; + int ret; + + data_ptr = zalloc(sizeof(*data_ptr)); + if (!data_ptr) + return -ENOMEM; + + name = strdup(ref->metric_name); + if (!name) { + free(data_ptr); + return -ENOMEM; } - ret = hashmap__set(&ctx->ids, name, val_ptr, - (const void **)&old_key, (void **)&old_val); + + /* + * The jevents tool converts all metric expressions + * to lowercase, including metric references, hence + * we need to add lowercase name for metric, so it's + * properly found. + */ + for (p = name; *p; p++) + *p = tolower(*p); + + /* + * Intentionally passing just const char pointers, + * originally from 'struct pmu_event' object. + * We don't need to change them, so there's no + * need to create our own copy. + */ + data_ptr->ref.metric_name = ref->metric_name; + data_ptr->ref.metric_expr = ref->metric_expr; + data_ptr->ref.counted = false; + data_ptr->is_ref = true; + + ret = hashmap__set(&ctx->ids, name, data_ptr, + (const void **)&old_key, (void **)&old_data); + if (ret) + free(data_ptr); + + pr_debug2("adding ref metric %s: %s\n", + ref->metric_name, ref->metric_expr); + free(old_key); - free(old_val); + free(old_data); return ret; } -int expr__get_id(struct expr_parse_ctx *ctx, const char *id, double *val_ptr) +int expr__get_id(struct expr_parse_ctx *ctx, const char *id, + struct expr_id_data **data) +{ + return hashmap__find(&ctx->ids, id, (void **)data) ? 0 : -1; +} + +int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, + struct expr_id_data **datap) { - double *data; + struct expr_id_data *data; - if (!hashmap__find(&ctx->ids, id, (void **)&data)) + if (expr__get_id(ctx, id, datap) || !*datap) { + pr_debug("%s not found\n", id); return -1; - *val_ptr = (data == NULL) ? 0.0 : *data; + } + + data = *datap; + + pr_debug2("lookup: is_ref %d, counted %d, val %f: %s\n", + data->is_ref, data->ref.counted, data->val, id); + + if (data->is_ref && !data->ref.counted) { + data->ref.counted = true; + pr_debug("processing metric: %s ENTRY\n", id); + if (expr__parse(&data->val, ctx, data->ref.metric_expr, 1)) { + pr_debug("%s failed to count\n", id); + return -1; + } + pr_debug("processing metric: %s EXIT: %f\n", id, data->val); + } + return 0; } +void expr__del_id(struct expr_parse_ctx *ctx, const char *id) +{ + struct expr_id_data *old_val = NULL; + char *old_key = NULL; + + hashmap__delete(&ctx->ids, id, + (const void **)&old_key, (void **)&old_val); + free(old_key); + free(old_val); +} + void expr__ctx_init(struct expr_parse_ctx *ctx) { hashmap__init(&ctx->ids, key_hash, key_equal, NULL); @@ -88,6 +204,8 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, void *scanner; int ret; + pr_debug2("parsing metric: %s\n", expr); + ret = expr_lex_init_extra(&scanner_ctx, &scanner); if (ret) return ret; @@ -116,16 +234,10 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx, int expr__find_other(const char *expr, const char *one, struct expr_parse_ctx *ctx, int runtime) { - double *old_val = NULL; - char *old_key = NULL; int ret = __expr__parse(NULL, ctx, expr, EXPR_OTHER, runtime); - if (one) { - hashmap__delete(&ctx->ids, one, - (const void **)&old_key, (void **)&old_val); - free(old_key); - free(old_val); - } + if (one) + expr__del_id(ctx, one); return ret; } diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 8a2c1074f90f..fc2b5e824a66 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -11,8 +11,30 @@ #include "util/hashmap.h" //#endif +struct metric_ref; + +struct expr_id { + char *id; + struct expr_id *parent; +}; + struct expr_parse_ctx { - struct hashmap ids; + struct hashmap ids; + struct expr_id *parent; +}; + +struct expr_id_data { + union { + double val; + struct { + const char *metric_name; + const char *metric_expr; + bool counted; + } ref; + struct expr_id *parent; + }; + + bool is_ref; }; struct expr_scanner_ctx { @@ -22,8 +44,14 @@ struct expr_scanner_ctx { void expr__ctx_init(struct expr_parse_ctx *ctx); void expr__ctx_clear(struct expr_parse_ctx *ctx); -int expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val); -int expr__get_id(struct expr_parse_ctx *ctx, const char *id, double *val_ptr); +void expr__del_id(struct expr_parse_ctx *ctx, const char *id); +int expr__add_id(struct expr_parse_ctx *ctx, const char *id); +int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); +int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref); +int expr__get_id(struct expr_parse_ctx *ctx, const char *id, + struct expr_id_data **data); +int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, + struct expr_id_data **datap); int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime); int expr__find_other(const char *expr, const char *one, diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index f397bf8b1a48..13e5e3c75f56 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -100,6 +100,7 @@ symbol ({spec}|{sym})+ } } +d_ratio { return D_RATIO; } max { return MAX; } min { return MIN; } if { return IF; } @@ -110,6 +111,8 @@ else { return ELSE; } "|" { return '|'; } "^" { return '^'; } "&" { return '&'; } +"<" { return '<'; } +">" { return '>'; } "-" { return '-'; } "+" { return '+'; } "*" { return '*'; } diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index bf3e898e3055..d34b370391c6 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -10,6 +10,14 @@ #include "smt.h" #include <string.h> +static double d_ratio(double val0, double val1) +{ + if (val1 == 0) { + return 0; + } + return val0 / val1; +} + %} %define api.pure full @@ -28,11 +36,12 @@ %token <num> NUMBER %token <str> ID %destructor { free ($$); } <str> -%token MIN MAX IF ELSE SMT_ON +%token MIN MAX IF ELSE SMT_ON D_RATIO %left MIN MAX IF %left '|' %left '^' %left '&' +%left '<' '>' %left '-' '+' %left '*' '/' '%' %left NEG NOT @@ -60,11 +69,12 @@ all_other: all_other other other: ID { - expr__add_id(ctx, $1, 0.0); + expr__add_id(ctx, $1); } | MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')' | ',' - +| +'<' | '>' | D_RATIO all_expr: if_expr { *final_val = $1; } ; @@ -75,16 +85,22 @@ if_expr: ; expr: NUMBER - | ID { if (expr__get_id(ctx, $1, &$$)) { - pr_debug("%s not found\n", $1); + | ID { + struct expr_id_data *data; + + if (expr__resolve_id(ctx, $1, &data)) { + free($1); + YYABORT; + } + + $$ = data->val; free($1); - YYABORT; - } - free($1); } | expr '|' expr { $$ = (long)$1 | (long)$3; } | expr '&' expr { $$ = (long)$1 & (long)$3; } | expr '^' expr { $$ = (long)$1 ^ (long)$3; } + | expr '<' expr { $$ = $1 < $3; } + | expr '>' expr { $$ = $1 > $3; } | expr '+' expr { $$ = $1 + $3; } | expr '-' expr { $$ = $1 - $3; } | expr '*' expr { $$ = $1 * $3; } @@ -105,6 +121,7 @@ expr: NUMBER | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } | SMT_ON { $$ = smt_on() > 0; } + | D_RATIO '(' expr ',' expr ')' { $$ = d_ratio($3,$5); } ; %% diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 7a67d017d72c..9cf4efdcbbbd 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -46,6 +46,7 @@ #include "util/util.h" // perf_exe() #include "cputopo.h" #include "bpf-event.h" +#include "clockid.h" #include <linux/ctype.h> #include <internal/lib.h> @@ -891,8 +892,42 @@ static int write_auxtrace(struct feat_fd *ff, static int write_clockid(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { - return do_write(ff, &ff->ph->env.clockid_res_ns, - sizeof(ff->ph->env.clockid_res_ns)); + return do_write(ff, &ff->ph->env.clock.clockid_res_ns, + sizeof(ff->ph->env.clock.clockid_res_ns)); +} + +static int write_clock_data(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + u64 *data64; + u32 data32; + int ret; + + /* version */ + data32 = 1; + + ret = do_write(ff, &data32, sizeof(data32)); + if (ret < 0) + return ret; + + /* clockid */ + data32 = ff->ph->env.clock.clockid; + + ret = do_write(ff, &data32, sizeof(data32)); + if (ret < 0) + return ret; + + /* TOD ref time */ + data64 = &ff->ph->env.clock.tod_ns; + + ret = do_write(ff, data64, sizeof(*data64)); + if (ret < 0) + return ret; + + /* clockid ref time */ + data64 = &ff->ph->env.clock.clockid_ns; + + return do_write(ff, data64, sizeof(*data64)); } static int write_dir_format(struct feat_fd *ff, @@ -1546,7 +1581,50 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp) static void print_clockid(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n", - ff->ph->env.clockid_res_ns * 1000); + ff->ph->env.clock.clockid_res_ns * 1000); +} + +static void print_clock_data(struct feat_fd *ff, FILE *fp) +{ + struct timespec clockid_ns; + char tstr[64], date[64]; + struct timeval tod_ns; + clockid_t clockid; + struct tm ltime; + u64 ref; + + if (!ff->ph->env.clock.enabled) { + fprintf(fp, "# reference time disabled\n"); + return; + } + + /* Compute TOD time. */ + ref = ff->ph->env.clock.tod_ns; + tod_ns.tv_sec = ref / NSEC_PER_SEC; + ref -= tod_ns.tv_sec * NSEC_PER_SEC; + tod_ns.tv_usec = ref / NSEC_PER_USEC; + + /* Compute clockid time. */ + ref = ff->ph->env.clock.clockid_ns; + clockid_ns.tv_sec = ref / NSEC_PER_SEC; + ref -= clockid_ns.tv_sec * NSEC_PER_SEC; + clockid_ns.tv_nsec = ref; + + clockid = ff->ph->env.clock.clockid; + + if (localtime_r(&tod_ns.tv_sec, <ime) == NULL) + snprintf(tstr, sizeof(tstr), "<error>"); + else { + strftime(date, sizeof(date), "%F %T", <ime); + scnprintf(tstr, sizeof(tstr), "%s.%06d", + date, (int) tod_ns.tv_usec); + } + + fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid); + fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n", + tstr, tod_ns.tv_sec, (int) tod_ns.tv_usec, + clockid_ns.tv_sec, clockid_ns.tv_nsec, + clockid_name(clockid)); } static void print_dir_format(struct feat_fd *ff, FILE *fp) @@ -1978,7 +2056,7 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, struct machine *machine; u16 cpumode; struct dso *dso; - enum dso_kernel_type dso_type; + enum dso_space_type dso_space; machine = perf_session__findnew_machine(session, bev->pid); if (!machine) @@ -1988,14 +2066,14 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - dso_type = DSO_TYPE_KERNEL; + dso_space = DSO_SPACE__KERNEL; break; case PERF_RECORD_MISC_GUEST_KERNEL: - dso_type = DSO_TYPE_GUEST_KERNEL; + dso_space = DSO_SPACE__KERNEL_GUEST; break; case PERF_RECORD_MISC_USER: case PERF_RECORD_MISC_GUEST_USER: - dso_type = DSO_TYPE_USER; + dso_space = DSO_SPACE__USER; break; default: goto out; @@ -2007,14 +2085,13 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, dso__set_build_id(dso, &bev->build_id); - if (dso_type != DSO_TYPE_USER) { + if (dso_space != DSO_SPACE__USER) { struct kmod_path m = { .name = NULL, }; if (!kmod_path__parse_name(&m, filename) && m.kmod) dso__set_module_info(dso, &m, machine); - else - dso->kernel = dso_type; + dso->kernel = dso_space; free(m.name); } @@ -2732,9 +2809,43 @@ out: static int process_clockid(struct feat_fd *ff, void *data __maybe_unused) { - if (do_read_u64(ff, &ff->ph->env.clockid_res_ns)) + if (do_read_u64(ff, &ff->ph->env.clock.clockid_res_ns)) + return -1; + + return 0; +} + +static int process_clock_data(struct feat_fd *ff, + void *_data __maybe_unused) +{ + u32 data32; + u64 data64; + + /* version */ + if (do_read_u32(ff, &data32)) + return -1; + + if (data32 != 1) + return -1; + + /* clockid */ + if (do_read_u32(ff, &data32)) + return -1; + + ff->ph->env.clock.clockid = data32; + + /* TOD ref time */ + if (do_read_u64(ff, &data64)) + return -1; + + ff->ph->env.clock.tod_ns = data64; + + /* clockid ref time */ + if (do_read_u64(ff, &data64)) return -1; + ff->ph->env.clock.clockid_ns = data64; + ff->ph->env.clock.enabled = true; return 0; } @@ -3008,6 +3119,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(BPF_BTF, bpf_btf, false), FEAT_OPR(COMPRESSED, compressed, false), FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false), + FEAT_OPR(CLOCK_DATA, clock_data, false), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 650bd1c7a99b..2aca71763ecf 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -44,6 +44,7 @@ enum { HEADER_BPF_BTF, HEADER_COMPRESSED, HEADER_CPU_PMU_CAPS, + HEADER_CLOCK_DATA, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index f8ccfd6be0ee..697513f35154 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -55,6 +55,7 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_TIP_PGD, INTEL_PT_STATE_FUP, INTEL_PT_STATE_FUP_NO_TIP, + INTEL_PT_STATE_RESAMPLE, }; static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) @@ -65,6 +66,7 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) case INTEL_PT_STATE_ERR_RESYNC: case INTEL_PT_STATE_IN_SYNC: case INTEL_PT_STATE_TNT_CONT: + case INTEL_PT_STATE_RESAMPLE: return true; case INTEL_PT_STATE_TNT: case INTEL_PT_STATE_TIP: @@ -109,6 +111,9 @@ struct intel_pt_decoder { bool fixup_last_mtc; bool have_last_ip; bool in_psb; + bool hop; + bool hop_psb_fup; + bool leap; enum intel_pt_param_flags flags; uint64_t pos; uint64_t last_ip; @@ -235,6 +240,8 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->data = params->data; decoder->return_compression = params->return_compression; decoder->branch_enable = params->branch_enable; + decoder->hop = params->quick >= 1; + decoder->leap = params->quick >= 2; decoder->flags = params->flags; @@ -275,6 +282,9 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) intel_pt_log("timestamp: tsc_ctc_mult %u\n", decoder->tsc_ctc_mult); intel_pt_log("timestamp: tsc_slip %#x\n", decoder->tsc_slip); + if (decoder->hop) + intel_pt_log("Hop mode: decoding FUP and TIPs, but not TNT\n"); + return decoder; } @@ -1164,6 +1174,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (intel_pt_fup_event(decoder)) return 0; return -EAGAIN; @@ -1729,8 +1740,14 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - if (decoder->packet.count) + if (decoder->packet.count) { intel_pt_set_last_ip(decoder); + if (decoder->hop) { + /* Act on FUP at PSBEND */ + decoder->ip = decoder->last_ip; + decoder->hop_psb_fup = true; + } + } break; case INTEL_PT_MODE_TSX: @@ -1874,6 +1891,127 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) } } +static int intel_pt_resample(struct intel_pt_decoder *decoder) +{ + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->state.type = INTEL_PT_INSTRUCTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; +} + +#define HOP_PROCESS 0 +#define HOP_IGNORE 1 +#define HOP_RETURN 2 +#define HOP_AGAIN 3 + +static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder); + +/* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */ +static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err) +{ + /* Leap from PSB to PSB, getting ip from FUP within PSB+ */ + if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) { + *err = intel_pt_scan_for_psb(decoder); + if (*err) + return HOP_RETURN; + } + + switch (decoder->packet.type) { + case INTEL_PT_TNT: + return HOP_IGNORE; + + case INTEL_PT_TIP_PGD: + if (!decoder->packet.count) + return HOP_IGNORE; + intel_pt_set_ip(decoder); + decoder->state.type |= INTEL_PT_TRACE_END; + decoder->state.from_ip = 0; + decoder->state.to_ip = decoder->ip; + return HOP_RETURN; + + case INTEL_PT_TIP: + if (!decoder->packet.count) + return HOP_IGNORE; + intel_pt_set_ip(decoder); + decoder->state.type = INTEL_PT_INSTRUCTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return HOP_RETURN; + + case INTEL_PT_FUP: + if (!decoder->packet.count) + return HOP_IGNORE; + intel_pt_set_ip(decoder); + if (intel_pt_fup_event(decoder)) + return HOP_RETURN; + if (!decoder->branch_enable) + *no_tip = true; + if (*no_tip) { + decoder->state.type = INTEL_PT_INSTRUCTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return HOP_RETURN; + } + *err = intel_pt_walk_fup_tip(decoder); + if (!*err) + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + return HOP_RETURN; + + case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + decoder->hop_psb_fup = false; + *err = intel_pt_walk_psbend(decoder); + if (*err == -EAGAIN) + return HOP_AGAIN; + if (*err) + return HOP_RETURN; + if (decoder->hop_psb_fup) { + decoder->hop_psb_fup = false; + decoder->state.type = INTEL_PT_INSTRUCTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return HOP_RETURN; + } + if (decoder->cbr != decoder->cbr_seen) { + decoder->state.type = 0; + return HOP_RETURN; + } + return HOP_IGNORE; + + case INTEL_PT_BAD: + case INTEL_PT_PAD: + case INTEL_PT_TIP_PGE: + case INTEL_PT_TSC: + case INTEL_PT_TMA: + case INTEL_PT_MODE_EXEC: + case INTEL_PT_MODE_TSX: + case INTEL_PT_MTC: + case INTEL_PT_CYC: + case INTEL_PT_VMCS: + case INTEL_PT_PSBEND: + case INTEL_PT_CBR: + case INTEL_PT_TRACESTOP: + case INTEL_PT_PIP: + case INTEL_PT_OVF: + case INTEL_PT_MNT: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: + case INTEL_PT_BBP: + case INTEL_PT_BIP: + case INTEL_PT_BEP: + case INTEL_PT_BEP_IP: + default: + return HOP_PROCESS; + } +} + static int intel_pt_walk_trace(struct intel_pt_decoder *decoder) { bool no_tip = false; @@ -1884,6 +2022,19 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder) if (err) return err; next: + if (decoder->hop) { + switch (intel_pt_hop_trace(decoder, &no_tip, &err)) { + case HOP_IGNORE: + continue; + case HOP_RETURN: + return err; + case HOP_AGAIN: + goto next; + default: + break; + } + } + switch (decoder->packet.type) { case INTEL_PT_TNT: if (!decoder->packet.count) @@ -1913,6 +2064,12 @@ next: decoder->state.from_ip = 0; decoder->state.to_ip = decoder->ip; decoder->state.type |= INTEL_PT_TRACE_BEGIN; + /* + * In hop mode, resample to get the to_ip as an + * "instruction" sample. + */ + if (decoder->hop) + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; return 0; } @@ -1942,17 +2099,13 @@ next: } if (decoder->set_fup_mwait) no_tip = true; + if (no_tip) + decoder->pkt_state = INTEL_PT_STATE_FUP_NO_TIP; + else + decoder->pkt_state = INTEL_PT_STATE_FUP; err = intel_pt_walk_fup(decoder); - if (err != -EAGAIN) { - if (err) - return err; - if (no_tip) - decoder->pkt_state = - INTEL_PT_STATE_FUP_NO_TIP; - else - decoder->pkt_state = INTEL_PT_STATE_FUP; - return 0; - } + if (err != -EAGAIN) + return err; if (no_tip) { no_tip = false; break; @@ -1980,8 +2133,10 @@ next: * possibility of another CBR change that gets caught up * in the PSB+. */ - if (decoder->cbr != decoder->cbr_seen) + if (decoder->cbr != decoder->cbr_seen) { + decoder->state.type = 0; return 0; + } break; case INTEL_PT_PIP: @@ -2022,8 +2177,10 @@ next: case INTEL_PT_CBR: intel_pt_calc_cbr(decoder); - if (decoder->cbr != decoder->cbr_seen) + if (decoder->cbr != decoder->cbr_seen) { + decoder->state.type = 0; return 0; + } break; case INTEL_PT_MODE_EXEC: @@ -2032,7 +2189,7 @@ next: case INTEL_PT_MODE_TSX: /* MODE_TSX need not be followed by FUP */ - if (!decoder->pge) { + if (!decoder->pge || decoder->in_psb) { intel_pt_update_in_tx(decoder); break; } @@ -2423,7 +2580,11 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) if (err) return err; - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + /* In hop mode, resample to get the to_ip as an "instruction" sample */ + if (decoder->hop) + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + else + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->overflow = false; decoder->state.from_ip = 0; @@ -2531,6 +2692,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); +leap: err = intel_pt_scan_for_psb(decoder); if (err) return err; @@ -2544,7 +2706,20 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (decoder->ip) { decoder->state.type = 0; /* Do not have a sample */ - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + /* + * In hop mode, resample to get the PSB FUP ip as an + * "instruction" sample. + */ + if (decoder->hop) + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + else + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + } else if (decoder->leap) { + /* + * In leap mode, only PSB+ is decoded, so keeping leaping to the + * next PSB until there is an ip. + */ + goto leap; } else { return intel_pt_sync_ip(decoder); } @@ -2599,19 +2774,18 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_tip(decoder); break; case INTEL_PT_STATE_FUP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_fup_tip(decoder); - else if (!err) - decoder->pkt_state = INTEL_PT_STATE_FUP; break; case INTEL_PT_STATE_FUP_NO_TIP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); break; + case INTEL_PT_STATE_RESAMPLE: + err = intel_pt_resample(decoder); + break; default: err = intel_pt_bug(decoder); break; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index e289e463d635..8645fc265481 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -250,6 +250,7 @@ struct intel_pt_params { uint32_t tsc_ctc_ratio_n; uint32_t tsc_ctc_ratio_d; enum intel_pt_param_flags flags; + unsigned int quick; }; struct intel_pt_decoder; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index cb3c1e569a2d..2a8d245351e7 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -236,7 +236,7 @@ static void intel_pt_log_event(union perf_event *event) if (!intel_pt_enable_logging || !f) return; - perf_event__fprintf(event, f); + perf_event__fprintf(event, NULL, f); } static void intel_pt_dump_sample(struct perf_session *session, @@ -249,6 +249,24 @@ static void intel_pt_dump_sample(struct perf_session *session, intel_pt_dump(pt, sample->aux_sample.data, sample->aux_sample.size); } +static bool intel_pt_log_events(struct intel_pt *pt, u64 tm) +{ + struct perf_time_interval *range = pt->synth_opts.ptime_range; + int n = pt->synth_opts.range_num; + + if (pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS) + return true; + + if (pt->synth_opts.log_minus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS) + return false; + + /* perf_time__ranges_skip_sample does not work if time is zero */ + if (!tm) + tm = 1; + + return !n || !perf_time__ranges_skip_sample(range, n, tm); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -520,6 +538,17 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset) return auxtrace_cache__lookup(dso->auxtrace_cache, offset); } +static void intel_pt_cache_invalidate(struct dso *dso, struct machine *machine, + u64 offset) +{ + struct auxtrace_cache *c = intel_pt_cache(dso, machine); + + if (!c) + return; + + auxtrace_cache__remove(dso->auxtrace_cache, offset); +} + static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip) { return ip >= pt->kernel_start ? @@ -1001,6 +1030,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.mtc_period = intel_pt_mtc_period(pt); params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n; params.tsc_ctc_ratio_d = pt->tsc_ctc_ratio_d; + params.quick = pt->synth_opts.quick; if (pt->filts.cnt > 0) params.pgd_ip = intel_pt_pgd_ip; @@ -1394,7 +1424,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) sample.id = ptq->pt->instructions_id; sample.stream_id = ptq->pt->instructions_id; - sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; + if (pt->synth_opts.quick) + sample.period = 1; + else + sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt; if (sample.cyc_cnt) { @@ -1852,6 +1885,15 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, char msg[MAX_AUXTRACE_ERROR_MSG]; int err; + if (pt->synth_opts.error_minus_flags) { + if (code == INTEL_PT_ERR_OVR && + pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_OVERFLOW) + return 0; + if (code == INTEL_PT_ERR_LOST && + pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_DATA_LOST) + return 0; + } + intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG); auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE, @@ -2566,10 +2608,6 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event, return -EINVAL; } - intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n", - cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time, - &pt->tc)); - ret = intel_pt_sync_switch(pt, cpu, tid, sample->time); if (ret <= 0) return ret; @@ -2594,6 +2632,67 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt, event->itrace_start.tid); } +static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) +{ + if (!al->map || addr < al->map->start || addr >= al->map->end) { + if (!thread__find_map(thread, cpumode, addr, al)) + return -1; + } + + return 0; +} + +/* Invalidate all instruction cache entries that overlap the text poke */ +static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + u64 addr = event->text_poke.addr + event->text_poke.new_len - 1; + /* Assume text poke begins in a basic block no more than 4096 bytes */ + int cnt = 4096 + event->text_poke.new_len; + struct thread *thread = pt->unknown_thread; + struct addr_location al = { .map = NULL }; + struct machine *machine = pt->machine; + struct intel_pt_cache_entry *e; + u64 offset; + + if (!event->text_poke.new_len) + return 0; + + for (; cnt; cnt--, addr--) { + if (intel_pt_find_map(thread, cpumode, addr, &al)) { + if (addr < event->text_poke.addr) + return 0; + continue; + } + + if (!al.map->dso || !al.map->dso->auxtrace_cache) + continue; + + offset = al.map->map_ip(al.map, addr); + + e = intel_pt_cache_lookup(al.map->dso, machine, offset); + if (!e) + continue; + + if (addr + e->byte_cnt + e->length <= event->text_poke.addr) { + /* + * No overlap. Working backwards there cannot be another + * basic block that overlaps the text poke if there is a + * branch instruction before the text poke address. + */ + if (e->branch != INTEL_PT_BR_NO_BRANCH) + return 0; + } else { + intel_pt_cache_invalidate(al.map->dso, machine, offset); + intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n", + al.map->dso->long_name, addr); + } + } + + return 0; +} + static int intel_pt_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -2662,9 +2761,14 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", - event->header.type, sample->cpu, sample->time, timestamp); - intel_pt_log_event(event); + if (!err && event->header.type == PERF_RECORD_TEXT_POKE) + err = intel_pt_text_poke(pt, event); + + if (intel_pt_enable_logging && intel_pt_log_events(pt, sample->time)) { + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); + } return err; } diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 32bb05e03fb2..0804308ef285 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -26,6 +26,7 @@ #include "jit.h" #include "jitdump.h" #include "genelf.h" +#include "thread.h" #include <linux/ctype.h> #include <linux/zalloc.h> @@ -749,6 +750,28 @@ jit_detect(char *mmap_name, pid_t pid) return 0; } +static void jit_add_pid(struct machine *machine, pid_t pid) +{ + struct thread *thread = machine__findnew_thread(machine, pid, pid); + + if (!thread) { + pr_err("%s: thread %d not found or created\n", __func__, pid); + return; + } + + thread->priv = (void *)1; +} + +static bool jit_has_pid(struct machine *machine, pid_t pid) +{ + struct thread *thread = machine__find_thread(machine, pid, pid); + + if (!thread) + return 0; + + return (bool)thread->priv; +} + int jit_process(struct perf_session *session, struct perf_data *output, @@ -764,8 +787,13 @@ jit_process(struct perf_session *session, /* * first, detect marker mmap (i.e., the jitdump mmap) */ - if (jit_detect(filename, pid)) + if (jit_detect(filename, pid)) { + // Strip //anon* mmaps if we processed a jitdump for this pid + if (jit_has_pid(machine, pid) && (strncmp(filename, "//anon", 6) == 0)) + return 1; + return 0; + } memset(&jd, 0, sizeof(jd)); @@ -784,6 +812,7 @@ jit_process(struct perf_session *session, ret = jit_inject(&jd, filename); if (!ret) { + jit_add_pid(machine, pid); *nbytes = jd.bytes_written; ret = 1; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index d5384807372b..208b813e00ea 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -703,7 +703,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); - dso->kernel = DSO_TYPE_KERNEL; + dso->kernel = DSO_SPACE__KERNEL; } dso__get(dso); @@ -753,7 +753,7 @@ static int machine__process_ksymbol_register(struct machine *machine, struct dso *dso = dso__new(event->ksymbol.name); if (dso) { - dso->kernel = DSO_TYPE_KERNEL; + dso->kernel = DSO_SPACE__KERNEL; map = map__new2(0, dso); } @@ -762,6 +762,12 @@ static int machine__process_ksymbol_register(struct machine *machine, return -ENOMEM; } + if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) { + map->dso->binary_type = DSO_BINARY_TYPE__OOL; + map->dso->data.file_size = event->ksymbol.len; + dso__set_loaded(map->dso); + } + map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; maps__insert(&machine->kmaps, map); @@ -808,6 +814,47 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, return machine__process_ksymbol_register(machine, event, sample); } +int machine__process_text_poke(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct map *map = maps__find(&machine->kmaps, event->text_poke.addr); + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + if (dump_trace) + perf_event__fprintf_text_poke(event, machine, stdout); + + if (!event->text_poke.new_len) + return 0; + + if (cpumode != PERF_RECORD_MISC_KERNEL) { + pr_debug("%s: unsupported cpumode - ignoring\n", __func__); + return 0; + } + + if (map && map->dso) { + u8 *new_bytes = event->text_poke.bytes + event->text_poke.old_len; + int ret; + + /* + * Kernel maps might be changed when loading symbols so loading + * must be done prior to using kernel maps. + */ + map__load(map); + ret = dso__data_write_cache_addr(map->dso, map, machine, + event->text_poke.addr, + new_bytes, + event->text_poke.new_len); + if (ret != event->text_poke.new_len) + pr_debug("Failed to write kernel text poke at %#" PRI_lx64 "\n", + event->text_poke.addr); + } else { + pr_debug("Failed to find kernel text poke address map for %#" PRI_lx64 "\n", + event->text_poke.addr); + } + + return 0; +} + static struct map *machine__addnew_module_map(struct machine *machine, u64 start, const char *filename) { @@ -924,14 +971,14 @@ static struct dso *machine__get_kernel(struct machine *machine) vmlinux_name = symbol_conf.vmlinux_name; kernel = machine__findnew_kernel(machine, vmlinux_name, - "[kernel]", DSO_TYPE_KERNEL); + "[kernel]", DSO_SPACE__KERNEL); } else { if (symbol_conf.default_guest_vmlinux_name) vmlinux_name = symbol_conf.default_guest_vmlinux_name; kernel = machine__findnew_kernel(machine, vmlinux_name, "[guest.kernel]", - DSO_TYPE_GUEST_KERNEL); + DSO_SPACE__KERNEL_GUEST); } if (kernel != NULL && (!kernel->has_build_id)) @@ -1559,7 +1606,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, union perf_event *event) { struct map *map; - enum dso_kernel_type kernel_type; + enum dso_space_type dso_space; bool is_kernel_mmap; /* If we have maps from kcore then we do not need or want any others */ @@ -1567,9 +1614,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, return 0; if (machine__is_host(machine)) - kernel_type = DSO_TYPE_KERNEL; + dso_space = DSO_SPACE__KERNEL; else - kernel_type = DSO_TYPE_GUEST_KERNEL; + dso_space = DSO_SPACE__KERNEL_GUEST; is_kernel_mmap = memcmp(event->mmap.filename, machine->mmap_name, @@ -1629,7 +1676,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (kernel == NULL) goto out_problem; - kernel->kernel = kernel_type; + kernel->kernel = dso_space; if (__machine__create_kernel_maps(machine, kernel) < 0) { dso__put(kernel); goto out_problem; @@ -1930,6 +1977,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_ksymbol(machine, event, sample); break; case PERF_RECORD_BPF_EVENT: ret = machine__process_bpf(machine, event, sample); break; + case PERF_RECORD_TEXT_POKE: + ret = machine__process_text_poke(machine, event, sample); break; default: ret = -1; break; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index fa1be9ea00fa..062c36a8433c 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -138,6 +138,9 @@ int machine__process_mmap2_event(struct machine *machine, union perf_event *even int machine__process_ksymbol(struct machine *machine, union perf_event *event, struct perf_sample *sample); +int machine__process_text_poke(struct machine *machine, + union perf_event *event, + struct perf_sample *sample); int machine__process_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 53d96611e6a6..1d7210804639 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -267,6 +267,11 @@ bool __map__is_bpf_prog(const struct map *map) return name && (strstr(name, "bpf_prog_") == name); } +bool __map__is_ool(const struct map *map) +{ + return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; +} + bool map__has_symbols(const struct map *map) { return dso__has_symbols(map->dso); @@ -481,7 +486,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) * kernel modules also have DSO_TYPE_USER in dso->kernel, * but all kernel modules are ET_REL, so won't get here. */ - if (map->dso->kernel == DSO_TYPE_USER) + if (map->dso->kernel == DSO_SPACE__USER) return rip + map->dso->text_offset; return map->unmap_ip(map, rip) - map->reloc; @@ -511,7 +516,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) * kernel modules also have DSO_TYPE_USER in dso->kernel, * but all kernel modules are ET_REL, so won't get here. */ - if (map->dso->kernel == DSO_TYPE_USER) + if (map->dso->kernel == DSO_SPACE__USER) return map->unmap_ip(map, ip - map->dso->text_offset); return ip + map->reloc; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 067036e8970c..9e312ae2d656 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -147,11 +147,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); bool __map__is_bpf_prog(const struct map *map); +bool __map__is_ool(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && - !__map__is_bpf_prog(map); + !__map__is_bpf_prog(map) && !__map__is_ool(map); } bool map__has_symbols(const struct map *map); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 9e21aa767e41..8831b964288f 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -24,6 +24,7 @@ #include <subcmd/parse-options.h> #include <api/fs/fs.h> #include "util.h" +#include <asm/bug.h> struct metric_event *metricgroup__lookup(struct rblist *metric_events, struct evsel *evsel, @@ -76,23 +77,78 @@ static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused, return &me->nd; } +static void metric_event_delete(struct rblist *rblist __maybe_unused, + struct rb_node *rb_node) +{ + struct metric_event *me = container_of(rb_node, struct metric_event, nd); + struct metric_expr *expr, *tmp; + + list_for_each_entry_safe(expr, tmp, &me->head, nd) { + free(expr->metric_refs); + free(expr); + } + + free(me); +} + static void metricgroup__rblist_init(struct rblist *metric_events) { rblist__init(metric_events); metric_events->node_cmp = metric_event_cmp; metric_events->node_new = metric_event_new; + metric_events->node_delete = metric_event_delete; } -struct egroup { +void metricgroup__rblist_exit(struct rblist *metric_events) +{ + rblist__exit(metric_events); +} + +/* + * A node in the list of referenced metrics. metric_expr + * is held as a convenience to avoid a search through the + * metric list. + */ +struct metric_ref_node { + const char *metric_name; + const char *metric_expr; + struct list_head list; +}; + +struct metric { struct list_head nd; struct expr_parse_ctx pctx; const char *metric_name; const char *metric_expr; const char *metric_unit; + struct list_head metric_refs; + int metric_refs_cnt; int runtime; bool has_constraint; }; +#define RECURSION_ID_MAX 1000 + +struct expr_ids { + struct expr_id id[RECURSION_ID_MAX]; + int cnt; +}; + +static struct expr_id *expr_ids__alloc(struct expr_ids *ids) +{ + if (ids->cnt >= RECURSION_ID_MAX) + return NULL; + return &ids->id[ids->cnt++]; +} + +static void expr_ids__exit(struct expr_ids *ids) +{ + int i; + + for (i = 0; i < ids->cnt; i++) + free(ids->id[i].id); +} + /** * Find a group of events in perf_evlist that correpond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as @@ -119,7 +175,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, unsigned long *evlist_used) { struct evsel *ev, *current_leader = NULL; - double *val_ptr; + struct expr_id_data *val_ptr; int i = 0, matched_events = 0, events_to_match; const int idnum = (int)hashmap__size(&pctx->ids); @@ -206,7 +262,7 @@ static int metricgroup__setup_events(struct list_head *groups, struct metric_expr *expr; int i = 0; int ret = 0; - struct egroup *eg; + struct metric *m; struct evsel *evsel, *tmp; unsigned long *evlist_used; @@ -214,22 +270,23 @@ static int metricgroup__setup_events(struct list_head *groups, if (!evlist_used) return -ENOMEM; - list_for_each_entry (eg, groups, nd) { + list_for_each_entry (m, groups, nd) { struct evsel **metric_events; + struct metric_ref *metric_refs = NULL; metric_events = calloc(sizeof(void *), - hashmap__size(&eg->pctx.ids) + 1); + hashmap__size(&m->pctx.ids) + 1); if (!metric_events) { ret = -ENOMEM; break; } - evsel = find_evsel_group(perf_evlist, &eg->pctx, + evsel = find_evsel_group(perf_evlist, &m->pctx, metric_no_merge, - eg->has_constraint, metric_events, + m->has_constraint, metric_events, evlist_used); if (!evsel) { pr_debug("Cannot resolve %s: %s\n", - eg->metric_name, eg->metric_expr); + m->metric_name, m->metric_expr); free(metric_events); continue; } @@ -247,11 +304,41 @@ static int metricgroup__setup_events(struct list_head *groups, free(metric_events); break; } - expr->metric_expr = eg->metric_expr; - expr->metric_name = eg->metric_name; - expr->metric_unit = eg->metric_unit; + + /* + * Collect and store collected nested expressions + * for metric processing. + */ + if (m->metric_refs_cnt) { + struct metric_ref_node *ref; + + metric_refs = zalloc(sizeof(struct metric_ref) * (m->metric_refs_cnt + 1)); + if (!metric_refs) { + ret = -ENOMEM; + free(metric_events); + break; + } + + i = 0; + list_for_each_entry(ref, &m->metric_refs, list) { + /* + * Intentionally passing just const char pointers, + * originally from 'struct pmu_event' object. + * We don't need to change them, so there's no + * need to create our own copy. + */ + metric_refs[i].metric_name = ref->metric_name; + metric_refs[i].metric_expr = ref->metric_expr; + i++; + } + }; + + expr->metric_refs = metric_refs; + expr->metric_expr = m->metric_expr; + expr->metric_name = m->metric_name; + expr->metric_unit = m->metric_unit; expr->metric_events = metric_events; - expr->runtime = eg->runtime; + expr->runtime = m->runtime; list_add(&expr->nd, &me->head); } @@ -552,123 +639,339 @@ int __weak arch_get_runtimeparam(void) return 1; } -static int __metricgroup__add_metric(struct list_head *group_list, - struct pmu_event *pe, - bool metric_no_group, - int runtime) +static int __add_metric(struct list_head *metric_list, + struct pmu_event *pe, + bool metric_no_group, + int runtime, + struct metric **mp, + struct expr_id *parent, + struct expr_ids *ids) { - struct egroup *eg; + struct metric_ref_node *ref; + struct metric *m; - eg = malloc(sizeof(*eg)); - if (!eg) - return -ENOMEM; + if (*mp == NULL) { + /* + * We got in here for the parent group, + * allocate it and put it on the list. + */ + m = zalloc(sizeof(*m)); + if (!m) + return -ENOMEM; + + expr__ctx_init(&m->pctx); + m->metric_name = pe->metric_name; + m->metric_expr = pe->metric_expr; + m->metric_unit = pe->unit; + m->runtime = runtime; + m->has_constraint = metric_no_group || metricgroup__has_constraint(pe); + INIT_LIST_HEAD(&m->metric_refs); + m->metric_refs_cnt = 0; + *mp = m; + + parent = expr_ids__alloc(ids); + if (!parent) { + free(m); + return -EINVAL; + } + + parent->id = strdup(pe->metric_name); + if (!parent->id) { + free(m); + return -ENOMEM; + } + } else { + /* + * We got here for the referenced metric, via the + * recursive metricgroup__add_metric call, add + * it to the parent group. + */ + m = *mp; - expr__ctx_init(&eg->pctx); - eg->metric_name = pe->metric_name; - eg->metric_expr = pe->metric_expr; - eg->metric_unit = pe->unit; - eg->runtime = runtime; - eg->has_constraint = metric_no_group || metricgroup__has_constraint(pe); + ref = malloc(sizeof(*ref)); + if (!ref) + return -ENOMEM; - if (expr__find_other(pe->metric_expr, NULL, &eg->pctx, runtime) < 0) { - expr__ctx_clear(&eg->pctx); - free(eg); + /* + * Intentionally passing just const char pointers, + * from 'pe' object, so they never go away. We don't + * need to change them, so there's no need to create + * our own copy. + */ + ref->metric_name = pe->metric_name; + ref->metric_expr = pe->metric_expr; + + list_add(&ref->list, &m->metric_refs); + m->metric_refs_cnt++; + } + + /* Force all found IDs in metric to have us as parent ID. */ + WARN_ON_ONCE(!parent); + m->pctx.parent = parent; + + /* + * For both the parent and referenced metrics, we parse + * all the metric's IDs and add it to the parent context. + */ + if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) { + expr__ctx_clear(&m->pctx); + free(m); return -EINVAL; } - if (list_empty(group_list)) - list_add(&eg->nd, group_list); + /* + * We add new group only in the 'parent' call, + * so bail out for referenced metric case. + */ + if (m->metric_refs_cnt) + return 0; + + if (list_empty(metric_list)) + list_add(&m->nd, metric_list); else { struct list_head *pos; /* Place the largest groups at the front. */ - list_for_each_prev(pos, group_list) { - struct egroup *old = list_entry(pos, struct egroup, nd); + list_for_each_prev(pos, metric_list) { + struct metric *old = list_entry(pos, struct metric, nd); - if (hashmap__size(&eg->pctx.ids) <= + if (hashmap__size(&m->pctx.ids) <= hashmap__size(&old->pctx.ids)) break; } - list_add(&eg->nd, pos); + list_add(&m->nd, pos); } return 0; } +#define map_for_each_event(__pe, __idx, __map) \ + for (__idx = 0, __pe = &__map->table[__idx]; \ + __pe->name || __pe->metric_group || __pe->metric_name; \ + __pe = &__map->table[++__idx]) + +#define map_for_each_metric(__pe, __idx, __map, __metric) \ + map_for_each_event(__pe, __idx, __map) \ + if (__pe->metric_expr && \ + (match_metric(__pe->metric_group, __metric) || \ + match_metric(__pe->metric_name, __metric))) + +static struct pmu_event *find_metric(const char *metric, struct pmu_events_map *map) +{ + struct pmu_event *pe; + int i; + + map_for_each_event(pe, i, map) { + if (match_metric(pe->metric_name, metric)) + return pe; + } + + return NULL; +} + +static int recursion_check(struct metric *m, const char *id, struct expr_id **parent, + struct expr_ids *ids) +{ + struct expr_id_data *data; + struct expr_id *p; + int ret; + + /* + * We get the parent referenced by 'id' argument and + * traverse through all the parent object IDs to check + * if we already processed 'id', if we did, it's recursion + * and we fail. + */ + ret = expr__get_id(&m->pctx, id, &data); + if (ret) + return ret; + + p = data->parent; + + while (p->parent) { + if (!strcmp(p->id, id)) { + pr_err("failed: recursion detected for %s\n", id); + return -1; + } + p = p->parent; + } + + /* + * If we are over the limit of static entris, the metric + * is too difficult/nested to process, fail as well. + */ + p = expr_ids__alloc(ids); + if (!p) { + pr_err("failed: too many nested metrics\n"); + return -EINVAL; + } + + p->id = strdup(id); + p->parent = data->parent; + *parent = p; + + return p->id ? 0 : -ENOMEM; +} + +static int add_metric(struct list_head *metric_list, + struct pmu_event *pe, + bool metric_no_group, + struct metric **mp, + struct expr_id *parent, + struct expr_ids *ids); + +static int __resolve_metric(struct metric *m, + bool metric_no_group, + struct list_head *metric_list, + struct pmu_events_map *map, + struct expr_ids *ids) +{ + struct hashmap_entry *cur; + size_t bkt; + bool all; + int ret; + + /* + * Iterate all the parsed IDs and if there's metric, + * add it to the context. + */ + do { + all = true; + hashmap__for_each_entry((&m->pctx.ids), cur, bkt) { + struct expr_id *parent; + struct pmu_event *pe; + + pe = find_metric(cur->key, map); + if (!pe) + continue; + + ret = recursion_check(m, cur->key, &parent, ids); + if (ret) + return ret; + + all = false; + /* The metric key itself needs to go out.. */ + expr__del_id(&m->pctx, cur->key); + + /* ... and it gets resolved to the parent context. */ + ret = add_metric(metric_list, pe, metric_no_group, &m, parent, ids); + if (ret) + return ret; + + /* + * We added new metric to hashmap, so we need + * to break the iteration and start over. + */ + break; + } + } while (!all); + + return 0; +} + +static int resolve_metric(bool metric_no_group, + struct list_head *metric_list, + struct pmu_events_map *map, + struct expr_ids *ids) +{ + struct metric *m; + int err; + + list_for_each_entry(m, metric_list, nd) { + err = __resolve_metric(m, metric_no_group, metric_list, map, ids); + if (err) + return err; + } + return 0; +} + +static int add_metric(struct list_head *metric_list, + struct pmu_event *pe, + bool metric_no_group, + struct metric **m, + struct expr_id *parent, + struct expr_ids *ids) +{ + struct metric *orig = *m; + int ret = 0; + + pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name); + + if (!strstr(pe->metric_expr, "?")) { + ret = __add_metric(metric_list, pe, metric_no_group, 1, m, parent, ids); + } else { + int j, count; + + count = arch_get_runtimeparam(); + + /* This loop is added to create multiple + * events depend on count value and add + * those events to metric_list. + */ + + for (j = 0; j < count && !ret; j++, *m = orig) + ret = __add_metric(metric_list, pe, metric_no_group, j, m, parent, ids); + } + + return ret; +} + static int metricgroup__add_metric(const char *metric, bool metric_no_group, struct strbuf *events, - struct list_head *group_list) + struct list_head *metric_list, + struct pmu_events_map *map) { - struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct expr_ids ids = { .cnt = 0, }; struct pmu_event *pe; - struct egroup *eg; + struct metric *m; + LIST_HEAD(list); int i, ret; bool has_match = false; - if (!map) - return 0; + map_for_each_metric(pe, i, map, metric) { + has_match = true; + m = NULL; - for (i = 0; ; i++) { - pe = &map->table[i]; + ret = add_metric(&list, pe, metric_no_group, &m, NULL, &ids); + if (ret) + return ret; - if (!pe->name && !pe->metric_group && !pe->metric_name) { - /* End of pmu events. */ - if (!has_match) - return -EINVAL; - break; - } - if (!pe->metric_expr) - continue; - if (match_metric(pe->metric_group, metric) || - match_metric(pe->metric_name, metric)) { - has_match = true; - pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name); - - if (!strstr(pe->metric_expr, "?")) { - ret = __metricgroup__add_metric(group_list, - pe, - metric_no_group, - 1); - if (ret) - return ret; - } else { - int j, count; - - count = arch_get_runtimeparam(); - - /* This loop is added to create multiple - * events depend on count value and add - * those events to group_list. - */ - - for (j = 0; j < count; j++) { - ret = __metricgroup__add_metric( - group_list, pe, - metric_no_group, j); - if (ret) - return ret; - } - } - } + /* + * Process any possible referenced metrics + * included in the expression. + */ + ret = resolve_metric(metric_no_group, + &list, map, &ids); + if (ret) + return ret; } - list_for_each_entry(eg, group_list, nd) { + + /* End of pmu events. */ + if (!has_match) + return -EINVAL; + + list_for_each_entry(m, &list, nd) { if (events->len > 0) strbuf_addf(events, ","); - if (eg->has_constraint) { + if (m->has_constraint) { metricgroup__add_metric_non_group(events, - &eg->pctx); + &m->pctx); } else { metricgroup__add_metric_weak_group(events, - &eg->pctx); + &m->pctx); } } + + list_splice(&list, metric_list); + expr_ids__exit(&ids); return 0; } static int metricgroup__add_metric_list(const char *list, bool metric_no_group, struct strbuf *events, - struct list_head *group_list) + struct list_head *metric_list, + struct pmu_events_map *map) { char *llist, *nlist, *p; int ret = -EINVAL; @@ -683,7 +986,7 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, while ((p = strsep(&llist, ",")) != NULL) { ret = metricgroup__add_metric(p, metric_no_group, events, - group_list); + metric_list, map); if (ret == -EINVAL) { fprintf(stderr, "Cannot find metric or group `%s'\n", p); @@ -698,50 +1001,88 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, return ret; } -static void metricgroup__free_egroups(struct list_head *group_list) +static void metric__free_refs(struct metric *metric) { - struct egroup *eg, *egtmp; + struct metric_ref_node *ref, *tmp; - list_for_each_entry_safe (eg, egtmp, group_list, nd) { - expr__ctx_clear(&eg->pctx); - list_del_init(&eg->nd); - free(eg); + list_for_each_entry_safe(ref, tmp, &metric->metric_refs, list) { + list_del(&ref->list); + free(ref); } } -int metricgroup__parse_groups(const struct option *opt, - const char *str, - bool metric_no_group, - bool metric_no_merge, - struct rblist *metric_events) +static void metricgroup__free_metrics(struct list_head *metric_list) +{ + struct metric *m, *tmp; + + list_for_each_entry_safe (m, tmp, metric_list, nd) { + metric__free_refs(m); + expr__ctx_clear(&m->pctx); + list_del_init(&m->nd); + free(m); + } +} + +static int parse_groups(struct evlist *perf_evlist, const char *str, + bool metric_no_group, + bool metric_no_merge, + struct perf_pmu *fake_pmu, + struct rblist *metric_events, + struct pmu_events_map *map) { struct parse_events_error parse_error; - struct evlist *perf_evlist = *(struct evlist **)opt->value; struct strbuf extra_events; - LIST_HEAD(group_list); + LIST_HEAD(metric_list); int ret; if (metric_events->nr_entries == 0) metricgroup__rblist_init(metric_events); ret = metricgroup__add_metric_list(str, metric_no_group, - &extra_events, &group_list); + &extra_events, &metric_list, map); if (ret) return ret; pr_debug("adding %s\n", extra_events.buf); bzero(&parse_error, sizeof(parse_error)); - ret = parse_events(perf_evlist, extra_events.buf, &parse_error); + ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu); if (ret) { parse_events_print_error(&parse_error, extra_events.buf); goto out; } strbuf_release(&extra_events); - ret = metricgroup__setup_events(&group_list, metric_no_merge, + ret = metricgroup__setup_events(&metric_list, metric_no_merge, perf_evlist, metric_events); out: - metricgroup__free_egroups(&group_list); + metricgroup__free_metrics(&metric_list); return ret; } +int metricgroup__parse_groups(const struct option *opt, + const char *str, + bool metric_no_group, + bool metric_no_merge, + struct rblist *metric_events) +{ + struct evlist *perf_evlist = *(struct evlist **)opt->value; + struct pmu_events_map *map = perf_pmu__find_map(NULL); + + if (!map) + return 0; + + return parse_groups(perf_evlist, str, metric_no_group, + metric_no_merge, NULL, metric_events, map); +} + +int metricgroup__parse_groups_test(struct evlist *evlist, + struct pmu_events_map *map, + const char *str, + bool metric_no_group, + bool metric_no_merge, + struct rblist *metric_events) +{ + return parse_groups(evlist, str, metric_no_group, + metric_no_merge, &perf_pmu__fake, metric_events, map); +} + bool metricgroup__has_metric(const char *metric) { struct pmu_events_map *map = perf_pmu__find_map(NULL); diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 287850bcdeca..62623a39cbec 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -7,8 +7,10 @@ #include <stdbool.h> struct evsel; +struct evlist; struct option; struct rblist; +struct pmu_events_map; struct metric_event { struct rb_node nd; @@ -16,12 +18,18 @@ struct metric_event { struct list_head head; /* list of metric_expr */ }; +struct metric_ref { + const char *metric_name; + const char *metric_expr; +}; + struct metric_expr { struct list_head nd; const char *metric_expr; const char *metric_name; const char *metric_unit; struct evsel **metric_events; + struct metric_ref *metric_refs; int runtime; }; @@ -34,8 +42,16 @@ int metricgroup__parse_groups(const struct option *opt, bool metric_no_merge, struct rblist *metric_events); +int metricgroup__parse_groups_test(struct evlist *evlist, + struct pmu_events_map *map, + const char *str, + bool metric_no_group, + bool metric_no_merge, + struct rblist *metric_events); + void metricgroup__print(bool metrics, bool groups, char *filter, bool raw, bool details); bool metricgroup__has_metric(const char *metric); int arch_get_runtimeparam(void); +void metricgroup__rblist_exit(struct rblist *metric_events); #endif diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3decbb203846..9f7260e69113 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -767,8 +767,8 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state, return 0; errout: - parse_state->error->help = strdup("(add -v to see detail)"); - parse_state->error->str = strdup(errbuf); + parse_events__handle_error(parse_state->error, 0, + strdup(errbuf), strdup("(add -v to see detail)")); return err; } @@ -784,36 +784,38 @@ parse_events_config_bpf(struct parse_events_state *parse_state, return 0; list_for_each_entry(term, head_config, list) { - char errbuf[BUFSIZ]; int err; if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) { - snprintf(errbuf, sizeof(errbuf), - "Invalid config term for BPF object"); - errbuf[BUFSIZ - 1] = '\0'; - - parse_state->error->idx = term->err_term; - parse_state->error->str = strdup(errbuf); + parse_events__handle_error(parse_state->error, term->err_term, + strdup("Invalid config term for BPF object"), + NULL); return -EINVAL; } err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos); if (err) { + char errbuf[BUFSIZ]; + int idx; + bpf__strerror_config_obj(obj, term, parse_state->evlist, &error_pos, err, errbuf, sizeof(errbuf)); - parse_state->error->help = strdup( + + if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) + idx = term->err_val; + else + idx = term->err_term + error_pos; + + parse_events__handle_error(parse_state->error, idx, + strdup(errbuf), + strdup( "Hint:\tValid config terms:\n" " \tmap:[<arraymap>].value<indices>=[value]\n" " \tmap:[<eventmap>].event<indices>=[event]\n" "\n" " \twhere <indices> is something like [0,3...5] or [all]\n" -" \t(add -v to see detail)"); - parse_state->error->str = strdup(errbuf); - if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) - parse_state->error->idx = term->err_val; - else - parse_state->error->idx = term->err_term + error_pos; +" \t(add -v to see detail)")); return err; } } @@ -877,8 +879,8 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, -err, errbuf, sizeof(errbuf)); - parse_state->error->help = strdup("(add -v to see detail)"); - parse_state->error->str = strdup(errbuf); + parse_events__handle_error(parse_state->error, 0, + strdup(errbuf), strdup("(add -v to see detail)")); return err; } @@ -1450,7 +1452,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = perf_pmu__find(name); + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; @@ -1483,7 +1485,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, } } - if (perf_pmu__check_alias(pmu, head_config, &info)) + if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info)) return -EINVAL; if (verbose > 1) { @@ -1516,7 +1518,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + if (!parse_state->fake_pmu && perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { struct evsel_config_term *pos, *tmp; list_for_each_entry_safe(pos, tmp, &config_terms, list) { @@ -2017,6 +2019,32 @@ err: perf_pmu__parse_cleanup(); } +/* + * This function injects special term in + * perf_pmu_events_list so the test code + * can check on this functionality. + */ +int perf_pmu__test_parse_init(void) +{ + struct perf_pmu_event_symbol *list; + + list = malloc(sizeof(*list) * 1); + if (!list) + return -ENOMEM; + + list->type = PMU_EVENT_SYMBOL; + list->symbol = strdup("read"); + + if (!list->symbol) { + free(list); + return -ENOMEM; + } + + perf_pmu_events_list = list; + perf_pmu_events_list_num = 1; + return 0; +} + enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name) { @@ -2078,6 +2106,8 @@ int parse_events_terms(struct list_head *terms, const char *str) int ret; ret = parse_events__scanner(str, &parse_state); + perf_pmu__parse_cleanup(); + if (!ret) { list_splice(parse_state.terms, terms); zfree(&parse_state.terms); @@ -2088,15 +2118,16 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct evlist *evlist, const char *str, - struct parse_events_error *err) +int __parse_events(struct evlist *evlist, const char *str, + struct parse_events_error *err, struct perf_pmu *fake_pmu) { struct parse_events_state parse_state = { - .list = LIST_HEAD_INIT(parse_state.list), - .idx = evlist->core.nr_entries, - .error = err, - .evlist = evlist, - .stoken = PE_START_EVENTS, + .list = LIST_HEAD_INIT(parse_state.list), + .idx = evlist->core.nr_entries, + .error = err, + .evlist = evlist, + .stoken = PE_START_EVENTS, + .fake_pmu = fake_pmu, }; int ret; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 1fe23a2f9b36..00cde7d2e30c 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -33,8 +33,15 @@ const char *event_type(int type); int parse_events_option(const struct option *opt, const char *str, int unset); int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset); -int parse_events(struct evlist *evlist, const char *str, - struct parse_events_error *error); +int __parse_events(struct evlist *evlist, const char *str, struct parse_events_error *error, + struct perf_pmu *fake_pmu); + +static inline int parse_events(struct evlist *evlist, const char *str, + struct parse_events_error *err) +{ + return __parse_events(evlist, str, err, NULL); +} + int parse_events_terms(struct list_head *terms, const char *str); int parse_filter(const struct option *opt, const char *str, int unset); int exclude_perf(const struct option *opt, const char *arg, int unset); @@ -127,9 +134,10 @@ struct parse_events_state { int idx; int nr_groups; struct parse_events_error *error; - struct evlist *evlist; + struct evlist *evlist; struct list_head *terms; int stoken; + struct perf_pmu *fake_pmu; }; void parse_events__handle_error(struct parse_events_error *err, int idx, @@ -253,4 +261,6 @@ static inline bool is_sdt_event(char *str __maybe_unused) } #endif /* HAVE_LIBELF_SUPPORT */ +int perf_pmu__test_parse_init(void); + #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 002802e17059..3ca5fd2829ca 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -41,14 +41,6 @@ static int value(yyscan_t scanner, int base) return __value(yylval, text, base, PE_VALUE); } -static int raw(yyscan_t scanner) -{ - YYSTYPE *yylval = parse_events_get_lval(scanner); - char *text = parse_events_get_text(scanner); - - return __value(yylval, text + 1, 16, PE_RAW); -} - static int str(yyscan_t scanner, int token) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -72,6 +64,17 @@ static int str(yyscan_t scanner, int token) return token; } +static int raw(yyscan_t scanner) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + if (perf_pmu__parse_check(text) == PMU_EVENT_SYMBOL) + return str(scanner, PE_NAME); + + return __value(yylval, text + 1, 16, PE_RAW); +} + static bool isbpf_suffix(char *text) { int len = strlen(text); @@ -129,12 +132,16 @@ do { \ yyless(0); \ } while (0) -static int pmu_str_check(yyscan_t scanner) +static int pmu_str_check(yyscan_t scanner, struct parse_events_state *parse_state) { YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); yylval->str = strdup(text); + + if (parse_state->fake_pmu) + return PE_PMU_EVENT_FAKE; + switch (perf_pmu__parse_check(text)) { case PMU_EVENT_SYMBOL_PREFIX: return PE_PMU_EVENT_PRE; @@ -289,6 +296,7 @@ percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } r{num_raw_hex} { return raw(yyscanner); } +r0x{num_raw_hex} { return raw(yyscanner); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } @@ -376,7 +384,7 @@ r{num_raw_hex} { return raw(yyscanner); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } {bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); } -{name} { return pmu_str_check(yyscanner); } +{name} { return pmu_str_check(yyscanner, _parse_state); } {name_tag} { return str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } - { return '-'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index acef87d9af58..b9fb91fdc5de 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -69,7 +69,7 @@ static void inc_group_count(struct list_head *list, %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR -%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT +%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %token PE_ARRAY_ALL PE_ARRAY_RANGE %token PE_DRV_CFG_TERM %type <num> PE_VALUE @@ -87,7 +87,7 @@ static void inc_group_count(struct list_head *list, %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME -%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT +%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type <str> PE_DRV_CFG_TERM %destructor { free ($$); } <str> %type <term> event_term @@ -356,6 +356,43 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc YYABORT; $$ = list; } +| +PE_PMU_EVENT_FAKE sep_dc +{ + struct list_head *list; + int err; + + list = alloc_list(); + if (!list) + YYABORT; + + err = parse_events_add_pmu(_parse_state, list, $1, NULL, false, false); + free($1); + if (err < 0) { + free(list); + YYABORT; + } + $$ = list; +} +| +PE_PMU_EVENT_FAKE opt_pmu_config +{ + struct list_head *list; + int err; + + list = alloc_list(); + if (!list) + YYABORT; + + err = parse_events_add_pmu(_parse_state, list, $1, $2, false, false); + free($1); + parse_events_terms__delete($2); + if (err < 0) { + free(list); + YYABORT; + } + $$ = list; +} value_sym: PE_VALUE_SYM_HW diff --git a/tools/perf/util/parse-sublevel-options.c b/tools/perf/util/parse-sublevel-options.c new file mode 100644 index 000000000000..a841d17ffd57 --- /dev/null +++ b/tools/perf/util/parse-sublevel-options.c @@ -0,0 +1,70 @@ +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <stdio.h> + +#include "util/debug.h" +#include "util/parse-sublevel-options.h" + +static int parse_one_sublevel_option(const char *str, + struct sublevel_option *opts) +{ + struct sublevel_option *opt = opts; + char *vstr, *s = strdup(str); + int v = 1; + + if (!s) { + pr_err("no memory\n"); + return -1; + } + + vstr = strchr(s, '='); + if (vstr) + *vstr++ = 0; + + while (opt->name) { + if (!strcmp(s, opt->name)) + break; + opt++; + } + + if (!opt->name) { + pr_err("Unknown option name '%s'\n", s); + free(s); + return -1; + } + + if (vstr) + v = atoi(vstr); + + *opt->value_ptr = v; + free(s); + return 0; +} + +/* parse options like --foo a=<n>,b,c... */ +int perf_parse_sublevel_options(const char *str, struct sublevel_option *opts) +{ + char *s = strdup(str); + char *p = NULL; + int ret; + + if (!s) { + pr_err("no memory\n"); + return -1; + } + + p = strtok(s, ","); + while (p) { + ret = parse_one_sublevel_option(p, opts); + if (ret) { + free(s); + return ret; + } + + p = strtok(NULL, ","); + } + + free(s); + return 0; +} diff --git a/tools/perf/util/parse-sublevel-options.h b/tools/perf/util/parse-sublevel-options.h new file mode 100644 index 000000000000..9b9efcc2aaad --- /dev/null +++ b/tools/perf/util/parse-sublevel-options.h @@ -0,0 +1,11 @@ +#ifndef _PERF_PARSE_SUBLEVEL_OPTIONS_H +#define _PERF_PARSE_SUBLEVEL_OPTIONS_H + +struct sublevel_option { + const char *name; + int *value_ptr; +}; + +int perf_parse_sublevel_options(const char *str, struct sublevel_option *opts); + +#endif
\ No newline at end of file diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 1337965673d7..3840d02f0f7b 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -93,6 +93,11 @@ static void perf_probe_context_switch(struct evsel *evsel) evsel->core.attr.context_switch = 1; } +static void perf_probe_text_poke(struct evsel *evsel) +{ + evsel->core.attr.text_poke = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); @@ -108,6 +113,11 @@ bool perf_can_record_switch_events(void) return perf_probe_api(perf_probe_context_switch); } +bool perf_can_record_text_poke_events(void) +{ + return perf_probe_api(perf_probe_text_poke); +} + bool perf_can_record_cpu_wide(void) { struct perf_event_attr attr = { diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h index 706c3c6426e2..d5506a983a94 100644 --- a/tools/perf/util/perf_api_probe.h +++ b/tools/perf/util/perf_api_probe.h @@ -9,6 +9,7 @@ bool perf_can_aux_sample(void); bool perf_can_comm_exec(void); bool perf_can_record_cpu_wide(void); bool perf_can_record_switch_events(void); +bool perf_can_record_text_poke_events(void); bool perf_can_sample_identifier(void); #endif // __PERF_API_PROBE_H diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index b94fa07f5d32..e67a227c0ce7 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -147,6 +147,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(aux_watermark, p_unsigned); PRINT_ATTRf(sample_max_stack, p_unsigned); PRINT_ATTRf(aux_sample_size, p_unsigned); + PRINT_ATTRf(text_poke, p_unsigned); return ret; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 93fe72a9dc0b..f1688e1f6ed7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -26,6 +26,8 @@ #include "strbuf.h" #include "fncache.h" +struct perf_pmu perf_pmu__fake; + struct perf_pmu_format { char *name; int value; @@ -1400,6 +1402,7 @@ struct sevent { char *pmu; char *metric_expr; char *metric_name; + int is_cpu; }; static int cmp_sevent(const void *a, const void *b) @@ -1416,6 +1419,11 @@ static int cmp_sevent(const void *a, const void *b) if (n) return n; } + + /* Order CPU core events to be first */ + if (as->is_cpu != bs->is_cpu) + return bs->is_cpu - as->is_cpu; + return strcmp(as->name, bs->name); } @@ -1475,7 +1483,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, list_for_each_entry(alias, &pmu->aliases, list) { char *name = alias->desc ? alias->name : format_alias(buf, sizeof(buf), pmu, alias); - bool is_cpu = !strcmp(pmu->name, "cpu"); + bool is_cpu = is_pmu_core(pmu->name); if (alias->deprecated && !deprecated) continue; @@ -1507,6 +1515,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, aliases[j].pmu = pmu->name; aliases[j].metric_expr = alias->metric_expr; aliases[j].metric_name = alias->metric_name; + aliases[j].is_cpu = is_cpu; j++; } if (pmu->selectable && diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index f971d9aa4570..44ccbdbb1c37 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -43,6 +43,8 @@ struct perf_pmu { struct list_head list; /* ELEM */ }; +extern struct perf_pmu perf_pmu__fake; + struct perf_pmu_info { const char *unit; const char *metric_expr; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index df713a5d1e26..99d36ac77c08 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -375,9 +375,13 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, /* Find the address of given function */ map__for_each_symbol_by_name(map, pp->function, sym) { - if (uprobes) + if (uprobes) { address = sym->start; - else + if (sym->type == STT_GNU_IFUNC) + pr_warning("Warning: The probe function (%s) is a GNU indirect function.\n" + "Consider identifying the final function used at run time and set the probe directly on that.\n", + pp->function); + } else address = map->unmap_ip(map, sym->start) - map->reloc; break; } @@ -2968,6 +2972,16 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, for (j = 0; j < num_matched_functions; j++) { sym = syms[j]; + /* There can be duplicated symbols in the map */ + for (i = 0; i < j; i++) + if (sym->start == syms[i]->start) { + pr_debug("Found duplicated symbol %s @ %" PRIx64 "\n", + sym->name, sym->start); + break; + } + if (i != j) + continue; + tev = (*tevs) + ret; tp = &tev->point; if (ret == num_matched_functions) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 55924255c535..659024342e9a 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1408,6 +1408,9 @@ static int fill_empty_trace_arg(struct perf_probe_event *pev, char *type; int i, j, ret; + if (!ntevs) + return -ENOENT; + for (i = 0; i < pev->nargs; i++) { type = NULL; for (j = 0; j < ntevs; j++) { @@ -1464,7 +1467,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, if (ret >= 0 && tf.pf.skip_empty_arg) ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs); - if (ret < 0) { + if (ret < 0 || tf.ntevs == 0) { for (i = 0; i < tf.ntevs; i++) clear_probe_trace_event(&tf.tevs[i]); zfree(tevs); diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 39d1de4b2a36..03678ff25539 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -48,6 +48,7 @@ struct record_opts { bool sample_id; bool no_bpf_event; bool kcore; + bool text_poke; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; @@ -61,7 +62,7 @@ struct record_opts { const char *auxtrace_snapshot_opts; const char *auxtrace_sample_opts; bool sample_transaction; - unsigned initial_delay; + int initial_delay; bool use_clockid; clockid_t clockid; u64 clockid_res_ns; @@ -70,6 +71,8 @@ struct record_opts { int mmap_flush; unsigned int comp_level; unsigned int nr_threads_synthesize; + int ctl_fd; + int ctl_fd_ack; }; extern const char * const *record_usage; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 1a157e84a04a..ffbc9d35a383 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -115,12 +115,12 @@ static int perf_session__open(struct perf_session *session) if (perf_header__has_feat(&session->header, HEADER_STAT)) return 0; - if (!perf_evlist__valid_sample_type(session->evlist)) { + if (!evlist__valid_sample_type(session->evlist)) { pr_err("non matching sample_type\n"); return -1; } - if (!perf_evlist__valid_sample_id_all(session->evlist)) { + if (!evlist__valid_sample_id_all(session->evlist)) { pr_err("non matching sample_id_all\n"); return -1; } @@ -252,10 +252,10 @@ struct perf_session *perf_session__new(struct perf_data *data, /* * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is - * processed, so perf_evlist__sample_id_all is not meaningful here. + * processed, so evlist__sample_id_all is not meaningful here. */ if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps && - tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { + tool->ordered_events && !evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; } @@ -490,6 +490,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->ksymbol = perf_event__process_ksymbol; if (tool->bpf == NULL) tool->bpf = perf_event__process_bpf; + if (tool->text_poke == NULL) + tool->text_poke = perf_event__process_text_poke; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -659,6 +661,24 @@ static void perf_event__switch_swap(union perf_event *event, bool sample_id_all) swap_sample_id_all(event, &event->context_switch + 1); } +static void perf_event__text_poke_swap(union perf_event *event, bool sample_id_all) +{ + event->text_poke.addr = bswap_64(event->text_poke.addr); + event->text_poke.old_len = bswap_16(event->text_poke.old_len); + event->text_poke.new_len = bswap_16(event->text_poke.new_len); + + if (sample_id_all) { + size_t len = sizeof(event->text_poke.old_len) + + sizeof(event->text_poke.new_len) + + event->text_poke.old_len + + event->text_poke.new_len; + void *data = &event->text_poke.old_len; + + data += PERF_ALIGN(len, sizeof(u64)); + swap_sample_id_all(event, data); + } +} + static void perf_event__throttle_swap(union perf_event *event, bool sample_id_all) { @@ -932,6 +952,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_SWITCH] = perf_event__switch_swap, [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap, [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, + [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -1160,10 +1181,10 @@ static void perf_evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = __perf_evlist__combined_sample_type(evlist); + u64 sample_type = __evlist__combined_sample_type(evlist); if (event->header.type != PERF_RECORD_SAMPLE && - !perf_evlist__sample_id_all(evlist)) { + !evlist__sample_id_all(evlist)) { fputs("-1 -1 ", stdout); return; } @@ -1474,6 +1495,8 @@ static int machines__deliver_event(struct machines *machines, return tool->ksymbol(tool, event, sample, machine); case PERF_RECORD_BPF_EVENT: return tool->bpf(tool, event, sample, machine); + case PERF_RECORD_TEXT_POKE: + return tool->text_poke(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -1655,7 +1678,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, return -1; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(session->evlist)); + event_swap(event, evlist__sample_id_all(session->evlist)); out_parse_sample: @@ -1704,7 +1727,7 @@ static s64 perf_session__process_event(struct perf_session *session, int ret; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(evlist)); + event_swap(event, evlist__sample_id_all(evlist)); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index a7c13a88ecb9..e1ba6c1b916a 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -730,25 +730,17 @@ static void print_smi_cost(struct perf_stat_config *config, out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num); } -static void generic_metric(struct perf_stat_config *config, - const char *metric_expr, - struct evsel **metric_events, - char *name, - const char *metric_name, - const char *metric_unit, - int runtime, - int cpu, - struct perf_stat_output_ctx *out, - struct runtime_stat *st) +static int prepare_metric(struct evsel **metric_events, + struct metric_ref *metric_refs, + struct expr_parse_ctx *pctx, + int cpu, + struct runtime_stat *st) { - print_metric_t print_metric = out->print_metric; - struct expr_parse_ctx pctx; - double ratio, scale; - int i; - void *ctxp = out->ctx; + double scale; char *n, *pn; + int i, j, ret; - expr__ctx_init(&pctx); + expr__ctx_init(pctx); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; @@ -771,7 +763,7 @@ static void generic_metric(struct perf_stat_config *config, n = strdup(metric_events[i]->name); if (!n) - return; + return -ENOMEM; /* * This display code with --no-merge adds [cpu] postfixes. * These are not supported by the parser. Remove everything @@ -782,11 +774,42 @@ static void generic_metric(struct perf_stat_config *config, *pn = 0; if (metric_total) - expr__add_id(&pctx, n, metric_total); + expr__add_id_val(pctx, n, metric_total); else - expr__add_id(&pctx, n, avg_stats(stats)*scale); + expr__add_id_val(pctx, n, avg_stats(stats)*scale); } + for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { + ret = expr__add_ref(pctx, &metric_refs[j]); + if (ret) + return ret; + } + + return i; +} + +static void generic_metric(struct perf_stat_config *config, + const char *metric_expr, + struct evsel **metric_events, + struct metric_ref *metric_refs, + char *name, + const char *metric_name, + const char *metric_unit, + int runtime, + int cpu, + struct perf_stat_output_ctx *out, + struct runtime_stat *st) +{ + print_metric_t print_metric = out->print_metric; + struct expr_parse_ctx pctx; + double ratio, scale; + int i; + void *ctxp = out->ctx; + + i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st); + if (i < 0) + return; + if (!metric_events[i]) { if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) { char *unit; @@ -827,6 +850,20 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_clear(&pctx); } +double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st) +{ + struct expr_parse_ctx pctx; + double ratio; + + if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0) + return 0.; + + if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1)) + return 0.; + + return ratio; +} + void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, double avg, int cpu, @@ -1035,8 +1072,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, name, 0); } else if (evsel->metric_expr) { - generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name, - evsel->metric_name, NULL, 1, cpu, out, st); + generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, + evsel->name, evsel->metric_name, NULL, 1, cpu, out, st); } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) { char unit = 'M'; char unit_buf[10]; @@ -1064,7 +1101,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (num++ > 0) out->new_line(config, ctxp); generic_metric(config, mexp->metric_expr, mexp->metric_events, - evsel->name, mexp->metric_name, + mexp->metric_refs, evsel->name, mexp->metric_name, mexp->metric_unit, mexp->runtime, cpu, out, st); } } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index f75ae679eb28..f8778cffd941 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -116,7 +116,7 @@ struct perf_stat_config { FILE *output; unsigned int interval; unsigned int timeout; - unsigned int initial_delay; + int initial_delay; unsigned int unit_width; unsigned int metric_only_len; int times; @@ -133,6 +133,8 @@ struct perf_stat_config { struct perf_cpu_map *cpus_aggr_map; u64 *walltime_run; struct rblist metric_events; + int ctl_fd; + int ctl_fd_ack; }; void perf_stat__set_big_num(int set); @@ -230,4 +232,7 @@ perf_evlist__print_counters(struct evlist *evlist, struct target *_target, struct timespec *ts, int argc, const char **argv); + +struct metric_expr; +double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st); #endif diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5e43054bffea..8cc4b0059fb0 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -789,7 +789,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (ss->opdshdr.sh_type != SHT_PROGBITS) ss->opdsec = NULL; - if (dso->kernel == DSO_TYPE_USER) + if (dso->kernel == DSO_SPACE__USER) ss->adjust_symbols = true; else ss->adjust_symbols = elf__needs_adjust_symbols(ehdr); @@ -872,7 +872,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, * kallsyms and identity maps. Overwrite it to * map to the kernel dso. */ - if (*remap_kernel && dso->kernel) { + if (*remap_kernel && dso->kernel && !kmodule) { *remap_kernel = false; map->start = shdr->sh_addr + ref_reloc(kmap); map->end = map->start + shdr->sh_size; @@ -1068,7 +1068,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, * Initial kernel and module mappings do not map to the dso. * Flag the fixups. */ - if (dso->kernel || kmodule) { + if (dso->kernel) { remap_kernel = true; adjust_kernel_syms = dso->adjust_symbols; } @@ -1130,7 +1130,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, (sym.st_value & 1)) --sym.st_value; - if (dso->kernel || kmodule) { + if (dso->kernel) { if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map, section_name, adjust_kernel_syms, kmodule, &remap_kernel)) goto out_elf_end; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 5ddf84dcbae7..1f5fcb828a21 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -666,6 +666,8 @@ static bool symbol__is_idle(const char *name) "poll_idle", "ppc64_runlatch_off", "pseries_dedicated_idle_sleep", + "psw_idle", + "psw_idle_exit", NULL }; int i; @@ -806,7 +808,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (strcmp(curr_map->dso->short_name, module)) { if (curr_map != initial_map && - dso->kernel == DSO_TYPE_GUEST_KERNEL && + dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(machine)) { /* * We assume all symbols of a module are @@ -863,7 +865,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, goto add_symbol; } - if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) snprintf(dso_name, sizeof(dso_name), "[guest.kernel].%d", kernel_range++); @@ -907,7 +909,7 @@ discard_symbol: } if (curr_map != initial_map && - dso->kernel == DSO_TYPE_GUEST_KERNEL && + dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(kmaps->machine)) { dso__set_loaded(curr_map->dso); } @@ -1385,7 +1387,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, * Set the data type and long name so that kcore can be read via * dso__data_read_addr(). */ - if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE; else dso->binary_type = DSO_BINARY_TYPE__KCORE; @@ -1449,7 +1451,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, symbols__fixup_end(&dso->symbols); symbols__fixup_duplicate(&dso->symbols); - if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; else dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; @@ -1535,17 +1537,17 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: - return !kmod && dso->kernel == DSO_TYPE_USER; + return !kmod && dso->kernel == DSO_SPACE__USER; case DSO_BINARY_TYPE__KALLSYMS: case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__KCORE: - return dso->kernel == DSO_TYPE_KERNEL; + return dso->kernel == DSO_SPACE__KERNEL; case DSO_BINARY_TYPE__GUEST_KALLSYMS: case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__GUEST_KCORE: - return dso->kernel == DSO_TYPE_GUEST_KERNEL; + return dso->kernel == DSO_SPACE__KERNEL_GUEST; case DSO_BINARY_TYPE__GUEST_KMODULE: case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: @@ -1563,6 +1565,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__BPF_PROG_INFO: case DSO_BINARY_TYPE__BPF_IMAGE: + case DSO_BINARY_TYPE__OOL: case DSO_BINARY_TYPE__NOT_FOUND: default: return false; @@ -1647,9 +1650,9 @@ int dso__load(struct dso *dso, struct map *map) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; if (dso->kernel && !kmod) { - if (dso->kernel == DSO_TYPE_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL) ret = dso__load_kernel_sym(dso, map); - else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + else if (dso->kernel == DSO_SPACE__KERNEL_GUEST) ret = dso__load_guest_kernel_sym(dso, map); machine = map__kmaps(map)->machine; @@ -1879,7 +1882,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, else symbol__join_symfs(symfs_vmlinux, vmlinux); - if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; else symtab_type = DSO_BINARY_TYPE__VMLINUX; @@ -1891,7 +1894,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, symsrc__destroy(&ss); if (err > 0) { - if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX; else dso->binary_type = DSO_BINARY_TYPE__VMLINUX; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 3fb67bd31e4a..bbbc0dcd461f 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -57,7 +57,8 @@ struct perf_tool { throttle, unthrottle, ksymbol, - bpf; + bpf, + text_poke; event_attr_op attr; event_attr_op event_update; |