diff options
Diffstat (limited to 'tools/perf/util')
64 files changed, 2684 insertions, 936 deletions
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 809b4c50beae..7dabde14ea54 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -232,9 +232,16 @@ static int mov__parse(struct ins_operands *ops) return -1; target = ++s; + comment = strchr(s, '#'); - while (s[0] != '\0' && !isspace(s[0])) - ++s; + if (comment != NULL) + s = comment - 1; + else + s = strchr(s, '\0') - 1; + + while (s > target && isspace(s[0])) + --s; + s++; prev = *s; *s = '\0'; @@ -244,7 +251,6 @@ static int mov__parse(struct ins_operands *ops) if (ops->target.raw == NULL) goto out_free_source; - comment = strchr(s, '#'); if (comment == NULL) return 0; @@ -472,7 +478,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); - if (addr < sym->start || addr > sym->end) + if (addr < sym->start || addr >= sym->end) return -ERANGE; offset = addr - sym->start; @@ -830,7 +836,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if ((u64)line_ip < start || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip >= end) offset = -1; else parsed_line = tmp2 + 1; @@ -899,10 +905,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) struct kcore_extract kce; bool delete_extract = false; - if (filename) { - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); - } + if (filename) + symbol__join_symfs(symfs_filename, filename); if (filename == NULL) { if (dso->has_build_id) { @@ -922,8 +926,7 @@ fallback: * DSO is the same as when 'perf record' ran. */ filename = (char *)dso->long_name; - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); + symbol__join_symfs(symfs_filename, filename); free_filename = false; } @@ -963,7 +966,7 @@ fallback: kce.kcore_filename = symfs_filename; kce.addr = map__rip_2objdump(map, sym->start); kce.offs = sym->start; - kce.len = sym->end + 1 - sym->start; + kce.len = sym->end - sym->start; if (!kcore_extract__create(&kce)) { delete_extract = true; strlcpy(symfs_filename, kce.extract_filename, @@ -984,7 +987,7 @@ fallback: disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", map__rip_2objdump(map, sym->start), - map__rip_2objdump(map, sym->end+1), + map__rip_2objdump(map, sym->end), symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", symbol_conf.annotate_src ? "-S" : "", symfs_filename, filename); diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 7b176dd02e1a..5cf9e1b5989d 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); extern int perf_config(config_fn_t fn, void *); extern int perf_config_int(const char *, const char *); +extern u64 perf_config_u64(const char *, const char *); extern int perf_config_bool(const char *, const char *); extern int config_error_nonbool(const char *); extern const char *perf_config_dirname(const char *, const char *); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 437ee09727e6..c84d3f8dcb75 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,77 +25,172 @@ __thread struct callchain_cursor callchain_cursor; -int -parse_callchain_report_opt(const char *arg) +#ifdef HAVE_DWARF_UNWIND_SUPPORT +static int get_stack_size(const char *str, unsigned long *_size) { - char *tok, *tok2; char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - symbol_conf.use_callchain = true; + size = strtoul(str, &endptr, 0); - if (!arg) + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; return 0; - tok = strtok((char *)arg, ","); - if (!tok) - return -1; + } while (0); - /* get the output mode */ - if (!strncmp(tok, "graph", strlen(arg))) { - callchain_param.mode = CHAIN_GRAPH_ABS; + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); + return -1; +} +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - } else if (!strncmp(tok, "flat", strlen(arg))) { - callchain_param.mode = CHAIN_FLAT; - } else if (!strncmp(tok, "fractal", strlen(arg))) { - callchain_param.mode = CHAIN_GRAPH_REL; - } else if (!strncmp(tok, "none", strlen(arg))) { - callchain_param.mode = CHAIN_NONE; - symbol_conf.use_callchain = false; - return 0; - } else { - return -1; - } +int parse_callchain_record_opt(const char *arg) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + callchain_param.record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for -g fp\n"); + break; - /* get the min percentage */ - tok = strtok(NULL, ","); - if (!tok) - goto setup; +#ifdef HAVE_DWARF_UNWIND_SUPPORT + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; - callchain_param.min_percent = strtod(tok, &endptr); - if (tok == endptr) - return -1; + ret = 0; + callchain_param.record_mode = CALLCHAIN_DWARF; + callchain_param.dump_size = default_stack_dump_size; - /* get the print limit */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; - if (tok2[0] != 'c') { - callchain_param.print_limit = strtoul(tok2, &endptr, 0); - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; + ret = get_stack_size(tok, &size); + callchain_param.dump_size = size; + } +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + return ret; +} + +static int parse_callchain_mode(const char *value) +{ + if (!strncmp(value, "graph", strlen(value))) { + callchain_param.mode = CHAIN_GRAPH_ABS; + return 0; + } + if (!strncmp(value, "flat", strlen(value))) { + callchain_param.mode = CHAIN_FLAT; + return 0; } + if (!strncmp(value, "fractal", strlen(value))) { + callchain_param.mode = CHAIN_GRAPH_REL; + return 0; + } + return -1; +} - /* get the call chain order */ - if (!strncmp(tok2, "caller", strlen("caller"))) +static int parse_callchain_order(const char *value) +{ + if (!strncmp(value, "caller", strlen(value))) { callchain_param.order = ORDER_CALLER; - else if (!strncmp(tok2, "callee", strlen("callee"))) + return 0; + } + if (!strncmp(value, "callee", strlen(value))) { callchain_param.order = ORDER_CALLEE; - else - return -1; + return 0; + } + return -1; +} - /* Get the sort key */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - if (!strncmp(tok2, "function", strlen("function"))) +static int parse_callchain_sort_key(const char *value) +{ + if (!strncmp(value, "function", strlen(value))) { callchain_param.key = CCKEY_FUNCTION; - else if (!strncmp(tok2, "address", strlen("address"))) + return 0; + } + if (!strncmp(value, "address", strlen(value))) { callchain_param.key = CCKEY_ADDRESS; - else - return -1; -setup: + return 0; + } + return -1; +} + +int +parse_callchain_report_opt(const char *arg) +{ + char *tok; + char *endptr; + bool minpcnt_set = false; + + symbol_conf.use_callchain = true; + + if (!arg) + return 0; + + while ((tok = strtok((char *)arg, ",")) != NULL) { + if (!strncmp(tok, "none", strlen(tok))) { + callchain_param.mode = CHAIN_NONE; + symbol_conf.use_callchain = false; + return 0; + } + + if (!parse_callchain_mode(tok) || + !parse_callchain_order(tok) || + !parse_callchain_sort_key(tok)) { + /* parsing ok - move on to the next */ + } else if (!minpcnt_set) { + /* try to get the min percent */ + callchain_param.min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + minpcnt_set = true; + } else { + /* try print limit at last */ + callchain_param.print_limit = strtoul(tok, &endptr, 0); + if (tok == endptr) + return -1; + } + + arg = NULL; + } + if (callchain_register_param(&callchain_param) < 0) { pr_err("Can't register callchain params\n"); return -1; @@ -103,6 +198,47 @@ setup: return 0; } +int perf_callchain_config(const char *var, const char *value) +{ + char *endptr; + + if (prefixcmp(var, "call-graph.")) + return 0; + var += sizeof("call-graph.") - 1; + + if (!strcmp(var, "record-mode")) + return parse_callchain_record_opt(value); +#ifdef HAVE_DWARF_UNWIND_SUPPORT + if (!strcmp(var, "dump-size")) { + unsigned long size = 0; + int ret; + + ret = get_stack_size(value, &size); + callchain_param.dump_size = size; + + return ret; + } +#endif + if (!strcmp(var, "print-type")) + return parse_callchain_mode(value); + if (!strcmp(var, "order")) + return parse_callchain_order(value); + if (!strcmp(var, "sort-key")) + return parse_callchain_sort_key(value); + if (!strcmp(var, "threshold")) { + callchain_param.min_percent = strtod(value, &endptr); + if (value == endptr) + return -1; + } + if (!strcmp(var, "print-limit")) { + callchain_param.print_limit = strtod(value, &endptr); + if (value == endptr) + return -1; + } + + return 0; +} + static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index da43619d6173..94cfefddf4db 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -54,6 +54,9 @@ enum chain_key { }; struct callchain_param { + bool enabled; + enum perf_call_graph_mode record_mode; + u32 dump_size; enum chain_mode mode; u32 print_limit; double min_percent; @@ -62,6 +65,8 @@ struct callchain_param { enum chain_key key; }; +extern struct callchain_param callchain_param; + struct callchain_list { u64 ip; struct map_symbol ms; @@ -154,7 +159,6 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; struct hist_entry; -int record_parse_callchain(const char *arg, struct record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); int record_callchain_opt(const struct option *opt, const char *arg, int unset); @@ -166,7 +170,9 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * bool hide_unresolved); extern const char record_callchain_help[]; +int parse_callchain_record_opt(const char *arg); int parse_callchain_report_opt(const char *arg); +int perf_callchain_config(const char *var, const char *value); static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, struct callchain_cursor *src) diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index c5d05ec17220..47b78b3f0325 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,7 +1,9 @@ +#include <sched.h> #include "util.h" #include "../perf.h" #include "cloexec.h" #include "asm/bug.h" +#include "debug.h" static unsigned long flag = PERF_FLAG_FD_CLOEXEC; @@ -9,15 +11,30 @@ static int perf_flag_probe(void) { /* use 'safest' configuration as used in perf_evsel__fallback() */ struct perf_event_attr attr = { - .type = PERF_COUNT_SW_CPU_CLOCK, + .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, + .exclude_kernel = 1, }; int fd; int err; + int cpu; + pid_t pid = -1; + char sbuf[STRERR_BUFSIZE]; - /* check cloexec flag */ - fd = sys_perf_event_open(&attr, 0, -1, -1, - PERF_FLAG_FD_CLOEXEC); + cpu = sched_getcpu(); + if (cpu < 0) + cpu = 0; + + while (1) { + /* check cloexec flag */ + fd = sys_perf_event_open(&attr, pid, cpu, -1, + PERF_FLAG_FD_CLOEXEC); + if (fd < 0 && pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + break; + } err = errno; if (fd >= 0) { @@ -25,17 +42,17 @@ static int perf_flag_probe(void) return 1; } - WARN_ONCE(err != EINVAL, + WARN_ONCE(err != EINVAL && err != EBUSY, "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n", - err, strerror(err)); + err, strerror_r(err, sbuf, sizeof(sbuf))); /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); err = errno; - if (WARN_ONCE(fd < 0, + if (WARN_ONCE(fd < 0 && err != EBUSY, "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", - err, strerror(err))) + err, strerror_r(err, sbuf, sizeof(sbuf)))) return -1; close(fd); diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 87b8672eb413..f4654183d391 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) va_end(args); return value_color_snprintf(bf, size, fmt, percent); } + +int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...) +{ + va_list args; + int len; + double percent; + const char *color; + + va_start(args, fmt); + len = va_arg(args, int); + percent = va_arg(args, double); + va_end(args); + + color = get_percent_color(percent); + return color_snprintf(bf, size, color, fmt, len, percent); +} diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 7ff30a62a132..0a594b8a0c26 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); int value_color_snprintf(char *bf, size_t size, const char *fmt, double value); int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); +int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...); int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index f9e777629e21..b2bb59df65e1 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) return new; } -struct comm *comm__new(const char *str, u64 timestamp) +struct comm *comm__new(const char *str, u64 timestamp, bool exec) { struct comm *comm = zalloc(sizeof(*comm)); @@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp) return NULL; comm->start = timestamp; + comm->exec = exec; comm->comm_str = comm_str__findnew(str, &comm_str_root); if (!comm->comm_str) { @@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp) return comm; } -int comm__override(struct comm *comm, const char *str, u64 timestamp) +int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec) { struct comm_str *new, *old = comm->comm_str; @@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp) comm_str__put(old); comm->comm_str = new; comm->start = timestamp; + if (exec) + comm->exec = true; return 0; } diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h index fac5bd51befc..51c10ab257f8 100644 --- a/tools/perf/util/comm.h +++ b/tools/perf/util/comm.h @@ -11,11 +11,13 @@ struct comm { struct comm_str *comm_str; u64 start; struct list_head list; + bool exec; }; void comm__free(struct comm *comm); -struct comm *comm__new(const char *str, u64 timestamp); +struct comm *comm__new(const char *str, u64 timestamp, bool exec); const char *comm__str(const struct comm *comm); -int comm__override(struct comm *comm, const char *str, u64 timestamp); +int comm__override(struct comm *comm, const char *str, u64 timestamp, + bool exec); #endif /* __PERF_COMM_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 1e5e2e5af6b1..57ff826f150b 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -222,7 +222,8 @@ static int perf_parse_file(config_fn_t fn, void *data) const unsigned char *bomptr = utf8_bom; for (;;) { - int c = get_next_char(); + int line, c = get_next_char(); + if (bomptr && *bomptr) { /* We are at the file beginning; skip UTF8-encoded BOM * if present. Sane editors won't put this in on their @@ -261,8 +262,16 @@ static int perf_parse_file(config_fn_t fn, void *data) if (!isalpha(c)) break; var[baselen] = tolower(c); - if (get_value(fn, data, var, baselen+1) < 0) + + /* + * The get_value function might or might not reach the '\n', + * so saving the current line number for error reporting. + */ + line = config_linenr; + if (get_value(fn, data, var, baselen+1) < 0) { + config_linenr = line; break; + } } die("bad config file line %d in %s", config_linenr, config_file_name); } @@ -286,6 +295,21 @@ static int parse_unit_factor(const char *end, unsigned long *val) return 0; } +static int perf_parse_llong(const char *value, long long *ret) +{ + if (value && *value) { + char *end; + long long val = strtoll(value, &end, 0); + unsigned long factor = 1; + + if (!parse_unit_factor(end, &factor)) + return 0; + *ret = val * factor; + return 1; + } + return 0; +} + static int perf_parse_long(const char *value, long *ret) { if (value && *value) { @@ -307,6 +331,15 @@ static void die_bad_config(const char *name) die("bad config value for '%s'", name); } +u64 perf_config_u64(const char *name, const char *value) +{ + long long ret = 0; + + if (!perf_parse_llong(value, &ret)) + die_bad_config(name); + return (u64) ret; +} + int perf_config_int(const char *name, const char *value) { long ret = 0; @@ -372,6 +405,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "ui.")) return perf_ui_config(var, value); + if (!prefixcmp(var, "call-graph.")) + return perf_callchain_config(var, value); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 29d720cf5844..1921942fc2e0 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -50,12 +50,14 @@ static int open_file_read(struct perf_data_file *file) { struct stat st; int fd; + char sbuf[STRERR_BUFSIZE]; fd = open(file->path, O_RDONLY); if (fd < 0) { int err = errno; - pr_err("failed to open %s: %s", file->path, strerror(err)); + pr_err("failed to open %s: %s", file->path, + strerror_r(err, sbuf, sizeof(sbuf))); if (err == ENOENT && !strcmp(file->path, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); @@ -88,6 +90,7 @@ static int open_file_read(struct perf_data_file *file) static int open_file_write(struct perf_data_file *file) { int fd; + char sbuf[STRERR_BUFSIZE]; if (check_backup(file)) return -1; @@ -95,7 +98,8 @@ static int open_file_write(struct perf_data_file *file) fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); if (fd < 0) - pr_err("failed to open %s : %s\n", file->path, strerror(errno)); + pr_err("failed to open %s : %s\n", file->path, + strerror_r(errno, sbuf, sizeof(sbuf))); return fd; } diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 71d419362634..ba357f3226c6 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -13,8 +13,12 @@ #include "util.h" #include "target.h" +#define NSECS_PER_SEC 1000000000ULL +#define NSECS_PER_USEC 1000ULL + int verbose; bool dump_trace = false, quiet = false; +int debug_ordered_events; static int _eprintf(int level, int var, const char *fmt, va_list args) { @@ -42,6 +46,35 @@ int eprintf(int level, int var, const char *fmt, ...) return ret; } +static int __eprintf_time(u64 t, const char *fmt, va_list args) +{ + int ret = 0; + u64 secs, usecs, nsecs = t; + + secs = nsecs / NSECS_PER_SEC; + nsecs -= secs * NSECS_PER_SEC; + usecs = nsecs / NSECS_PER_USEC; + + ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ", + secs, usecs); + ret += vfprintf(stderr, fmt, args); + return ret; +} + +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) +{ + int ret = 0; + va_list args; + + if (var >= level) { + va_start(args, fmt); + ret = __eprintf_time(t, fmt, args); + va_end(args); + } + + return ret; +} + /* * Overloading libtraceevent standard info print * function, display with -v in perf. @@ -110,7 +143,8 @@ static struct debug_variable { const char *name; int *ptr; } debug_variables[] = { - { .name = "verbose", .ptr = &verbose }, + { .name = "verbose", .ptr = &verbose }, + { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 89fb6b0f7ab2..be264d6f3b30 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -3,6 +3,7 @@ #define __PERF_DEBUG_H #include <stdbool.h> +#include <string.h> #include "event.h" #include "../ui/helpline.h" #include "../ui/progress.h" @@ -10,6 +11,7 @@ extern int verbose; extern bool quiet, dump_trace; +extern int debug_ordered_events; #ifndef pr_fmt #define pr_fmt(fmt) fmt @@ -29,6 +31,14 @@ extern bool quiet, dump_trace; #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_time_N(n, var, t, fmt, ...) \ + eprintf_time(n, var, t, fmt, ##__VA_ARGS__) + +#define pr_oe_time(t, fmt, ...) pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) + +#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ + int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); @@ -38,6 +48,7 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); void pr_stat(const char *fmt, ...); int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); int perf_debug_option(const char *str); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 90d02c661dd4..0247acfdfaca 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso, { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; int ret = 0; + size_t len; switch (type) { case DSO_BINARY_TYPE__DEBUGLINK: { @@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso, break; case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: - snprintf(filename, size, "%s/usr/lib/debug%s.debug", - symbol_conf.symfs, dso->long_name); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug"); + snprintf(filename + len, size - len, "%s.debug", dso->long_name); break; case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: - snprintf(filename, size, "%s/usr/lib/debug%s", - symbol_conf.symfs, dso->long_name); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug"); + snprintf(filename + len, size - len, "%s", dso->long_name); break; case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: { const char *last_slash; - size_t len; size_t dir_size; last_slash = dso->long_name + dso->long_name_len; while (last_slash != dso->long_name && *last_slash != '/') last_slash--; - len = scnprintf(filename, size, "%s", symbol_conf.symfs); + len = __symbol__join_symfs(filename, size, ""); dir_size = last_slash - dso->long_name + 2; if (dir_size > (size - len)) { ret = -1; @@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso, build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); - snprintf(filename, size, - "%s/usr/lib/debug/.build-id/%.2s/%s.debug", - symbol_conf.symfs, build_id_hex, build_id_hex + 2); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/"); + snprintf(filename + len, size - len, "%.2s/%s.debug", + build_id_hex, build_id_hex + 2); break; case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: - snprintf(filename, size, "%s%s", - symbol_conf.symfs, dso->long_name); + __symbol__join_symfs(filename, size, dso->long_name); break; case DSO_BINARY_TYPE__GUEST_KMODULE: - snprintf(filename, size, "%s%s%s", symbol_conf.symfs, - root_dir, dso->long_name); + path__join3(filename, size, symbol_conf.symfs, + root_dir, dso->long_name); break; case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: - snprintf(filename, size, "%s%s", symbol_conf.symfs, - dso->long_name); + __symbol__join_symfs(filename, size, dso->long_name); break; case DSO_BINARY_TYPE__KCORE: @@ -164,13 +162,15 @@ static void close_first_dso(void); static int do_open(char *name) { int fd; + char sbuf[STRERR_BUFSIZE]; do { fd = open(name, O_RDONLY); if (fd >= 0) return fd; - pr_debug("dso open failed, mmap: %s\n", strerror(errno)); + pr_debug("dso open failed, mmap: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); if (!dso__data_open_cnt || errno != EMFILE) break; @@ -532,10 +532,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size) static int data_file_size(struct dso *dso) { struct stat st; + char sbuf[STRERR_BUFSIZE]; if (!dso->data.file_size) { if (fstat(dso->data.fd, &st)) { - pr_err("dso mmap failed, fstat: %s\n", strerror(errno)); + pr_err("dso mmap failed, fstat: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } dso->data.file_size = st.st_size; @@ -651,6 +653,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name, return dso; } +/* + * Find a matching entry and/or link current entry to RB tree. + * Either one of the dso or name parameter must be non-NULL or the + * function will not work. + */ +static struct dso *dso__findlink_by_longname(struct rb_root *root, + struct dso *dso, const char *name) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + if (!name) + name = dso->long_name; + /* + * Find node with the matching name + */ + while (*p) { + struct dso *this = rb_entry(*p, struct dso, rb_node); + int rc = strcmp(name, this->long_name); + + parent = *p; + if (rc == 0) { + /* + * In case the new DSO is a duplicate of an existing + * one, print an one-time warning & put the new entry + * at the end of the list of duplicates. + */ + if (!dso || (dso == this)) + return this; /* Find matching dso */ + /* + * The core kernel DSOs may have duplicated long name. + * In this case, the short name should be different. + * Comparing the short names to differentiate the DSOs. + */ + rc = strcmp(dso->short_name, this->short_name); + if (rc == 0) { + pr_err("Duplicated dso name: %s\n", name); + return NULL; + } + } + if (rc < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + if (dso) { + /* Add new node and rebalance tree */ + rb_link_node(&dso->rb_node, parent, p); + rb_insert_color(&dso->rb_node, root); + } + return NULL; +} + +static inline struct dso * +dso__find_by_longname(const struct rb_root *root, const char *name) +{ + return dso__findlink_by_longname((struct rb_root *)root, NULL, name); +} + void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) { if (name == NULL) @@ -753,6 +814,7 @@ struct dso *dso__new(const char *name) dso->a2l_fails = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; + RB_CLEAR_NODE(&dso->rb_node); INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); } @@ -763,6 +825,10 @@ struct dso *dso__new(const char *name) void dso__delete(struct dso *dso) { int i; + + if (!RB_EMPTY_NODE(&dso->rb_node)) + pr_err("DSO %s is still in rbtree when being deleted!\n", + dso->long_name); for (i = 0; i < MAP__NR_TYPES; ++i) symbols__delete(&dso->symbols[i]); @@ -849,35 +915,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } -void dsos__add(struct list_head *head, struct dso *dso) +void dsos__add(struct dsos *dsos, struct dso *dso) { - list_add_tail(&dso->node, head); + list_add_tail(&dso->node, &dsos->head); + dso__findlink_by_longname(&dsos->root, dso, NULL); } -struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short) +struct dso *dsos__find(const struct dsos *dsos, const char *name, + bool cmp_short) { struct dso *pos; if (cmp_short) { - list_for_each_entry(pos, head, node) + list_for_each_entry(pos, &dsos->head, node) if (strcmp(pos->short_name, name) == 0) return pos; return NULL; } - list_for_each_entry(pos, head, node) - if (strcmp(pos->long_name, name) == 0) - return pos; - return NULL; + return dso__find_by_longname(&dsos->root, name); } -struct dso *__dsos__findnew(struct list_head *head, const char *name) +struct dso *__dsos__findnew(struct dsos *dsos, const char *name) { - struct dso *dso = dsos__find(head, name, false); + struct dso *dso = dsos__find(dsos, name, false); if (!dso) { dso = dso__new(name); if (dso != NULL) { - dsos__add(head, dso); + dsos__add(dsos, dso); dso__set_basename(dso); } } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 5e463c0964d4..acb651acc7fd 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -90,8 +90,18 @@ struct dso_cache { char data[0]; }; +/* + * DSOs are put into both a list for fast iteration and rbtree for fast + * long name lookup. + */ +struct dsos { + struct list_head head; + struct rb_root root; /* rbtree root sorted by long name */ +}; + struct dso { struct list_head node; + struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; void *a2l; @@ -224,10 +234,10 @@ struct map *dso__new_map(const char *name); struct dso *dso__kernel_findnew(struct machine *machine, const char *name, const char *short_name, int dso_type); -void dsos__add(struct list_head *head, struct dso *dso); -struct dso *dsos__find(const struct list_head *head, const char *name, +void dsos__add(struct dsos *dsos, struct dso *dso); +struct dso *dsos__find(const struct dsos *dsos, const char *name, bool cmp_short); -struct dso *__dsos__findnew(struct list_head *head, const char *name); +struct dso *__dsos__findnew(struct dsos *dsos, const char *name); bool __dsos__read_build_ids(struct list_head *head, bool with_hits); size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1398c83d896d..4af6b279e34a 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -558,13 +558,17 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, struct map *map; struct kmap *kmap; int err; + union perf_event *event; + + if (machine->vmlinux_maps[0] == NULL) + return -1; + /* * We should get this from /sys/kernel/sections/.text, but till that is * available use this, and after it is use this as a fallback for older * kernels. */ - union perf_event *event = zalloc((sizeof(event->mmap) + - machine->id_hdr_size)); + event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -784,9 +788,9 @@ try_again: * "[vdso]" dso, but for now lets use the old trick of looking * in the whole kernel symbol list. */ - if ((long long)al->addr < 0 && - cpumode == PERF_RECORD_MISC_USER && - machine && mg != &machine->kmaps) { + if (cpumode == PERF_RECORD_MISC_USER && machine && + mg != &machine->kmaps && + machine__kernel_ip(machine, al->addr)) { mg = &machine->kmaps; load_map = true; goto try_again; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 94d6976180da..5699e7e2a790 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -156,6 +156,8 @@ struct perf_sample { u32 cpu; u32 raw_size; u64 data_src; + u32 flags; + u16 insn_len; void *raw_data; struct ip_callchain *callchain; struct branch_stack *branch_stack; @@ -188,6 +190,32 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_HEADER_MAX }; +/* + * The kernel collects the number of events it couldn't send in a stretch and + * when possible sends this number in a PERF_RECORD_LOST event. The number of + * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while + * total_lost tells exactly how many events the kernel in fact lost, i.e. it is + * the sum of all struct lost_event.lost fields reported. + * + * The total_period is needed because by default auto-freq is used, so + * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get + * the total number of low level events, it is necessary to to sum all struct + * sample_event.period and stash the result in total_period. + */ +struct events_stats { + u64 total_period; + u64 total_non_filtered_period; + u64 total_lost; + u64 total_invalid_chains; + u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_non_filtered_samples; + u32 nr_lost_warned; + u32 nr_unknown_events; + u32 nr_invalid_chains; + u32 nr_unknown_id; + u32 nr_unprocessable_samples; +}; + struct attr_event { struct perf_event_header header; struct perf_event_attr attr; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 814e954c1318..3c9e77d6b4c2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -25,6 +25,9 @@ #include <linux/bitops.h> #include <linux/hash.h> +static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx); +static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx); + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) @@ -37,6 +40,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, INIT_HLIST_HEAD(&evlist->heads[i]); INIT_LIST_HEAD(&evlist->entries); perf_evlist__set_maps(evlist, cpus, threads); + fdarray__init(&evlist->pollfd, 64); evlist->workload.pid = -1; } @@ -102,7 +106,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { zfree(&evlist->mmap); - zfree(&evlist->pollfd); + fdarray__exit(&evlist->pollfd); } void perf_evlist__delete(struct perf_evlist *evlist) @@ -122,6 +126,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { list_add_tail(&entry->node, &evlist->entries); entry->idx = evlist->nr_entries; + entry->tracking = !entry->idx; if (!evlist->nr_entries++) perf_evlist__set_id_pos(evlist); @@ -265,17 +270,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, return 0; } +static int perf_evlist__nr_threads(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + if (evsel->system_wide) + return 1; + else + return thread_map__nr(evlist->threads); +} + void perf_evlist__disable(struct perf_evlist *evlist) { int cpu, thread; struct perf_evsel *pos; int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_threads; for (cpu = 0; cpu < nr_cpus; cpu++) { evlist__for_each(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; + nr_threads = perf_evlist__nr_threads(evlist, pos); for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); @@ -288,12 +303,13 @@ void perf_evlist__enable(struct perf_evlist *evlist) int cpu, thread; struct perf_evsel *pos; int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_threads; for (cpu = 0; cpu < nr_cpus; cpu++) { evlist__for_each(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; + nr_threads = perf_evlist__nr_threads(evlist, pos); for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); @@ -305,12 +321,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist, struct perf_evsel *evsel) { int cpu, thread, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return 0; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { + for (thread = 0; thread < nr_threads; thread++) { err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); if (err) @@ -324,12 +342,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist, struct perf_evsel *evsel) { int cpu, thread, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return -EINVAL; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { + for (thread = 0; thread < nr_threads; thread++) { err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) @@ -339,21 +359,111 @@ int perf_evlist__enable_event(struct perf_evlist *evlist, return 0; } -static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, + struct perf_evsel *evsel, int cpu) +{ + int thread, err; + int nr_threads = perf_evlist__nr_threads(evlist, evsel); + + if (!evsel->fd) + return -EINVAL; + + for (thread = 0; thread < nr_threads; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + return 0; +} + +static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int thread) +{ + int cpu, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + + if (!evsel->fd) + return -EINVAL; + + for (cpu = 0; cpu < nr_cpus; cpu++) { + err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + return 0; +} + +int perf_evlist__enable_event_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx) +{ + bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus); + + if (per_cpu_mmaps) + return perf_evlist__enable_event_cpu(evlist, evsel, idx); + else + return perf_evlist__enable_event_thread(evlist, evsel, idx); +} + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nr_cpus = cpu_map__nr(evlist->cpus); int nr_threads = thread_map__nr(evlist->threads); - int nfds = nr_cpus * nr_threads * evlist->nr_entries; - evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); - return evlist->pollfd != NULL ? 0 : -ENOMEM; + int nfds = 0; + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->system_wide) + nfds += nr_cpus; + else + nfds += nr_cpus * nr_threads; + } + + if (fdarray__available_entries(&evlist->pollfd) < nfds && + fdarray__grow(&evlist->pollfd, nfds) < 0) + return -ENOMEM; + + return 0; +} + +static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx) +{ + int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP); + /* + * Save the idx so that when we filter out fds POLLHUP'ed we can + * close the associated evlist->mmap[] entry. + */ + if (pos >= 0) { + evlist->pollfd.priv[pos].idx = idx; + + fcntl(fd, F_SETFL, O_NONBLOCK); + } + + return pos; +} + +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +{ + return __perf_evlist__add_pollfd(evlist, fd, -1); +} + +static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd) +{ + struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd); + + perf_evlist__mmap_put(evlist, fda->priv[fd].idx); +} + +int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) +{ + return fdarray__filter(&evlist->pollfd, revents_and_mask, + perf_evlist__munmap_filtered); } -void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +int perf_evlist__poll(struct perf_evlist *evlist, int timeout) { - fcntl(fd, F_SETFL, O_NONBLOCK); - evlist->pollfd[evlist->nr_fds].fd = fd; - evlist->pollfd[evlist->nr_fds].events = POLLIN; - evlist->nr_fds++; + return fdarray__poll(&evlist->pollfd, timeout); } static void perf_evlist__id_hash(struct perf_evlist *evlist, @@ -566,14 +676,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) return event; } +static bool perf_mmap__empty(struct perf_mmap *md) +{ + return perf_mmap__read_head(md) != md->prev; +} + +static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx) +{ + ++evlist->mmap[idx].refcnt; +} + +static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx) +{ + BUG_ON(evlist->mmap[idx].refcnt == 0); + + if (--evlist->mmap[idx].refcnt == 0) + __perf_evlist__munmap(evlist, idx); +} + void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { + struct perf_mmap *md = &evlist->mmap[idx]; + if (!evlist->overwrite) { - struct perf_mmap *md = &evlist->mmap[idx]; unsigned int old = md->prev; perf_mmap__write_tail(md, old); } + + if (md->refcnt == 1 && perf_mmap__empty(md)) + perf_evlist__mmap_put(evlist, idx); } static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) @@ -581,6 +713,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) if (evlist->mmap[idx].base != NULL) { munmap(evlist->mmap[idx].base, evlist->mmap_len); evlist->mmap[idx].base = NULL; + evlist->mmap[idx].refcnt = 0; } } @@ -614,6 +747,20 @@ struct mmap_params { static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, struct mmap_params *mp, int fd) { + /* + * The last one will be done at perf_evlist__mmap_consume(), so that we + * make sure we don't prevent tools from consuming every last event in + * the ring buffer. + * + * I.e. we can get the POLLHUP meaning that the fd doesn't exist + * anymore, but the last events for it are still in the ring buffer, + * waiting to be consumed. + * + * Tools can chose to ignore this at their own discretion, but the + * evlist layer can't just drop it when filtering events in + * perf_evlist__filter_pollfd(). + */ + evlist->mmap[idx].refcnt = 2; evlist->mmap[idx].prev = 0; evlist->mmap[idx].mask = mp->mask; evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot, @@ -625,7 +772,6 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, return -1; } - perf_evlist__add_pollfd(evlist, fd); return 0; } @@ -636,7 +782,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, struct perf_evsel *evsel; evlist__for_each(evlist, evsel) { - int fd = FD(evsel, cpu, thread); + int fd; + + if (evsel->system_wide && thread) + continue; + + fd = FD(evsel, cpu, thread); if (*output == -1) { *output = fd; @@ -645,6 +796,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; + + perf_evlist__mmap_get(evlist, idx); + } + + if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) { + perf_evlist__mmap_put(evlist, idx); + return -1; } if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -804,7 +962,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; - if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM; evlist->overwrite = overwrite; @@ -845,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) out_delete_threads: thread_map__delete(evlist->threads); + evlist->threads = NULL; return -1; } @@ -1017,11 +1176,51 @@ void perf_evlist__close(struct perf_evlist *evlist) } } +static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) +{ + int err = -ENOMEM; + + /* + * Try reading /sys/devices/system/cpu/online to get + * an all cpus map. + * + * FIXME: -ENOMEM is the best we can do here, the cpu_map + * code needs an overhaul to properly forward the + * error, and we may not want to do that fallback to a + * default cpu identity map :-\ + */ + evlist->cpus = cpu_map__new(NULL); + if (evlist->cpus == NULL) + goto out; + + evlist->threads = thread_map__new_dummy(); + if (evlist->threads == NULL) + goto out_free_cpus; + + err = 0; +out: + return err; +out_free_cpus: + cpu_map__delete(evlist->cpus); + evlist->cpus = NULL; + goto out; +} + int perf_evlist__open(struct perf_evlist *evlist) { struct perf_evsel *evsel; int err; + /* + * Default: one fd per CPU, all threads, aka systemwide + * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL + */ + if (evlist->threads == NULL && evlist->cpus == NULL) { + err = perf_evlist__create_syswide_maps(evlist); + if (err < 0) + goto out_err; + } + perf_evlist__update_id_pos(evlist); evlist__for_each(evlist, evsel) { @@ -1061,6 +1260,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar } if (!evlist->workload.pid) { + int ret; + if (pipe_output) dup2(2, 1); @@ -1078,8 +1279,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar /* * Wait until the parent tells us to go. */ - if (read(go_pipe[0], &bf, 1) == -1) - perror("unable to read pipe"); + ret = read(go_pipe[0], &bf, 1); + /* + * The parent will ask for the execvp() to be performed by + * writing exactly one byte, in workload.cork_fd, usually via + * perf_evlist__start_workload(). + * + * For cancelling the workload without actuallin running it, + * the parent will just close workload.cork_fd, without writing + * anything, i.e. read will return zero and we just exit() + * here. + */ + if (ret != 1) { + if (ret == -1) + perror("unable to read pipe"); + exit(ret); + } execvp(argv[0], (char **)argv); @@ -1102,8 +1317,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar sigaction(SIGUSR1, &act, NULL); } - if (target__none(target)) + if (target__none(target)) { + if (evlist->threads == NULL) { + fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n", + __func__, __LINE__); + goto out_close_pipes; + } evlist->threads->map[0] = evlist->workload.pid; + } close(child_ready_pipe[1]); close(go_pipe[0]); @@ -1202,7 +1423,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, int err, char *buf, size_t size) { int printed, value; - char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); switch (err) { case EACCES: @@ -1250,3 +1471,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist, list_splice(&move, &evlist->entries); } + +void perf_evlist__set_tracking_event(struct perf_evlist *evlist, + struct perf_evsel *tracking_evsel) +{ + struct perf_evsel *evsel; + + if (tracking_evsel->tracking) + return; + + evlist__for_each(evlist, evsel) { + if (evsel != tracking_evsel) + evsel->tracking = false; + } + + tracking_evsel->tracking = true; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index f5173cd63693..649b0c597283 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -2,6 +2,7 @@ #define __PERF_EVLIST_H 1 #include <linux/list.h> +#include <api/fd/array.h> #include <stdio.h> #include "../perf.h" #include "event.h" @@ -17,9 +18,15 @@ struct record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +/** + * struct perf_mmap - perf's ring buffer mmap details + * + * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this + */ struct perf_mmap { void *base; int mask; + int refcnt; unsigned int prev; char event_copy[PERF_SAMPLE_MAX_SIZE]; }; @@ -29,7 +36,6 @@ struct perf_evlist { struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; int nr_groups; - int nr_fds; int nr_mmaps; size_t mmap_len; int id_pos; @@ -40,8 +46,8 @@ struct perf_evlist { pid_t pid; } workload; bool overwrite; + struct fdarray pollfd; struct perf_mmap *mmap; - struct pollfd *pollfd; struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; @@ -82,7 +88,11 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); -void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); +int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask); + +int perf_evlist__poll(struct perf_evlist *evlist, int timeout); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); @@ -107,6 +117,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, void *ucontext)); int perf_evlist__start_workload(struct perf_evlist *evlist); +struct option; + int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); @@ -122,6 +134,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist, struct perf_evsel *evsel); int perf_evlist__enable_event(struct perf_evlist *evlist, struct perf_evsel *evsel); +int perf_evlist__enable_event_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx); void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); @@ -262,4 +276,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, #define evlist__for_each_safe(evlist, tmp, evsel) \ __evlist__for_each_safe(&(evlist)->entries, tmp, evsel) +void perf_evlist__set_tracking_event(struct perf_evlist *evlist, + struct perf_evsel *tracking_evsel); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 21a373ebea22..2f9e68025ede 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -15,6 +15,8 @@ #include <linux/perf_event.h> #include <sys/resource.h> #include "asm/bug.h" +#include "callchain.h" +#include "cgroup.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -32,6 +34,48 @@ static struct { bool cloexec; } perf_missing_features; +static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) +{ + return 0; +} + +static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) +{ +} + +static struct { + size_t size; + int (*init)(struct perf_evsel *evsel); + void (*fini)(struct perf_evsel *evsel); +} perf_evsel__object = { + .size = sizeof(struct perf_evsel), + .init = perf_evsel__no_extra_init, + .fini = perf_evsel__no_extra_fini, +}; + +int perf_evsel__object_config(size_t object_size, + int (*init)(struct perf_evsel *evsel), + void (*fini)(struct perf_evsel *evsel)) +{ + + if (object_size == 0) + goto set_methods; + + if (perf_evsel__object.size > object_size) + return -EINVAL; + + perf_evsel__object.size = object_size; + +set_methods: + if (init != NULL) + perf_evsel__object.init = init; + + if (fini != NULL) + perf_evsel__object.fini = fini; + + return 0; +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) int __perf_evsel__sample_size(u64 sample_type) @@ -116,16 +160,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel) evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); } -void hists__init(struct hists *hists) -{ - memset(hists, 0, sizeof(*hists)); - hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; - hists->entries_in = &hists->entries_in_array[0]; - hists->entries_collapsed = RB_ROOT; - hists->entries = RB_ROOT; - pthread_mutex_init(&hists->lock, NULL); -} - void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, enum perf_event_sample_format bit) { @@ -162,19 +196,20 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; + evsel->tracking = !idx; evsel->attr = *attr; evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; INIT_LIST_HEAD(&evsel->node); - hists__init(&evsel->hists); + perf_evsel__object.init(evsel); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) perf_evsel__init(evsel, attr, idx); @@ -184,7 +219,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) { struct perf_event_attr attr = { @@ -502,20 +537,19 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) } static void -perf_evsel__config_callgraph(struct perf_evsel *evsel, - struct record_opts *opts) +perf_evsel__config_callgraph(struct perf_evsel *evsel) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - if (opts->call_graph == CALLCHAIN_DWARF) { + if (callchain_param.record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = opts->stack_dump_size; + attr->sample_stack_user = callchain_param.dump_size; attr->exclude_callchain_user = 1; } else { pr_info("Cannot use DWARF unwind for function trace event," @@ -561,7 +595,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) { struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; - int track = !evsel->idx; /* only the first counter needs these */ + int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; @@ -624,8 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph_enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel, opts); + if (callchain_param.enabled && !evsel->no_aux_samples) + perf_evsel__config_callgraph(evsel); if (target__has_cpu(&opts->target)) perf_evsel__set_sample_bit(evsel, CPU); @@ -633,9 +667,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->period) perf_evsel__set_sample_bit(evsel, PERIOD); - if (!perf_missing_features.sample_id_all && - (opts->sample_time || !opts->no_inherit || - target__has_cpu(&opts->target) || per_cpu)) + /* + * When the user explicitely disabled time don't force it here. + */ + if (opts->sample_time && + (!perf_missing_features.sample_id_all && + (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu))) perf_evsel__set_sample_bit(evsel, TIME); if (opts->raw_samples && !evsel->no_aux_samples) { @@ -689,9 +726,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) } } -int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; + + if (evsel->system_wide) + nthreads = 1; + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { @@ -710,6 +751,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd = FD(evsel, cpu, thread), @@ -740,6 +784,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { + if (evsel->system_wide) + nthreads = 1; + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); if (evsel->sample_id == NULL) return -ENOMEM; @@ -767,13 +814,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) return evsel->counts != NULL ? 0 : -ENOMEM; } -void perf_evsel__free_fd(struct perf_evsel *evsel) +static void perf_evsel__free_fd(struct perf_evsel *evsel) { xyarray__delete(evsel->fd); evsel->fd = NULL; } -void perf_evsel__free_id(struct perf_evsel *evsel) +static void perf_evsel__free_id(struct perf_evsel *evsel) { xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; @@ -784,6 +831,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) for (thread = 0; thread < nthreads; ++thread) { close(FD(evsel, cpu, thread)); @@ -801,16 +851,17 @@ void perf_evsel__exit(struct perf_evsel *evsel) assert(list_empty(&evsel->node)); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); -} - -void perf_evsel__delete(struct perf_evsel *evsel) -{ - perf_evsel__exit(evsel); close_cgroup(evsel->cgrp); zfree(&evsel->group_name); if (evsel->tp_format) pevent_free_format(evsel->tp_format); zfree(&evsel->name); + perf_evsel__object.fini(evsel); +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + perf_evsel__exit(evsel); free(evsel); } @@ -872,6 +923,9 @@ int __perf_evsel__read(struct perf_evsel *evsel, int cpu, thread; struct perf_counts_values *aggr = &evsel->counts->aggr, count; + if (evsel->system_wide) + nthreads = 1; + aggr->val = aggr->ena = aggr->run = 0; for (cpu = 0; cpu < ncpus; cpu++) { @@ -994,13 +1048,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { - int cpu, thread; + int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; + if (evsel->system_wide) + nthreads = 1; + else + nthreads = threads->nr; + if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0) return -ENOMEM; if (evsel->cgrp) { @@ -1024,10 +1083,10 @@ retry_sample_id: for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { + for (thread = 0; thread < nthreads; thread++) { int group_fd; - if (!evsel->cgrp) + if (!evsel->cgrp && !evsel->system_wide) pid = threads->map[thread]; group_fd = get_group_fd(evsel, cpu, thread); @@ -1100,7 +1159,7 @@ out_close: close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } - thread = threads->nr; + thread = nthreads; } while (--cpu >= 0); return err; } @@ -2002,6 +2061,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { + char sbuf[STRERR_BUFSIZE]; + switch (err) { case EPERM: case EACCES: @@ -2036,13 +2097,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); #endif break; + case EBUSY: + if (find_process("oprofiled")) + return scnprintf(msg, size, + "The PMU counters are busy/taken by another profiler.\n" + "We found oprofile daemon running, please stop it and try again."); + break; default: break; } return scnprintf(msg, size, - "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg may provide additional information.\n" "No CONFIG_PERF_EVENTS=y kernel support configured?\n", - err, strerror(err), perf_evsel__name(evsel)); + err, strerror_r(err, sbuf, sizeof(sbuf)), + perf_evsel__name(evsel)); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d7f93ce0ebc1..163c5604e5d1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -7,8 +7,6 @@ #include <linux/perf_event.h> #include <linux/types.h> #include "xyarray.h" -#include "cgroup.h" -#include "hist.h" #include "symbol.h" struct perf_counts_values { @@ -43,6 +41,8 @@ struct perf_sample_id { u64 period; }; +struct cgroup_sel; + /** struct perf_evsel - event selector * * @name - Can be set to retain the original event name passed by the user, @@ -66,7 +66,6 @@ struct perf_evsel { struct perf_counts *prev_raw_counts; int idx; u32 ids; - struct hists hists; char *name; double scale; const char *unit; @@ -85,6 +84,8 @@ struct perf_evsel { bool needs_swap; bool no_aux_samples; bool immediate; + bool system_wide; + bool tracking; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -98,13 +99,16 @@ union u64_swap { u32 val32[2]; }; -#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) - struct cpu_map; +struct target; struct thread_map; struct perf_evlist; struct record_opts; +int perf_evsel__object_config(size_t object_size, + int (*init)(struct perf_evsel *evsel), + void (*fini)(struct perf_evsel *evsel)); + struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) @@ -151,12 +155,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel); const char *perf_evsel__group_name(struct perf_evsel *evsel); int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); -int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); -void perf_evsel__free_fd(struct perf_evsel *evsel); -void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__free_counts(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); @@ -279,8 +280,6 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel, return __perf_evsel__read(evsel, ncpus, nthreads, true); } -void hists__init(struct hists *hists); - int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 158c787ce0c4..26f5b2fe5dc8 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -214,11 +214,11 @@ static int machine__hit_all_dsos(struct machine *machine) { int err; - err = __dsos__hit_all(&machine->kernel_dsos); + err = __dsos__hit_all(&machine->kernel_dsos.head); if (err) return err; - return __dsos__hit_all(&machine->user_dsos); + return __dsos__hit_all(&machine->user_dsos.head); } int dsos__hit_all(struct perf_session *session) @@ -288,11 +288,12 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine, machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, machine, - machine->pid, umisc, fd); + err = __dsos__write_buildid_table(&machine->user_dsos.head, + machine, machine->pid, umisc, + fd); return err; } @@ -455,9 +456,10 @@ static int __dsos__cache_build_ids(struct list_head *head, static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine, + debugdir); return ret; } @@ -483,8 +485,10 @@ static int perf_session__cache_build_ids(struct perf_session *session) static bool machine__read_build_ids(struct machine *machine, bool with_hits) { - bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits); - ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits); + bool ret; + + ret = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits); + ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits); return ret; } @@ -575,16 +579,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused, return do_write_string(fd, perf_version_string); } -static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int __write_cpudesc(int fd, const char *cpuinfo_proc) { -#ifndef CPUINFO_PROC -#define CPUINFO_PROC NULL -#endif FILE *file; char *buf = NULL; char *s, *p; - const char *search = CPUINFO_PROC; + const char *search = cpuinfo_proc; size_t len = 0; int ret = -1; @@ -634,6 +634,25 @@ done: return ret; } +static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ +#ifndef CPUINFO_PROC +#define CPUINFO_PROC {"model name", } +#endif + const char *cpuinfo_procs[] = CPUINFO_PROC; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { + int ret; + ret = __write_cpudesc(fd, cpuinfo_procs[i]); + if (ret >= 0) + return ret; + } + return -1; +} + + static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused) { @@ -1548,7 +1567,7 @@ static int __event_process_build_id(struct build_id_event *bev, struct perf_session *session) { int err = -1; - struct list_head *head; + struct dsos *dsos; struct machine *machine; u16 misc; struct dso *dso; @@ -1563,22 +1582,22 @@ static int __event_process_build_id(struct build_id_event *bev, switch (misc) { case PERF_RECORD_MISC_KERNEL: dso_type = DSO_TYPE_KERNEL; - head = &machine->kernel_dsos; + dsos = &machine->kernel_dsos; break; case PERF_RECORD_MISC_GUEST_KERNEL: dso_type = DSO_TYPE_GUEST_KERNEL; - head = &machine->kernel_dsos; + dsos = &machine->kernel_dsos; break; case PERF_RECORD_MISC_USER: case PERF_RECORD_MISC_GUEST_USER: dso_type = DSO_TYPE_USER; - head = &machine->user_dsos; + dsos = &machine->user_dsos; break; default: goto out; } - dso = __dsos__findnew(head, filename); + dso = __dsos__findnew(dsos, filename); if (dso != NULL) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 30df6187ee02..6e88b9e395df 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -3,6 +3,7 @@ #include "hist.h" #include "session.h" #include "sort.h" +#include "evlist.h" #include "evsel.h" #include "annotate.h" #include <math.h> @@ -14,13 +15,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); -struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_REL, - .min_percent = 0.5, - .order = ORDER_CALLEE, - .key = CCKEY_FUNCTION -}; - u16 hists__col_len(struct hists *hists, enum hist_column col) { return hists->col_len[col]; @@ -277,6 +271,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) } } +void hists__delete_entries(struct hists *hists) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hists->entries); + + if (sort__need_collapse) + rb_erase(&n->rb_node_in, &hists->entries_collapsed); + + --hists->nr_entries; + if (!n->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__free(n); + } +} + /* * histogram, sorted on item, collects periods */ @@ -494,6 +510,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al { u64 cost; struct mem_info *mi = iter->priv; + struct hists *hists = evsel__hists(iter->evsel); struct hist_entry *he; if (mi == NULL) @@ -510,7 +527,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al * and this is indirectly achieved by passing period=weight here * and the he_stat__add_period() function. */ - he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi, + he = __hists__add_entry(hists, al, iter->parent, NULL, mi, cost, cost, 0, true); if (!he) return -ENOMEM; @@ -524,13 +541,14 @@ iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he = iter->he; int err = -EINVAL; if (he == NULL) goto out; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); err = hist_entry__append_callchain(he, iter->sample); @@ -596,6 +614,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a { struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he = NULL; int i = iter->curr; int err = 0; @@ -609,12 +628,12 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ - he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL, + he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, 1, 1, 0, true); if (he == NULL) return -ENOMEM; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); out: iter->he = he; @@ -646,7 +665,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct perf_sample *sample = iter->sample; struct hist_entry *he; - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, true); if (he == NULL) @@ -669,7 +688,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, iter->he = NULL; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(evsel__hists(evsel), he->filtered); return hist_entry__append_callchain(he, sample); } @@ -702,12 +721,13 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; struct hist_entry *he; int err = 0; - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(hists, al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, true); if (he == NULL) @@ -724,7 +744,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, */ callchain_cursor_commit(&callchain_cursor); - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); return err; } @@ -780,7 +800,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } } - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, false); if (he == NULL) @@ -1386,6 +1406,21 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } + +size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) +{ + struct perf_evsel *pos; + size_t ret = 0; + + evlist__for_each(evlist, pos) { + ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); + ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp); + } + + return ret; +} + + u64 hists__total_period(struct hists *hists) { return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period : @@ -1412,3 +1447,31 @@ int perf_hist_config(const char *var, const char *value) return 0; } + +static int hists_evsel__init(struct perf_evsel *evsel) +{ + struct hists *hists = evsel__hists(evsel); + + memset(hists, 0, sizeof(*hists)); + hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; + hists->entries_in = &hists->entries_in_array[0]; + hists->entries_collapsed = RB_ROOT; + hists->entries = RB_ROOT; + pthread_mutex_init(&hists->lock, NULL); + return 0; +} + +/* + * XXX We probably need a hists_evsel__exit() to free the hist_entries + * stored in the rbtree... + */ + +int hists__init(void) +{ + int err = perf_evsel__object_config(sizeof(struct hists_evsel), + hists_evsel__init, NULL); + if (err) + fputs("FATAL ERROR: Couldn't setup hists class\n", stderr); + + return err; +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 742f49a85725..d0ef9a19a744 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -4,12 +4,11 @@ #include <linux/types.h> #include <pthread.h> #include "callchain.h" +#include "evsel.h" #include "header.h" #include "color.h" #include "ui/progress.h" -extern struct callchain_param callchain_param; - struct hist_entry; struct addr_location; struct symbol; @@ -23,32 +22,6 @@ enum hist_filter { HIST_FILTER__HOST, }; -/* - * The kernel collects the number of events it couldn't send in a stretch and - * when possible sends this number in a PERF_RECORD_LOST event. The number of - * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while - * total_lost tells exactly how many events the kernel in fact lost, i.e. it is - * the sum of all struct lost_event.lost fields reported. - * - * The total_period is needed because by default auto-freq is used, so - * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get - * the total number of low level events, it is necessary to to sum all struct - * sample_event.period and stash the result in total_period. - */ -struct events_stats { - u64 total_period; - u64 total_non_filtered_period; - u64 total_lost; - u64 total_invalid_chains; - u32 nr_events[PERF_RECORD_HEADER_MAX]; - u32 nr_non_filtered_samples; - u32 nr_lost_warned; - u32 nr_unknown_events; - u32 nr_invalid_chains; - u32 nr_unknown_id; - u32 nr_unprocessable_samples; -}; - enum hist_column { HISTC_SYMBOL, HISTC_DSO, @@ -152,6 +125,7 @@ void hists__output_resort(struct hists *hists); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); +void hists__delete_entries(struct hists *hists); void hists__output_recalc_col_len(struct hists *hists, int max_rows); u64 hists__total_period(struct hists *hists); @@ -164,6 +138,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp); +size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -184,6 +159,25 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he); void hists__match(struct hists *leader, struct hists *other); int hists__link(struct hists *leader, struct hists *other); +struct hists_evsel { + struct perf_evsel evsel; + struct hists hists; +}; + +static inline struct perf_evsel *hists_to_evsel(struct hists *hists) +{ + struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists); + return &hevsel->evsel; +} + +static inline struct hists *evsel__hists(struct perf_evsel *evsel) +{ + struct hists_evsel *hevsel = (struct hists_evsel *)evsel; + return &hevsel->hists; +} + +int hists__init(void); + struct perf_hpp { char *buf; size_t size; @@ -192,6 +186,7 @@ struct perf_hpp { }; struct perf_hpp_fmt { + const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct perf_evsel *evsel); int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -207,6 +202,8 @@ struct perf_hpp_fmt { struct list_head list; struct list_head sort_list; bool elide; + int len; + int user_len; }; extern struct list_head perf_hpp__list; @@ -261,17 +258,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) } void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); +void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists); +void perf_hpp__set_user_width(const char *width_list_str); typedef u64 (*hpp_field_fn)(struct hist_entry *he); typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); -int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent); -int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent); +int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent); +int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 97a800738226..6f19c548ecc0 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1,4 +1,3 @@ #include <string.h> void *memdup(const void *src, size_t len); -int str_append(char **s, int *len, const char *a); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 0b5a8cd2ee79..cf1d7913783b 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -92,7 +92,6 @@ struct perf_kvm_stat { u64 lost_events; u64 duration; - const char *pid_str; struct intlist *pid_list; struct rb_root result; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 16bba9fff2c8..34fc7c8672e4 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -13,12 +13,18 @@ #include <symbol/kallsyms.h> #include "unwind.h" +static void dsos__init(struct dsos *dsos) +{ + INIT_LIST_HEAD(&dsos->head); + dsos->root = RB_ROOT; +} + int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { map_groups__init(&machine->kmaps); RB_CLEAR_NODE(&machine->rb_node); - INIT_LIST_HEAD(&machine->user_dsos); - INIT_LIST_HEAD(&machine->kernel_dsos); + dsos__init(&machine->user_dsos); + dsos__init(&machine->kernel_dsos); machine->threads = RB_ROOT; INIT_LIST_HEAD(&machine->dead_threads); @@ -31,6 +37,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->symbol_filter = NULL; machine->id_hdr_size = 0; + machine->comm_exec = false; + machine->kernel_start = 0; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) @@ -70,11 +78,12 @@ out_delete: return NULL; } -static void dsos__delete(struct list_head *dsos) +static void dsos__delete(struct dsos *dsos) { struct dso *pos, *n; - list_for_each_entry_safe(pos, n, dsos, node) { + list_for_each_entry_safe(pos, n, &dsos->head, node) { + RB_CLEAR_NODE(&pos->rb_node); list_del(&pos->node); dso__delete(pos); } @@ -179,6 +188,19 @@ void machines__set_symbol_filter(struct machines *machines, } } +void machines__set_comm_exec(struct machines *machines, bool comm_exec) +{ + struct rb_node *nd; + + machines->host.comm_exec = comm_exec; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *machine = rb_entry(nd, struct machine, rb_node); + + machine->comm_exec = comm_exec; + } +} + struct machine *machines__find(struct machines *machines, pid_t pid) { struct rb_node **p = &machines->guests.rb_node; @@ -398,17 +420,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid, return __machine__findnew_thread(machine, pid, tid, false); } +struct comm *machine__thread_exec_comm(struct machine *machine, + struct thread *thread) +{ + if (machine->comm_exec) + return thread__exec_comm(thread); + else + return thread__comm(thread); +} + int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) { struct thread *thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid); + bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC; + + if (exec) + machine->comm_exec = true; if (dump_trace) perf_event__fprintf_comm(event, stdout); - if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { + if (thread == NULL || + __thread__set_comm(thread, event->comm.comm, sample->time, exec)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -448,23 +484,23 @@ struct map *machine__new_module(struct machine *machine, u64 start, size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) { struct rb_node *nd; - size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) + - __dsos__fprintf(&machines->host.user_dsos, fp); + size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) + + __dsos__fprintf(&machines->host.user_dsos.head, fp); for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += __dsos__fprintf(&pos->kernel_dsos, fp); - ret += __dsos__fprintf(&pos->user_dsos, fp); + ret += __dsos__fprintf(&pos->kernel_dsos.head, fp); + ret += __dsos__fprintf(&pos->user_dsos.head, fp); } return ret; } -size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, +size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { - return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) + - __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm); + return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) + + __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm); } size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, @@ -565,8 +601,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * Returns the name of the start symbol in *symbol_name. Pass in NULL as * symbol_name if it's not that important. */ -static u64 machine__get_kernel_start_addr(struct machine *machine, - const char **symbol_name) +static u64 machine__get_running_kernel_start(struct machine *machine, + const char **symbol_name) { char filename[PATH_MAX]; int i; @@ -593,7 +629,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine, int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { enum map_type type; - u64 start = machine__get_kernel_start_addr(machine, NULL); + u64 start = machine__get_running_kernel_start(machine, NULL); for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -912,7 +948,7 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name; - u64 addr = machine__get_kernel_start_addr(machine, &name); + u64 addr = machine__get_running_kernel_start(machine, &name); if (!addr) return -1; @@ -965,7 +1001,7 @@ static bool machine__uses_kcore(struct machine *machine) { struct dso *dso; - list_for_each_entry(dso, &machine->kernel_dsos, node) { + list_for_each_entry(dso, &machine->kernel_dsos.head, node) { if (dso__is_kcore(dso)) return true; } @@ -1285,6 +1321,16 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread, thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al); + if (al.map == NULL) { + /* + * some shared data regions have execute bit set which puts + * their mapping in the MAP__FUNCTION type array. + * Check there as a fallback option before dropping the sample. + */ + thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr, + &al); + } + ams->addr = addr; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1531,3 +1577,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, return 0; } + +int machine__get_kernel_start(struct machine *machine) +{ + struct map *map = machine__kernel_map(machine, MAP__FUNCTION); + int err = 0; + + /* + * The only addresses above 2^63 are kernel addresses of a 64-bit + * kernel. Note that addresses are unsigned so that on a 32-bit system + * all addresses including kernel addresses are less than 2^32. In + * that case (32-bit system), if the kernel mapping is unknown, all + * addresses will be assumed to be in user space - see + * machine__kernel_ip(). + */ + machine->kernel_start = 1ULL << 63; + if (map) { + err = map__load(map, machine->symbol_filter); + if (map->start) + machine->kernel_start = map->start; + } + return err; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index b972824e6294..2b651a7f5d0d 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -4,6 +4,7 @@ #include <sys/types.h> #include <linux/rbtree.h> #include "map.h" +#include "dso.h" #include "event.h" struct addr_location; @@ -26,15 +27,17 @@ struct machine { struct rb_node rb_node; pid_t pid; u16 id_hdr_size; + bool comm_exec; char *root_dir; struct rb_root threads; struct list_head dead_threads; struct thread *last_match; struct vdso_info *vdso_info; - struct list_head user_dsos; - struct list_head kernel_dsos; + struct dsos user_dsos; + struct dsos kernel_dsos; struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; + u64 kernel_start; symbol_filter_t symbol_filter; pid_t *current_tid; }; @@ -45,8 +48,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } +int machine__get_kernel_start(struct machine *machine); + +static inline u64 machine__kernel_start(struct machine *machine) +{ + if (!machine->kernel_start) + machine__get_kernel_start(machine); + return machine->kernel_start; +} + +static inline bool machine__kernel_ip(struct machine *machine, u64 ip) +{ + u64 kernel_start = machine__kernel_start(machine); + + return ip >= kernel_start; +} + struct thread *machine__find_thread(struct machine *machine, pid_t pid, pid_t tid); +struct comm *machine__thread_exec_comm(struct machine *machine, + struct thread *thread); int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); @@ -88,6 +109,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_symbol_filter(struct machines *machines, symbol_filter_t symbol_filter); +void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 31b8905dd863..2137c4596ec7 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -31,6 +31,7 @@ static inline int is_anon_memory(const char *filename) static inline int is_no_dso_memory(const char *filename) { return !strncmp(filename, "[stack", 6) || + !strncmp(filename, "/SYSV",5) || !strcmp(filename, "[heap]"); } @@ -555,7 +556,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) { - if (ams->addr < ams->map->start || ams->addr > ams->map->end) { + if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { if (ams->map->groups == NULL) return -1; ams->map = map_groups__find(ams->map->groups, ams->map->type, @@ -663,7 +664,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, goto move_map; } - before->end = map->start - 1; + before->end = map->start; map_groups__insert(mg, before); if (verbose >= 2) map__fprintf(before, fp); @@ -677,7 +678,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, goto move_map; } - after->start = map->end + 1; + after->start = map->end; map_groups__insert(mg, after); if (verbose >= 2) map__fprintf(after, fp); @@ -751,7 +752,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip) m = rb_entry(parent, struct map, rb_node); if (ip < m->start) p = &(*p)->rb_left; - else if (ip > m->end) + else if (ip >= m->end) p = &(*p)->rb_right; else return m; diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c new file mode 100644 index 000000000000..fd4be94125fb --- /dev/null +++ b/tools/perf/util/ordered-events.c @@ -0,0 +1,286 @@ +#include <linux/list.h> +#include <linux/compiler.h> +#include <linux/string.h> +#include "ordered-events.h" +#include "evlist.h" +#include "session.h" +#include "asm/bug.h" +#include "debug.h" + +#define pr_N(n, fmt, ...) \ + eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__) + +#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__) + +static void queue_event(struct ordered_events *oe, struct ordered_event *new) +{ + struct ordered_event *last = oe->last; + u64 timestamp = new->timestamp; + struct list_head *p; + + ++oe->nr_events; + oe->last = new; + + pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events); + + if (!last) { + list_add(&new->list, &oe->events); + oe->max_timestamp = timestamp; + return; + } + + /* + * last event might point to some random place in the list as it's + * the last queued event. We expect that the new event is close to + * this. + */ + if (last->timestamp <= timestamp) { + while (last->timestamp <= timestamp) { + p = last->list.next; + if (p == &oe->events) { + list_add_tail(&new->list, &oe->events); + oe->max_timestamp = timestamp; + return; + } + last = list_entry(p, struct ordered_event, list); + } + list_add_tail(&new->list, &last->list); + } else { + while (last->timestamp > timestamp) { + p = last->list.prev; + if (p == &oe->events) { + list_add(&new->list, &oe->events); + return; + } + last = list_entry(p, struct ordered_event, list); + } + list_add(&new->list, &last->list); + } +} + +static union perf_event *__dup_event(struct ordered_events *oe, + union perf_event *event) +{ + union perf_event *new_event = NULL; + + if (oe->cur_alloc_size < oe->max_alloc_size) { + new_event = memdup(event, event->header.size); + if (new_event) + oe->cur_alloc_size += event->header.size; + } + + return new_event; +} + +static union perf_event *dup_event(struct ordered_events *oe, + union perf_event *event) +{ + return oe->copy_on_queue ? __dup_event(oe, event) : event; +} + +static void free_dup_event(struct ordered_events *oe, union perf_event *event) +{ + if (oe->copy_on_queue) { + oe->cur_alloc_size -= event->header.size; + free(event); + } +} + +#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct ordered_event)) +static struct ordered_event *alloc_event(struct ordered_events *oe, + union perf_event *event) +{ + struct list_head *cache = &oe->cache; + struct ordered_event *new = NULL; + union perf_event *new_event; + + new_event = dup_event(oe, event); + if (!new_event) + return NULL; + + if (!list_empty(cache)) { + new = list_entry(cache->next, struct ordered_event, list); + list_del(&new->list); + } else if (oe->buffer) { + new = oe->buffer + oe->buffer_idx; + if (++oe->buffer_idx == MAX_SAMPLE_BUFFER) + oe->buffer = NULL; + } else if (oe->cur_alloc_size < oe->max_alloc_size) { + size_t size = MAX_SAMPLE_BUFFER * sizeof(*new); + + oe->buffer = malloc(size); + if (!oe->buffer) { + free_dup_event(oe, new_event); + return NULL; + } + + pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n", + oe->cur_alloc_size, size, oe->max_alloc_size); + + oe->cur_alloc_size += size; + list_add(&oe->buffer->list, &oe->to_free); + + /* First entry is abused to maintain the to_free list. */ + oe->buffer_idx = 2; + new = oe->buffer + 1; + } else { + pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size); + } + + new->event = new_event; + return new; +} + +struct ordered_event * +ordered_events__new(struct ordered_events *oe, u64 timestamp, + union perf_event *event) +{ + struct ordered_event *new; + + new = alloc_event(oe, event); + if (new) { + new->timestamp = timestamp; + queue_event(oe, new); + } + + return new; +} + +void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event) +{ + list_move(&event->list, &oe->cache); + oe->nr_events--; + free_dup_event(oe, event->event); +} + +static int __ordered_events__flush(struct perf_session *s, + struct perf_tool *tool) +{ + struct ordered_events *oe = &s->ordered_events; + struct list_head *head = &oe->events; + struct ordered_event *tmp, *iter; + struct perf_sample sample; + u64 limit = oe->next_flush; + u64 last_ts = oe->last ? oe->last->timestamp : 0ULL; + bool show_progress = limit == ULLONG_MAX; + struct ui_progress prog; + int ret; + + if (!tool->ordered_events || !limit) + return 0; + + if (show_progress) + ui_progress__init(&prog, oe->nr_events, "Processing time ordered events..."); + + list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + + if (iter->timestamp > limit) + break; + + ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); + if (ret) + pr_err("Can't parse sample, err = %d\n", ret); + else { + ret = perf_session__deliver_event(s, iter->event, &sample, tool, + iter->file_offset); + if (ret) + return ret; + } + + ordered_events__delete(oe, iter); + oe->last_flush = iter->timestamp; + + if (show_progress) + ui_progress__update(&prog, 1); + } + + if (list_empty(head)) + oe->last = NULL; + else if (last_ts <= limit) + oe->last = list_entry(head->prev, struct ordered_event, list); + + return 0; +} + +int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, + enum oe_flush how) +{ + struct ordered_events *oe = &s->ordered_events; + static const char * const str[] = { + "NONE", + "FINAL", + "ROUND", + "HALF ", + }; + int err; + + switch (how) { + case OE_FLUSH__FINAL: + oe->next_flush = ULLONG_MAX; + break; + + case OE_FLUSH__HALF: + { + struct ordered_event *first, *last; + struct list_head *head = &oe->events; + + first = list_entry(head->next, struct ordered_event, list); + last = oe->last; + + /* Warn if we are called before any event got allocated. */ + if (WARN_ONCE(!last || list_empty(head), "empty queue")) + return 0; + + oe->next_flush = first->timestamp; + oe->next_flush += (last->timestamp - first->timestamp) / 2; + break; + } + + case OE_FLUSH__ROUND: + case OE_FLUSH__NONE: + default: + break; + }; + + pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE %s, nr_events %u\n", + str[how], oe->nr_events); + pr_oe_time(oe->max_timestamp, "max_timestamp\n"); + + err = __ordered_events__flush(s, tool); + + if (!err) { + if (how == OE_FLUSH__ROUND) + oe->next_flush = oe->max_timestamp; + + oe->last_flush_type = how; + } + + pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n", + str[how], oe->nr_events); + pr_oe_time(oe->last_flush, "last_flush\n"); + + return err; +} + +void ordered_events__init(struct ordered_events *oe) +{ + INIT_LIST_HEAD(&oe->events); + INIT_LIST_HEAD(&oe->cache); + INIT_LIST_HEAD(&oe->to_free); + oe->max_alloc_size = (u64) -1; + oe->cur_alloc_size = 0; +} + +void ordered_events__free(struct ordered_events *oe) +{ + while (!list_empty(&oe->to_free)) { + struct ordered_event *event; + + event = list_entry(oe->to_free.next, struct ordered_event, list); + list_del(&event->list); + free_dup_event(oe, event->event); + free(event); + } +} diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h new file mode 100644 index 000000000000..7b8f9b011f38 --- /dev/null +++ b/tools/perf/util/ordered-events.h @@ -0,0 +1,59 @@ +#ifndef __ORDERED_EVENTS_H +#define __ORDERED_EVENTS_H + +#include <linux/types.h> +#include "tool.h" + +struct perf_session; + +struct ordered_event { + u64 timestamp; + u64 file_offset; + union perf_event *event; + struct list_head list; +}; + +enum oe_flush { + OE_FLUSH__NONE, + OE_FLUSH__FINAL, + OE_FLUSH__ROUND, + OE_FLUSH__HALF, +}; + +struct ordered_events { + u64 last_flush; + u64 next_flush; + u64 max_timestamp; + u64 max_alloc_size; + u64 cur_alloc_size; + struct list_head events; + struct list_head cache; + struct list_head to_free; + struct ordered_event *buffer; + struct ordered_event *last; + int buffer_idx; + unsigned int nr_events; + enum oe_flush last_flush_type; + bool copy_on_queue; +}; + +struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, + union perf_event *event); +void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); +int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, + enum oe_flush how); +void ordered_events__init(struct ordered_events *oe); +void ordered_events__free(struct ordered_events *oe); + +static inline +void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size) +{ + oe->max_alloc_size = size; +} + +static inline +void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy) +{ + oe->copy_on_queue = copy; +} +#endif /* __ORDERED_EVENTS_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1e15df10a88c..c659a3ca1283 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -6,10 +6,11 @@ #include "parse-options.h" #include "parse-events.h" #include "exec_cmd.h" -#include "linux/string.h" +#include "string.h" #include "symbol.h" #include "cache.h" #include "header.h" +#include "debug.h" #include <api/fs/debugfs.h> #include "parse-events-bison.h" #define YY_EXTRA_TYPE int @@ -29,6 +30,15 @@ extern int parse_events_debug; #endif int parse_events_parse(void *data, void *scanner); +static struct perf_pmu_event_symbol *perf_pmu_events_list; +/* + * The variable indicates the number of supported pmu event symbols. + * 0 means not initialized and ready to init + * -1 means failed to init, don't try anymore + * >0 is the number of supported pmu event symbols + */ +static int perf_pmu_events_list_num; + static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { .symbol = "cpu-cycles", @@ -633,18 +643,28 @@ int parse_events_add_pmu(struct list_head *list, int *idx, char *name, struct list_head *head_config) { struct perf_event_attr attr; + struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; - const char *unit; - double scale; pmu = perf_pmu__find(name); if (!pmu) return -EINVAL; - memset(&attr, 0, sizeof(attr)); + if (pmu->default_config) { + memcpy(&attr, pmu->default_config, + sizeof(struct perf_event_attr)); + } else { + memset(&attr, 0, sizeof(attr)); + } - if (perf_pmu__check_alias(pmu, head_config, &unit, &scale)) + if (!head_config) { + attr.type = pmu->type; + evsel = __add_event(list, idx, &attr, NULL, pmu->cpus); + return evsel ? 0 : -ENOMEM; + } + + if (perf_pmu__check_alias(pmu, head_config, &info)) return -EINVAL; /* @@ -659,8 +679,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx, evsel = __add_event(list, idx, &attr, pmu_event_name(head_config), pmu->cpus); if (evsel) { - evsel->unit = unit; - evsel->scale = scale; + evsel->unit = info.unit; + evsel->scale = info.scale; } return evsel ? 0 : -ENOMEM; @@ -852,30 +872,111 @@ int parse_events_name(struct list_head *list, char *name) return 0; } -static int parse_events__scanner(const char *str, void *data, int start_token); +static int +comp_pmu(const void *p1, const void *p2) +{ + struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1; + struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2; -static int parse_events_fixup(int ret, const char *str, void *data, - int start_token) + return strcmp(pmu1->symbol, pmu2->symbol); +} + +static void perf_pmu__parse_cleanup(void) { - char *o = strdup(str); - char *s = NULL; - char *t = o; - char *p; + if (perf_pmu_events_list_num > 0) { + struct perf_pmu_event_symbol *p; + int i; + + for (i = 0; i < perf_pmu_events_list_num; i++) { + p = perf_pmu_events_list + i; + free(p->symbol); + } + free(perf_pmu_events_list); + perf_pmu_events_list = NULL; + perf_pmu_events_list_num = 0; + } +} + +#define SET_SYMBOL(str, stype) \ +do { \ + p->symbol = str; \ + if (!p->symbol) \ + goto err; \ + p->type = stype; \ +} while (0) + +/* + * Read the pmu events list from sysfs + * Save it into perf_pmu_events_list + */ +static void perf_pmu__parse_init(void) +{ + + struct perf_pmu *pmu = NULL; + struct perf_pmu_alias *alias; int len = 0; - if (!o) - return ret; - while ((p = strsep(&t, ",")) != NULL) { - if (s) - str_append(&s, &len, ","); - str_append(&s, &len, "cpu/"); - str_append(&s, &len, p); - str_append(&s, &len, "/"); + pmu = perf_pmu__find("cpu"); + if ((pmu == NULL) || list_empty(&pmu->aliases)) { + perf_pmu_events_list_num = -1; + return; } - free(o); - if (!s) - return -ENOMEM; - return parse_events__scanner(s, data, start_token); + list_for_each_entry(alias, &pmu->aliases, list) { + if (strchr(alias->name, '-')) + len++; + len++; + } + perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); + if (!perf_pmu_events_list) + return; + perf_pmu_events_list_num = len; + + len = 0; + list_for_each_entry(alias, &pmu->aliases, list) { + struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; + char *tmp = strchr(alias->name, '-'); + + if (tmp != NULL) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); + len += 2; + } else { + SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); + len++; + } + } + qsort(perf_pmu_events_list, len, + sizeof(struct perf_pmu_event_symbol), comp_pmu); + + return; +err: + perf_pmu__parse_cleanup(); +} + +enum perf_pmu_event_symbol_type +perf_pmu__parse_check(const char *name) +{ + struct perf_pmu_event_symbol p, *r; + + /* scan kernel pmu events from sysfs if needed */ + if (perf_pmu_events_list_num == 0) + perf_pmu__parse_init(); + /* + * name "cpu" could be prefix of cpu-cycles or cpu// events. + * cpu-cycles has been handled by hardcode. + * So it must be cpu// events, not kernel pmu event. + */ + if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu")) + return PMU_EVENT_SYMBOL_ERR; + + p.symbol = strdup(name); + r = bsearch(&p, perf_pmu_events_list, + (size_t) perf_pmu_events_list_num, + sizeof(struct perf_pmu_event_symbol), comp_pmu); + free(p.symbol); + return r ? r->type : PMU_EVENT_SYMBOL_ERR; } static int parse_events__scanner(const char *str, void *data, int start_token) @@ -898,8 +999,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token) parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); parse_events_lex_destroy(scanner); - if (ret && !strchr(str, '/')) - ret = parse_events_fixup(ret, str, data, start_token); return ret; } @@ -934,6 +1033,7 @@ int parse_events(struct perf_evlist *evlist, const char *str) int ret; ret = parse_events__scanner(str, &data, PE_START_EVENTS); + perf_pmu__parse_cleanup(); if (!ret) { int entries = data.idx - evlist->nr_entries; perf_evlist__splice_list_tail(evlist, &data.list, entries); @@ -973,7 +1073,7 @@ int parse_filter(const struct option *opt, const char *str, if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, - "-F option should follow a -e tracepoint option\n"); + "--filter option should follow a -e tracepoint option\n"); return -1; } @@ -1006,9 +1106,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; + char sbuf[STRERR_BUFSIZE]; if (debugfs_valid_mountpoint(tracing_events_path)) { - printf(" [ Tracepoints not available: %s ]\n", strerror(errno)); + printf(" [ Tracepoints not available: %s ]\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index df094b4ed5ed..db2cf78ff0f3 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) +enum perf_pmu_event_symbol_type { + PMU_EVENT_SYMBOL_ERR, /* not a PMU EVENT */ + PMU_EVENT_SYMBOL, /* normal style PMU event */ + PMU_EVENT_SYMBOL_PREFIX, /* prefix of pre-suf style event */ + PMU_EVENT_SYMBOL_SUFFIX, /* suffix of pre-suf style event */ +}; + +struct perf_pmu_event_symbol { + char *symbol; + enum perf_pmu_event_symbol_type type; +}; + enum { PARSE_EVENTS__TERM_TYPE_NUM, PARSE_EVENTS__TERM_TYPE_STR, @@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type); int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); +enum perf_pmu_event_symbol_type +perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 343299575b30..906630bbf8eb 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token) return token; } +static int pmu_str_check(yyscan_t scanner) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->str = strdup(text); + switch (perf_pmu__parse_check(text)) { + case PMU_EVENT_SYMBOL_PREFIX: + return PE_PMU_EVENT_PRE; + case PMU_EVENT_SYMBOL_SUFFIX: + return PE_PMU_EVENT_SUF; + case PMU_EVENT_SYMBOL: + return PE_KERNEL_PMU_EVENT; + default: + return PE_NAME; + } +} + static int sym(yyscan_t scanner, int type, int config) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -178,6 +196,16 @@ alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } + /* + * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. + * Because the prefix cycles is mixed up with cpu-cycles. + * loads and stores are mixed up with cache event + */ +cycles-ct { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +cycles-t { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +mem-loads { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +mem-stores { return str(yyscanner, PE_KERNEL_PMU_EVENT); } + L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | LLC|L2 | @@ -199,7 +227,7 @@ r{num_raw_hex} { return raw(yyscanner); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } -{name} { return str(yyscanner, PE_NAME); } +{name} { return pmu_str_check(yyscanner); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 0bc87ba46bf3..93c4c9fbc922 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -47,6 +47,7 @@ static 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 %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW @@ -58,6 +59,7 @@ static 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 <num> value_sym %type <head> event_config %type <term> event_term @@ -210,6 +212,54 @@ PE_NAME '/' event_config '/' parse_events__free_terms($3); $$ = list; } +| +PE_NAME '/' '/' +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL)); + $$ = list; +} +| +PE_KERNEL_PMU_EVENT sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + + ALLOC_LIST(head); + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1)); + list_add_tail(&term->list, head); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + parse_events__free_terms(head); + $$ = list; +} +| +PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + char pmu_name[128]; + snprintf(&pmu_name, 128, "%s-%s", $1, $3); + + ALLOC_LIST(head); + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + &pmu_name, 1)); + list_add_tail(&term->list, head); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + parse_events__free_terms(head); + $$ = list; +} value_sym: PE_VALUE_SYM_HW diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7a811eb61f75..e243ad962a4d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -2,6 +2,8 @@ #include <sys/types.h> #include <unistd.h> #include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> #include <dirent.h> #include <api/fs/fs.h> #include <locale.h> @@ -10,16 +12,6 @@ #include "parse-events.h" #include "cpumap.h" -#define UNIT_MAX_LEN 31 /* max length for event unit name */ - -struct perf_pmu_alias { - char *name; - struct list_head terms; - struct list_head list; - char unit[UNIT_MAX_LEN+1]; - double scale; -}; - struct perf_pmu_format { char *name; int value; @@ -208,6 +200,19 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI return 0; } +static inline bool pmu_alias_info_file(char *name) +{ + size_t len; + + len = strlen(name); + if (len > 5 && !strcmp(name + len - 5, ".unit")) + return true; + if (len > 6 && !strcmp(name + len - 6, ".scale")) + return true; + + return false; +} + /* * Process all the sysfs attributes located under the directory * specified in 'dir' parameter. @@ -216,7 +221,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) { struct dirent *evt_ent; DIR *event_dir; - size_t len; int ret = 0; event_dir = opendir(dir); @@ -232,13 +236,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) continue; /* - * skip .unit and .scale info files - * parsed in perf_pmu__new_alias() + * skip info files parsed in perf_pmu__new_alias() */ - len = strlen(name); - if (len > 5 && !strcmp(name + len - 5, ".unit")) - continue; - if (len > 6 && !strcmp(name + len - 6, ".scale")) + if (pmu_alias_info_file(name)) continue; snprintf(path, PATH_MAX, "%s/%s", dir, name); @@ -387,6 +387,12 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } +struct perf_event_attr *__attribute__((weak)) +perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +{ + return NULL; +} + static struct perf_pmu *pmu_lookup(const char *name) { struct perf_pmu *pmu; @@ -421,6 +427,9 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->name = strdup(name); pmu->type = type; list_add_tail(&pmu->list, &pmus); + + pmu->default_config = perf_pmu__get_default_config(pmu); + return pmu; } @@ -479,28 +488,24 @@ pmu_find_format(struct list_head *formats, char *name) } /* - * Returns value based on the format definition (format parameter) + * Sets value based on the format definition (format parameter) * and unformated value (value parameter). - * - * TODO maybe optimize a little ;) */ -static __u64 pmu_format_value(unsigned long *format, __u64 value) +static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, + bool zero) { unsigned long fbit, vbit; - __u64 v = 0; for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) { if (!test_bit(fbit, format)) continue; - if (!(value & (1llu << vbit++))) - continue; - - v |= (1llu << fbit); + if (value & (1llu << vbit++)) + *v |= (1llu << fbit); + else if (zero) + *v &= ~(1llu << fbit); } - - return v; } /* @@ -509,7 +514,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value) */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, - struct parse_events_term *term) + struct parse_events_term *term, + bool zero) { struct perf_pmu_format *format; __u64 *vp; @@ -548,18 +554,19 @@ static int pmu_config_term(struct list_head *formats, * non-hardcoded terms, here's the place to translate * them into value. */ - *vp |= pmu_format_value(format->bits, term->val.num); + pmu_format_value(format->bits, term->val.num, vp, zero); return 0; } int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, - struct list_head *head_terms) + struct list_head *head_terms, + bool zero) { struct parse_events_term *term; list_for_each_entry(term, head_terms, list) - if (pmu_config_term(formats, attr, term)) + if (pmu_config_term(formats, attr, term, zero)) return -EINVAL; return 0; @@ -573,8 +580,10 @@ int perf_pmu__config_terms(struct list_head *formats, int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms) { + bool zero = !!pmu->default_config; + attr->type = pmu->type; - return perf_pmu__config_terms(&pmu->format, attr, head_terms); + return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero); } static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, @@ -634,7 +643,7 @@ static int check_unit_scale(struct perf_pmu_alias *alias, * defined for the alias */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - const char **unit, double *scale) + struct perf_pmu_info *info) { struct parse_events_term *term, *h; struct perf_pmu_alias *alias; @@ -644,8 +653,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, * Mark unit and scale as not set * (different from default values, see below) */ - *unit = NULL; - *scale = 0.0; + info->unit = NULL; + info->scale = 0.0; list_for_each_entry_safe(term, h, head_terms, list) { alias = pmu_find_alias(pmu, term); @@ -655,7 +664,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (ret) return ret; - ret = check_unit_scale(alias, unit, scale); + ret = check_unit_scale(alias, &info->unit, &info->scale); if (ret) return ret; @@ -668,11 +677,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, * set defaults as for evsel * unit cannot left to NULL */ - if (*unit == NULL) - *unit = ""; + if (info->unit == NULL) + info->unit = ""; - if (*scale == 0.0) - *scale = 1.0; + if (info->scale == 0.0) + info->scale = 1.0; return 0; } @@ -794,3 +803,39 @@ bool pmu_have_event(const char *pname, const char *name) } return false; } + +static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + + sysfs = sysfs__mountpoint(); + if (!sysfs) + return NULL; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name); + + if (stat(path, &st) < 0) + return NULL; + + return fopen(path, "r"); +} + +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, + ...) +{ + va_list args; + FILE *file; + int ret = EOF; + + va_start(args, fmt); + file = perf_pmu__open_file(pmu, name); + if (file) { + ret = vfscanf(file, fmt, args); + fclose(file); + } + va_end(args); + return ret; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index c14a543ce1f3..fe9dfbee8eed 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -13,13 +13,31 @@ enum { #define PERF_PMU_FORMAT_BITS 64 +struct perf_event_attr; + struct perf_pmu { char *name; __u32 type; + struct perf_event_attr *default_config; struct cpu_map *cpus; - struct list_head format; - struct list_head aliases; - struct list_head list; + struct list_head format; /* HEAD struct perf_pmu_format -> list */ + struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ + struct list_head list; /* ELEM */ +}; + +struct perf_pmu_info { + const char *unit; + double scale; +}; + +#define UNIT_MAX_LEN 31 /* max length for event unit name */ + +struct perf_pmu_alias { + char *name; + struct list_head terms; /* HEAD struct parse_events_term -> list */ + struct list_head list; /* ELEM */ + char unit[UNIT_MAX_LEN+1]; + double scale; }; struct perf_pmu *perf_pmu__find(const char *name); @@ -27,9 +45,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, - struct list_head *head_terms); + struct list_head *head_terms, + bool zero); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - const char **unit, double *scale); + struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, struct list_head *head_terms); int perf_pmu_wrap(void); @@ -45,5 +64,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); void print_pmu_events(const char *event_glob, bool name_only); bool pmu_have_event(const char *pname, const char *name); +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, + ...) __attribute__((format(scanf, 3, 4))); + int perf_pmu__test(void); + +struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); + #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9a0a1839a377..c150ca4343eb 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only) int ret; symbol_conf.sort_by_name = true; - ret = symbol__init(); + ret = symbol__init(NULL); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); goto out; @@ -184,7 +184,8 @@ static struct dso *kernel_get_module_dso(const char *module) const char *vmlinux_name; if (module) { - list_for_each_entry(dso, &host_machine->kernel_dsos, node) { + list_for_each_entry(dso, &host_machine->kernel_dsos.head, + node) { if (strncmp(dso->short_name + 1, module, dso->short_name_len - 2) == 0) goto found; @@ -258,21 +259,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) #ifdef HAVE_DWARF_SUPPORT /* Open new debuginfo of given module */ -static struct debuginfo *open_debuginfo(const char *module) +static struct debuginfo *open_debuginfo(const char *module, bool silent) { const char *path = module; + struct debuginfo *ret; if (!module || !strchr(module, '/')) { path = kernel_get_module_path(module); if (!path) { - pr_err("Failed to find path of %s module.\n", - module ?: "kernel"); + if (!silent) + pr_err("Failed to find path of %s module.\n", + module ?: "kernel"); return NULL; } } - return debuginfo__new(path); + ret = debuginfo__new(path); + if (!ret && !silent) { + pr_warning("The %s file has no debug information.\n", path); + if (!module || !strtailcmp(path, ".ko")) + pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, "); + else + pr_warning("Rebuild with -g, "); + pr_warning("or install an appropriate debuginfo package.\n"); + } + return ret; } + static int get_text_start_address(const char *exec, unsigned long *address) { Elf *elf; @@ -333,15 +346,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, pr_debug("try to find information at %" PRIx64 " in %s\n", addr, tp->module ? : "kernel"); - dinfo = open_debuginfo(tp->module); + dinfo = open_debuginfo(tp->module, verbose == 0); if (dinfo) { ret = debuginfo__find_probe_point(dinfo, (unsigned long)addr, pp); debuginfo__delete(dinfo); - } else { - pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr); + } else ret = -ENOENT; - } if (ret > 0) { pp->retprobe = tp->retprobe; @@ -457,13 +468,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct debuginfo *dinfo; int ntevs, ret = 0; - dinfo = open_debuginfo(target); + dinfo = open_debuginfo(target, !need_dwarf); if (!dinfo) { - if (need_dwarf) { - pr_warning("Failed to open debuginfo file.\n"); + if (need_dwarf) return -ENOENT; - } pr_debug("Could not open debuginfo. Try to use symbols.\n"); return 0; } @@ -565,7 +574,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir, static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) { - char buf[LINEBUF_SIZE]; + char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE]; const char *color = show_num ? "" : PERF_COLOR_BLUE; const char *prefix = NULL; @@ -585,7 +594,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) return 1; error: if (ferror(fp)) { - pr_warning("File read error: %s\n", strerror(errno)); + pr_warning("File read error: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } return 0; @@ -618,13 +628,12 @@ static int __show_line_range(struct line_range *lr, const char *module) FILE *fp; int ret; char *tmp; + char sbuf[STRERR_BUFSIZE]; /* Search a line range */ - dinfo = open_debuginfo(module); - if (!dinfo) { - pr_warning("Failed to open debuginfo file.\n"); + dinfo = open_debuginfo(module, false); + if (!dinfo) return -ENOENT; - } ret = debuginfo__find_line_range(dinfo, lr); debuginfo__delete(dinfo); @@ -656,7 +665,7 @@ static int __show_line_range(struct line_range *lr, const char *module) fp = fopen(lr->path, "r"); if (fp == NULL) { pr_warning("Failed to open %s: %s\n", lr->path, - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); return -errno; } /* Skip to starting line number */ @@ -689,11 +698,11 @@ end: return ret; } -int show_line_range(struct line_range *lr, const char *module) +int show_line_range(struct line_range *lr, const char *module, bool user) { int ret; - ret = init_symbol_maps(false); + ret = init_symbol_maps(user); if (ret < 0) return ret; ret = __show_line_range(lr, module); @@ -768,13 +777,12 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, int i, ret = 0; struct debuginfo *dinfo; - ret = init_symbol_maps(false); + ret = init_symbol_maps(pevs->uprobes); if (ret < 0) return ret; - dinfo = open_debuginfo(module); + dinfo = open_debuginfo(module, false); if (!dinfo) { - pr_warning("Failed to open debuginfo file.\n"); ret = -ENOENT; goto out; } @@ -815,7 +823,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } int show_line_range(struct line_range *lr __maybe_unused, - const char *module __maybe_unused) + const char *module __maybe_unused, + bool user __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; @@ -1405,8 +1414,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) return tmp - buf; error: - pr_debug("Failed to synthesize perf probe argument: %s\n", - strerror(-ret)); + pr_debug("Failed to synthesize perf probe argument: %d\n", ret); return ret; } @@ -1455,8 +1463,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) return buf; error: - pr_debug("Failed to synthesize perf probe point: %s\n", - strerror(-ret)); + pr_debug("Failed to synthesize perf probe point: %d\n", ret); free(buf); return NULL; } @@ -1780,10 +1787,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev) memset(tev, 0, sizeof(*tev)); } -static void print_warn_msg(const char *file, bool is_kprobe) +static void print_open_warning(int err, bool is_kprobe) { + char sbuf[STRERR_BUFSIZE]; - if (errno == ENOENT) { + if (err == -ENOENT) { const char *config; if (!is_kprobe) @@ -1791,25 +1799,43 @@ static void print_warn_msg(const char *file, bool is_kprobe) else config = "CONFIG_KPROBE_EVENTS"; - pr_warning("%s file does not exist - please rebuild kernel" - " with %s.\n", file, config); - } else - pr_warning("Failed to open %s file: %s\n", file, - strerror(errno)); + pr_warning("%cprobe_events file does not exist" + " - please rebuild kernel with %s.\n", + is_kprobe ? 'k' : 'u', config); + } else if (err == -ENOTSUP) + pr_warning("Debugfs is not mounted.\n"); + else + pr_warning("Failed to open %cprobe_events: %s\n", + is_kprobe ? 'k' : 'u', + strerror_r(-err, sbuf, sizeof(sbuf))); +} + +static void print_both_open_warning(int kerr, int uerr) +{ + /* Both kprobes and uprobes are disabled, warn it. */ + if (kerr == -ENOTSUP && uerr == -ENOTSUP) + pr_warning("Debugfs is not mounted.\n"); + else if (kerr == -ENOENT && uerr == -ENOENT) + pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " + "or/and CONFIG_UPROBE_EVENTS.\n"); + else { + char sbuf[STRERR_BUFSIZE]; + pr_warning("Failed to open kprobe events: %s.\n", + strerror_r(-kerr, sbuf, sizeof(sbuf))); + pr_warning("Failed to open uprobe events: %s.\n", + strerror_r(-uerr, sbuf, sizeof(sbuf))); + } } -static int open_probe_events(const char *trace_file, bool readwrite, - bool is_kprobe) +static int open_probe_events(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; const char *__debugfs; int ret; __debugfs = debugfs_find_mountpoint(); - if (__debugfs == NULL) { - pr_warning("Debugfs is not mounted.\n"); - return -ENOENT; - } + if (__debugfs == NULL) + return -ENOTSUP; ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file); if (ret >= 0) { @@ -1820,19 +1846,19 @@ static int open_probe_events(const char *trace_file, bool readwrite, ret = open(buf, O_RDONLY, 0); if (ret < 0) - print_warn_msg(buf, is_kprobe); + ret = -errno; } return ret; } static int open_kprobe_events(bool readwrite) { - return open_probe_events("tracing/kprobe_events", readwrite, true); + return open_probe_events("tracing/kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("tracing/uprobe_events", readwrite, false); + return open_probe_events("tracing/uprobe_events", readwrite); } /* Get raw string list of current kprobe_events or uprobe_events */ @@ -1857,7 +1883,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) p[idx] = '\0'; ret = strlist__add(sl, buf); if (ret < 0) { - pr_debug("strlist__add failed: %s\n", strerror(-ret)); + pr_debug("strlist__add failed (%d)\n", ret); strlist__delete(sl); return NULL; } @@ -1916,7 +1942,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) rawlist = get_probe_trace_command_rawlist(fd); if (!rawlist) - return -ENOENT; + return -ENOMEM; strlist__for_each(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); @@ -1940,27 +1966,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) /* List up current perf-probe events */ int show_perf_probe_events(void) { - int fd, ret; + int kp_fd, up_fd, ret; setup_pager(); - fd = open_kprobe_events(false); - - if (fd < 0) - return fd; ret = init_symbol_maps(false); if (ret < 0) return ret; - ret = __show_perf_probe_events(fd, true); - close(fd); + kp_fd = open_kprobe_events(false); + if (kp_fd >= 0) { + ret = __show_perf_probe_events(kp_fd, true); + close(kp_fd); + if (ret < 0) + goto out; + } - fd = open_uprobe_events(false); - if (fd >= 0) { - ret = __show_perf_probe_events(fd, false); - close(fd); + up_fd = open_uprobe_events(false); + if (kp_fd < 0 && up_fd < 0) { + print_both_open_warning(kp_fd, up_fd); + ret = kp_fd; + goto out; } + if (up_fd >= 0) { + ret = __show_perf_probe_events(up_fd, false); + close(up_fd); + } +out: exit_symbol_maps(); return ret; } @@ -1976,6 +2009,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group) memset(&tev, 0, sizeof(tev)); rawlist = get_probe_trace_command_rawlist(fd); + if (!rawlist) + return NULL; sl = strlist__new(true, NULL); strlist__for_each(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); @@ -2005,6 +2040,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) { int ret = 0; char *buf = synthesize_probe_trace_command(tev); + char sbuf[STRERR_BUFSIZE]; if (!buf) { pr_debug("Failed to synthesize probe trace event.\n"); @@ -2016,7 +2052,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) ret = write(fd, buf, strlen(buf)); if (ret <= 0) pr_warning("Failed to write event: %s\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); } free(buf); return ret; @@ -2030,7 +2066,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base, /* Try no suffix */ ret = e_snprintf(buf, len, "%s", base); if (ret < 0) { - pr_debug("snprintf() failed: %s\n", strerror(-ret)); + pr_debug("snprintf() failed: %d\n", ret); return ret; } if (!strlist__has_entry(namelist, buf)) @@ -2046,7 +2082,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base, for (i = 1; i < MAX_EVENT_INDEX; i++) { ret = e_snprintf(buf, len, "%s_%d", base, i); if (ret < 0) { - pr_debug("snprintf() failed: %s\n", strerror(-ret)); + pr_debug("snprintf() failed: %d\n", ret); return ret; } if (!strlist__has_entry(namelist, buf)) @@ -2075,8 +2111,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, else fd = open_kprobe_events(true); - if (fd < 0) + if (fd < 0) { + print_open_warning(fd, !pev->uprobes); return fd; + } + /* Get current event names */ namelist = get_probe_trace_event_names(fd, false); if (!namelist) { @@ -2408,7 +2447,8 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) printf("Removed event: %s\n", ent->s); return 0; error: - pr_warning("Failed to delete event: %s\n", strerror(-ret)); + pr_warning("Failed to delete event: %s\n", + strerror_r(-ret, buf, sizeof(buf))); return ret; } @@ -2449,15 +2489,18 @@ int del_perf_probe_events(struct strlist *dellist) /* Get current event names */ kfd = open_kprobe_events(true); - if (kfd < 0) - return kfd; + if (kfd >= 0) + namelist = get_probe_trace_event_names(kfd, true); - namelist = get_probe_trace_event_names(kfd, true); ufd = open_uprobe_events(true); - if (ufd >= 0) unamelist = get_probe_trace_event_names(ufd, true); + if (kfd < 0 && ufd < 0) { + print_both_open_warning(kfd, ufd); + goto error; + } + if (namelist == NULL && unamelist == NULL) goto error; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 776c9347a3b6..e01e9943139f 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, bool force_add); extern int del_perf_probe_events(struct strlist *dellist); extern int show_perf_probe_events(void); -extern int show_line_range(struct line_range *lr, const char *module); +extern int show_line_range(struct line_range *lr, const char *module, + bool user); extern int show_available_vars(struct perf_probe_event *pevs, int npevs, int max_probe_points, const char *module, struct strfilter *filter, bool externs); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index dca9145d704c..c7918f83b300 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -281,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg_ref **ref_ptr = &tvar->ref; Dwarf_Die type; char buf[16]; + char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; @@ -367,7 +368,7 @@ formatted: if (ret >= 16) ret = -E2BIG; pr_warning("Failed to convert variable type: %s\n", - strerror(-ret)); + strerror_r(-ret, sbuf, sizeof(sbuf))); return ret; } tvar->type = strdup(buf); @@ -608,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, return -EINVAL; } - /* Get an appropriate symbol from symtab */ - symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + symbol = dwarf_diename(sp_die); if (!symbol) { - pr_warning("Failed to find symbol at 0x%lx\n", - (unsigned long)paddr); - return -ENOENT; + /* Try to get the symbol name from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + eaddr = sym.st_value; } - tp->offset = (unsigned long)(paddr - sym.st_value); + tp->offset = (unsigned long)(paddr - eaddr); tp->address = (unsigned long)paddr; tp->symbol = strdup(symbol); if (!tp->symbol) @@ -779,10 +784,12 @@ static int find_lazy_match_lines(struct intlist *list, size_t line_len; ssize_t len; int count = 0, linenum = 1; + char sbuf[STRERR_BUFSIZE]; fp = fopen(fname, "r"); if (!fp) { - pr_warning("Failed to open %s: %s\n", fname, strerror(errno)); + pr_warning("Failed to open %s: %s\n", fname, + strerror_r(errno, sbuf, sizeof(sbuf))); return -errno; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 12aa9b0d0ba1..3dda85ca50c1 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -736,7 +736,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) return NULL; - n = poll(evlist->pollfd, evlist->nr_fds, timeout); + n = perf_evlist__poll(evlist, timeout); if (n < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; @@ -753,9 +753,9 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, PyObject *list = PyList_New(0); int i; - for (i = 0; i < evlist->nr_fds; ++i) { + for (i = 0; i < evlist->pollfd.nr; ++i) { PyObject *file; - FILE *fp = fdopen(evlist->pollfd[i].fd, "r"); + FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r"); if (fp == NULL) goto free_list; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index fe8079edbdc1..cf69325b985f 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -14,6 +14,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) struct perf_evsel *evsel; unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; + static pid_t pid = -1; evlist = perf_evlist__new(); if (!evlist) @@ -24,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = perf_evlist__first(evlist); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); - if (fd < 0) - goto out_delete; + while (1) { + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + if (fd < 0) { + if (pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + goto out_delete; + } + break; + } close(fd); fn(evsel); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -47,7 +56,7 @@ out_delete: static bool perf_probe_api(setup_probe_fn_t fn) { - const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL}; + const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; struct cpu_map *cpus; int cpu, ret, i = 0; @@ -106,7 +115,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) evlist__for_each(evlist, evsel) { perf_evsel__config(evsel, opts); - if (!evsel->idx && use_comm_exec) + if (evsel->tracking && use_comm_exec) evsel->attr.comm_exec = 1; } @@ -201,6 +210,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) struct perf_evsel *evsel; int err, fd, cpu; bool ret = false; + pid_t pid = -1; temp_evlist = perf_evlist__new(); if (!temp_evlist) @@ -221,12 +231,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) cpu = evlist->cpus->map[0]; } - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, - perf_event_open_cloexec_flag()); - if (fd >= 0) { - close(fd); - ret = true; + while (1) { + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, + perf_event_open_cloexec_flag()); + if (fd < 0) { + if (pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + goto out_delete; + } + break; } + close(fd); + ret = true; out_delete: perf_evlist__delete(temp_evlist); diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c index da8e9b285f51..34622b53e733 100644 --- a/tools/perf/util/run-command.c +++ b/tools/perf/util/run-command.c @@ -1,6 +1,7 @@ #include "cache.h" #include "run-command.h" #include "exec_cmd.h" +#include "debug.h" static inline void close_pair(int fd[2]) { @@ -19,6 +20,7 @@ int start_command(struct child_process *cmd) { int need_in, need_out, need_err; int fdin[2], fdout[2], fderr[2]; + char sbuf[STRERR_BUFSIZE]; /* * In case of errors we must keep the promise to close FDs @@ -99,7 +101,7 @@ int start_command(struct child_process *cmd) if (cmd->dir && chdir(cmd->dir)) die("exec %s: cd to %s failed (%s)", cmd->argv[0], - cmd->dir, strerror(errno)); + cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf))); if (cmd->env) { for (; *cmd->env; cmd->env++) { if (strchr(*cmd->env, '=')) @@ -153,6 +155,8 @@ int start_command(struct child_process *cmd) static int wait_or_whine(pid_t pid) { + char sbuf[STRERR_BUFSIZE]; + for (;;) { int status, code; pid_t waiting = waitpid(pid, &status, 0); @@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid) if (waiting < 0) { if (errno == EINTR) continue; - error("waitpid failed (%s)", strerror(errno)); + error("waitpid failed (%s)", + strerror_r(errno, sbuf, sizeof(sbuf))); return -ERR_RUN_COMMAND_WAITPID; } if (waiting != pid) diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index b2dba9c0a3a1..0a01bac4ce02 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -432,6 +432,11 @@ error: return err; } +static int perl_flush_script(void) +{ + return 0; +} + /* * Stop trace script */ @@ -633,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) struct scripting_ops perl_scripting_ops = { .name = "Perl", .start_script = perl_start_script, + .flush_script = perl_flush_script, .stop_script = perl_stop_script, .process_event = perl_process_event, .generate_script = perl_generate_script, diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cbce2545da45..496f21cadd97 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -28,6 +28,7 @@ #include "../../perf.h" #include "../debug.h" +#include "../callchain.h" #include "../evsel.h" #include "../util.h" #include "../event.h" @@ -73,6 +74,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj Py_DECREF(val); } +static PyObject *get_handler(const char *handler_name) +{ + PyObject *handler; + + handler = PyDict_GetItemString(main_dict, handler_name); + if (handler && !PyCallable_Check(handler)) + return NULL; + return handler; +} + +static void call_object(PyObject *handler, PyObject *args, const char *die_msg) +{ + PyObject *retval; + + retval = PyObject_CallObject(handler, args); + if (retval == NULL) + handler_call_die(die_msg); + Py_DECREF(retval); +} + +static void try_call_object(const char *handler_name, PyObject *args) +{ + PyObject *handler; + + handler = get_handler(handler_name); + if (handler) + call_object(handler, args, handler_name); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -80,7 +110,7 @@ static void define_value(enum print_arg_type field_type, const char *field_str) { const char *handler_name = "define_flag_value"; - PyObject *handler, *t, *retval; + PyObject *t; unsigned long long value; unsigned n = 0; @@ -98,13 +128,7 @@ static void define_value(enum print_arg_type field_type, PyTuple_SetItem(t, n++, PyInt_FromLong(value)); PyTuple_SetItem(t, n++, PyString_FromString(field_str)); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && PyCallable_Check(handler)) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - Py_DECREF(retval); - } + try_call_object(handler_name, t); Py_DECREF(t); } @@ -127,7 +151,7 @@ static void define_field(enum print_arg_type field_type, const char *delim) { const char *handler_name = "define_flag_field"; - PyObject *handler, *t, *retval; + PyObject *t; unsigned n = 0; if (field_type == PRINT_SYMBOL) @@ -145,13 +169,7 @@ static void define_field(enum print_arg_type field_type, if (field_type == PRINT_FLAGS) PyTuple_SetItem(t, n++, PyString_FromString(delim)); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && PyCallable_Check(handler)) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - Py_DECREF(retval); - } + try_call_object(handler_name, t); Py_DECREF(t); } @@ -362,7 +380,7 @@ static void python_process_tracepoint(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *context, *t, *obj, *callchain; + PyObject *handler, *context, *t, *obj, *callchain; PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; @@ -387,9 +405,7 @@ static void python_process_tracepoint(struct perf_sample *sample, sprintf(handler_name, "%s__%s", event->system, event->name); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && !PyCallable_Check(handler)) - handler = NULL; + handler = get_handler(handler_name); if (!handler) { dict = PyDict_New(); if (!dict) @@ -450,19 +466,9 @@ static void python_process_tracepoint(struct perf_sample *sample, Py_FatalError("error resizing Python tuple"); if (handler) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - Py_DECREF(retval); + call_object(handler, t, handler_name); } else { - handler = PyDict_GetItemString(main_dict, "trace_unhandled"); - if (handler && PyCallable_Check(handler)) { - - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die("trace_unhandled"); - Py_DECREF(retval); - } + try_call_object("trace_unhandled", t); Py_DECREF(dict); } @@ -474,7 +480,7 @@ static void python_process_general_event(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample; + PyObject *handler, *t, *dict, *callchain, *dict_sample; static char handler_name[64]; unsigned n = 0; @@ -496,8 +502,8 @@ static void python_process_general_event(struct perf_sample *sample, snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); - handler = PyDict_GetItemString(main_dict, handler_name); - if (!handler || !PyCallable_Check(handler)) + handler = get_handler(handler_name); + if (!handler) goto exit; pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); @@ -539,10 +545,7 @@ static void python_process_general_event(struct perf_sample *sample, if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - Py_DECREF(retval); + call_object(handler, t, handler_name); exit: Py_DECREF(dict); Py_DECREF(t); @@ -566,36 +569,24 @@ static void python_process_event(union perf_event *event __maybe_unused, static int run_start_sub(void) { - PyObject *handler, *retval; - int err = 0; - main_module = PyImport_AddModule("__main__"); if (main_module == NULL) return -1; Py_INCREF(main_module); main_dict = PyModule_GetDict(main_module); - if (main_dict == NULL) { - err = -1; + if (main_dict == NULL) goto error; - } Py_INCREF(main_dict); - handler = PyDict_GetItemString(main_dict, "trace_begin"); - if (handler == NULL || !PyCallable_Check(handler)) - goto out; + try_call_object("trace_begin", NULL); - retval = PyObject_CallObject(handler, NULL); - if (retval == NULL) - handler_call_die("trace_begin"); + return 0; - Py_DECREF(retval); - return err; error: Py_XDECREF(main_dict); Py_XDECREF(main_module); -out: - return err; + return -1; } /* @@ -649,28 +640,23 @@ error: return err; } +static int python_flush_script(void) +{ + return 0; +} + /* * Stop trace script */ static int python_stop_script(void) { - PyObject *handler, *retval; - int err = 0; + try_call_object("trace_end", NULL); - handler = PyDict_GetItemString(main_dict, "trace_end"); - if (handler == NULL || !PyCallable_Check(handler)) - goto out; - - retval = PyObject_CallObject(handler, NULL); - if (retval == NULL) - handler_call_die("trace_end"); - Py_DECREF(retval); -out: Py_XDECREF(main_dict); Py_XDECREF(main_module); Py_Finalize(); - return err; + return 0; } static int python_generate_script(struct pevent *pevent, const char *outfile) @@ -843,6 +829,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) struct scripting_ops python_scripting_ops = { .name = "Python", .start_script = python_start_script, + .flush_script = python_flush_script, .stop_script = python_stop_script, .process_event = python_process_event, .generate_script = python_generate_script, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 88dfef70c13d..6702ac28754b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,6 +14,7 @@ #include "util.h" #include "cpumap.h" #include "perf_regs.h" +#include "asm/bug.h" static int perf_session__open(struct perf_session *session) { @@ -66,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session) machines__destroy_kernel_maps(&session->machines); } +static bool perf_session__has_comm_exec(struct perf_session *session) +{ + struct perf_evsel *evsel; + + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.comm_exec) + return true; + } + + return false; +} + +static void perf_session__set_comm_exec(struct perf_session *session) +{ + bool comm_exec = perf_session__has_comm_exec(session); + + machines__set_comm_exec(&session->machines, comm_exec); +} + struct perf_session *perf_session__new(struct perf_data_file *file, bool repipe, struct perf_tool *tool) { @@ -75,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out; session->repipe = repipe; - INIT_LIST_HEAD(&session->ordered_samples.samples); - INIT_LIST_HEAD(&session->ordered_samples.sample_cache); - INIT_LIST_HEAD(&session->ordered_samples.to_free); + ordered_events__init(&session->ordered_events); machines__init(&session->machines); if (file) { @@ -91,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out_close; perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); } } @@ -100,13 +119,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file, * kernel MMAP event, in perf_event__process_mmap(). */ if (perf_session__create_kernel_maps(session) < 0) - goto out_delete; + pr_warning("Cannot read kernel map\n"); } if (tool && tool->ordering_requires_timestamps && - tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) { + tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); - tool->ordered_samples = false; + tool->ordered_events = false; } return session; @@ -238,7 +257,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->build_id == NULL) tool->build_id = process_finished_round_stub; if (tool->finished_round == NULL) { - if (tool->ordered_samples) + if (tool->ordered_events) tool->finished_round = process_finished_round; else tool->finished_round = process_finished_round_stub; @@ -444,87 +463,6 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_HEADER_MAX] = NULL, }; -struct sample_queue { - u64 timestamp; - u64 file_offset; - union perf_event *event; - struct list_head list; -}; - -static void perf_session_free_sample_buffers(struct perf_session *session) -{ - struct ordered_samples *os = &session->ordered_samples; - - while (!list_empty(&os->to_free)) { - struct sample_queue *sq; - - sq = list_entry(os->to_free.next, struct sample_queue, list); - list_del(&sq->list); - free(sq); - } -} - -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset); - -static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) -{ - struct ordered_samples *os = &s->ordered_samples; - struct list_head *head = &os->samples; - struct sample_queue *tmp, *iter; - struct perf_sample sample; - u64 limit = os->next_flush; - u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; - bool show_progress = limit == ULLONG_MAX; - struct ui_progress prog; - int ret; - - if (!tool->ordered_samples || !limit) - return 0; - - if (show_progress) - ui_progress__init(&prog, os->nr_samples, "Processing time ordered events..."); - - list_for_each_entry_safe(iter, tmp, head, list) { - if (session_done()) - return 0; - - if (iter->timestamp > limit) - break; - - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); - if (ret) - pr_err("Can't parse sample, err = %d\n", ret); - else { - ret = perf_session_deliver_event(s, iter->event, &sample, tool, - iter->file_offset); - if (ret) - return ret; - } - - os->last_flush = iter->timestamp; - list_del(&iter->list); - list_add(&iter->list, &os->sample_cache); - os->nr_samples--; - - if (show_progress) - ui_progress__update(&prog, 1); - } - - if (list_empty(head)) { - os->last_sample = NULL; - } else if (last_ts <= limit) { - os->last_sample = - list_entry(head->prev, struct sample_queue, list); - } - - return 0; -} - /* * When perf record finishes a pass on every buffers, it records this pseudo * event. @@ -568,99 +506,42 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event __maybe_unused, struct perf_session *session) { - int ret = flush_sample_queue(session, tool); - if (!ret) - session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; - - return ret; -} - -/* The queue is ordered by time */ -static void __queue_event(struct sample_queue *new, struct perf_session *s) -{ - struct ordered_samples *os = &s->ordered_samples; - struct sample_queue *sample = os->last_sample; - u64 timestamp = new->timestamp; - struct list_head *p; - - ++os->nr_samples; - os->last_sample = new; - - if (!sample) { - list_add(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - - /* - * last_sample might point to some random place in the list as it's - * the last queued event. We expect that the new event is close to - * this. - */ - if (sample->timestamp <= timestamp) { - while (sample->timestamp <= timestamp) { - p = sample->list.next; - if (p == &os->samples) { - list_add_tail(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add_tail(&new->list, &sample->list); - } else { - while (sample->timestamp > timestamp) { - p = sample->list.prev; - if (p == &os->samples) { - list_add(&new->list, &os->samples); - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add(&new->list, &sample->list); - } + return ordered_events__flush(session, tool, OE_FLUSH__ROUND); } -#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) - int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_sample *sample, u64 file_offset) + struct perf_tool *tool, struct perf_sample *sample, + u64 file_offset) { - struct ordered_samples *os = &s->ordered_samples; - struct list_head *sc = &os->sample_cache; + struct ordered_events *oe = &s->ordered_events; u64 timestamp = sample->time; - struct sample_queue *new; + struct ordered_event *new; if (!timestamp || timestamp == ~0ULL) return -ETIME; - if (timestamp < s->ordered_samples.last_flush) { - printf("Warning: Timestamp below last timeslice flush\n"); - return -EINVAL; - } + if (timestamp < oe->last_flush) { + WARN_ONCE(1, "Timestamp below last timeslice flush\n"); - if (!list_empty(sc)) { - new = list_entry(sc->next, struct sample_queue, list); - list_del(&new->list); - } else if (os->sample_buffer) { - new = os->sample_buffer + os->sample_buffer_idx; - if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER) - os->sample_buffer = NULL; - } else { - os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new)); - if (!os->sample_buffer) - return -ENOMEM; - list_add(&os->sample_buffer->list, &os->to_free); - os->sample_buffer_idx = 2; - new = os->sample_buffer + 1; + pr_oe_time(timestamp, "out of order event"); + pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", + oe->last_flush_type); + + /* We could get out of order messages after forced flush. */ + if (oe->last_flush_type != OE_FLUSH__HALF) + return -EINVAL; } - new->timestamp = timestamp; - new->file_offset = file_offset; - new->event = event; + new = ordered_events__new(oe, timestamp, event); + if (!new) { + ordered_events__flush(s, tool, OE_FLUSH__HALF); + new = ordered_events__new(oe, timestamp, event); + } - __queue_event(new, s); + if (!new) + return -ENOMEM; + new->file_offset = file_offset; return 0; } @@ -920,11 +801,10 @@ perf_session__deliver_sample(struct perf_session *session, &sample->read.one, machine); } -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset) +int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; struct machine *machine; @@ -932,22 +812,6 @@ static int perf_session_deliver_event(struct perf_session *session, dump_event(session, event, file_offset, sample); evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) { - /* - * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here - * because the tools right now may apply filters, discarding - * some of the samples. For consistency, in the future we - * should have something like nr_filtered_samples and remove - * the sample->period from total_sample_period, etc, KISS for - * now tho. - * - * Also testing against NULL allows us to handle files without - * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the - * future probably it'll be a good idea to restrict event - * processing via perf_session to files with both set. - */ - hists__inc_nr_events(&evsel->hists, event->header.type); - } machine = perf_session__find_machine_for_cpumode(session, event, sample); @@ -1005,8 +869,10 @@ static s64 perf_session__process_user_event(struct perf_session *session, switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: err = tool->attr(tool, event, &session->evlist); - if (err == 0) + if (err == 0) { perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } return err; case PERF_RECORD_HEADER_EVENT_TYPE: /* @@ -1036,6 +902,61 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } +int perf_session__peek_event(struct perf_session *session, off_t file_offset, + void *buf, size_t buf_sz, + union perf_event **event_ptr, + struct perf_sample *sample) +{ + union perf_event *event; + size_t hdr_sz, rest; + int fd; + + if (session->one_mmap && !session->header.needs_swap) { + event = file_offset - session->one_mmap_offset + + session->one_mmap_addr; + goto out_parse_sample; + } + + if (perf_data_file__is_pipe(session->file)) + return -1; + + fd = perf_data_file__fd(session->file); + hdr_sz = sizeof(struct perf_event_header); + + if (buf_sz < hdr_sz) + return -1; + + if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 || + readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz) + return -1; + + event = (union perf_event *)buf; + + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); + + if (event->header.size < hdr_sz) + return -1; + + rest = event->header.size - hdr_sz; + + if (readn(fd, &buf, rest) != (ssize_t)rest) + return -1; + + if (session->header.needs_swap) + event_swap(event, perf_evlist__sample_id_all(session->evlist)); + +out_parse_sample: + + if (sample && event->header.type < PERF_RECORD_USER_TYPE_START && + perf_evlist__parse_sample(session->evlist, event, sample)) + return -1; + + *event_ptr = event; + + return 0; +} + static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, @@ -1062,15 +983,15 @@ static s64 perf_session__process_event(struct perf_session *session, if (ret) return ret; - if (tool->ordered_samples) { - ret = perf_session_queue_event(session, event, &sample, + if (tool->ordered_events) { + ret = perf_session_queue_event(session, event, tool, &sample, file_offset); if (ret != -ETIME) return ret; } - return perf_session_deliver_event(session, event, &sample, tool, - file_offset); + return perf_session__deliver_event(session, event, &sample, tool, + file_offset); } void perf_event_header__bswap(struct perf_event_header *hdr) @@ -1222,12 +1143,11 @@ more: goto more; done: /* do the final flush for ordered samples */ - session->ordered_samples.next_flush = ULLONG_MAX; - err = flush_sample_queue(session, tool); + err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: free(buf); perf_session__warn_about_errors(session, tool); - perf_session_free_sample_buffers(session); + ordered_events__free(&session->ordered_events); return err; } @@ -1368,12 +1288,11 @@ more: out: /* do the final flush for ordered samples */ - session->ordered_samples.next_flush = ULLONG_MAX; - err = flush_sample_queue(session, tool); + err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: ui_progress__finish(); perf_session__warn_about_errors(session, tool); - perf_session_free_sample_buffers(session); + ordered_events__free(&session->ordered_events); session->one_mmap = false; return err; } @@ -1455,16 +1374,9 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { - struct perf_evsel *pos; size_t ret = fprintf(fp, "Aggregated stats:\n"); ret += events_stats__fprintf(&session->stats, fp); - - evlist__for_each(session->evlist, pos) { - ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); - ret += events_stats__fprintf(&pos->hists.stats, fp); - } - return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 0321013bd9fd..a4be851f1a90 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -2,33 +2,19 @@ #define __PERF_SESSION_H #include "trace-event.h" -#include "hist.h" #include "event.h" #include "header.h" #include "machine.h" #include "symbol.h" #include "thread.h" #include "data.h" +#include "ordered-events.h" #include <linux/rbtree.h> #include <linux/perf_event.h> -struct sample_queue; struct ip_callchain; struct thread; -struct ordered_samples { - u64 last_flush; - u64 next_flush; - u64 max_timestamp; - struct list_head samples; - struct list_head sample_cache; - struct list_head to_free; - struct sample_queue *sample_buffer; - struct sample_queue *last_sample; - int sample_buffer_idx; - unsigned int nr_samples; -}; - struct perf_session { struct perf_header header; struct machines machines; @@ -39,7 +25,7 @@ struct perf_session { bool one_mmap; void *one_mmap_addr; u64 one_mmap_offset; - struct ordered_samples ordered_samples; + struct ordered_events ordered_events; struct perf_data_file *file; }; @@ -58,6 +44,11 @@ void perf_session__delete(struct perf_session *session); void perf_event_header__bswap(struct perf_event_header *hdr); +int perf_session__peek_event(struct perf_session *session, off_t file_offset, + void *buf, size_t buf_sz, + union perf_event **event_ptr, + struct perf_sample *sample); + int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 size, struct perf_tool *tool); @@ -65,10 +56,16 @@ int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_sample *sample, u64 file_offset); + struct perf_tool *tool, struct perf_sample *sample, + u64 file_offset); void perf_tool__fill_defaults(struct perf_tool *tool); +int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset); + int perf_session__resolve_callchain(struct perf_session *session, struct perf_evsel *evsel, struct thread *thread, @@ -128,5 +125,5 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; -#define session_done() (*(volatile int *)(&session_done)) +#define session_done() ACCESS_ONCE(session_done) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 14e5a039bc45..9402885a77f3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { const char *comm = thread__comm_str(he->thread); - return repsep_snprintf(bf, size, "%*s:%5d", width - 6, - comm ?: "", he->thread->tid); + + width = max(7U, width) - 6; + return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid, + width, width, comm ?: ""); } struct sort_entry sort_thread = { - .se_header = "Command: Pid", + .se_header = " Pid:Command", .se_cmp = sort__thread_cmp, .se_snprintf = hist_entry__thread_snprintf, .se_width_idx = HISTC_THREAD, @@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right) static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm)); + return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm)); } struct sort_entry sort_comm = { @@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, if (map && map->dso) { const char *dso_name = !verbose ? map->dso->short_name : map->dso->long_name; - return repsep_snprintf(bf, size, "%-*s", width, dso_name); + return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); } - return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); + return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]"); } static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, @@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, width - ret, ""); } - return ret; + if (ret > width) + bf[width] = '\0'; + + return width; } static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, @@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) } static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%s", he->srcline); + return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline); } struct sort_entry sort_srcline = { @@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*s", width, + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->parent ? he->parent->name : "[other]"); } @@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*d", width, he->cpu); + return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu); } struct sort_entry sort_cpu = { @@ -369,6 +373,9 @@ struct sort_entry sort_cpu = { static int64_t sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return _sort__dso_cmp(left->branch_info->from.map, right->branch_info->from.map); } @@ -376,13 +383,19 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(he->branch_info->from.map, - bf, size, width); + if (he->branch_info) + return _hist_entry__dso_snprintf(he->branch_info->from.map, + bf, size, width); + else + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int64_t sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return _sort__dso_cmp(left->branch_info->to.map, right->branch_info->to.map); } @@ -390,8 +403,11 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(he->branch_info->to.map, - bf, size, width); + if (he->branch_info) + return _hist_entry__dso_snprintf(he->branch_info->to.map, + bf, size, width); + else + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int64_t @@ -400,6 +416,12 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) struct addr_map_symbol *from_l = &left->branch_info->from; struct addr_map_symbol *from_r = &right->branch_info->from; + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + from_l = &left->branch_info->from; + from_r = &right->branch_info->from; + if (!from_l->sym && !from_r->sym) return _sort__addr_cmp(from_l->addr, from_r->addr); @@ -409,8 +431,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) static int64_t sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) { - struct addr_map_symbol *to_l = &left->branch_info->to; - struct addr_map_symbol *to_r = &right->branch_info->to; + struct addr_map_symbol *to_l, *to_r; + + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + to_l = &left->branch_info->to; + to_r = &right->branch_info->to; if (!to_l->sym && !to_r->sym) return _sort__addr_cmp(to_l->addr, to_r->addr); @@ -421,19 +448,27 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *from = &he->branch_info->from; - return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - he->level, bf, size, width); + if (he->branch_info) { + struct addr_map_symbol *from = &he->branch_info->from; + return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, + he->level, bf, size, width); + } + + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *to = &he->branch_info->to; - return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - he->level, bf, size, width); + if (he->branch_info) { + struct addr_map_symbol *to = &he->branch_info->to; + return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, + he->level, bf, size, width); + } + + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } struct sort_entry sort_dso_from = { @@ -467,11 +502,13 @@ struct sort_entry sort_sym_to = { static int64_t sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) { - const unsigned char mp = left->branch_info->flags.mispred != - right->branch_info->flags.mispred; - const unsigned char p = left->branch_info->flags.predicted != - right->branch_info->flags.predicted; + unsigned char mp, p; + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred; + p = left->branch_info->flags.predicted != right->branch_info->flags.predicted; return mp || p; } @@ -479,12 +516,14 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width){ static const char *out = "N/A"; - if (he->branch_info->flags.predicted) - out = "N"; - else if (he->branch_info->flags.mispred) - out = "Y"; + if (he->branch_info) { + if (he->branch_info->flags.predicted) + out = "N"; + else if (he->branch_info->flags.mispred) + out = "Y"; + } - return repsep_snprintf(bf, size, "%-*s", width, out); + return repsep_snprintf(bf, size, "%-*.*s", width, width, out); } /* --sort daddr_sym */ @@ -985,6 +1024,9 @@ struct sort_entry sort_mem_dcacheline = { static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.abort != right->branch_info->flags.abort; } @@ -992,10 +1034,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - static const char *out = "."; + static const char *out = "N/A"; + + if (he->branch_info) { + if (he->branch_info->flags.abort) + out = "A"; + else + out = "."; + } - if (he->branch_info->flags.abort) - out = "A"; return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -1009,6 +1056,9 @@ struct sort_entry sort_abort = { static int64_t sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.in_tx != right->branch_info->flags.in_tx; } @@ -1016,10 +1066,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - static const char *out = "."; + static const char *out = "N/A"; - if (he->branch_info->flags.in_tx) - out = "T"; + if (he->branch_info) { + if (he->branch_info->flags.in_tx) + out = "T"; + else + out = "."; + } return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -1194,7 +1248,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) return hse_a->se == hse_b->se; } -void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) { struct hpp_sort_entry *hse; @@ -1202,20 +1256,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) return; hse = container_of(fmt, struct hpp_sort_entry, hpp); - hists__new_col_len(hists, hse->se->se_width_idx, - strlen(hse->se->se_header)); + hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name)); } static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct perf_evsel *evsel) { struct hpp_sort_entry *hse; - size_t len; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - len = hists__col_len(&evsel->hists, hse->se->se_width_idx); - return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header); + if (!len) + len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + + return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name); } static int __sort__hpp_width(struct perf_hpp_fmt *fmt, @@ -1223,20 +1278,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt, struct perf_evsel *evsel) { struct hpp_sort_entry *hse; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - return hists__col_len(&evsel->hists, hse->se->se_width_idx); + if (!len) + len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + + return len; } static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { struct hpp_sort_entry *hse; - size_t len; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - len = hists__col_len(he->hists, hse->se->se_width_idx); + + if (!len) + len = hists__col_len(he->hists, hse->se->se_width_idx); return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); } @@ -1253,6 +1314,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) } hse->se = sd->entry; + hse->hpp.name = sd->entry->se_header; hse->hpp.header = __sort__hpp_header; hse->hpp.width = __sort__hpp_width; hse->hpp.entry = __sort__hpp_entry; @@ -1265,6 +1327,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); hse->hpp.elide = false; + hse->hpp.len = 0; + hse->hpp.user_len = 0; return hse; } @@ -1432,14 +1496,49 @@ static const char *get_default_sort_order(void) return default_sort_orders[sort__mode]; } +static int setup_sort_order(void) +{ + char *new_sort_order; + + /* + * Append '+'-prefixed sort order to the default sort + * order string. + */ + if (!sort_order || is_strict_order(sort_order)) + return 0; + + if (sort_order[1] == '\0') { + error("Invalid --sort key: `+'"); + return -EINVAL; + } + + /* + * We allocate new sort_order string, but we never free it, + * because it's checked over the rest of the code. + */ + if (asprintf(&new_sort_order, "%s,%s", + get_default_sort_order(), sort_order + 1) < 0) { + error("Not enough memory to set up --sort"); + return -ENOMEM; + } + + sort_order = new_sort_order; + return 0; +} + static int __setup_sorting(void) { char *tmp, *tok, *str; - const char *sort_keys = sort_order; + const char *sort_keys; int ret = 0; + ret = setup_sort_order(); + if (ret) + return ret; + + sort_keys = sort_order; if (sort_keys == NULL) { - if (field_order) { + if (is_strict_order(field_order)) { /* * If user specified field order but no sort order, * we'll honor it and not add default sort orders. @@ -1625,23 +1724,36 @@ static void reset_dimensions(void) memory_sort_dimensions[i].taken = 0; } +bool is_strict_order(const char *order) +{ + return order && (*order != '+'); +} + static int __setup_output_field(void) { - char *tmp, *tok, *str; - int ret = 0; + char *tmp, *tok, *str, *strp; + int ret = -EINVAL; if (field_order == NULL) return 0; reset_dimensions(); - str = strdup(field_order); + strp = str = strdup(field_order); if (str == NULL) { error("Not enough memory to setup output fields"); return -ENOMEM; } - for (tok = strtok_r(str, ", ", &tmp); + if (!is_strict_order(field_order)) + strp++; + + if (!strlen(strp)) { + error("Invalid --fields key: `+'"); + goto out; + } + + for (tok = strtok_r(strp, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = output_field_add(tok); if (ret == -EINVAL) { @@ -1653,6 +1765,7 @@ static int __setup_output_field(void) } } +out: free(str); return ret; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 041f0c9cea2b..c03e4ff8beff 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); +bool is_strict_order(const char *order); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 2553e5b55b89..6afd6106ceb5 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -9,78 +9,48 @@ */ s64 perf_atoll(const char *str) { - unsigned int i; - s64 length = -1, unit = 1; + s64 length; + char *p; + char c; if (!isdigit(str[0])) goto out_err; - for (i = 1; i < strlen(str); i++) { - switch (str[i]) { - case 'B': - case 'b': - break; - case 'K': - if (str[i + 1] != 'B') - goto out_err; - else - goto kilo; - case 'k': - if (str[i + 1] != 'b') - goto out_err; -kilo: - unit = K; - break; - case 'M': - if (str[i + 1] != 'B') - goto out_err; - else - goto mega; - case 'm': - if (str[i + 1] != 'b') - goto out_err; -mega: - unit = K * K; - break; - case 'G': - if (str[i + 1] != 'B') + length = strtoll(str, &p, 10); + switch (c = *p++) { + case 'b': case 'B': + if (*p) goto out_err; - else - goto giga; - case 'g': - if (str[i + 1] != 'b') - goto out_err; -giga: - unit = K * K * K; + case '\0': + return length; + default: + goto out_err; + /* two-letter suffices */ + case 'k': case 'K': + length <<= 10; break; - case 'T': - if (str[i + 1] != 'B') - goto out_err; - else - goto tera; - case 't': - if (str[i + 1] != 'b') - goto out_err; -tera: - unit = K * K * K * K; + case 'm': case 'M': + length <<= 20; break; - case '\0': /* only specified figures */ - unit = 1; + case 'g': case 'G': + length <<= 30; break; - default: - if (!isdigit(str[i])) - goto out_err; + case 't': case 'T': + length <<= 40; break; - } } - - length = atoll(str) * unit; - goto out; + /* we want the cases to match */ + if (islower(c)) { + if (strcmp(p, "b") != 0) + goto out_err; + } else { + if (strcmp(p, "B") != 0) + goto out_err; + } + return length; out_err: - length = -1; -out: - return length; + return -1; } /* @@ -387,27 +357,3 @@ void *memdup(const void *src, size_t len) return p; } - -/** - * str_append - reallocate string and append another - * @s: pointer to string pointer - * @len: pointer to len (initialized) - * @a: string to append. - */ -int str_append(char **s, int *len, const char *a) -{ - int olen = *s ? strlen(*s) : 0; - int nlen = olen + strlen(a) + 1; - if (*len < nlen) { - *len = *len * 2; - if (*len < nlen) - *len = nlen; - *s = realloc(*s, *len); - if (!*s) - return -ENOMEM; - if (olen == 0) - **s = 0; - } - strcat(*s, a); - return 0; -} diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index d75349979e65..1e23a5bfb044 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -6,6 +6,7 @@ #include <inttypes.h> #include "symbol.h" +#include "machine.h" #include "vdso.h" #include <symbol/kallsyms.h> #include "debug.h" @@ -680,6 +681,11 @@ static u64 ref_reloc(struct kmap *kmap) return 0; } +static bool want_demangle(bool is_kernel_sym) +{ + return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, int kmodule) @@ -712,6 +718,14 @@ int dso__load_sym(struct dso *dso, struct map *map, symbols__delete(&dso->symbols[map->type]); if (!syms_ss->symtab) { + /* + * If the vmlinux is stripped, fail so we will fall back + * to using kallsyms. The vmlinux runtime symbols aren't + * of much use. + */ + if (dso->kernel) + goto out_elf_end; + syms_ss->symtab = syms_ss->dynsym; syms_ss->symshdr = syms_ss->dynshdr; } @@ -736,7 +750,7 @@ int dso__load_sym(struct dso *dso, struct map *map, if (symstrs == NULL) goto out_elf_end; - sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); if (sec_strndx == NULL) goto out_elf_end; @@ -916,7 +930,11 @@ int dso__load_sym(struct dso *dso, struct map *map, } curr_dso->symtab_type = dso->symtab_type; map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&dso->node, curr_dso); + /* + * The new DSO should go to the kernel DSOS + */ + dsos__add(&map->groups->machine->kernel_dsos, + curr_dso); dso__set_loaded(curr_dso, map->type); } else curr_dso = curr_map->dso; @@ -938,9 +956,12 @@ new_symbol: * DWARF DW_compile_unit has this, but we don't always have access * to it... */ - if (symbol_conf.demangle) { - demangled = bfd_demangle(NULL, elf_name, - DMGL_PARAMS | DMGL_ANSI); + if (want_demangle(dso->kernel || kmodule)) { + int demangle_flags = DMGL_NO_OPTS; + if (verbose) + demangle_flags = DMGL_PARAMS | DMGL_ANSI; + + demangled = bfd_demangle(NULL, elf_name, demangle_flags); if (demangled != NULL) elf_name = demangled; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index eb06746b06b2..078331140d8c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -15,6 +15,7 @@ #include "machine.h" #include "symbol.h" #include "strlist.h" +#include "header.h" #include <elf.h> #include <limits.h> @@ -33,6 +34,7 @@ struct symbol_conf symbol_conf = { .try_vmlinux_path = true, .annotate_src = true, .demangle = true, + .demangle_kernel = false, .cumulate_callchain = true, .show_hist_headers = true, .symfs = "", @@ -184,7 +186,7 @@ void symbols__fixup_end(struct rb_root *symbols) curr = rb_entry(nd, struct symbol, rb_node); if (prev->end == prev->start && prev->end != curr->start) - prev->end = curr->start - 1; + prev->end = curr->start; } /* Last entry */ @@ -205,7 +207,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { prev = curr; curr = rb_entry(nd, struct map, rb_node); - prev->end = curr->start - 1; + prev->end = curr->start; } /* @@ -227,7 +229,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) sym = ((void *)sym) + symbol_conf.priv_size; sym->start = start; - sym->end = len ? start + len - 1 : start; + sym->end = len ? start + len : start; sym->binding = binding; sym->namelen = namelen - 1; @@ -323,7 +325,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) if (ip < s->start) n = n->rb_left; - else if (ip > s->end) + else if (ip >= s->end) n = n->rb_right; else return s; @@ -523,10 +525,15 @@ struct process_kallsyms_args { struct dso *dso; }; +/* + * These are symbols in the kernel image, so make sure that + * sym is from a kernel DSO. + */ bool symbol__is_idle(struct symbol *sym) { const char * const idle_symbols[] = { "cpu_idle", + "cpu_startup_entry", "intel_idle", "default_idle", "native_safe_halt", @@ -1468,8 +1475,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, if (vmlinux[0] == '/') snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux); else - snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", - symbol_conf.symfs, vmlinux); + symbol__join_symfs(symfs_vmlinux, vmlinux); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; @@ -1745,12 +1751,13 @@ static void vmlinux_path__exit(void) zfree(&vmlinux_path); } -static int vmlinux_path__init(void) +static int vmlinux_path__init(struct perf_session_env *env) { struct utsname uts; char bf[PATH_MAX]; + char *kernel_version; - vmlinux_path = malloc(sizeof(char *) * 5); + vmlinux_path = malloc(sizeof(char *) * 6); if (vmlinux_path == NULL) return -1; @@ -1763,25 +1770,37 @@ static int vmlinux_path__init(void) goto out_fail; ++vmlinux_path__nr_entries; - /* only try running kernel version if no symfs was given */ + /* only try kernel version if no symfs was given */ if (symbol_conf.symfs[0] != 0) return 0; - if (uname(&uts) < 0) - return -1; + if (env) { + kernel_version = env->os_release; + } else { + if (uname(&uts) < 0) + goto out_fail; - snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release); + kernel_version = uts.release; + } + + snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; ++vmlinux_path__nr_entries; - snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release); + snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s", + kernel_version); + vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; ++vmlinux_path__nr_entries; snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux", - uts.release); + kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; @@ -1827,7 +1846,7 @@ static bool symbol__read_kptr_restrict(void) return value; } -int symbol__init(void) +int symbol__init(struct perf_session_env *env) { const char *symfs; @@ -1842,7 +1861,7 @@ int symbol__init(void) symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) - sizeof(struct symbol)); - if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0) + if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0) return -1; if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index e7295e93cff9..eb2c19bf8d90 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,6 +13,7 @@ #include <libgen.h> #include "build-id.h" #include "event.h" +#include "util.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -59,6 +60,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, #endif #ifndef DMGL_PARAMS +#define DMGL_NO_OPTS 0 /* For readability... */ #define DMGL_PARAMS (1 << 0) /* Include function args */ #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif @@ -93,7 +95,7 @@ void symbols__delete(struct rb_root *symbols); static inline size_t symbol__size(const struct symbol *sym) { - return sym->end - sym->start + 1; + return sym->end - sym->start; } struct strlist; @@ -118,6 +120,7 @@ struct symbol_conf { annotate_src, event_group, demangle, + demangle_kernel, filter_relative, show_hist_headers; const char *vmlinux_name, @@ -143,6 +146,14 @@ struct symbol_conf { }; extern struct symbol_conf symbol_conf; + +static inline int __symbol__join_symfs(char *bf, size_t size, const char *path) +{ + return path__join(bf, size, symbol_conf.symfs, path); +} + +#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path) + extern int vmlinux_path__nr_entries; extern char **vmlinux_path; @@ -253,7 +264,8 @@ int modules__parse(const char *filename, void *arg, int filename__read_debuglink(const char *filename, char *debuglink, size_t size); -int symbol__init(void); +struct perf_session_env; +int symbol__init(struct perf_session_env *env); void symbol__exit(void); void symbol__elf_init(void); struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 12c7a253a63c..c41411726c7a 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,6 +7,7 @@ #include "util.h" #include "debug.h" #include "comm.h" +#include "unwind.h" int thread__init_map_groups(struct thread *thread, struct machine *machine) { @@ -37,17 +38,21 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->cpu = -1; INIT_LIST_HEAD(&thread->comm_list); + if (unwind__prepare_access(thread) < 0) + goto err_thread; + comm_str = malloc(32); if (!comm_str) goto err_thread; snprintf(comm_str, 32, ":%d", tid); - comm = comm__new(comm_str, 0); + comm = comm__new(comm_str, 0, false); free(comm_str); if (!comm) goto err_thread; list_add(&comm->list, &thread->comm_list); + } return thread; @@ -69,6 +74,7 @@ void thread__delete(struct thread *thread) list_del(&comm->list); comm__free(comm); } + unwind__finish_access(thread); free(thread); } @@ -81,22 +87,39 @@ struct comm *thread__comm(const struct thread *thread) return list_first_entry(&thread->comm_list, struct comm, list); } +struct comm *thread__exec_comm(const struct thread *thread) +{ + struct comm *comm, *last = NULL; + + list_for_each_entry(comm, &thread->comm_list, list) { + if (comm->exec) + return comm; + last = comm; + } + + return last; +} + /* CHECKME: time should always be 0 if event aren't ordered */ -int thread__set_comm(struct thread *thread, const char *str, u64 timestamp) +int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, + bool exec) { struct comm *new, *curr = thread__comm(thread); int err; /* Override latest entry if it had no specific time coverage */ - if (!curr->start) { - err = comm__override(curr, str, timestamp); + if (!curr->start && !curr->exec) { + err = comm__override(curr, str, timestamp, exec); if (err) return err; } else { - new = comm__new(str, timestamp); + new = comm__new(str, timestamp, exec); if (!new) return -ENOMEM; list_add(&new->list, &thread->comm_list); + + if (exec) + unwind__flush_access(thread); } thread->comm_set = true; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 716b7723cce2..8c75fa774706 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } -int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp); +int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, + bool exec); +static inline int thread__set_comm(struct thread *thread, const char *comm, + u64 timestamp) +{ + return __thread__set_comm(thread, comm, timestamp, false); +} + int thread__comm_len(struct thread *thread); struct comm *thread__comm(const struct thread *thread); +struct comm *thread__exec_comm(const struct thread *thread); const char *thread__comm_str(const struct thread *thread); void thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 5d3215912105..f93b9734735b 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -214,6 +214,17 @@ out_free_threads: goto out; } +struct thread_map *thread_map__new_dummy(void) +{ + struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t)); + + if (threads != NULL) { + threads->map[0] = -1; + threads->nr = 1; + } + return threads; +} + static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) { struct thread_map *threads = NULL, *nt; @@ -224,14 +235,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) struct strlist *slist; /* perf-stat expects threads to be generated even if tid not given */ - if (!tid_str) { - threads = malloc(sizeof(*threads) + sizeof(pid_t)); - if (threads != NULL) { - threads->map[0] = -1; - threads->nr = 1; - } - return threads; - } + if (!tid_str) + return thread_map__new_dummy(); slist = strlist__new(false, tid_str); if (!slist) diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 0cd8b3108084..95313f43cc0f 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -9,6 +9,7 @@ struct thread_map { pid_t map[]; }; +struct thread_map *thread_map__new_dummy(void); struct thread_map *thread_map__new_by_pid(pid_t pid); struct thread_map *thread_map__new_by_tid(pid_t tid); struct thread_map *thread_map__new_by_uid(uid_t uid); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 4385816d3d49..f11636966a0f 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -40,7 +40,7 @@ struct perf_tool { event_op2 tracing_data; event_op2 finished_round, build_id; - bool ordered_samples; + bool ordered_events; bool ordering_requires_timestamps; }; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 57aaccc1692e..5c9bdd1591a9 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -30,6 +30,11 @@ struct scripting_context *scripting_context; +static int flush_script_unsupported(void) +{ + return 0; +} + static int stop_script_unsupported(void) { return 0; @@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent struct scripting_ops python_scripting_unsupported_ops = { .name = "Python", .start_script = python_start_script_unsupported, + .flush_script = flush_script_unsupported, .stop_script = stop_script_unsupported, .process_event = process_event_unsupported, .generate_script = python_generate_script_unsupported, @@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent struct scripting_ops perl_scripting_unsupported_ops = { .name = "Perl", .start_script = perl_start_script_unsupported, + .flush_script = flush_script_unsupported, .stop_script = stop_script_unsupported, .process_event = process_event_unsupported, .generate_script = perl_generate_script_unsupported, diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 7b6d68688327..52aaa19e1eb1 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -64,6 +64,7 @@ struct perf_session; struct scripting_ops { const char *name; int (*start_script) (const char *script, int argc, const char **argv); + int (*flush_script) (void); int (*stop_script) (void); void (*process_event) (union perf_event *event, struct perf_sample *sample, diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 92b56db52471..4d45c0dfe343 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -24,6 +24,7 @@ #include <linux/list.h> #include <libunwind.h> #include <libunwind-ptrace.h> +#include "callchain.h" #include "thread.h" #include "session.h" #include "perf_regs.h" @@ -525,12 +526,12 @@ static unw_accessors_t accessors = { .get_proc_name = get_proc_name, }; -static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, - void *arg, int max_stack) +int unwind__prepare_access(struct thread *thread) { unw_addr_space_t addr_space; - unw_cursor_t c; - int ret; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return 0; addr_space = unw_create_addr_space(&accessors, 0); if (!addr_space) { @@ -538,6 +539,45 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -ENOMEM; } + unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL); + thread__set_priv(thread, addr_space); + + return 0; +} + +void unwind__flush_access(struct thread *thread) +{ + unw_addr_space_t addr_space; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + addr_space = thread__priv(thread); + unw_flush_cache(addr_space, 0, 0); +} + +void unwind__finish_access(struct thread *thread) +{ + unw_addr_space_t addr_space; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + addr_space = thread__priv(thread); + unw_destroy_addr_space(addr_space); +} + +static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, + void *arg, int max_stack) +{ + unw_addr_space_t addr_space; + unw_cursor_t c; + int ret; + + addr_space = thread__priv(ui->thread); + if (addr_space == NULL) + return -1; + ret = unw_init_remote(&c, addr_space, ui); if (ret) display_error(ret); @@ -549,7 +589,6 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; } - unw_destroy_addr_space(addr_space); return ret; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index f03061260b4e..f50b737235eb 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include "event.h" #include "symbol.h" +#include "thread.h" struct unwind_entry { struct map *map; @@ -21,6 +22,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT int libunwind__arch_reg_id(int regnum); +int unwind__prepare_access(struct thread *thread); +void unwind__flush_access(struct thread *thread); +void unwind__finish_access(struct thread *thread); +#else +static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +{ + return 0; +} + +static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} +static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} #endif #else static inline int @@ -33,5 +45,13 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, { return 0; } + +static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +{ + return 0; +} + +static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} +static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} #endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index e52e7461911b..d5eab3f3323f 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -13,6 +13,15 @@ #include <limits.h> #include <byteswap.h> #include <linux/kernel.h> +#include <unistd.h> +#include "callchain.h" + +struct callchain_param callchain_param = { + .mode = CHAIN_GRAPH_REL, + .min_percent = 0.5, + .order = ORDER_CALLEE, + .key = CCKEY_FUNCTION +}; /* * XXX We need to find a better place for these things... @@ -282,6 +291,18 @@ void get_term_dimensions(struct winsize *ws) ws->ws_col = 80; } +void set_term_quiet_input(struct termios *old) +{ + struct termios tc; + + tcgetattr(0, old); + tc = *old; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; + tcsetattr(0, TCSANOW, &tc); +} + static void set_tracing_events_path(const char *mountpoint) { snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", @@ -443,6 +464,7 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) size_t size = 0, alloc_size = 0; void *bf = NULL, *nbf; int fd, n, err = 0; + char sbuf[STRERR_BUFSIZE]; fd = open(filename, O_RDONLY); if (fd < 0) @@ -463,8 +485,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) n = read(fd, bf + size, alloc_size - size); if (n < 0) { if (size) { - pr_warning("read failed %d: %s\n", - errno, strerror(errno)); + pr_warning("read failed %d: %s\n", errno, + strerror_r(errno, sbuf, sizeof(sbuf))); err = 0; } else err = -errno; @@ -536,3 +558,39 @@ void mem_bswap_64(void *src, int byte_size) ++m; } } + +bool find_process(const char *name) +{ + size_t len = strlen(name); + DIR *dir; + struct dirent *d; + int ret = -1; + + dir = opendir(procfs__mountpoint()); + if (!dir) + return -1; + + /* Walk through the directory. */ + while (ret && (d = readdir(dir)) != NULL) { + char path[PATH_MAX]; + char *data; + size_t size; + + if ((d->d_type != DT_DIR) || + !strcmp(".", d->d_name) || + !strcmp("..", d->d_name)) + continue; + + scnprintf(path, sizeof(path), "%s/%s/comm", + procfs__mountpoint(), d->d_name); + + if (filename__read_str(path, &data, &size)) + continue; + + ret = strncmp(name, data, len); + free(data); + } + + closedir(dir); + return ret ? false : true; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 66864364ccb4..80bfdaa0e2a4 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -39,6 +39,8 @@ #define _ALL_SOURCE 1 #define _BSD_SOURCE 1 +/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ +#define _DEFAULT_SOURCE 1 #define HAS_BOOL #include <unistd.h> @@ -64,16 +66,18 @@ #include <regex.h> #include <utime.h> #include <sys/wait.h> -#include <sys/poll.h> +#include <poll.h> #include <sys/socket.h> #include <sys/ioctl.h> #include <inttypes.h> +#include <linux/kernel.h> #include <linux/magic.h> #include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/debugfs.h> #include <termios.h> #include <linux/bitops.h> +#include <termios.h> extern const char *graph_line; extern const char *graph_dotted_line; @@ -307,6 +311,7 @@ extern unsigned int page_size; extern int cacheline_size; void get_term_dimensions(struct winsize *ws); +void set_term_quiet_input(struct termios *old); struct parse_tag { char tag; @@ -317,6 +322,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags); #define SRCLINE_UNKNOWN ((char *) "??:0") +static inline int path__join(char *bf, size_t size, + const char *path1, const char *path2) +{ + return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); +} + +static inline int path__join3(char *bf, size_t size, + const char *path1, const char *path2, + const char *path3) +{ + return scnprintf(bf, size, "%s%s%s%s%s", + path1, path1[0] ? "/" : "", + path2, path2[0] ? "/" : "", path3); +} + struct dso; char *get_srcline(struct dso *dso, unsigned long addr); @@ -330,4 +350,5 @@ void mem_bswap_64(void *src, int byte_size); void mem_bswap_32(void *src, int byte_size); const char *get_filename_for_perf_kvm(void); +bool find_process(const char *name); #endif /* GIT_COMPAT_UTIL_H */ |