diff options
Diffstat (limited to 'tools/perf/util')
76 files changed, 3644 insertions, 601 deletions
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 56ad4f5287de..112d6e268150 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -3,7 +3,7 @@ #include <stdbool.h> #include <stdint.h> -#include "types.h" +#include <linux/types.h> #include "symbol.h" #include "hist.h" #include "sort.h" diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 6baabe63182b..a904a4cfe7d3 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -25,7 +25,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread = machine__findnew_thread(machine, sample->pid, - sample->pid); + sample->tid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 845ef865eced..ae392561470b 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -4,7 +4,7 @@ #define BUILD_ID_SIZE 20 #include "tool.h" -#include "types.h" +#include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8d9db454f1a9..437ee09727e6 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,6 +25,84 @@ __thread struct callchain_cursor callchain_cursor; +int +parse_callchain_report_opt(const char *arg) +{ + char *tok, *tok2; + char *endptr; + + symbol_conf.use_callchain = true; + + if (!arg) + return 0; + + tok = strtok((char *)arg, ","); + if (!tok) + return -1; + + /* get the output mode */ + if (!strncmp(tok, "graph", strlen(arg))) { + callchain_param.mode = CHAIN_GRAPH_ABS; + + } 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; + } + + /* get the min percentage */ + tok = strtok(NULL, ","); + if (!tok) + goto setup; + + callchain_param.min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + + /* get the print limit */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + + if (tok2[0] != 'c') { + callchain_param.print_limit = strtoul(tok2, &endptr, 0); + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + } + + /* get the call chain order */ + if (!strncmp(tok2, "caller", strlen("caller"))) + callchain_param.order = ORDER_CALLER; + else if (!strncmp(tok2, "callee", strlen("callee"))) + callchain_param.order = ORDER_CALLEE; + else + return -1; + + /* Get the sort key */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + if (!strncmp(tok2, "function", strlen("function"))) + callchain_param.key = CCKEY_FUNCTION; + else if (!strncmp(tok2, "address", strlen("address"))) + callchain_param.key = CCKEY_ADDRESS; + else + return -1; +setup: + if (callchain_register_param(&callchain_param) < 0) { + pr_err("Can't register callchain params\n"); + return -1; + } + return 0; +} + static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) @@ -538,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (sample->callchain == NULL) return 0; - if (symbol_conf.use_callchain || sort__has_parent) { + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || + sort__has_parent) { return machine__resolve_callchain(al->machine, evsel, al->thread, sample, parent, al, max_stack); } @@ -547,7 +626,49 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) { - if (!symbol_conf.use_callchain) + if (!symbol_conf.use_callchain || sample->callchain == NULL) return 0; return callchain_append(he->callchain, &callchain_cursor, sample->period); } + +int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, + bool hide_unresolved) +{ + al->map = node->map; + al->sym = node->sym; + if (node->map) + al->addr = node->map->map_ip(node->map, node->ip); + else + al->addr = node->ip; + + if (al->sym == NULL) { + if (hide_unresolved) + return 0; + if (al->map == NULL) + goto out; + } + + if (al->map->groups == &al->machine->kmaps) { + if (machine__is_host(al->machine)) { + al->cpumode = PERF_RECORD_MISC_KERNEL; + al->level = 'k'; + } else { + al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL; + al->level = 'g'; + } + } else { + if (machine__is_host(al->machine)) { + al->cpumode = PERF_RECORD_MISC_USER; + al->level = '.'; + } else if (perf_guest) { + al->cpumode = PERF_RECORD_MISC_GUEST_USER; + al->level = 'u'; + } else { + al->cpumode = PERF_RECORD_MISC_HYPERVISOR; + al->level = 'H'; + } + } + +out: + return 1; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 8ad97e9b119f..da43619d6173 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,13 @@ #include "event.h" #include "symbol.h" +enum perf_call_graph_mode { + CALLCHAIN_NONE, + CALLCHAIN_FP, + CALLCHAIN_DWARF, + CALLCHAIN_MAX +}; + enum chain_mode { CHAIN_NONE, CHAIN_FLAT, @@ -155,6 +162,31 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent struct perf_evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); +int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, + bool hide_unresolved); extern const char record_callchain_help[]; +int parse_callchain_report_opt(const char *arg); + +static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, + struct callchain_cursor *src) +{ + *dest = *src; + + dest->first = src->curr; + dest->nr -= src->pos; +} + +#ifdef HAVE_SKIP_CALLCHAIN_IDX +extern int arch_skip_callchain_idx(struct machine *machine, + struct thread *thread, struct ip_callchain *chain); +#else +static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + struct ip_callchain *chain __maybe_unused) +{ + return -1; +} +#endif + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c new file mode 100644 index 000000000000..c5d05ec17220 --- /dev/null +++ b/tools/perf/util/cloexec.c @@ -0,0 +1,57 @@ +#include "util.h" +#include "../perf.h" +#include "cloexec.h" +#include "asm/bug.h" + +static unsigned long flag = PERF_FLAG_FD_CLOEXEC; + +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, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + int fd; + int err; + + /* check cloexec flag */ + fd = sys_perf_event_open(&attr, 0, -1, -1, + PERF_FLAG_FD_CLOEXEC); + err = errno; + + if (fd >= 0) { + close(fd); + return 1; + } + + WARN_ONCE(err != EINVAL, + "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n", + err, strerror(err)); + + /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + err = errno; + + if (WARN_ONCE(fd < 0, + "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", + err, strerror(err))) + return -1; + + close(fd); + + return 0; +} + +unsigned long perf_event_open_cloexec_flag(void) +{ + static bool probed; + + if (!probed) { + if (perf_flag_probe() <= 0) + flag = 0; + probed = true; + } + + return flag; +} diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h new file mode 100644 index 000000000000..94a5a7d829d5 --- /dev/null +++ b/tools/perf/util/cloexec.h @@ -0,0 +1,6 @@ +#ifndef __PERF_CLOEXEC_H +#define __PERF_CLOEXEC_H + +unsigned long perf_event_open_cloexec_flag(void); + +#endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3e0fdd369ccb..1e5e2e5af6b1 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -11,6 +11,7 @@ #include "util.h" #include "cache.h" #include "exec_cmd.h" +#include "util/hist.h" /* perf_hist_config */ #define MAXNAME (256) @@ -349,12 +350,28 @@ static int perf_default_core_config(const char *var __maybe_unused, return 0; } +static int perf_ui_config(const char *var, const char *value) +{ + /* Add other config variables here. */ + if (!strcmp(var, "ui.show-headers")) { + symbol_conf.show_hist_headers = perf_config_bool(var, value); + return 0; + } + return 0; +} + int perf_default_config(const char *var, const char *value, void *dummy __maybe_unused) { if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); + if (!prefixcmp(var, "hist.")) + return perf_hist_config(var, value); + + if (!prefixcmp(var, "ui.")) + return perf_ui_config(var, value); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 7fe4994eeb63..c4e55b71010c 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core); } + +/* setup simple routines to easily access node numbers given a cpu number */ +static int get_max_num(char *path, int *max) +{ + size_t num; + char *buf; + int err = 0; + + if (filename__read_str(path, &buf, &num)) + return -1; + + buf[num] = '\0'; + + /* start on the right, to find highest node num */ + while (--num) { + if ((buf[num] == ',') || (buf[num] == '-')) { + num++; + break; + } + } + if (sscanf(&buf[num], "%d", max) < 1) { + err = -1; + goto out; + } + + /* convert from 0-based to 1-based */ + (*max)++; + +out: + free(buf); + return err; +} + +/* Determine highest possible cpu in the system for sparse allocation */ +static void set_max_cpu_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_cpu_num = 4096; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_cpu_num); + +out: + if (ret) + pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num); +} + +/* Determine highest possible node in the system for sparse allocation */ +static void set_max_node_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_node_num = 8; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_node_num); + +out: + if (ret) + pr_err("Failed to read max nodes, using default of %d\n", max_node_num); +} + +static int init_cpunode_map(void) +{ + int i; + + set_max_cpu_num(); + set_max_node_num(); + + cpunode_map = calloc(max_cpu_num, sizeof(int)); + if (!cpunode_map) { + pr_err("%s: calloc failed\n", __func__); + return -1; + } + + for (i = 0; i < max_cpu_num; i++) + cpunode_map[i] = -1; + + return 0; +} + +int cpu__setup_cpunode_map(void) +{ + struct dirent *dent1, *dent2; + DIR *dir1, *dir2; + unsigned int cpu, mem; + char buf[PATH_MAX]; + char path[PATH_MAX]; + const char *mnt; + int n; + + /* initialize globals */ + if (init_cpunode_map()) + return -1; + + mnt = sysfs__mountpoint(); + if (!mnt) + return 0; + + n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + return -1; + } + + dir1 = opendir(path); + if (!dir1) + return 0; + + /* walk tree and setup map */ + while ((dent1 = readdir(dir1)) != NULL) { + if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1) + continue; + + n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + continue; + } + + dir2 = opendir(buf); + if (!dir2) + continue; + while ((dent2 = readdir(dir2)) != NULL) { + if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1) + continue; + cpunode_map[cpu] = mem; + } + closedir(dir2); + } + closedir(dir1); + return 0; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index b123bb9d6f55..61a654849002 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -4,6 +4,9 @@ #include <stdio.h> #include <stdbool.h> +#include "perf.h" +#include "util/debug.h" + struct cpu_map { int nr; int map[]; @@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } +int max_cpu_num; +int max_node_num; +int *cpunode_map; + +int cpu__setup_cpunode_map(void); + +static inline int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + pr_debug("cpu_map not initialized\n"); + + return max_node_num; +} + +static inline int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + pr_debug("cpu_map not initialized\n"); + + return max_cpu_num; +} + +static inline int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 55de44ecebef..29d720cf5844 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -7,6 +7,7 @@ #include "data.h" #include "util.h" +#include "debug.h" static bool check_pipe(struct perf_data_file *file) { @@ -65,7 +66,7 @@ static int open_file_read(struct perf_data_file *file) goto out_close; if (!file->force && st.st_uid && (st.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", + pr_err("File %s not owned by current user or root (use -f to override)\n", file->path); goto out_close; } diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 299b55586502..71d419362634 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -16,11 +16,11 @@ int verbose; bool dump_trace = false, quiet = false; -static int _eprintf(int level, const char *fmt, va_list args) +static int _eprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; - if (verbose >= level) { + if (var >= level) { if (use_browser >= 1) ui_helpline__vshow(fmt, args); else @@ -30,13 +30,13 @@ static int _eprintf(int level, const char *fmt, va_list args) return ret; } -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); - ret = _eprintf(level, fmt, args); + ret = _eprintf(level, var, fmt, args); va_end(args); return ret; @@ -51,9 +51,9 @@ void pr_stat(const char *fmt, ...) va_list args; va_start(args, fmt); - _eprintf(1, fmt, args); + _eprintf(1, verbose, fmt, args); va_end(args); - eprintf(1, "\n"); + eprintf(1, verbose, "\n"); } int dump_printf(const char *fmt, ...) @@ -105,3 +105,47 @@ void trace_event(union perf_event *event) } printf(".\n"); } + +static struct debug_variable { + const char *name; + int *ptr; +} debug_variables[] = { + { .name = "verbose", .ptr = &verbose }, + { .name = NULL, } +}; + +int perf_debug_option(const char *str) +{ + struct debug_variable *var = &debug_variables[0]; + char *vstr, *s = strdup(str); + int v = 1; + + vstr = strchr(s, '='); + if (vstr) + *vstr++ = 0; + + while (var->name) { + if (!strcmp(s, var->name)) + break; + var++; + } + + if (!var->name) { + pr_err("Unknown debug variable name '%s'\n", s); + free(s); + return -1; + } + + if (vstr) { + v = atoi(vstr); + /* + * Allow only values in range (0, 10), + * otherwise set 0. + */ + v = (v < 0) || (v > 10) ? 0 : v; + } + + *var->ptr = v; + free(s); + return 0; +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 443694c36b03..89fb6b0f7ab2 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -11,6 +11,24 @@ extern int verbose; extern bool quiet, dump_trace; +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_err(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug(fmt, ...) \ + eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) + int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); @@ -19,4 +37,8 @@ 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 perf_debug_option(const char *str); + #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 64453d63b971..90d02c661dd4 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1,3 +1,6 @@ +#include <asm/bug.h> +#include <sys/time.h> +#include <sys/resource.h> #include "symbol.h" #include "dso.h" #include "machine.h" @@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } -static int open_dso(struct dso *dso, struct machine *machine) +/* + * Global list of open DSOs and the counter. + */ +static LIST_HEAD(dso__data_open); +static long dso__data_open_cnt; + +static void dso__list_add(struct dso *dso) +{ + list_add_tail(&dso->data.open_entry, &dso__data_open); + dso__data_open_cnt++; +} + +static void dso__list_del(struct dso *dso) +{ + list_del(&dso->data.open_entry); + WARN_ONCE(dso__data_open_cnt <= 0, + "DSO data fd counter out of bounds."); + dso__data_open_cnt--; +} + +static void close_first_dso(void); + +static int do_open(char *name) +{ + int fd; + + do { + fd = open(name, O_RDONLY); + if (fd >= 0) + return fd; + + pr_debug("dso open failed, mmap: %s\n", strerror(errno)); + if (!dso__data_open_cnt || errno != EMFILE) + break; + + close_first_dso(); + } while (1); + + return -1; +} + +static int __open_dso(struct dso *dso, struct machine *machine) { int fd; char *root_dir = (char *)""; @@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine) return -EINVAL; } - fd = open(name, O_RDONLY); + fd = do_open(name); free(name); return fd; } +static void check_data_close(void); + +/** + * dso_close - Open DSO data file + * @dso: dso object + * + * Open @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static int open_dso(struct dso *dso, struct machine *machine) +{ + int fd = __open_dso(dso, machine); + + if (fd >= 0) { + dso__list_add(dso); + /* + * Check if we crossed the allowed number + * of opened DSOs and close one if needed. + */ + check_data_close(); + } + + return fd; +} + +static void close_data_fd(struct dso *dso) +{ + if (dso->data.fd >= 0) { + close(dso->data.fd); + dso->data.fd = -1; + dso->data.file_size = 0; + dso__list_del(dso); + } +} + +/** + * dso_close - Close DSO data file + * @dso: dso object + * + * Close @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static void close_dso(struct dso *dso) +{ + close_data_fd(dso); +} + +static void close_first_dso(void) +{ + struct dso *dso; + + dso = list_first_entry(&dso__data_open, struct dso, data.open_entry); + close_dso(dso); +} + +static rlim_t get_fd_limit(void) +{ + struct rlimit l; + rlim_t limit = 0; + + /* Allow half of the current open fd limit. */ + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (l.rlim_cur == RLIM_INFINITY) + limit = l.rlim_cur; + else + limit = l.rlim_cur / 2; + } else { + pr_err("failed to get fd limit\n"); + limit = 1; + } + + return limit; +} + +static bool may_cache_fd(void) +{ + static rlim_t limit; + + if (!limit) + limit = get_fd_limit(); + + if (limit == RLIM_INFINITY) + return true; + + return limit > (rlim_t) dso__data_open_cnt; +} + +/* + * Check and close LRU dso if we crossed allowed limit + * for opened dso file descriptors. The limit is half + * of the RLIMIT_NOFILE files opened. +*/ +static void check_data_close(void) +{ + bool cache_fd = may_cache_fd(); + + if (!cache_fd) + close_first_dso(); +} + +/** + * dso__data_close - Close DSO data file + * @dso: dso object + * + * External interface to close @dso's data file descriptor. + */ +void dso__data_close(struct dso *dso) +{ + close_dso(dso); +} + +/** + * dso__data_fd - Get dso's data file descriptor + * @dso: dso object + * @machine: machine object + * + * External interface to find dso's file, open it and + * returns file descriptor. + */ int dso__data_fd(struct dso *dso, struct machine *machine) { enum dso_binary_type binary_type_data[] = { @@ -168,21 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine) }; int i = 0; - if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) - return open_dso(dso, machine); + if (dso->data.status == DSO_DATA_STATUS_ERROR) + return -1; - do { - int fd; + if (dso->data.fd >= 0) + goto out; + if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) { + dso->data.fd = open_dso(dso, machine); + goto out; + } + + do { dso->binary_type = binary_type_data[i++]; - fd = open_dso(dso, machine); - if (fd >= 0) - return fd; + dso->data.fd = open_dso(dso, machine); + if (dso->data.fd >= 0) + goto out; } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND); +out: + if (dso->data.fd >= 0) + dso->data.status = DSO_DATA_STATUS_OK; + else + dso->data.status = DSO_DATA_STATUS_ERROR; + + return dso->data.fd; +} - return -EINVAL; +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) +{ + u32 flag = 1 << by; + + if (dso->data.status_seen & flag) + return true; + + dso->data.status_seen |= flag; + + return false; } static void @@ -260,16 +446,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset, } static ssize_t -dso_cache__read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size) { struct dso_cache *cache; ssize_t ret; - int fd; - - fd = dso__data_fd(dso, machine); - if (fd < 0) - return -1; do { u64 cache_offset; @@ -283,16 +463,16 @@ dso_cache__read(struct dso *dso, struct machine *machine, cache_offset = offset & DSO__DATA_CACHE_MASK; ret = -EINVAL; - if (-1 == lseek(fd, cache_offset, SEEK_SET)) + if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET)) break; - ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE); + ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE); if (ret <= 0) break; cache->offset = cache_offset; cache->size = ret; - dso_cache__insert(&dso->cache, cache); + dso_cache__insert(&dso->data.cache, cache); ret = dso_cache__memcpy(cache, offset, data, size); @@ -301,24 +481,27 @@ dso_cache__read(struct dso *dso, struct machine *machine, if (ret <= 0) free(cache); - close(fd); return ret; } -static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t dso_cache_read(struct dso *dso, u64 offset, + u8 *data, ssize_t size) { struct dso_cache *cache; - cache = dso_cache__find(&dso->cache, offset); + cache = dso_cache__find(&dso->data.cache, offset); if (cache) return dso_cache__memcpy(cache, offset, data, size); else - return dso_cache__read(dso, machine, offset, data, size); + return dso_cache__read(dso, offset, data, size); } -ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +/* + * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks + * in the rb_tree. Any read to already cached data is served + * by cached data. + */ +static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size) { ssize_t r = 0; u8 *p = data; @@ -326,7 +509,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, do { ssize_t ret; - ret = dso_cache_read(dso, machine, offset, p, size); + ret = dso_cache_read(dso, offset, p, size); if (ret < 0) return ret; @@ -346,6 +529,89 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, return r; } +static int data_file_size(struct dso *dso) +{ + struct stat st; + + if (!dso->data.file_size) { + if (fstat(dso->data.fd, &st)) { + pr_err("dso mmap failed, fstat: %s\n", strerror(errno)); + return -1; + } + dso->data.file_size = st.st_size; + } + + return 0; +} + +/** + * dso__data_size - Return dso data size + * @dso: dso object + * @machine: machine object + * + * Return: dso data size + */ +off_t dso__data_size(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return fd; + + if (data_file_size(dso)) + return -1; + + /* For now just estimate dso data size is close to file size */ + return dso->data.file_size; +} + +static ssize_t data_read_offset(struct dso *dso, u64 offset, + u8 *data, ssize_t size) +{ + if (data_file_size(dso)) + return -1; + + /* Check the offset sanity. */ + if (offset > dso->data.file_size) + return -1; + + if (offset + size < offset) + return -1; + + return cached_read(dso, offset, data, size); +} + +/** + * dso__data_read_offset - Read data from dso file offset + * @dso: dso object + * @machine: machine object + * @offset: file offset + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso file offset. Open + * dso data file and use cached_read to get the data. + */ +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + if (dso__data_fd(dso, machine) < 0) + return -1; + + return data_read_offset(dso, offset, data, size); +} + +/** + * dso__data_read_addr - Read data from dso address + * @dso: dso object + * @machine: machine object + * @add: virtual memory address + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso address. + */ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size) @@ -473,9 +739,12 @@ struct dso *dso__new(const char *name) dso__set_short_name(dso, dso->name, false); for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; - dso->cache = RB_ROOT; + dso->data.cache = RB_ROOT; + dso->data.fd = -1; + dso->data.status = DSO_DATA_STATUS_UNKNOWN; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->is_64_bit = (sizeof(void *) == 8); dso->loaded = 0; dso->rel = 0; dso->sorted_by_name = 0; @@ -485,6 +754,7 @@ struct dso *dso__new(const char *name) dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; INIT_LIST_HEAD(&dso->node); + INIT_LIST_HEAD(&dso->data.open_entry); } return dso; @@ -506,7 +776,8 @@ void dso__delete(struct dso *dso) dso->long_name_allocated = false; } - dso_cache__free(&dso->cache); + dso__data_close(dso); + dso_cache__free(&dso->data.cache); dso__free_a2l(dso); zfree(&dso->symsrc_filename); free(dso); @@ -669,3 +940,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) return ret; } + +enum dso_type dso__type(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return DSO__TYPE_UNKNOWN; + + return dso__type_fd(fd); +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ab06f1c03655..5e463c0964d4 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -4,7 +4,8 @@ #include <linux/types.h> #include <linux/rbtree.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> +#include <linux/bitops.h> #include "map.h" #include "build-id.h" @@ -40,6 +41,23 @@ enum dso_swap_type { DSO_SWAP__YES, }; +enum dso_data_status { + DSO_DATA_STATUS_ERROR = -1, + DSO_DATA_STATUS_UNKNOWN = 0, + DSO_DATA_STATUS_OK = 1, +}; + +enum dso_data_status_seen { + DSO_DATA_STATUS_SEEN_ITRACE, +}; + +enum dso_type { + DSO__TYPE_UNKNOWN, + DSO__TYPE_64BIT, + DSO__TYPE_32BIT, + DSO__TYPE_X32BIT, +}; + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -76,7 +94,6 @@ struct dso { struct list_head node; struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; - struct rb_root cache; void *a2l; char *symsrc_filename; unsigned int a2l_fails; @@ -91,6 +108,7 @@ struct dso { u8 annotate_warned:1; u8 short_name_allocated:1; u8 long_name_allocated:1; + u8 is_64_bit:1; u8 sorted_by_name; u8 loaded; u8 rel; @@ -99,6 +117,17 @@ struct dso { const char *long_name; u16 long_name_len; u16 short_name_len; + + /* dso data file */ + struct { + struct rb_root cache; + int fd; + int status; + u32 status_seen; + size_t file_size; + struct list_head open_entry; + } data; + char name[0]; }; @@ -141,12 +170,55 @@ char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); +/* + * The dso__data_* external interface provides following functions: + * dso__data_fd + * dso__data_close + * dso__data_size + * dso__data_read_offset + * dso__data_read_addr + * + * Please refer to the dso.c object code for each function and + * arguments documentation. Following text tries to explain the + * dso file descriptor caching. + * + * The dso__data* interface allows caching of opened file descriptors + * to speed up the dso data accesses. The idea is to leave the file + * descriptor opened ideally for the whole life of the dso object. + * + * The current usage of the dso__data_* interface is as follows: + * + * Get DSO's fd: + * int fd = dso__data_fd(dso, machine); + * USE 'fd' SOMEHOW + * + * Read DSO's data: + * n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE); + * n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE); + * + * Eventually close DSO's fd: + * dso__data_close(dso); + * + * It is not necessary to close the DSO object data file. Each time new + * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once + * it is crossed, the oldest opened DSO object is closed. + * + * The dso__delete function calls close_dso function to ensure the + * data file descriptor gets closed/unmapped before the dso object + * is freed. + * + * TODO +*/ int dso__data_fd(struct dso *dso, struct machine *machine); +void dso__data_close(struct dso *dso); + +off_t dso__data_size(struct dso *dso, struct machine *machine); ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by); struct map *dso__new_map(const char *name); struct dso *dso__kernel_findnew(struct machine *machine, const char *name, @@ -181,4 +253,6 @@ static inline bool dso__is_kcore(struct dso *dso) void dso__free_a2l(struct dso *dso); +enum dso_type dso__type(struct dso *dso, struct machine *machine); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9d12aa6dd485..1398c83d896d 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,4 +1,5 @@ #include <linux/types.h> +#include <sys/mman.h> #include "event.h" #include "debug.h" #include "hist.h" @@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, return -1; } - event->header.type = PERF_RECORD_MMAP; + event->header.type = PERF_RECORD_MMAP2; while (1) { char bf[BUFSIZ]; char prot[5]; char execname[PATH_MAX]; char anonstr[] = "//anon"; + unsigned int ino; size_t size; ssize_t n; @@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", - &event->mmap.start, &event->mmap.len, prot, - &event->mmap.pgoff, - execname); + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + /* * Anon maps don't have the execname. */ - if (n < 4) + if (n < 7) continue; + + event->mmap2.ino = (u64)ino; + /* * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c */ @@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, else event->header.misc = PERF_RECORD_MISC_GUEST_USER; + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; + if (prot[2] != 'x') { if (!mmap_data || prot[0] != 'r') continue; @@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, anonstr); size = strlen(execname) + 1; - memcpy(event->mmap.filename, execname, size); + memcpy(event->mmap2.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.len -= event->mmap.start; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.pid = tgid; - event->mmap.tid = pid; + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; if (process(tool, event, &synth_sample, machine) != 0) { rc = -1; @@ -581,7 +603,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) { - return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); + const char *s; + + if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC) + s = " exec"; + else + s = ""; + + return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, @@ -612,12 +641,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 - " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n", + " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n", event->mmap2.pid, event->mmap2.tid, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, - (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x', + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', event->mmap2.filename); } @@ -699,7 +731,7 @@ void thread__find_addr_map(struct thread *thread, enum map_type type, u64 addr, struct addr_location *al) { - struct map_groups *mg = &thread->mg; + struct map_groups *mg = thread->mg; bool load_map = false; al->machine = machine; @@ -756,6 +788,7 @@ try_again: cpumode == PERF_RECORD_MISC_USER && machine && mg != &machine->kmaps) { mg = &machine->kmaps; + load_map = true; goto try_again; } } else { @@ -788,7 +821,7 @@ int perf_event__preprocess_sample(const union perf_event *event, { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread = machine__findnew_thread(machine, sample->pid, - sample->pid); + sample->tid); if (thread == NULL) return -1; @@ -841,3 +874,45 @@ int perf_event__preprocess_sample(const union perf_event *event, return 0; } + +bool is_bts_event(struct perf_event_attr *attr) +{ + return attr->type == PERF_TYPE_HARDWARE && + (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && + attr->sample_period == 1; +} + +bool sample_addr_correlates_sym(struct perf_event_attr *attr) +{ + if (attr->type == PERF_TYPE_SOFTWARE && + (attr->config == PERF_COUNT_SW_PAGE_FAULTS || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)) + return true; + + if (is_bts_event(attr)) + return true; + + return false; +} + +void perf_event__preprocess_sample_addr(union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + struct thread *thread, + struct addr_location *al) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + sample->addr, al); + if (!al->map) + thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, + sample->addr, al); + + al->cpu = sample->cpu; + al->sym = NULL; + + if (al->map) + al->sym = map__find_symbol(al->map, al->addr, NULL); +} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 38457d447a13..94d6976180da 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -7,6 +7,7 @@ #include "../perf.h" #include "map.h" #include "build-id.h" +#include "perf_regs.h" struct mmap_event { struct perf_event_header header; @@ -27,6 +28,8 @@ struct mmap2_event { u32 min; u64 ino; u64 ino_generation; + u32 prot; + u32 flags; char filename[PATH_MAX]; }; @@ -87,6 +90,10 @@ struct regs_dump { u64 abi; u64 mask; u64 *regs; + + /* Cached values/mask filled by first register access. */ + u64 cache_regs[PERF_REGS_MAX]; + u64 cache_mask; }; struct stack_dump { @@ -112,6 +119,30 @@ struct sample_read { }; }; +struct ip_callchain { + u64 nr; + u64 ips[0]; +}; + +struct branch_flags { + u64 mispred:1; + u64 predicted:1; + u64 in_tx:1; + u64 abort:1; + u64 reserved:60; +}; + +struct branch_entry { + u64 from; + u64 to; + struct branch_flags flags; +}; + +struct branch_stack { + u64 nr; + struct branch_entry entries[0]; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -257,6 +288,16 @@ int perf_event__preprocess_sample(const union perf_event *event, struct addr_location *al, struct perf_sample *sample); +struct thread; + +bool is_bts_event(struct perf_event_attr *attr); +bool sample_addr_correlates_sym(struct perf_event_attr *attr); +void perf_event__preprocess_sample_addr(union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + struct thread *thread, + struct addr_location *al); + const char *perf_event__name(unsigned int id); size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 59ef2802fcf6..814e954c1318 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -606,12 +606,17 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) return evlist->mmap != NULL ? 0 : -ENOMEM; } -static int __perf_evlist__mmap(struct perf_evlist *evlist, - int idx, int prot, int mask, int fd) +struct mmap_params { + int prot; + int mask; +}; + +static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, + struct mmap_params *mp, int fd) { evlist->mmap[idx].prev = 0; - evlist->mmap[idx].mask = mask; - evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, + evlist->mmap[idx].mask = mp->mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot, MAP_SHARED, fd, 0); if (evlist->mmap[idx].base == MAP_FAILED) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", @@ -625,8 +630,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, } static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, - int prot, int mask, int cpu, int thread, - int *output) + struct mmap_params *mp, int cpu, + int thread, int *output) { struct perf_evsel *evsel; @@ -635,8 +640,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (*output == -1) { *output = fd; - if (__perf_evlist__mmap(evlist, idx, prot, mask, - *output) < 0) + if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) @@ -651,8 +655,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, return 0; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, + struct mmap_params *mp) { int cpu, thread; int nr_cpus = cpu_map__nr(evlist->cpus); @@ -663,8 +667,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int output = -1; for (thread = 0; thread < nr_threads; thread++) { - if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask, - cpu, thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, + thread, &output)) goto out_unmap; } } @@ -677,8 +681,8 @@ out_unmap: return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, + struct mmap_params *mp) { int thread; int nr_threads = thread_map__nr(evlist->threads); @@ -687,8 +691,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, for (thread = 0; thread < nr_threads; thread++) { int output = -1; - if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0, - thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, + &output)) goto out_unmap; } @@ -793,7 +797,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; - int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; + struct mmap_params mp = { + .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), + }; if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -804,7 +810,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, evlist->overwrite = overwrite; evlist->mmap_len = perf_evlist__mmap_size(pages); pr_debug("mmap size %zuB\n", evlist->mmap_len); - mask = evlist->mmap_len - page_size - 1; + mp.mask = evlist->mmap_len - page_size - 1; evlist__for_each(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -814,9 +820,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, } if (cpu_map__empty(cpus)) - return perf_evlist__mmap_per_thread(evlist, prot, mask); + return perf_evlist__mmap_per_thread(evlist, &mp); - return perf_evlist__mmap_per_cpu(evlist, prot, mask); + return perf_evlist__mmap_per_cpu(evlist, &mp); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) @@ -1214,10 +1220,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, "For your workloads it needs to be <= 1\nHint:\t"); } printed += scnprintf(buf + printed, size - printed, - "For system wide tracing it needs to be set to -1"); + "For system wide tracing it needs to be set to -1.\n"); printed += scnprintf(buf + printed, size - printed, - ".\nHint:\tThe current value is %d.", value); + "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n" + "Hint:\tThe current value is %d.", value); break; default: scnprintf(buf, size, "%s", emsg); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5c28d82b76c4..21a373ebea22 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -29,6 +29,7 @@ static struct { bool sample_id_all; bool exclude_guest; bool mmap2; + bool cloexec; } perf_missing_features; #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) @@ -589,10 +590,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) } /* - * We default some events to a 1 default interval. But keep + * We default some events to have a default interval. But keep * it a weak assumption overridable by the user. */ - if (!attr->sample_period || (opts->user_freq != UINT_MAX && + if (!attr->sample_period || (opts->user_freq != UINT_MAX || opts->user_interval != ULLONG_MAX)) { if (opts->freq) { perf_evsel__set_sample_bit(evsel, PERIOD); @@ -623,7 +624,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph_enabled) + if (opts->call_graph_enabled && !evsel->no_aux_samples) perf_evsel__config_callgraph(evsel, opts); if (target__has_cpu(&opts->target)) @@ -637,7 +638,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) target__has_cpu(&opts->target) || per_cpu)) perf_evsel__set_sample_bit(evsel, TIME); - if (opts->raw_samples) { + if (opts->raw_samples && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, TIME); perf_evsel__set_sample_bit(evsel, RAW); perf_evsel__set_sample_bit(evsel, CPU); @@ -650,7 +651,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->watermark = 0; attr->wakeup_events = 1; } - if (opts->branch_stack) { + if (opts->branch_stack && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } @@ -659,6 +660,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) perf_evsel__set_sample_bit(evsel, WEIGHT); attr->mmap = track; + attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; if (opts->sample_transaction) @@ -680,6 +682,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) && !opts->initial_delay) attr->enable_on_exec = 1; + + if (evsel->immediate) { + attr->disabled = 0; + attr->enable_on_exec = 0; + } } int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -959,6 +966,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_user, exclude_kernel); ret += PRINT_ATTR2(exclude_hv, exclude_idle); ret += PRINT_ATTR2(mmap, comm); + ret += PRINT_ATTR2(mmap2, comm_exec); ret += PRINT_ATTR2(freq, inherit_stat); ret += PRINT_ATTR2(enable_on_exec, task); ret += PRINT_ATTR2(watermark, precise_ip); @@ -966,7 +974,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_host, exclude_guest); ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, "excl.callchain_user", exclude_callchain_user); - ret += PRINT_ATTR_U32(mmap2); ret += PRINT_ATTR_U32(wakeup_events); ret += PRINT_ATTR_U32(wakeup_watermark); @@ -988,7 +995,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { int cpu, thread; - unsigned long flags = 0; + unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; @@ -997,11 +1004,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, return -ENOMEM; if (evsel->cgrp) { - flags = PERF_FLAG_PID_CGROUP; + flags |= PERF_FLAG_PID_CGROUP; pid = evsel->cgrp->fd; } fallback_missing_features: + if (perf_missing_features.cloexec) + flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) @@ -1070,7 +1079,10 @@ try_fallback: if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { + perf_missing_features.cloexec = true; + goto fallback_missing_features; + } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && @@ -1939,6 +1951,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(mmap); if_print(mmap2); if_print(comm); + if_print(comm_exec); if_print(freq); if_print(inherit_stat); if_print(enable_on_exec); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0c9926cfb292..d7f93ce0ebc1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -5,12 +5,12 @@ #include <stdbool.h> #include <stddef.h> #include <linux/perf_event.h> -#include "types.h" +#include <linux/types.h> #include "xyarray.h" #include "cgroup.h" #include "hist.h" #include "symbol.h" - + struct perf_counts_values { union { struct { @@ -83,6 +83,8 @@ struct perf_evsel { int is_pos; bool supported; bool needs_swap; + bool no_aux_samples; + bool immediate; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -91,6 +93,11 @@ struct perf_evsel { char *group_name; }; +union u64_swap { + u64 val64; + u32 val32[2]; +}; + #define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) struct cpu_map; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 893f8e2df928..158c787ce0c4 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -200,6 +200,47 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } +static int __dsos__hit_all(struct list_head *head) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) + pos->hit = true; + + return 0; +} + +static int machine__hit_all_dsos(struct machine *machine) +{ + int err; + + err = __dsos__hit_all(&machine->kernel_dsos); + if (err) + return err; + + return __dsos__hit_all(&machine->user_dsos); +} + +int dsos__hit_all(struct perf_session *session) +{ + struct rb_node *nd; + int err; + + err = machine__hit_all_dsos(&session->machines.host); + if (err) + return err; + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + + err = machine__hit_all_dsos(pos); + if (err) + return err; + } + + return 0; +} + static int __dsos__write_buildid_table(struct list_head *head, struct machine *machine, pid_t pid, u16 misc, int fd) @@ -215,9 +256,9 @@ static int __dsos__write_buildid_table(struct list_head *head, if (!pos->hit) continue; - if (is_vdso_map(pos->short_name)) { - name = (char *) VDSO__MAP_NAME; - name_len = sizeof(VDSO__MAP_NAME) + 1; + if (dso__is_vdso(pos)) { + name = pos->short_name; + name_len = pos->short_name_len + 1; } else if (dso__is_kcore(pos)) { machine__mmap_name(machine, nm, sizeof(nm)); name = nm; @@ -298,7 +339,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, len = scnprintf(filename, size, "%s%s%s", debugdir, slash ? "/" : "", - is_vdso ? VDSO__MAP_NAME : realname); + is_vdso ? DSO__NAME_VDSO : realname); if (mkdir_p(filename, 0755)) goto out_free; @@ -386,7 +427,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; - bool is_vdso = is_vdso_map(dso->short_name); + bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; char nm[PATH_MAX]; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index a2d047bdf4ef..8f5cbaea64a5 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -4,10 +4,10 @@ #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> -#include "types.h" +#include <linux/bitmap.h> +#include <linux/types.h> #include "event.h" -#include <linux/bitmap.h> enum { HEADER_RESERVED = 0, /* always cleared */ @@ -151,6 +151,8 @@ int perf_event__process_build_id(struct perf_tool *tool, struct perf_session *session); bool is_perf_magic(u64 magic); +int dsos__hit_all(struct perf_session *session); + /* * arch specific callback */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f38590d7561b..30df6187ee02 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -4,6 +4,7 @@ #include "session.h" #include "sort.h" #include "evsel.h" +#include "annotate.h" #include <math.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -127,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen + 1); } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, @@ -225,14 +228,20 @@ static void he_stat__decay(struct he_stat *he_stat) static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { u64 prev_period = he->stat.period; + u64 diff; if (prev_period == 0) return true; he_stat__decay(&he->stat); + if (symbol_conf.cumulate_callchain) + he_stat__decay(he->stat_acc); + diff = prev_period - he->stat.period; + + hists->stats.total_period -= diff; if (!he->filtered) - hists->stats.total_period -= prev_period - he->stat.period; + hists->stats.total_non_filtered_period -= diff; return he->stat.period == 0; } @@ -259,8 +268,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) if (sort__need_collapse) rb_erase(&n->rb_node_in, &hists->entries_collapsed); - hist_entry__free(n); --hists->nr_entries; + if (!n->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__free(n); } } } @@ -269,14 +281,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) * histogram, sorted on item, collects periods */ -static struct hist_entry *hist_entry__new(struct hist_entry *template) +static struct hist_entry *hist_entry__new(struct hist_entry *template, + bool sample_self) { - size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0; - struct hist_entry *he = zalloc(sizeof(*he) + callchain_size); + size_t callchain_size = 0; + struct hist_entry *he; + + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) + callchain_size = sizeof(struct callchain_root); + + he = zalloc(sizeof(*he) + callchain_size); if (he != NULL) { *he = *template; + if (symbol_conf.cumulate_callchain) { + he->stat_acc = malloc(sizeof(he->stat)); + if (he->stat_acc == NULL) { + free(he); + return NULL; + } + memcpy(he->stat_acc, &he->stat, sizeof(he->stat)); + if (!sample_self) + memset(&he->stat, 0, sizeof(he->stat)); + } + if (he->ms.map) he->ms.map->referenced = true; @@ -288,6 +317,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) */ he->branch_info = malloc(sizeof(*he->branch_info)); if (he->branch_info == NULL) { + free(he->stat_acc); free(he); return NULL; } @@ -317,15 +347,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return he; } -void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) -{ - if (!h->filtered) { - hists__calc_col_len(hists, h); - ++hists->nr_entries; - hists->stats.total_period += h->stat.period; - } -} - static u8 symbol__parent_filter(const struct symbol *parent) { if (symbol_conf.exclude_other && parent == NULL) @@ -335,7 +356,8 @@ static u8 symbol__parent_filter(const struct symbol *parent) static struct hist_entry *add_hist_entry(struct hists *hists, struct hist_entry *entry, - struct addr_location *al) + struct addr_location *al, + bool sample_self) { struct rb_node **p; struct rb_node *parent = NULL; @@ -359,7 +381,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - he_stat__add_period(&he->stat, period, weight); + if (sample_self) + he_stat__add_period(&he->stat, period, weight); + if (symbol_conf.cumulate_callchain) + he_stat__add_period(he->stat_acc, period, weight); /* * This mem info was allocated from sample__resolve_mem @@ -387,15 +412,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists, p = &(*p)->rb_right; } - he = hist_entry__new(entry); + he = hist_entry__new(entry, sample_self); if (!he) return NULL; - hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: - he_stat__add_cpumode_period(&he->stat, al->cpumode, period); + if (sample_self) + he_stat__add_cpumode_period(&he->stat, al->cpumode, period); + if (symbol_conf.cumulate_callchain) + he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period); return he; } @@ -404,7 +431,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, - u64 period, u64 weight, u64 transaction) + u64 period, u64 weight, u64 transaction, + bool sample_self) { struct hist_entry entry = { .thread = al->thread, @@ -413,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .map = al->map, .sym = al->sym, }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, + .cpu = al->cpu, + .cpumode = al->cpumode, + .ip = al->addr, + .level = al->level, .stat = { .nr_events = 1, .period = period, @@ -429,17 +458,442 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .transaction = transaction, }; - return add_hist_entry(hists, &entry, al); + return add_hist_entry(hists, &entry, al, sample_self); +} + +static int +iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_sample *sample = iter->sample; + struct mem_info *mi; + + mi = sample__resolve_mem(sample, al); + if (mi == NULL) + return -ENOMEM; + + iter->priv = mi; + return 0; +} + +static int +iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + u64 cost; + struct mem_info *mi = iter->priv; + struct hist_entry *he; + + if (mi == NULL) + return -EINVAL; + + cost = iter->sample->weight; + if (!cost) + cost = 1; + + /* + * must pass period=weight in order to get the correct + * sorting from hists__collapse_resort() which is solely + * based on periods. We want sorting be done on nr_events * weight + * 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, + cost, cost, 0, true); + if (!he) + return -ENOMEM; + + iter->he = he; + return 0; +} + +static int +iter_finish_mem_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = iter->he; + int err = -EINVAL; + + if (he == NULL) + goto out; + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + err = hist_entry__append_callchain(he, iter->sample); + +out: + /* + * We don't need to free iter->priv (mem_info) here since + * the mem info was either already freed in add_hist_entry() or + * passed to a new hist entry by hist_entry__new(). + */ + iter->priv = NULL; + + iter->he = NULL; + return err; +} + +static int +iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi; + struct perf_sample *sample = iter->sample; + + bi = sample__resolve_bstack(sample, al); + if (!bi) + return -ENOMEM; + + iter->curr = 0; + iter->total = sample->branch_stack->nr; + + iter->priv = bi; + return 0; +} + +static int +iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + /* to avoid calling callback function */ + iter->he = NULL; + + return 0; +} + +static int +iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi = iter->priv; + int i = iter->curr; + + if (bi == NULL) + return 0; + + if (iter->curr >= iter->total) + return 0; + + al->map = bi[i].to.map; + al->sym = bi[i].to.sym; + al->addr = bi[i].to.addr; + return 1; +} + +static int +iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi; + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = NULL; + int i = iter->curr; + int err = 0; + + bi = iter->priv; + + if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + goto out; + + /* + * 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, + 1, 1, 0, true); + if (he == NULL) + return -ENOMEM; + + hists__inc_nr_samples(&evsel->hists, he->filtered); + +out: + iter->he = he; + iter->curr++; + return err; +} + +static int +iter_finish_branch_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + zfree(&iter->priv); + iter->he = NULL; + + return iter->curr >= iter->total ? 0 : -1; +} + +static int +iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry *he; + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, true); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + return 0; +} + +static int +iter_finish_normal_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + + if (he == NULL) + return 0; + + iter->he = NULL; + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + return hist_entry__append_callchain(he, sample); +} + +static int +iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + struct hist_entry **he_cache; + + callchain_cursor_commit(&callchain_cursor); + + /* + * This is for detecting cycles or recursions so that they're + * cumulated only one time to prevent entries more than 100% + * overhead. + */ + he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1)); + if (he_cache == NULL) + return -ENOMEM; + + iter->priv = he_cache; + iter->curr = 0; + + return 0; +} + +static int +iter_add_single_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct perf_evsel *evsel = iter->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, + sample->period, sample->weight, + sample->transaction, true); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + he_cache[iter->curr++] = he; + + callchain_append(he->callchain, &callchain_cursor, sample->period); + + /* + * We need to re-initialize the cursor since callchain_append() + * advanced the cursor to the end. + */ + callchain_cursor_commit(&callchain_cursor); + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + return err; +} + +static int +iter_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct callchain_cursor_node *node; + + node = callchain_cursor_current(&callchain_cursor); + if (node == NULL) + return 0; + + return fill_callchain_info(al, node, iter->hide_unresolved); +} + +static int +iter_add_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry **he_cache = iter->priv; + struct hist_entry *he; + struct hist_entry he_tmp = { + .cpu = al->cpu, + .thread = al->thread, + .comm = thread__comm(al->thread), + .ip = al->addr, + .ms = { + .map = al->map, + .sym = al->sym, + }, + .parent = iter->parent, + }; + int i; + struct callchain_cursor cursor; + + callchain_cursor_snapshot(&cursor, &callchain_cursor); + + callchain_cursor_advance(&callchain_cursor); + + /* + * Check if there's duplicate entries in the callchain. + * It's possible that it has cycles or recursive calls. + */ + for (i = 0; i < iter->curr; i++) { + if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) { + /* to avoid calling callback function */ + iter->he = NULL; + return 0; + } + } + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, false); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + he_cache[iter->curr++] = he; + + callchain_append(he->callchain, &cursor, sample->period); + return 0; +} + +static int +iter_finish_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + zfree(&iter->priv); + iter->he = NULL; + + return 0; +} + +const struct hist_iter_ops hist_iter_mem = { + .prepare_entry = iter_prepare_mem_entry, + .add_single_entry = iter_add_single_mem_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_mem_entry, +}; + +const struct hist_iter_ops hist_iter_branch = { + .prepare_entry = iter_prepare_branch_entry, + .add_single_entry = iter_add_single_branch_entry, + .next_entry = iter_next_branch_entry, + .add_next_entry = iter_add_next_branch_entry, + .finish_entry = iter_finish_branch_entry, +}; + +const struct hist_iter_ops hist_iter_normal = { + .prepare_entry = iter_prepare_normal_entry, + .add_single_entry = iter_add_single_normal_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_normal_entry, +}; + +const struct hist_iter_ops hist_iter_cumulative = { + .prepare_entry = iter_prepare_cumulative_entry, + .add_single_entry = iter_add_single_cumulative_entry, + .next_entry = iter_next_cumulative_entry, + .add_next_entry = iter_add_next_cumulative_entry, + .finish_entry = iter_finish_cumulative_entry, +}; + +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth, void *arg) +{ + int err, err2; + + err = sample__resolve_callchain(sample, &iter->parent, evsel, al, + max_stack_depth); + if (err) + return err; + + iter->evsel = evsel; + iter->sample = sample; + + err = iter->ops->prepare_entry(iter, al); + if (err) + goto out; + + err = iter->ops->add_single_entry(iter, al); + if (err) + goto out; + + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, true, arg); + if (err) + goto out; + } + + while (iter->ops->next_entry(iter, al)) { + err = iter->ops->add_next_entry(iter, al); + if (err) + break; + + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, false, arg); + if (err) + goto out; + } + } + +out: + err2 = iter->ops->finish_entry(iter, al); + if (!err) + err = err2; + + return err; } int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; int64_t cmp = 0; - list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->se_cmp(left, right); + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + + cmp = fmt->cmp(left, right); if (cmp) break; } @@ -450,15 +904,14 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; int64_t cmp = 0; - list_for_each_entry(se, &hist_entry__sort_list, list) { - int64_t (*f)(struct hist_entry *, struct hist_entry *); - - f = se->se_collapse ?: se->se_cmp; + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - cmp = f(left, right); + cmp = fmt->collapse(left, right); if (cmp) break; } @@ -470,6 +923,7 @@ void hist_entry__free(struct hist_entry *he) { zfree(&he->branch_info); zfree(&he->mem_info); + zfree(&he->stat_acc); free_srcline(he->srcline); free(he); } @@ -495,6 +949,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, if (!cmp) { he_stat__add_stat(&iter->stat, &he->stat); + if (symbol_conf.cumulate_callchain) + he_stat__add_stat(iter->stat_acc, he->stat_acc); if (symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); @@ -571,64 +1027,50 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) } } -/* - * reverse the map, sort on period. - */ - -static int period_cmp(u64 period_a, u64 period_b) -{ - if (period_a > period_b) - return 1; - if (period_a < period_b) - return -1; - return 0; -} - -static int hist_entry__sort_on_period(struct hist_entry *a, - struct hist_entry *b) +static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { - int ret; - int i, nr_members; - struct perf_evsel *evsel; - struct hist_entry *pair; - u64 *periods_a, *periods_b; + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; - ret = period_cmp(a->stat.period, b->stat.period); - if (ret || !symbol_conf.event_group) - return ret; + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - evsel = hists_to_evsel(a->hists); - nr_members = evsel->nr_members; - if (nr_members <= 1) - return ret; + cmp = fmt->sort(a, b); + if (cmp) + break; + } - periods_a = zalloc(sizeof(periods_a) * nr_members); - periods_b = zalloc(sizeof(periods_b) * nr_members); + return cmp; +} - if (!periods_a || !periods_b) - goto out; +static void hists__reset_filter_stats(struct hists *hists) +{ + hists->nr_non_filtered_entries = 0; + hists->stats.total_non_filtered_period = 0; +} - list_for_each_entry(pair, &a->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period; - } +void hists__reset_stats(struct hists *hists) +{ + hists->nr_entries = 0; + hists->stats.total_period = 0; - list_for_each_entry(pair, &b->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period; - } + hists__reset_filter_stats(hists); +} - for (i = 1; i < nr_members; i++) { - ret = period_cmp(periods_a[i], periods_b[i]); - if (ret) - break; - } +static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h) +{ + hists->nr_non_filtered_entries++; + hists->stats.total_non_filtered_period += h->stat.period; +} -out: - free(periods_a); - free(periods_b); +void hists__inc_stats(struct hists *hists, struct hist_entry *h) +{ + if (!h->filtered) + hists__inc_filter_stats(hists, h); - return ret; + hists->nr_entries++; + hists->stats.total_period += h->stat.period; } static void __hists__insert_output_entry(struct rb_root *entries, @@ -647,7 +1089,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__sort_on_period(he, iter) > 0) + if (hist_entry__sort(he, iter) > 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -674,8 +1116,7 @@ void hists__output_resort(struct hists *hists) next = rb_first(root); hists->entries = RB_ROOT; - hists->nr_entries = 0; - hists->stats.total_period = 0; + hists__reset_stats(hists); hists__reset_col_len(hists); while (next) { @@ -683,7 +1124,10 @@ void hists__output_resort(struct hists *hists) next = rb_next(&n->rb_node_in); __hists__insert_output_entry(&hists->entries, n, min_callchain_hits); - hists__inc_nr_entries(hists, n); + hists__inc_stats(hists, n); + + if (!n->filtered) + hists__calc_col_len(hists, n); } } @@ -694,13 +1138,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h if (h->filtered) return; - ++hists->nr_entries; - if (h->ms.unfolded) - hists->nr_entries += h->nr_rows; + /* force fold unfiltered entry for simplicity */ + h->ms.unfolded = false; h->row_offset = 0; - hists->stats.total_period += h->stat.period; - hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events; + hists->stats.nr_non_filtered_samples += h->stat.nr_events; + + hists__inc_filter_stats(hists, h); hists__calc_col_len(hists, h); } @@ -721,8 +1165,9 @@ void hists__filter_by_dso(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -754,8 +1199,9 @@ void hists__filter_by_thread(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -785,8 +1231,9 @@ void hists__filter_by_symbol(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -810,6 +1257,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type) events_stats__inc(&hists->stats, type); } +void hists__inc_nr_samples(struct hists *hists, bool filtered) +{ + events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE); + if (!filtered) + hists->stats.nr_non_filtered_samples++; +} + static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct hist_entry *pair) { @@ -841,13 +1295,13 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, p = &(*p)->rb_right; } - he = hist_entry__new(pair); + he = hist_entry__new(pair, true); if (he) { memset(&he->stat, 0, sizeof(he->stat)); he->hists = hists; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); - hists__inc_nr_entries(hists, he); + hists__inc_stats(hists, he); he->dummy = true; } out: @@ -931,3 +1385,30 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } + +u64 hists__total_period(struct hists *hists) +{ + return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period : + hists->stats.total_period; +} + +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!strcmp(arg, "relative")) + symbol_conf.filter_relative = true; + else if (!strcmp(arg, "absolute")) + symbol_conf.filter_relative = false; + else + return -1; + + return 0; +} + +int perf_hist_config(const char *var, const char *value) +{ + if (!strcmp(var, "hist.percentage")) + return parse_filter_percentage(NULL, value, 0); + + return 0; +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1f1f513dfe7f..742f49a85725 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -37,9 +37,11 @@ enum hist_filter { */ 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; @@ -70,6 +72,7 @@ enum hist_column { HISTC_MEM_TLB, HISTC_MEM_LVL, HISTC_MEM_SNOOP, + HISTC_MEM_DCACHELINE, HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; @@ -83,6 +86,7 @@ struct hists { struct rb_root entries; struct rb_root entries_collapsed; u64 nr_entries; + u64 nr_non_filtered_entries; const struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; @@ -93,12 +97,50 @@ struct hists { u16 col_len[HISTC_NR_COLS]; }; +struct hist_entry_iter; + +struct hist_iter_ops { + int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *); + int (*next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*finish_entry)(struct hist_entry_iter *, struct addr_location *); +}; + +struct hist_entry_iter { + int total; + int curr; + + bool hide_unresolved; + + struct perf_evsel *evsel; + struct perf_sample *sample; + struct hist_entry *he; + struct symbol *parent; + void *priv; + + const struct hist_iter_ops *ops; + /* user-defined callback function (optional) */ + int (*add_entry_cb)(struct hist_entry_iter *iter, + struct addr_location *al, bool single, void *arg); +}; + +extern const struct hist_iter_ops hist_iter_normal; +extern const struct hist_iter_ops hist_iter_branch; +extern const struct hist_iter_ops hist_iter_mem; +extern const struct hist_iter_ops hist_iter_cumulative; + struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *parent, struct branch_info *bi, struct mem_info *mi, u64 period, - u64 weight, u64 transaction); + u64 weight, u64 transaction, + bool sample_self); +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth, void *arg); + int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); @@ -112,8 +154,11 @@ 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__output_recalc_col_len(struct hists *hists, int max_rows); -void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); +u64 hists__total_period(struct hists *hists); +void hists__reset_stats(struct hists *hists); +void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists, u32 type); +void hists__inc_nr_samples(struct hists *hists, bool filtered); void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); @@ -124,6 +169,12 @@ void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(struct hists *hists); +static inline bool hists__has_filter(struct hists *hists) +{ + return hists->thread_filter || hists->dso_filter || + hists->symbol_filter_str; +} + u16 hists__col_len(struct hists *hists, enum hist_column col); void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len); bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len); @@ -149,15 +200,30 @@ struct perf_hpp_fmt { struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); + int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b); + int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b); + int64_t (*sort)(struct hist_entry *a, struct hist_entry *b); struct list_head list; + struct list_head sort_list; + bool elide; }; extern struct list_head perf_hpp__list; +extern struct list_head perf_hpp__sort_list; #define perf_hpp__for_each_format(format) \ list_for_each_entry(format, &perf_hpp__list, list) +#define perf_hpp__for_each_format_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__list, list) + +#define perf_hpp__for_each_sort_list(format) \ + list_for_each_entry(format, &perf_hpp__sort_list, sort_list) + +#define perf_hpp__for_each_sort_list_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list) + extern struct perf_hpp_fmt perf_hpp__format[]; enum { @@ -167,6 +233,7 @@ enum { PERF_HPP__OVERHEAD_US, PERF_HPP__OVERHEAD_GUEST_SYS, PERF_HPP__OVERHEAD_GUEST_US, + PERF_HPP__OVERHEAD_ACC, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, @@ -175,15 +242,36 @@ enum { void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); +void perf_hpp__column_unregister(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +void perf_hpp__column_disable(unsigned col); +void perf_hpp__cancel_cumulate(void); + +void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); +void perf_hpp__setup_output_field(void); +void perf_hpp__reset_output_field(void); +void perf_hpp__append_sort_keys(void); + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); + +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +{ + return format->elide; +} + +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); 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, hpp_callback_fn callback, - const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent); + 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); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { @@ -250,4 +338,10 @@ static inline int script_browse(const char *script_opt __maybe_unused) #endif unsigned int hists__sort_list_width(struct hists *hists); + +struct option; +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused); +int perf_hist_config(const char *var, const char *value); + #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index bb162e40c76c..01ffd12dc791 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -4,6 +4,9 @@ #include <string.h> #include <linux/bitops.h> +#define DECLARE_BITMAP(name,bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); diff --git a/tools/perf/util/include/linux/export.h b/tools/perf/util/include/linux/export.h deleted file mode 100644 index b43e2dc21e04..000000000000 --- a/tools/perf/util/include/linux/export.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_MODULE_H -#define PERF_LINUX_MODULE_H - -#define EXPORT_SYMBOL(name) - -#endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 9844c31b7c2b..09e8e7aea7c6 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -int eprintf(int level, - const char *fmt, ...) __attribute__((format(printf, 2, 3))); - -#ifndef pr_fmt -#define pr_fmt(fmt) fmt -#endif - -#define pr_err(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug(fmt, ...) \ - eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debugN(n, fmt, ...) \ - eprintf(n, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) - /* * This looks more complex than it should be. But we need to * get the type for the ~ right in round_down (it needs to be diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h index bfe0a2afd0d2..76ddbc726343 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/perf/util/include/linux/list.h @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/types.h> #include "../../../../include/linux/list.h" diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h deleted file mode 100644 index eb464786c084..000000000000 --- a/tools/perf/util/include/linux/types.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef _PERF_LINUX_TYPES_H_ -#define _PERF_LINUX_TYPES_H_ - -#include <asm/types.h> - -#ifndef __bitwise -#define __bitwise -#endif - -#ifndef __le32 -typedef __u32 __bitwise __le32; -#endif - -#define DECLARE_BITMAP(name,bits) \ - unsigned long name[BITS_TO_LONGS(bits)] - -struct list_head { - struct list_head *next, *prev; -}; - -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - -#endif diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h new file mode 100644 index 000000000000..0b5a8cd2ee79 --- /dev/null +++ b/tools/perf/util/kvm-stat.h @@ -0,0 +1,140 @@ +#ifndef __PERF_KVM_STAT_H +#define __PERF_KVM_STAT_H + +#include "../perf.h" +#include "evsel.h" +#include "evlist.h" +#include "session.h" +#include "tool.h" +#include "stat.h" + +struct event_key { + #define INVALID_KEY (~0ULL) + u64 key; + int info; + struct exit_reasons_table *exit_reasons; +}; + +struct kvm_event_stats { + u64 time; + struct stats stats; +}; + +struct kvm_event { + struct list_head hash_entry; + struct rb_node rb; + + struct event_key key; + + struct kvm_event_stats total; + + #define DEFAULT_VCPU_NUM 8 + int max_vcpu; + struct kvm_event_stats *vcpu; +}; + +typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); + +struct kvm_event_key { + const char *name; + key_cmp_fun key; +}; + +struct perf_kvm_stat; + +struct child_event_ops { + void (*get_key)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + const char *name; +}; + +struct kvm_events_ops { + bool (*is_begin_event)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + bool (*is_end_event)(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key); + struct child_event_ops *child_ops; + void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, + char *decode); + const char *name; +}; + +struct exit_reasons_table { + unsigned long exit_code; + const char *reason; +}; + +#define EVENTS_BITS 12 +#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) + +struct perf_kvm_stat { + struct perf_tool tool; + struct record_opts opts; + struct perf_evlist *evlist; + struct perf_session *session; + + const char *file_name; + const char *report_event; + const char *sort_key; + int trace_vcpu; + + struct exit_reasons_table *exit_reasons; + const char *exit_reasons_isa; + + struct kvm_events_ops *events_ops; + key_cmp_fun compare; + struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + + u64 total_time; + u64 total_count; + u64 lost_events; + u64 duration; + + const char *pid_str; + struct intlist *pid_list; + + struct rb_root result; + + int timerfd; + unsigned int display_time; + bool live; +}; + +struct kvm_reg_events_ops { + const char *name; + struct kvm_events_ops *ops; +}; + +void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode); + +bool kvm_exit_event(struct perf_evsel *evsel); +bool kvm_entry_event(struct perf_evsel *evsel); + +#define define_exit_reasons_table(name, symbols) \ + static struct exit_reasons_table name[] = { \ + symbols, { -1, NULL } \ + } + +/* + * arch specific callbacks and data structures + */ +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); + +extern const char * const kvm_events_tp[]; +extern struct kvm_reg_events_ops kvm_reg_events_ops[]; +extern const char * const kvm_skip_events[]; + +#endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 27c2a5efe450..16bba9fff2c8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -8,6 +8,7 @@ #include "sort.h" #include "strlist.h" #include "thread.h" +#include "vdso.h" #include <stdbool.h> #include <symbol/kallsyms.h> #include "unwind.h" @@ -23,6 +24,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) INIT_LIST_HEAD(&machine->dead_threads); machine->last_match = NULL; + machine->vdso_info = NULL; + machine->kmaps.machine = machine; machine->pid = pid; @@ -34,7 +37,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, 0, + struct thread *thread = machine__findnew_thread(machine, -1, pid); char comm[64]; @@ -45,6 +48,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) thread__set_comm(thread, comm, 0); } + machine->current_tid = NULL; + return 0; } @@ -103,7 +108,9 @@ void machine__exit(struct machine *machine) map_groups__exit(&machine->kmaps); dsos__delete(&machine->user_dsos); dsos__delete(&machine->kernel_dsos); + vdso__exit(machine); zfree(&machine->root_dir); + zfree(&machine->current_tid); } void machine__delete(struct machine *machine) @@ -272,6 +279,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) return; } +static void machine__update_thread_pid(struct machine *machine, + struct thread *th, pid_t pid) +{ + struct thread *leader; + + if (pid == th->pid_ || pid == -1 || th->pid_ != -1) + return; + + th->pid_ = pid; + + if (th->pid_ == th->tid) + return; + + leader = machine__findnew_thread(machine, th->pid_, th->pid_); + if (!leader) + goto out_err; + + if (!leader->mg) + leader->mg = map_groups__new(); + + if (!leader->mg) + goto out_err; + + if (th->mg == leader->mg) + return; + + if (th->mg) { + /* + * Maps are created from MMAP events which provide the pid and + * tid. Consequently there never should be any maps on a thread + * with an unknown pid. Just print an error if there are. + */ + if (!map_groups__empty(th->mg)) + pr_err("Discarding thread maps for %d:%d\n", + th->pid_, th->tid); + map_groups__delete(th->mg); + } + + th->mg = map_groups__get(leader->mg); + + return; + +out_err: + pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid); +} + static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid, bool create) @@ -285,10 +338,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * so most of the time we dont have to look up * the full rbtree: */ - if (machine->last_match && machine->last_match->tid == tid) { - if (pid && pid != machine->last_match->pid_) - machine->last_match->pid_ = pid; - return machine->last_match; + th = machine->last_match; + if (th && th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; } while (*p != NULL) { @@ -297,8 +350,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th->tid == tid) { machine->last_match = th; - if (pid && pid != th->pid_) - th->pid_ = pid; + machine__update_thread_pid(machine, th, pid); return th; } @@ -316,6 +368,19 @@ static struct thread *__machine__findnew_thread(struct machine *machine, rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); machine->last_match = th; + + /* + * We have to initialize map_groups separately + * after rb tree is updated. + * + * The reason is that we call machine__findnew_thread + * within thread__init_map_groups to find the thread + * leader and that would screwed the rb tree. + */ + if (thread__init_map_groups(th, machine)) { + thread__delete(th); + return NULL; + } } return th; @@ -485,18 +550,6 @@ struct process_args { u64 start; }; -static int symbol__in_kernel(void *arg, const char *name, - char type __maybe_unused, u64 start) -{ - struct process_args *args = arg; - - if (strchr(name, '[')) - return 0; - - args->start = start; - return 1; -} - static void machine__get_kallsyms_filename(struct machine *machine, char *buf, size_t bufsz) { @@ -506,27 +559,41 @@ static void machine__get_kallsyms_filename(struct machine *machine, char *buf, scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir); } -/* Figure out the start address of kernel map from /proc/kallsyms */ -static u64 machine__get_kernel_start_addr(struct machine *machine) +const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; + +/* Figure out the start address of kernel map from /proc/kallsyms. + * 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) { char filename[PATH_MAX]; - struct process_args args; + int i; + const char *name; + u64 addr = 0; machine__get_kallsyms_filename(machine, filename, PATH_MAX); if (symbol__restricted_filename(filename, "/proc/kallsyms")) return 0; - if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) - return 0; + for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { + addr = kallsyms__get_function_start(filename, name); + if (addr) + break; + } - return args.start; + if (symbol_name) + *symbol_name = name; + + return addr; } int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { enum map_type type; - u64 start = machine__get_kernel_start_addr(machine); + u64 start = machine__get_kernel_start_addr(machine, NULL); for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -841,23 +908,11 @@ static int machine__create_modules(struct machine *machine) return 0; } -const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; - int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); - char filename[PATH_MAX]; const char *name; - u64 addr = 0; - int i; - - machine__get_kallsyms_filename(machine, filename, PATH_MAX); - - for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr = kallsyms__get_function_start(filename, name); - if (addr) - break; - } + u64 addr = machine__get_kernel_start_addr(machine, &name); if (!addr) return -1; @@ -1044,12 +1099,14 @@ int machine__process_mmap2_event(struct machine *machine, else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap2.start, + map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.pid, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, - event->mmap2.filename, type); + event->mmap2.prot, + event->mmap2.flags, + event->mmap2.filename, type, thread); if (map == NULL) goto out_problem; @@ -1092,11 +1149,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap.start, + map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - event->mmap.pid, 0, 0, 0, 0, + event->mmap.pid, 0, 0, 0, 0, 0, 0, event->mmap.filename, - type); + type, thread); if (map == NULL) goto out_problem; @@ -1278,7 +1335,9 @@ static int machine__resolve_callchain_sample(struct machine *machine, u8 cpumode = PERF_RECORD_MISC_USER; int chain_nr = min(max_stack, (int)chain->nr); int i; + int j; int err; + int skip_idx __maybe_unused; callchain_cursor_reset(&callchain_cursor); @@ -1287,14 +1346,26 @@ static int machine__resolve_callchain_sample(struct machine *machine, return 0; } + /* + * Based on DWARF debug information, some architectures skip + * a callchain entry saved by the kernel. + */ + skip_idx = arch_skip_callchain_idx(machine, thread, chain); + for (i = 0; i < chain_nr; i++) { u64 ip; struct addr_location al; if (callchain_param.order == ORDER_CALLEE) - ip = chain->ips[i]; + j = i; else - ip = chain->ips[chain->nr - i - 1]; + j = chain->nr - i - 1; + +#ifdef HAVE_SKIP_CALLCHAIN_IDX + if (j == skip_idx) + continue; +#endif + ip = chain->ips[j]; if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -1417,3 +1488,46 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too /* command specified */ return 0; } + +pid_t machine__get_current_tid(struct machine *machine, int cpu) +{ + if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid) + return -1; + + return machine->current_tid[cpu]; +} + +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid) +{ + struct thread *thread; + + if (cpu < 0) + return -EINVAL; + + if (!machine->current_tid) { + int i; + + machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t)); + if (!machine->current_tid) + return -ENOMEM; + for (i = 0; i < MAX_NR_CPUS; i++) + machine->current_tid[i] = -1; + } + + if (cpu >= MAX_NR_CPUS) { + pr_err("Requested CPU %d too large. ", cpu); + pr_err("Consider raising MAX_NR_CPUS\n"); + return -EINVAL; + } + + machine->current_tid[cpu] = tid; + + thread = machine__findnew_thread(machine, pid, tid); + if (!thread) + return -ENOMEM; + + thread->cpu = cpu; + + return 0; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index c8c74a119398..b972824e6294 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -20,6 +20,8 @@ union perf_event; extern const char *ref_reloc_sym_names[]; +struct vdso_info; + struct machine { struct rb_node rb_node; pid_t pid; @@ -28,11 +30,13 @@ struct machine { 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 map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; symbol_filter_t symbol_filter; + pid_t *current_tid; }; static inline @@ -191,4 +195,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target, perf_event__process, data_mmap); } +pid_t machine__get_current_tid(struct machine *machine, int cpu); +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 39cd2d0faff6..31b8905dd863 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -12,6 +12,8 @@ #include "vdso.h" #include "build-id.h" #include "util.h" +#include "debug.h" +#include "machine.h" #include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { @@ -32,6 +34,93 @@ static inline int is_no_dso_memory(const char *filename) !strcmp(filename, "[heap]"); } +static inline int is_android_lib(const char *filename) +{ + return !strncmp(filename, "/data/app-lib", 13) || + !strncmp(filename, "/system/lib", 11); +} + +static inline bool replace_android_lib(const char *filename, char *newfilename) +{ + const char *libname; + char *app_abi; + size_t app_abi_length, new_length; + size_t lib_length = 0; + + libname = strrchr(filename, '/'); + if (libname) + lib_length = strlen(libname); + + app_abi = getenv("APP_ABI"); + if (!app_abi) + return false; + + app_abi_length = strlen(app_abi); + + if (!strncmp(filename, "/data/app-lib", 13)) { + char *apk_path; + + if (!app_abi_length) + return false; + + new_length = 7 + app_abi_length + lib_length; + + apk_path = getenv("APK_PATH"); + if (apk_path) { + new_length += strlen(apk_path) + 1; + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/libs/%s/%s", apk_path, app_abi, libname); + } else { + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "libs/%s/%s", app_abi, libname); + } + return true; + } + + if (!strncmp(filename, "/system/lib/", 11)) { + char *ndk, *app; + const char *arch; + size_t ndk_length; + size_t app_length; + + ndk = getenv("NDK_ROOT"); + app = getenv("APP_PLATFORM"); + + if (!(ndk && app)) + return false; + + ndk_length = strlen(ndk); + app_length = strlen(app); + + if (!(ndk_length && app_length && app_abi_length)) + return false; + + arch = !strncmp(app_abi, "arm", 3) ? "arm" : + !strncmp(app_abi, "mips", 4) ? "mips" : + !strncmp(app_abi, "x86", 3) ? "x86" : NULL; + + if (!arch) + return false; + + new_length = 27 + ndk_length + + app_length + lib_length + + strlen(arch); + + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/platforms/%s/arch-%s/usr/lib/%s", + ndk, app, arch, libname); + + return true; + } + return false; +} + void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { @@ -49,18 +138,19 @@ void map__init(struct map *map, enum map_type type, map->erange_warned = false; } -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, char *filename, - enum map_type type) + u64 ino_gen, u32 prot, u32 flags, char *filename, + enum map_type type, struct thread *thread) { struct map *map = malloc(sizeof(*map)); if (map != NULL) { char newfilename[PATH_MAX]; struct dso *dso; - int anon, no_dso, vdso; + int anon, no_dso, vdso, android; + android = is_android_lib(filename); anon = is_anon_memory(filename); vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); @@ -69,17 +159,24 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, map->min = d_min; map->ino = ino; map->ino_generation = ino_gen; + map->prot = prot; + map->flags = flags; if ((anon || no_dso) && type == MAP__FUNCTION) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); filename = newfilename; } + if (android) { + if (replace_android_lib(filename, newfilename)) + filename = newfilename; + } + if (vdso) { pgoff = 0; - dso = vdso__dso_findnew(dsos__list); + dso = vdso__dso_findnew(machine, thread); } else - dso = __dsos__findnew(dsos__list, filename); + dso = __dsos__findnew(&machine->user_dsos, filename); if (dso == NULL) goto out_delete; @@ -323,6 +420,7 @@ void map_groups__init(struct map_groups *mg) INIT_LIST_HEAD(&mg->removed_maps[i]); } mg->machine = NULL; + mg->refcnt = 1; } static void maps__delete(struct rb_root *maps) @@ -358,6 +456,42 @@ void map_groups__exit(struct map_groups *mg) } } +bool map_groups__empty(struct map_groups *mg) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + if (maps__first(&mg->maps[i])) + return false; + if (!list_empty(&mg->removed_maps[i])) + return false; + } + + return true; +} + +struct map_groups *map_groups__new(void) +{ + struct map_groups *mg = malloc(sizeof(*mg)); + + if (mg != NULL) + map_groups__init(mg); + + return mg; +} + +void map_groups__delete(struct map_groups *mg) +{ + map_groups__exit(mg); + free(mg); +} + +void map_groups__put(struct map_groups *mg) +{ + if (--mg->refcnt == 0) + map_groups__delete(mg); +} + void map_groups__flush(struct map_groups *mg) { int type; @@ -436,8 +570,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) return ams->sym ? 0 : -1; } -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp) +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; @@ -455,17 +589,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg, return printed; } -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp) +static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_maps(mg, i, fp); return printed; } static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, - enum map_type type, - int verbose, FILE *fp) + enum map_type type, FILE *fp) { struct map *pos; size_t printed = 0; @@ -482,23 +615,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, } static size_t map_groups__fprintf_removed_maps(struct map_groups *mg, - int verbose, FILE *fp) + FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_removed_maps(mg, i, fp); return printed; } -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp) +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) { - size_t printed = map_groups__fprintf_maps(mg, verbose, fp); + size_t printed = map_groups__fprintf_maps(mg, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(mg, verbose, fp); + return printed + map_groups__fprintf_removed_maps(mg, fp); } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp) + FILE *fp) { struct rb_root *root = &mg->maps[map->type]; struct rb_node *next = rb_first(root); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f00f058afb3b..2f83954af050 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -6,7 +6,7 @@ #include <linux/rbtree.h> #include <stdio.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> enum map_type { MAP__FUNCTION = 0, @@ -35,6 +35,8 @@ struct map { bool referenced; bool erange_warned; u32 priv; + u32 prot; + u32 flags; u64 pgoff; u64 reloc; u32 maj, min; /* only valid for MMAP2 record */ @@ -59,8 +61,21 @@ struct map_groups { struct rb_root maps[MAP__NR_TYPES]; struct list_head removed_maps[MAP__NR_TYPES]; struct machine *machine; + int refcnt; }; +struct map_groups *map_groups__new(void); +void map_groups__delete(struct map_groups *mg); +bool map_groups__empty(struct map_groups *mg); + +static inline struct map_groups *map_groups__get(struct map_groups *mg) +{ + ++mg->refcnt; + return mg; +} + +void map_groups__put(struct map_groups *mg); + static inline struct kmap *map__kmap(struct map *map) { return (struct kmap *)(map + 1); @@ -89,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip); u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +struct thread; /* map__for_each_symbol - iterate over the symbols in the given map * @@ -104,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, - char *filename, enum map_type type); + u64 ino_gen, u32 prot, u32 flags, + char *filename, enum map_type type, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -127,8 +143,8 @@ void map__fixup_end(struct map *map); void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp); +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); @@ -138,8 +154,7 @@ void map_groups__init(struct map_groups *mg); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct map_groups *mg, struct map_groups *parent, enum map_type type); -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp); -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp); +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); @@ -196,7 +211,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg, } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp); + FILE *fp); struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c index 3322b8446e89..31ee02d4e988 100644 --- a/tools/perf/util/pager.c +++ b/tools/perf/util/pager.c @@ -57,13 +57,13 @@ void setup_pager(void) } if (!pager) pager = getenv("PAGER"); - if (!pager) { - if (!access("/usr/bin/pager", X_OK)) - pager = "/usr/bin/pager"; - } + if (!(pager || access("/usr/bin/pager", X_OK))) + pager = "/usr/bin/pager"; + if (!(pager || access("/usr/bin/less", X_OK))) + pager = "/usr/bin/less"; if (!pager) - pager = "less"; - else if (!*pager || !strcmp(pager, "cat")) + pager = "cat"; + if (!*pager || !strcmp(pager, "cat")) return; spawned_pager = 1; /* means we are emitting to terminal */ diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f1cb4c4b3c70..df094b4ed5ed 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -6,9 +6,8 @@ #include <linux/list.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> #include <linux/perf_event.h> -#include "types.h" struct list_head; struct perf_evsel; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 4eb67ec333f1..0bc87ba46bf3 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -9,7 +9,7 @@ #include <linux/compiler.h> #include <linux/list.h> -#include "types.h" +#include <linux/types.h> #include "util.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -299,6 +299,18 @@ PE_PREFIX_MEM PE_VALUE sep_dc } event_legacy_tracepoint: +PE_NAME '-' PE_NAME ':' PE_NAME +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + char sys_name[128]; + snprintf(&sys_name, 128, "%s-%s", $1, $3); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5)); + $$ = list; +} +| PE_NAME ':' PE_NAME { struct parse_events_evlist *data = _data; diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index d8dac8ac5f37..b59ba858e73d 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -98,6 +98,7 @@ struct option { parse_opt_cb *callback; intptr_t defval; bool *set; + void *data; }; #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v ) @@ -131,6 +132,10 @@ struct option { { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} +#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ + .value = (v), (a), .help = (h), .callback = (f), \ + .flags = PARSE_OPT_OPTARG, .data = (d) } /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index a3539ef30b15..43168fb0d9a2 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,11 +1,15 @@ #include <errno.h> #include "perf_regs.h" +#include "event.h" int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { int i, idx = 0; u64 mask = regs->mask; + if (regs->cache_mask & (1 << id)) + goto out; + if (!(mask & (1 << id))) return -EINVAL; @@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) idx++; } - *valp = regs->regs[idx]; + regs->cache_mask |= (1 << id); + regs->cache_regs[id] = regs->regs[idx]; + +out: + *valp = regs->cache_regs[id]; return 0; } diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index d6e8b6a8d7f3..980dbf76bc98 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,8 +1,9 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H -#include "types.h" -#include "event.h" +#include <linux/types.h> + +struct regs_dump; #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> @@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); #else #define PERF_REGS_MASK 0 +#define PERF_REGS_MAX 0 static inline const char *perf_reg_name(int id __maybe_unused) { diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 00a7dcb2f55c..7a811eb61f75 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head) static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { - struct parse_events_term *term, *clone; + struct parse_events_term *term, *cloned; LIST_HEAD(list); int ret; list_for_each_entry(term, &alias->terms, list) { - ret = parse_events_term__clone(&clone, term); + ret = parse_events_term__clone(&cloned, term); if (ret) { parse_events__free_terms(&list); return ret; } - list_add_tail(&clone->list, &list); + list_add_tail(&cloned->list, &list); } list_splice(&list, terms); return 0; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 8b64125a9281..c14a543ce1f3 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -1,7 +1,7 @@ #ifndef __PMU_H #define __PMU_H -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/perf_event.h> #include <stdbool.h> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 0d1542f33d87..9a0a1839a377 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module) ret = debuginfo__find_line_range(dinfo, lr); debuginfo__delete(dinfo); - if (ret == 0) { + if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); return -ENOENT; } else if (ret < 0) { - pr_warning("Debuginfo analysis failed. (%d)\n", ret); + pr_warning("Debuginfo analysis failed.\n"); return ret; } @@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module) ret = get_real_path(tmp, lr->comp_dir, &lr->path); free(tmp); /* Free old path */ if (ret < 0) { - pr_warning("Failed to find source file. (%d)\n", ret); + pr_warning("Failed to find source file path.\n"); return ret; } @@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo, ret = debuginfo__find_available_vars_at(dinfo, pev, &vls, max_vls, externs); if (ret <= 0) { - pr_err("Failed to find variables at %s (%d)\n", buf, ret); + if (ret == 0 || ret == -ENOENT) { + pr_err("Failed to find the address of %s\n", buf); + ret = -ENOENT; + } else + pr_warning("Debuginfo analysis failed.\n"); goto end; } + /* Some variables are found */ fprintf(stdout, "Available variables at %s\n", buf); for (i = 0; i < ret; i++) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 9d8eb26f0533..dca9145d704c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -26,7 +26,6 @@ #include <errno.h> #include <stdio.h> #include <unistd.h> -#include <getopt.h> #include <stdlib.h> #include <string.h> #include <stdarg.h> @@ -573,14 +572,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) { /* Search again in global variables */ if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) + pr_warning("Failed to find '%s' in this function.\n", + pf->pvar->var); ret = -ENOENT; } if (ret >= 0) ret = convert_variable(&vr_die, pf); - if (ret < 0) - pr_warning("Failed to find '%s' in this function.\n", - pf->pvar->var); return ret; } @@ -1281,7 +1279,11 @@ out: return ret; } -/* Find available variables at given probe point */ +/* + * Find available variables at given probe point + * Return the number of found probe points. Return 0 if there is no + * matched probe point. Return <0 if an error occurs. + */ int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index daa17aeb6c63..a126e6cc6e73 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -6,6 +6,7 @@ #include "util.h" #include "pstack.h" +#include "debug.h" #include <linux/kernel.h> #include <stdlib.h> diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 122669c18ff4..12aa9b0d0ba1 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -14,12 +14,12 @@ */ int verbose; -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret = 0; - if (verbose >= level) { + if (var >= level) { va_start(args, fmt); ret = vfprintf(stderr, fmt, args); va_end(args); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 049e0a09ccd3..fe8079edbdc1 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -4,6 +4,7 @@ #include "parse-events.h" #include <api/fs/fs.h> #include "util.h" +#include "cloexec.h" typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); @@ -11,6 +12,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) { struct perf_evlist *evlist; struct perf_evsel *evsel; + unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; evlist = perf_evlist__new(); @@ -22,14 +24,14 @@ 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, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); if (fd < 0) goto out_delete; close(fd); fn(evsel); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -69,15 +71,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel) evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; } +static void perf_probe_comm_exec(struct perf_evsel *evsel) +{ + evsel->attr.comm_exec = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); } +static bool perf_can_comm_exec(void) +{ + return perf_probe_api(perf_probe_comm_exec); +} + void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) { struct perf_evsel *evsel; bool use_sample_identifier = false; + bool use_comm_exec; /* * Set the evsel leader links before we configure attributes, @@ -89,8 +102,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - evlist__for_each(evlist, evsel) + use_comm_exec = perf_can_comm_exec(); + + evlist__for_each(evlist, evsel) { perf_evsel__config(evsel, opts); + if (!evsel->idx && use_comm_exec) + evsel->attr.comm_exec = 1; + } if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -203,7 +221,8 @@ 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, 0); + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, + perf_event_open_cloexec_flag()); if (fd >= 0) { close(fd); ret = true; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e108207c5de0..b2dba9c0a3a1 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -34,6 +34,7 @@ #include "../event.h" #include "../trace-event.h" #include "../evsel.h" +#include "../debug.h" void boot_Perf__Trace__Context(pTHX_ CV *cv); void boot_DynaLoader(pTHX_ CV *cv); @@ -215,6 +216,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: + case PRINT_BITMASK: break; case PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cd9774df3750..cbce2545da45 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -27,11 +27,13 @@ #include <errno.h> #include "../../perf.h" +#include "../debug.h" #include "../evsel.h" #include "../util.h" #include "../event.h" #include "../thread.h" #include "../trace-event.h" +#include "../machine.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -50,10 +52,14 @@ static int zero_flag_atom; static PyObject *main_module, *main_dict; +static void handler_call_die(const char *handler_name) NORETURN; static void handler_call_die(const char *handler_name) { PyErr_Print(); Py_FatalError("problem in Python trace event handler"); + // Py_FatalError does not return + // but we have to make the compiler happy + abort(); } /* @@ -97,6 +103,7 @@ static void define_value(enum print_arg_type field_type, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } Py_DECREF(t); @@ -143,6 +150,7 @@ static void define_field(enum print_arg_type field_type, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } Py_DECREF(t); @@ -197,6 +205,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_FUNC: + case PRINT_BITMASK: /* we should warn... */ return; } @@ -230,15 +239,133 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel) return event; } +static PyObject *get_field_numeric_entry(struct event_format *event, + struct format_field *field, void *data) +{ + bool is_array = field->flags & FIELD_IS_ARRAY; + PyObject *obj, *list = NULL; + unsigned long long val; + unsigned int item_size, n_items, i; + + if (is_array) { + list = PyList_New(field->arraylen); + item_size = field->size / field->arraylen; + n_items = field->arraylen; + } else { + item_size = field->size; + n_items = 1; + } + + for (i = 0; i < n_items; i++) { + + val = read_size(event, data + field->offset + i * item_size, + item_size); + if (field->flags & FIELD_IS_SIGNED) { + if ((long long)val >= LONG_MIN && + (long long)val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromLongLong(val); + } else { + if (val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromUnsignedLongLong(val); + } + if (is_array) + PyList_SET_ITEM(list, i, obj); + } + if (is_array) + obj = list; + return obj; +} + + +static PyObject *python_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + PyObject *pylist; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (machine__resolve_callchain(al->machine, evsel, al->thread, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + PyObject *pyelem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + + pydict_set_item_string_decref(pyelem, "ip", + PyLong_FromUnsignedLongLong(node->ip)); + + if (node->sym) { + PyObject *pysym = PyDict_New(); + if (!pysym) + Py_FatalError("couldn't create Python dictionary"); + pydict_set_item_string_decref(pysym, "start", + PyLong_FromUnsignedLongLong(node->sym->start)); + pydict_set_item_string_decref(pysym, "end", + PyLong_FromUnsignedLongLong(node->sym->end)); + pydict_set_item_string_decref(pysym, "binding", + PyInt_FromLong(node->sym->binding)); + pydict_set_item_string_decref(pysym, "name", + PyString_FromStringAndSize(node->sym->name, + node->sym->namelen)); + pydict_set_item_string_decref(pyelem, "sym", pysym); + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + pydict_set_item_string_decref(pyelem, "dso", + PyString_FromString(dsoname)); + } + + callchain_cursor_advance(&callchain_cursor); + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; + PyObject *handler, *retval, *context, *t, *obj, *callchain; + PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; - unsigned long long val; unsigned long s, ns; struct event_format *event; unsigned n = 0; @@ -279,18 +406,23 @@ static void python_process_tracepoint(struct perf_sample *sample, PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); PyTuple_SetItem(t, n++, context); + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); + PyTuple_SetItem(t, n++, callchain); } else { pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -302,20 +434,7 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(event, data + field->offset, - field->size); - if (field->flags & FIELD_IS_SIGNED) { - if ((long long)val >= LONG_MIN && - (long long)val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromLongLong(val); - } else { - if (val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromUnsignedLongLong(val); - } + obj = get_field_numeric_entry(event, field, data); } if (handler) PyTuple_SetItem(t, n++, obj); @@ -323,6 +442,7 @@ static void python_process_tracepoint(struct perf_sample *sample, pydict_set_item_string_decref(dict, field->name, obj); } + if (!handler) PyTuple_SetItem(t, n++, dict); @@ -333,6 +453,7 @@ static void python_process_tracepoint(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); } else { handler = PyDict_GetItemString(main_dict, "trace_unhandled"); if (handler && PyCallable_Check(handler)) { @@ -340,6 +461,7 @@ static void python_process_tracepoint(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die("trace_unhandled"); + Py_DECREF(retval); } Py_DECREF(dict); } @@ -352,7 +474,7 @@ static void python_process_general_event(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *t, *dict; + PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample; static char handler_name[64]; unsigned n = 0; @@ -368,6 +490,10 @@ static void python_process_general_event(struct perf_sample *sample, if (!dict) Py_FatalError("couldn't create Python dictionary"); + dict_sample = PyDict_New(); + if (!dict_sample) + Py_FatalError("couldn't create Python dictionary"); + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); handler = PyDict_GetItemString(main_dict, handler_name); @@ -377,8 +503,21 @@ static void python_process_general_event(struct perf_sample *sample, pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( - (const char *)sample, sizeof(*sample))); + + pydict_set_item_string_decref(dict_sample, "pid", + PyInt_FromLong(sample->pid)); + pydict_set_item_string_decref(dict_sample, "tid", + PyInt_FromLong(sample->tid)); + pydict_set_item_string_decref(dict_sample, "cpu", + PyInt_FromLong(sample->cpu)); + pydict_set_item_string_decref(dict_sample, "ip", + PyLong_FromUnsignedLongLong(sample->ip)); + pydict_set_item_string_decref(dict_sample, "time", + PyLong_FromUnsignedLongLong(sample->time)); + pydict_set_item_string_decref(dict_sample, "period", + PyLong_FromUnsignedLongLong(sample->period)); + pydict_set_item_string_decref(dict, "sample", dict_sample); + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); pydict_set_item_string_decref(dict, "comm", @@ -392,6 +531,10 @@ static void python_process_general_event(struct perf_sample *sample, PyString_FromString(al->sym->name)); } + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + pydict_set_item_string_decref(dict, "callchain", callchain); + PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); @@ -399,6 +542,7 @@ static void python_process_general_event(struct perf_sample *sample, retval = PyObject_CallObject(handler, t); if (retval == NULL) handler_call_die(handler_name); + Py_DECREF(retval); exit: Py_DECREF(dict); Py_DECREF(t); @@ -520,8 +664,7 @@ static int python_stop_script(void) retval = PyObject_CallObject(handler, NULL); if (retval == NULL) handler_call_die("trace_end"); - else - Py_DECREF(retval); + Py_DECREF(retval); out: Py_XDECREF(main_dict); Py_XDECREF(main_module); @@ -588,6 +731,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "common_nsecs, "); fprintf(ofp, "common_pid, "); fprintf(ofp, "common_comm,\n\t"); + fprintf(ofp, "common_callchain, "); not_first = 0; count = 0; @@ -622,6 +766,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s=", f->name); if (f->flags & FIELD_IS_STRING || f->flags & FIELD_IS_FLAG || + f->flags & FIELD_IS_ARRAY || f->flags & FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); else if (f->flags & FIELD_IS_SIGNED) @@ -630,7 +775,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%%u"); } - fprintf(ofp, "\\n\" %% \\\n\t\t("); + fprintf(ofp, "\" %% \\\n\t\t("); not_first = 0; count = 0; @@ -666,7 +811,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, "),\n\n"); + fprintf(ofp, ")\n\n"); + + fprintf(ofp, "\t\tfor node in common_callchain:"); + fprintf(ofp, "\n\t\t\tif 'sym' in node:"); + fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\telse:"); + fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); + fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + } fprintf(ofp, "def trace_unhandled(event_name, context, " diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 55960f22233c..88dfef70c13d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,7 +14,6 @@ #include "util.h" #include "cpumap.h" #include "perf_regs.h" -#include "vdso.h" static int perf_session__open(struct perf_session *session) { @@ -156,7 +155,6 @@ void perf_session__delete(struct perf_session *session) if (session->file) perf_data_file__close(session->file); free(session); - vdso__exit(); } static int process_event_synth_tracing_data_stub(struct perf_tool *tool @@ -511,6 +509,7 @@ static int flush_sample_queue(struct perf_session *s, 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); @@ -523,8 +522,6 @@ static int flush_sample_queue(struct perf_session *s, list_entry(head->prev, struct sample_queue, list); } - os->nr_samples = 0; - return 0; } @@ -994,8 +991,10 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) +static s64 perf_session__process_user_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) { int fd = perf_data_file__fd(session->file); int err; @@ -1037,7 +1036,7 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } -static int perf_session__process_event(struct perf_session *session, +static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) @@ -1083,13 +1082,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, 0, pid); + return machine__findnew_thread(&session->machines.host, -1, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, 0); + struct thread *thread; + thread = machine__findnew_thread(&session->machines.host, 0, 0); if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; @@ -1147,7 +1147,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session, union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; - int skip = 0; + s64 skip = 0; u64 head; ssize_t err; void *p; @@ -1276,13 +1276,13 @@ int __perf_session__process_events(struct perf_session *session, u64 file_size, struct perf_tool *tool) { int fd = perf_data_file__fd(session->file); - u64 head, page_offset, file_offset, file_pos; + u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; - uint32_t size; struct ui_progress prog; + s64 skip; perf_tool__fill_defaults(tool); @@ -1296,8 +1296,10 @@ int __perf_session__process_events(struct perf_session *session, ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; - if (mmap_size > file_size) + if (mmap_size > file_size) { mmap_size = file_size; + session->one_mmap = true; + } memset(mmaps, 0, sizeof(mmaps)); @@ -1319,6 +1321,10 @@ remap: mmaps[map_idx] = buf; map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); file_pos = file_offset + head; + if (session->one_mmap) { + session->one_mmap_addr = buf; + session->one_mmap_offset = file_offset; + } more: event = fetch_mmaped_event(session, head, mmap_size, buf); @@ -1337,7 +1343,8 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - perf_session__process_event(session, event, tool, file_pos) < 0) { + (skip = perf_session__process_event(session, event, tool, file_pos)) + < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1345,6 +1352,9 @@ more: goto out_err; } + if (skip) + size += skip; + head += size; file_pos += size; @@ -1364,6 +1374,7 @@ out_err: ui_progress__finish(); perf_session__warn_about_errors(session, tool); perf_session_free_sample_buffers(session); + session->one_mmap = false; return err; } @@ -1625,13 +1636,14 @@ out_delete_map: void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { - int fd = perf_data_file__fd(session->file); struct stat st; - int ret; + int fd, ret; if (session == NULL || fp == NULL) return; + fd = perf_data_file__fd(session->file); + ret = fstat(fd, &st); if (ret == -1) return; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3140f8ae6148..0321013bd9fd 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -36,6 +36,9 @@ struct perf_session { struct trace_event tevent; struct events_stats stats; bool repipe; + bool one_mmap; + void *one_mmap_addr; + u64 one_mmap_offset; struct ordered_samples ordered_samples; struct perf_data_file *file; }; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 635cd8f8b22e..14e5a039bc45 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,13 +1,20 @@ +#include <sys/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" #include "symbol.h" +#include "evsel.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; -const char *sort_order = default_sort_order; +const char default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; +const char default_top_sort_order[] = "dso,symbol"; +const char default_diff_sort_order[] = "dso,symbol"; +const char *sort_order; +const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; int sort__need_collapse = 0; @@ -16,9 +23,6 @@ int sort__has_sym = 0; int sort__has_dso = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; -enum sort_type sort__first_dimension; - -LIST_HEAD(hist_entry__sort_list); static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) { @@ -93,6 +97,12 @@ sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) return comm__str(right->comm) - comm__str(left->comm); } +static int64_t +sort__comm_sort(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp(comm__str(right->comm), comm__str(left->comm)); +} + static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { @@ -103,6 +113,7 @@ struct sort_entry sort_comm = { .se_header = "Command", .se_cmp = sort__comm_cmp, .se_collapse = sort__comm_collapse, + .se_sort = sort__comm_sort, .se_snprintf = hist_entry__comm_snprintf, .se_width_idx = HISTC_COMM, }; @@ -116,7 +127,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) const char *dso_name_l, *dso_name_r; if (!dso_l || !dso_r) - return cmp_null(dso_l, dso_r); + return cmp_null(dso_r, dso_l); if (verbose) { dso_name_l = dso_l->long_name; @@ -132,7 +143,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) static int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { - return _sort__dso_cmp(left->ms.map, right->ms.map); + return _sort__dso_cmp(right->ms.map, left->ms.map); } static int _hist_entry__dso_snprintf(struct map *map, char *bf, @@ -204,6 +215,15 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__sym_cmp(left->ms.sym, right->ms.sym); } +static int64_t +sort__sym_sort(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->ms.sym || !right->ms.sym) + return cmp_null(left->ms.sym, right->ms.sym); + + return strcmp(right->ms.sym->name, left->ms.sym->name); +} + static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, u64 ip, char level, char *bf, size_t size, unsigned int width) @@ -250,6 +270,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, + .se_sort = sort__sym_sort, .se_snprintf = hist_entry__sym_snprintf, .se_width_idx = HISTC_SYMBOL, }; @@ -277,7 +298,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, right->ip)); } } - return strcmp(left->srcline, right->srcline); + return strcmp(right->srcline, left->srcline); } static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, @@ -305,7 +326,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) if (!sym_l || !sym_r) return cmp_null(sym_l, sym_r); - return strcmp(sym_l->name, sym_r->name); + return strcmp(sym_r->name, sym_l->name); } static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, @@ -764,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } +static inline u64 cl_address(u64 address) +{ + /* return the cacheline of the address */ + return (address & ~(cacheline_size - 1)); +} + +static int64_t +sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + u64 l, r; + struct map *l_map, *r_map; + + if (!left->mem_info) return -1; + if (!right->mem_info) return 1; + + /* group event types together */ + if (left->cpumode > right->cpumode) return -1; + if (left->cpumode < right->cpumode) return 1; + + l_map = left->mem_info->daddr.map; + r_map = right->mem_info->daddr.map; + + /* if both are NULL, jump to sort on al_addr instead */ + if (!l_map && !r_map) + goto addr; + + if (!l_map) return -1; + if (!r_map) return 1; + + if (l_map->maj > r_map->maj) return -1; + if (l_map->maj < r_map->maj) return 1; + + if (l_map->min > r_map->min) return -1; + if (l_map->min < r_map->min) return 1; + + if (l_map->ino > r_map->ino) return -1; + if (l_map->ino < r_map->ino) return 1; + + if (l_map->ino_generation > r_map->ino_generation) return -1; + if (l_map->ino_generation < r_map->ino_generation) return 1; + + /* + * Addresses with no major/minor numbers are assumed to be + * anonymous in userspace. Sort those on pid then address. + * + * The kernel and non-zero major/minor mapped areas are + * assumed to be unity mapped. Sort those on address. + */ + + if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && + (!(l_map->flags & MAP_SHARED)) && + !l_map->maj && !l_map->min && !l_map->ino && + !l_map->ino_generation) { + /* userspace anonymous */ + + if (left->thread->pid_ > right->thread->pid_) return -1; + if (left->thread->pid_ < right->thread->pid_) return 1; + } + +addr: + /* al_addr does all the right addr - start + offset calculations */ + l = cl_address(left->mem_info->daddr.al_addr); + r = cl_address(right->mem_info->daddr.al_addr); + + if (l > r) return -1; + if (l < r) return 1; + + return 0; +} + +static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + + uint64_t addr = 0; + struct map *map = NULL; + struct symbol *sym = NULL; + char level = he->level; + + if (he->mem_info) { + addr = cl_address(he->mem_info->daddr.al_addr); + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; + + /* print [s] for shared data mmaps */ + if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && + map && (map->type == MAP__VARIABLE) && + (map->flags & MAP_SHARED) && + (map->maj || map->min || map->ino || + map->ino_generation)) + level = 's'; + else if (!map) + level = 'X'; + } + return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, + width); +} + struct sort_entry sort_mispredict = { .se_header = "Branch Mispredicted", .se_cmp = sort__mispredict_cmp, @@ -856,6 +975,13 @@ struct sort_entry sort_mem_snoop = { .se_width_idx = HISTC_MEM_SNOOP, }; +struct sort_entry sort_mem_dcacheline = { + .se_header = "Data Cacheline", + .se_cmp = sort__dcacheline_cmp, + .se_snprintf = hist_entry__dcacheline_snprintf, + .se_width_idx = HISTC_MEM_DCACHELINE, +}; + static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -1023,23 +1149,199 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb), DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), + DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), +}; + +#undef DIM + +struct hpp_dimension { + const char *name; + struct perf_hpp_fmt *fmt; + int taken; +}; + +#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], } + +static struct hpp_dimension hpp_sort_dimensions[] = { + DIM(PERF_HPP__OVERHEAD, "overhead"), + DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"), + DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), + DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), + DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), + DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"), + DIM(PERF_HPP__SAMPLES, "sample"), + DIM(PERF_HPP__PERIOD, "period"), }; #undef DIM -static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx) +struct hpp_sort_entry { + struct perf_hpp_fmt hpp; + struct sort_entry *se; +}; + +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) { - if (sd->taken) + struct hpp_sort_entry *hse_a; + struct hpp_sort_entry *hse_b; + + if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) + return false; + + hse_a = container_of(a, struct hpp_sort_entry, hpp); + hse_b = container_of(b, struct hpp_sort_entry, hpp); + + return hse_a->se == hse_b->se; +} + +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + struct hpp_sort_entry *hse; + + if (!perf_hpp__is_sort_entry(fmt)) 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)); +} + +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; + + 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); +} + +static int __sort__hpp_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + + return hists__col_len(&evsel->hists, hse->se->se_width_idx); +} + +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; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + len = hists__col_len(he->hists, hse->se->se_width_idx); + + return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); +} + +static struct hpp_sort_entry * +__sort_dimension__alloc_hpp(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse; + + hse = malloc(sizeof(*hse)); + if (hse == NULL) { + pr_err("Memory allocation failed\n"); + return NULL; + } + + hse->se = sd->entry; + hse->hpp.header = __sort__hpp_header; + hse->hpp.width = __sort__hpp_width; + hse->hpp.entry = __sort__hpp_entry; + hse->hpp.color = NULL; + + hse->hpp.cmp = sd->entry->se_cmp; + hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp; + hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse; + + INIT_LIST_HEAD(&hse->hpp.list); + INIT_LIST_HEAD(&hse->hpp.sort_list); + hse->hpp.elide = false; + + return hse; +} + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +{ + return format->header == __sort__hpp_header; +} + +static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__register_sort_field(&hse->hpp); + return 0; +} + +static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__column_register(&hse->hpp); + return 0; +} + +static int __sort_dimension__add(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_sort(sd) < 0) + return -1; + if (sd->entry->se_collapse) sort__need_collapse = 1; - if (list_empty(&hist_entry__sort_list)) - sort__first_dimension = idx; + sd->taken = 1; + + return 0; +} + +static int __hpp_dimension__add(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__register_sort_field(hd->fmt); + } + return 0; +} + +static int __sort_dimension__add_output(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_output(sd) < 0) + return -1; - list_add_tail(&sd->entry->list, &hist_entry__sort_list); sd->taken = 1; + return 0; +} + +static int __hpp_dimension__add_output(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__column_register(hd->fmt); + } + return 0; } int sort_dimension__add(const char *tok) @@ -1068,8 +1370,16 @@ int sort_dimension__add(const char *tok) sort__has_dso = 1; } - __sort_dimension__add(sd, i); - return 0; + return __sort_dimension__add(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add(hd); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -1084,7 +1394,7 @@ int sort_dimension__add(const char *tok) if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) sort__has_sym = 1; - __sort_dimension__add(sd, i + __SORT_BRANCH_STACK); + __sort_dimension__add(sd); return 0; } @@ -1100,18 +1410,47 @@ int sort_dimension__add(const char *tok) if (sd->entry == &sort_mem_daddr_sym) sort__has_sym = 1; - __sort_dimension__add(sd, i + __SORT_MEMORY_MODE); + __sort_dimension__add(sd); return 0; } return -ESRCH; } -int setup_sorting(void) +static const char *get_default_sort_order(void) +{ + const char *default_sort_orders[] = { + default_sort_order, + default_branch_sort_order, + default_mem_sort_order, + default_top_sort_order, + default_diff_sort_order, + }; + + BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); + + return default_sort_orders[sort__mode]; +} + +static int __setup_sorting(void) { - char *tmp, *tok, *str = strdup(sort_order); + char *tmp, *tok, *str; + const char *sort_keys = sort_order; int ret = 0; + if (sort_keys == NULL) { + if (field_order) { + /* + * If user specified field order but no sort order, + * we'll honor it and not add default sort orders. + */ + return 0; + } + + sort_keys = get_default_sort_order(); + } + + str = strdup(sort_keys); if (str == NULL) { error("Not enough memory to setup sort keys"); return -ENOMEM; @@ -1133,66 +1472,235 @@ int setup_sorting(void) return ret; } -static void sort_entry__setup_elide(struct sort_entry *se, - struct strlist *list, - const char *list_name, FILE *fp) +void perf_hpp__set_elide(int idx, bool elide) +{ + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (hse->se->se_width_idx == idx) { + fmt->elide = elide; + break; + } + } +} + +static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp) { if (list && strlist__nr_entries(list) == 1) { if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - se->elide = true; + return true; } + return false; +} + +static bool get_elide(int idx, FILE *output) +{ + switch (idx) { + case HISTC_SYMBOL: + return __get_elide(symbol_conf.sym_list, "symbol", output); + case HISTC_DSO: + return __get_elide(symbol_conf.dso_list, "dso", output); + case HISTC_COMM: + return __get_elide(symbol_conf.comm_list, "comm", output); + default: + break; + } + + if (sort__mode != SORT_MODE__BRANCH) + return false; + + switch (idx) { + case HISTC_SYMBOL_FROM: + return __get_elide(symbol_conf.sym_from_list, "sym_from", output); + case HISTC_SYMBOL_TO: + return __get_elide(symbol_conf.sym_to_list, "sym_to", output); + case HISTC_DSO_FROM: + return __get_elide(symbol_conf.dso_from_list, "dso_from", output); + case HISTC_DSO_TO: + return __get_elide(symbol_conf.dso_to_list, "dso_to", output); + default: + break; + } + + return false; } void sort__setup_elide(FILE *output) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "dso", output); - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, - "comm", output); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, - "symbol", output); - - if (sort__mode == SORT_MODE__BRANCH) { - sort_entry__setup_elide(&sort_dso_from, - symbol_conf.dso_from_list, - "dso_from", output); - sort_entry__setup_elide(&sort_dso_to, - symbol_conf.dso_to_list, - "dso_to", output); - sort_entry__setup_elide(&sort_sym_from, - symbol_conf.sym_from_list, - "sym_from", output); - sort_entry__setup_elide(&sort_sym_to, - symbol_conf.sym_to_list, - "sym_to", output); - } else if (sort__mode == SORT_MODE__MEMORY) { - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "symbol_daddr", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "dso_daddr", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "mem", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "local_weight", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "tlb", output); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "snoop", output); + hse = container_of(fmt, struct hpp_sort_entry, hpp); + fmt->elide = get_elide(hse->se->se_width_idx, output); } /* * It makes no sense to elide all of sort entries. * Just revert them to show up again. */ - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (!se->elide) + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + if (!fmt->elide) return; } - list_for_each_entry(se, &hist_entry__sort_list, list) - se->elide = false; + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + fmt->elide = false; + } +} + +static int output_field_add(char *tok) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add_output(hd); + } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { + struct sort_dimension *sd = &memory_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + return -ESRCH; +} + +static void reset_dimensions(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) + common_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) + hpp_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) + bstack_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) + memory_sort_dimensions[i].taken = 0; +} + +static int __setup_output_field(void) +{ + char *tmp, *tok, *str; + int ret = 0; + + if (field_order == NULL) + return 0; + + reset_dimensions(); + + str = strdup(field_order); + if (str == NULL) { + error("Not enough memory to setup output fields"); + return -ENOMEM; + } + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = output_field_add(tok); + if (ret == -EINVAL) { + error("Invalid --fields key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --fields key: `%s'", tok); + break; + } + } + + free(str); + return ret; +} + +int setup_sorting(void) +{ + int err; + + err = __setup_sorting(); + if (err < 0) + return err; + + if (parent_pattern != default_parent_pattern) { + err = sort_dimension__add("parent"); + if (err < 0) + return err; + } + + reset_dimensions(); + + /* + * perf diff doesn't use default hpp output fields. + */ + if (sort__mode != SORT_MODE__DIFF) + perf_hpp__init(); + + err = __setup_output_field(); + if (err < 0) + return err; + + /* copy sort keys to output fields */ + perf_hpp__setup_output_field(); + /* and then copy output fields to sort keys */ + perf_hpp__append_sort_keys(); + + return 0; +} + +void reset_output_field(void) +{ + sort__need_collapse = 0; + sort__has_parent = 0; + sort__has_sym = 0; + sort__has_dso = 0; + + field_order = NULL; + sort_order = NULL; + + reset_dimensions(); + perf_hpp__reset_output_field(); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 43e5ff42a609..041f0c9cea2b 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -20,11 +20,12 @@ #include "parse-options.h" #include "parse-events.h" - +#include "hist.h" #include "thread.h" extern regex_t parent_regex; extern const char *sort_order; +extern const char *field_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; @@ -81,12 +82,14 @@ struct hist_entry { struct list_head head; } pairs; struct he_stat stat; + struct he_stat *stat_acc; struct map_symbol ms; struct thread *thread; struct comm *comm; u64 ip; u64 transaction; s32 cpu; + u8 cpumode; struct hist_entry_diff diff; @@ -129,10 +132,27 @@ static inline void hist_entry__add_pair(struct hist_entry *pair, list_add_tail(&pair->pairs.node, &he->pairs.head); } +static inline float hist_entry__get_percent_limit(struct hist_entry *he) +{ + u64 period = he->stat.period; + u64 total_period = hists__total_period(he->hists); + + if (unlikely(total_period == 0)) + return 0; + + if (symbol_conf.cumulate_callchain) + period = he->stat_acc->period; + + return period * 100.0 / total_period; +} + + enum sort_mode { SORT_MODE__NORMAL, SORT_MODE__BRANCH, SORT_MODE__MEMORY, + SORT_MODE__TOP, + SORT_MODE__DIFF, }; enum sort_type { @@ -166,6 +186,7 @@ enum sort_type { SORT_MEM_TLB, SORT_MEM_LVL, SORT_MEM_SNOOP, + SORT_MEM_DCACHELINE, }; /* @@ -179,18 +200,21 @@ struct sort_entry { int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); + int64_t (*se_sort)(struct hist_entry *, struct hist_entry *); int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; - bool elide; }; extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; int setup_sorting(void); +int setup_output_field(void); +void reset_output_field(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +void perf_hpp__set_elide(int idx, bool elide); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index ae8ccd7227cf..5667fc3e39cf 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -1,7 +1,7 @@ #ifndef __PERF_STATS_H #define __PERF_STATS_H -#include "types.h" +#include <linux/types.h> struct stats { diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 43262b83c541..283d3e73e2f2 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -17,7 +17,7 @@ #include <stdlib.h> #include <unistd.h> #include <string.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include "perf.h" #include "svghelper.h" @@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq; #define SLOT_MULT 30.0 #define SLOT_HEIGHT 25.0 +#define SLOT_HALF (SLOT_HEIGHT / 2) int svg_page_width = 1000; u64 svg_highlight; @@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " rect { stroke-width: 1; }\n"); fprintf(svgfile, " rect.process { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample { fill:rgb( 0, 0,255); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample_hi{ fill:rgb(255,128, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.error { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.net { fill:rgb( 0,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.disk { fill:rgb( 0, 0,255); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.sync { fill:rgb(128,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.poll { fill:rgb( 0,128,128); fill-opacity:0.2; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.blocked { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.waiting { fill:rgb(224,214, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.WAITING { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); @@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " ]]>\n </style>\n</defs>\n"); } +static double normalize_height(double height) +{ + if (height < 0.25) + return 0.25; + else if (height < 0.50) + return 0.50; + else if (height < 0.75) + return 0.75; + else + return 0.100; +} + +void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height, + SLOT_HEIGHT * height, + type); + fprintf(svgfile, "</g>\n"); +} + void svg_box(int Yslot, u64 start, u64 end, const char *type) { if (!svgfile) return; - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); } @@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); @@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) text_size = round_text_size(text_size); if (text_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n", time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1); fprintf(svgfile, "</g>\n"); @@ -202,10 +278,10 @@ static char *time_to_string(u64 duration) return text; if (duration < 1000 * 1000) { /* less than 1 msec */ - sprintf(text, "%4.1f us", duration / 1000.0); + sprintf(text, "%.1f us", duration / 1000.0); return text; } - sprintf(text, "%4.1f ms", duration / 1000.0 / 1000); + sprintf(text, "%.1f ms", duration / 1000.0 / 1000); return text; } @@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) font_size = round_text_size(font_size); - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style); if (font_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n", font_size, text); fprintf(svgfile, "</g>\n"); } @@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq) fprintf(svgfile, "<g>\n"); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n", time2pixels(first_time), time2pixels(last_time)-time2pixels(first_time), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); sprintf(cpu_string, "CPU %i", (int)cpu); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string); - fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model()); fprintf(svgfile, "</g>\n"); @@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c else type = "sample"; - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu)); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu)); fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type); width = time2pixels(end)-time2pixels(start); if (width > 6) @@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n", width, name); fprintf(svgfile, "</g>\n"); @@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) type = 6; sprintf(style, "c%i", type); - fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n", + fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n", style, time2pixels(start), time2pixels(end)-time2pixels(start), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); @@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n", time2pixels(start), cpu2y(cpu)+width, width, type); fprintf(svgfile, "</g>\n"); @@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq) if (max_freq) height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT); height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height; - fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n", time2pixels(start), time2pixels(end), height, height); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n", time2pixels(start), height+0.9, HzToHuman(freq)); fprintf(svgfile, "</g>\n"); @@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row1 < row2) { if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2); } if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row2 * SLOT_MULT); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1); } } else { if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1); } if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row1 * SLOT_MULT); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2); } } @@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row2 > row1) height += SLOT_HEIGHT; if (row1) - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); if (row1 < row2) - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT); else - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT); height = row1 * SLOT_MULT; if (row2 > row1) height += SLOT_HEIGHT; - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace) if (backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT); fprintf(svgfile, "</g>\n"); @@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text) if (!svgfile) return; - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text); } @@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style) double boxsize; boxsize = SLOT_HEIGHT / 2; - fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", X, boxsize, boxsize, style); - fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n", X + boxsize + 5, boxsize, 0.8 * boxsize, text); } +void svg_io_legenda(void) +{ + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + svg_legenda_box(0, "Disk", "disk"); + svg_legenda_box(100, "Network", "net"); + svg_legenda_box(200, "Sync", "sync"); + svg_legenda_box(300, "Poll", "poll"); + svg_legenda_box(400, "Error", "error"); + fprintf(svgfile, "</g>\n"); +} + void svg_legenda(void) { if (!svgfile) @@ -559,7 +649,7 @@ void svg_legenda(void) fprintf(svgfile, "</g>\n"); } -void svg_time_grid(void) +void svg_time_grid(double min_thickness) { u64 i; @@ -579,8 +669,10 @@ void svg_time_grid(void) color = 128; } - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n", - time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness); + if (thickness >= min_thickness) + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n", + time2pixels(i), SLOT_MULT/2, time2pixels(i), + total_height, color, color, color, thickness); i += 10000000; } diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index f7b4d6e699ea..9292a5291445 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -1,9 +1,12 @@ #ifndef __PERF_SVGHELPER_H #define __PERF_SVGHELPER_H -#include "types.h" +#include <linux/types.h> extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); +extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); extern void svg_box(int Yslot, u64 start, u64 end, const char *type); extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); @@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type); extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq); -extern void svg_time_grid(void); +extern void svg_time_grid(double min_thickness); +extern void svg_io_legenda(void); extern void svg_legenda(void); extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace); extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 6864661a79dd..d75349979e65 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -49,7 +49,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) static inline int elf_sym__is_function(const GElf_Sym *sym) { - return elf_sym__type(sym) == STT_FUNC && + return (elf_sym__type(sym) == STT_FUNC || + elf_sym__type(sym) == STT_GNU_IFUNC) && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF; } @@ -598,6 +599,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, goto out_elf_end; } + ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", NULL); if (ss->symshdr.sh_type != SHT_SYMTAB) @@ -619,7 +622,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || - is_vdso_map(dso->short_name) || + dso__is_vdso(dso) || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); @@ -698,6 +701,7 @@ int dso__load_sym(struct dso *dso, struct map *map, bool remap_kernel = false, adjust_kernel_syms = false; dso->symtab_type = syms_ss->type; + dso->is_64_bit = syms_ss->is_64_bit; dso->rel = syms_ss->ehdr.e_type == ET_REL; /* @@ -1024,6 +1028,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, return err; } +enum dso_type dso__type_fd(int fd) +{ + enum dso_type dso_type = DSO__TYPE_UNKNOWN; + GElf_Ehdr ehdr; + Elf_Kind ek; + Elf *elf; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + goto out; + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_end; + + if (gelf_getclass(elf) == ELFCLASS64) { + dso_type = DSO__TYPE_64BIT; + goto out_end; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out_end; + + if (ehdr.e_machine == EM_X86_64) + dso_type = DSO__TYPE_X32BIT; + else + dso_type = DSO__TYPE_32BIT; +out_end: + elf_end(elf); +out: + return dso_type; +} + static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len) { ssize_t r; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index bd15f490d04f..c9541fea9514 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -288,6 +288,44 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, return 0; } +static int fd__is_64_bit(int fd) +{ + u8 e_ident[EI_NIDENT]; + + if (lseek(fd, 0, SEEK_SET)) + return -1; + + if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident)) + return -1; + + if (memcmp(e_ident, ELFMAG, SELFMAG) || + e_ident[EI_VERSION] != EV_CURRENT) + return -1; + + return e_ident[EI_CLASS] == ELFCLASS64; +} + +enum dso_type dso__type_fd(int fd) +{ + Elf64_Ehdr ehdr; + int ret; + + ret = fd__is_64_bit(fd); + if (ret < 0) + return DSO__TYPE_UNKNOWN; + + if (ret) + return DSO__TYPE_64BIT; + + if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr)) + return DSO__TYPE_UNKNOWN; + + if (ehdr.e_machine == EM_X86_64) + return DSO__TYPE_X32BIT; + + return DSO__TYPE_32BIT; +} + int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *ss, struct symsrc *runtime_ss __maybe_unused, @@ -295,6 +333,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, int kmodule __maybe_unused) { unsigned char *build_id[BUILD_ID_SIZE]; + int ret; + + ret = fd__is_64_bit(ss->fd); + if (ret >= 0) + dso->is_64_bit = ret; if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { dso__set_build_id(dso, build_id); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 95e249779931..eb06746b06b2 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -29,11 +29,13 @@ int vmlinux_path__nr_entries; char **vmlinux_path; struct symbol_conf symbol_conf = { - .use_modules = true, - .try_vmlinux_path = true, - .annotate_src = true, - .demangle = true, - .symfs = "", + .use_modules = true, + .try_vmlinux_path = true, + .annotate_src = true, + .demangle = true, + .cumulate_callchain = true, + .show_hist_headers = true, + .symfs = "", }; static enum dso_binary_type binary_type_symtab[] = { @@ -340,6 +342,16 @@ static struct symbol *symbols__first(struct rb_root *symbols) return NULL; } +static struct symbol *symbols__next(struct symbol *sym) +{ + struct rb_node *n = rb_next(&sym->rb_node); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -410,11 +422,16 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } -static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { return symbols__first(&dso->symbols[type]); } +struct symbol *dso__next_symbol(struct symbol *sym) +{ + return symbols__next(sym); +} + struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -1063,6 +1080,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, &is_64_bit); if (err) goto out_err; + dso->is_64_bit = is_64_bit; if (list_empty(&md.maps)) { err = -EINVAL; @@ -1661,6 +1679,7 @@ do_kallsyms: free(kallsyms_allocated_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__KALLSYMS; dso__set_long_name(dso, "[kernel.kallsyms]", false); map__fixup_start(map); map__fixup_end(map); @@ -1708,6 +1727,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; machine__mmap_name(machine, path, sizeof(path)); dso__set_long_name(dso, strdup(path), true); map__fixup_start(map); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 501e4e722e8e..e7295e93cff9 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -12,6 +12,7 @@ #include <byteswap.h> #include <libgen.h> #include "build-id.h" +#include "event.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -108,6 +109,7 @@ struct symbol_conf { show_nr_samples, show_total_period, use_callchain, + cumulate_callchain, exclude_other, show_cpu_utilization, initialized, @@ -115,7 +117,9 @@ struct symbol_conf { annotate_asm_raw, annotate_src, event_group, - demangle; + demangle, + filter_relative, + show_hist_headers; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -212,6 +216,7 @@ struct symsrc { GElf_Shdr dynshdr; bool adjust_symbols; + bool is_64_bit; #endif }; @@ -235,6 +240,11 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__next_symbol(struct symbol *sym); + +enum dso_type dso__type_fd(int fd); + int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int modules__parse(const char *filename, void *arg, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 3ce0498bdae6..12c7a253a63c 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -8,6 +8,22 @@ #include "debug.h" #include "comm.h" +int thread__init_map_groups(struct thread *thread, struct machine *machine) +{ + struct thread *leader; + pid_t pid = thread->pid_; + + if (pid == thread->tid || pid == -1) { + thread->mg = map_groups__new(); + } else { + leader = machine__findnew_thread(machine, pid, pid); + if (leader) + thread->mg = map_groups__get(leader->mg); + } + + return thread->mg ? 0 : -1; +} + struct thread *thread__new(pid_t pid, pid_t tid) { char *comm_str; @@ -15,10 +31,10 @@ struct thread *thread__new(pid_t pid, pid_t tid) struct thread *thread = zalloc(sizeof(*thread)); if (thread != NULL) { - map_groups__init(&thread->mg); thread->pid_ = pid; thread->tid = tid; thread->ppid = -1; + thread->cpu = -1; INIT_LIST_HEAD(&thread->comm_list); comm_str = malloc(32); @@ -45,7 +61,10 @@ void thread__delete(struct thread *thread) { struct comm *comm, *tmp; - map_groups__exit(&thread->mg); + if (thread->mg) { + map_groups__put(thread->mg); + thread->mg = NULL; + } list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); @@ -111,18 +130,35 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(&thread->mg, verbose, fp); + map_groups__fprintf(thread->mg, fp); } void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr); - map_groups__insert(&thread->mg, map); + map_groups__fixup_overlappings(thread->mg, map, stderr); + map_groups__insert(thread->mg, map); +} + +static int thread__clone_map_groups(struct thread *thread, + struct thread *parent) +{ + int i; + + /* This is new thread, we share map groups for process. */ + if (thread->pid_ == parent->pid_) + return 0; + + /* But this one is new process, copy maps. */ + for (i = 0; i < MAP__NR_TYPES; ++i) + if (map_groups__clone(thread->mg, parent->mg, i) < 0) + return -ENOMEM; + + return 0; } int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int i, err; + int err; if (parent->comm_set) { const char *comm = thread__comm_str(parent); @@ -134,13 +170,8 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) thread->comm_set = true; } - for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(&thread->mg, &parent->mg, i) < 0) - return -ENOMEM; - thread->ppid = parent->tid; - - return 0; + return thread__clone_map_groups(thread, parent); } void thread__find_cpumode_addr_location(struct thread *thread, diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 9b29f085aede..716b7723cce2 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -13,10 +13,11 @@ struct thread { struct rb_node rb_node; struct list_head node; }; - struct map_groups mg; + struct map_groups *mg; pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; + int cpu; char shortname[3]; bool comm_set; bool dead; /* if set thread has exited */ @@ -30,6 +31,7 @@ struct machine; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); +int thread__init_map_groups(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); static inline void thread__exited(struct thread *thread) { diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index dab14d0ad3d0..f92c37abb0a8 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -2,7 +2,7 @@ #define __PERF_TOP_H 1 #include "tool.h" -#include "types.h" +#include <linux/types.h> #include <stddef.h> #include <stdbool.h> #include <termios.h> diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 7e6fcfe8b438..eb72716017ac 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -40,6 +40,7 @@ #include "trace-event.h" #include <api/fs/debugfs.h> #include "evsel.h" +#include "debug.h" #define VERSION "0.5" @@ -191,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); free(format); if (ret < 0) @@ -217,12 +216,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); if (ret >= 0) { @@ -317,12 +314,10 @@ static int record_event_files(struct tracepoint_path *tps) strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; - sys = malloc(strlen(path) + strlen(dent->d_name) + 2); - if (!sys) { + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(sys, "%s/%s", path, dent->d_name); ret = stat(sys, &st); if (ret >= 0) { ssize_t size = strlen(dent->d_name) + 1; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index e113e180c48f..54d9e9b548a8 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -22,7 +22,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <getopt.h> #include <stdarg.h> #include <sys/types.h> #include <sys/stat.h> @@ -36,6 +35,7 @@ #include "../perf.h" #include "util.h" #include "trace-event.h" +#include "debug.h" static int input_fd; diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c new file mode 100644 index 000000000000..4d4210d4e13d --- /dev/null +++ b/tools/perf/util/tsc.c @@ -0,0 +1,30 @@ +#include <linux/compiler.h> +#include <linux/types.h> + +#include "tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) +{ + u64 t, quot, rem; + + t = ns - tc->time_zero; + quot = t / tc->time_mult; + rem = t % tc->time_mult; + return (quot << tc->time_shift) + + (rem << tc->time_shift) / tc->time_mult; +} + +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) +{ + u64 quot, rem; + + quot = cyc >> tc->time_shift; + rem = cyc & ((1 << tc->time_shift) - 1); + return tc->time_zero + quot * tc->time_mult + + ((rem * tc->time_mult) >> tc->time_shift); +} + +u64 __weak rdtsc(void) +{ + return 0; +} diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h new file mode 100644 index 000000000000..a8b78f1b3243 --- /dev/null +++ b/tools/perf/util/tsc.h @@ -0,0 +1,12 @@ +#ifndef __PERF_TSC_H +#define __PERF_TSC_H + +#include <linux/types.h> + +#include "../arch/x86/util/tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); +u64 rdtsc(void); + +#endif diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h deleted file mode 100644 index c51fa6b70a28..000000000000 --- a/tools/perf/util/types.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef __PERF_TYPES_H -#define __PERF_TYPES_H - -#include <stdint.h> - -/* - * We define u64 as uint64_t for every architecture - * so that we can print it with "%"PRIx64 without getting warnings. - */ -typedef uint64_t u64; -typedef int64_t s64; -typedef unsigned int u32; -typedef signed int s32; -typedef unsigned short u16; -typedef signed short s16; -typedef unsigned char u8; -typedef signed char s8; - -union u64_swap { - u64 val64; - u32 val32[2]; -}; - -#endif /* __PERF_TYPES_H */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 67db73ec3dab..7419768c38b1 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -3,11 +3,12 @@ #include <elfutils/libdwfl.h> #include <inttypes.h> #include <errno.h> +#include "debug.h" #include "unwind.h" #include "unwind-libdw.h" #include "machine.h" #include "thread.h" -#include "types.h" +#include <linux/types.h> #include "event.h" #include "perf_regs.h" diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index bd5768d74f01..92b56db52471 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -30,6 +30,7 @@ #include "unwind.h" #include "symbol.h" #include "util.h" +#include "debug.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -250,7 +251,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, /* Check the .eh_frame section for unwinding info */ offset = elf_section_offset(fd, ".eh_frame_hdr"); - close(fd); if (offset) ret = unwind_spec_ehframe(dso, machine, offset, @@ -271,7 +271,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso, /* Check the .debug_frame section for unwinding info */ *offset = elf_section_offset(fd, ".debug_frame"); - close(fd); if (*offset) return 0; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index b031316f221a..f03061260b4e 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -1,7 +1,7 @@ #ifndef __UNWIND_H #define __UNWIND_H -#include "types.h" +#include <linux/types.h> #include "event.h" #include "symbol.h" diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 9f66549562bd..e52e7461911b 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,5 +1,6 @@ #include "../perf.h" #include "util.h" +#include "debug.h" #include <api/fs/fs.h> #include <sys/mman.h> #ifdef HAVE_BACKTRACE_SUPPORT @@ -17,6 +18,7 @@ * XXX We need to find a better place for these things... */ unsigned int page_size; +int cacheline_size; bool test_attr__enabled; @@ -166,6 +168,8 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n) ssize_t ret = is_read ? read(fd, buf, left) : write(fd, buf, left); + if (ret < 0 && errno == EINTR) + continue; if (ret <= 0) return ret; @@ -330,12 +334,9 @@ const char *find_tracing_dir(void) if (!debugfs) return NULL; - tracing = malloc(strlen(debugfs) + 9); - if (!tracing) + if (asprintf(&tracing, "%s/tracing", debugfs) < 0) return NULL; - sprintf(tracing, "%s/tracing", debugfs); - tracing_found = 1; return tracing; } @@ -349,11 +350,9 @@ char *get_tracing_file(const char *name) if (!tracing) return NULL; - file = malloc(strlen(tracing) + strlen(name) + 2); - if (!file) + if (asprintf(&file, "%s/%s", tracing, name) < 0) return NULL; - sprintf(file, "%s/%s", tracing, name); return file; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 6995d66f225c..66864364ccb4 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -69,7 +69,7 @@ #include <sys/ioctl.h> #include <inttypes.h> #include <linux/magic.h> -#include "types.h" +#include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/debugfs.h> #include <termios.h> @@ -304,6 +304,7 @@ char *rtrim(char *s); void dump_stack(void); extern unsigned int page_size; +extern int cacheline_size; void get_term_dimensions(struct winsize *ws); diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index 2fa967e1a88a..b21a80c6cf8d 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -1,7 +1,7 @@ #ifndef __PERF_VALUES_H #define __PERF_VALUES_H -#include "types.h" +#include <linux/types.h> struct perf_read_values { int threads; diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 0ddb3b8a89ec..adca69384fcc 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -11,10 +11,34 @@ #include "vdso.h" #include "util.h" #include "symbol.h" +#include "machine.h" #include "linux/string.h" +#include "debug.h" -static bool vdso_found; -static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX"; +#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" + +struct vdso_file { + bool found; + bool error; + char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)]; + const char *dso_name; +}; + +struct vdso_info { + struct vdso_file vdso; +}; + +static struct vdso_info *vdso_info__new(void) +{ + static const struct vdso_info vdso_info_init = { + .vdso = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSO, + }, + }; + + return memdup(&vdso_info_init, sizeof(vdso_info_init)); +} static int find_vdso_map(void **start, void **end) { @@ -47,7 +71,7 @@ static int find_vdso_map(void **start, void **end) return !found; } -static char *get_file(void) +static char *get_file(struct vdso_file *vdso_file) { char *vdso = NULL; char *buf = NULL; @@ -55,10 +79,10 @@ static char *get_file(void) size_t size; int fd; - if (vdso_found) - return vdso_file; + if (vdso_file->found) + return vdso_file->temp_file_name; - if (find_vdso_map(&start, &end)) + if (vdso_file->error || find_vdso_map(&start, &end)) return NULL; size = end - start; @@ -67,45 +91,78 @@ static char *get_file(void) if (!buf) return NULL; - fd = mkstemp(vdso_file); + fd = mkstemp(vdso_file->temp_file_name); if (fd < 0) goto out; if (size == (size_t) write(fd, buf, size)) - vdso = vdso_file; + vdso = vdso_file->temp_file_name; close(fd); out: free(buf); - vdso_found = (vdso != NULL); + vdso_file->found = (vdso != NULL); + vdso_file->error = !vdso_file->found; return vdso; } -void vdso__exit(void) +void vdso__exit(struct machine *machine) { - if (vdso_found) - unlink(vdso_file); + struct vdso_info *vdso_info = machine->vdso_info; + + if (!vdso_info) + return; + + if (vdso_info->vdso.found) + unlink(vdso_info->vdso.temp_file_name); + + zfree(&machine->vdso_info); } -struct dso *vdso__dso_findnew(struct list_head *head) +static struct dso *vdso__new(struct machine *machine, const char *short_name, + const char *long_name) { - struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true); + struct dso *dso; + dso = dso__new(short_name); + if (dso != NULL) { + dsos__add(&machine->user_dsos, dso); + dso__set_long_name(dso, long_name, false); + } + + return dso; +} + +struct dso *vdso__dso_findnew(struct machine *machine, + struct thread *thread __maybe_unused) +{ + struct vdso_info *vdso_info; + struct dso *dso; + + if (!machine->vdso_info) + machine->vdso_info = vdso_info__new(); + + vdso_info = machine->vdso_info; + if (!vdso_info) + return NULL; + + dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true); if (!dso) { char *file; - file = get_file(); + file = get_file(&vdso_info->vdso); if (!file) return NULL; - dso = dso__new(VDSO__MAP_NAME); - if (dso != NULL) { - dsos__add(head, dso); - dso__set_long_name(dso, file, false); - } + dso = vdso__new(machine, DSO__NAME_VDSO, file); } return dso; } + +bool dso__is_vdso(struct dso *dso) +{ + return !strcmp(dso->short_name, DSO__NAME_VDSO); +} diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h index 0f76e7caf6f8..af9d6929a215 100644 --- a/tools/perf/util/vdso.h +++ b/tools/perf/util/vdso.h @@ -7,12 +7,21 @@ #define VDSO__MAP_NAME "[vdso]" +#define DSO__NAME_VDSO "[vdso]" + static inline bool is_vdso_map(const char *filename) { return !strcmp(filename, VDSO__MAP_NAME); } -struct dso *vdso__dso_findnew(struct list_head *head); -void vdso__exit(void); +struct dso; + +bool dso__is_vdso(struct dso *dso); + +struct machine; +struct thread; + +struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread); +void vdso__exit(struct machine *machine); #endif /* __PERF_VDSO__ */ |
